feat: add workflow visualization with FlowDisplay and bump version to 2.2.77

- Added execute_sync_callback call in custom LLM path to match OpenAI behavior
- Fixed issue where Gemini/custom LLM responses were not triggering callbacks
- Prevents duplicate display by relying on LLM class to handle verbose display
- Ensures both paths execute callbacks for consistent behavior

The issue was that custom LLM providers (like Gemini) were not calling
_execute_callback_and_display after guardrail validation, while OpenAI
path was. This caused missing Task/Response display boxes for Gemini.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <[email protected]>

.github/actions/gemini/action.yml

@@ -0,0 +1,81 @@
+name: 'Gemini CLI Action'
+description: 'Uses the Gemini CLI to automate software development tasks.'
+author: 'Gemini'
+
+inputs:
+  prompt:
+    description: 'A specific prompt to guide Gemini.'
+    required: false
+    default: 'You are a helpful assistant.'
+  GEMINI_API_KEY:
+    description: 'Your Gemini API key.'
+    required: true
+  OTLP_GCP_WIF_PROVIDER:
+    description: 'The workload identity provider for GCP authentication.'
+    required: false
+  OTLP_GOOGLE_CLOUD_PROJECT:
+    description: 'The Google Cloud project for telemetry.'
+    required: false
+  settings_json:
+    description: |
+      A JSON string to configure the Gemini CLI. This will be written to .gemini/settings.json.
+      To enable observability with Google Cloud, include:
+      {"telemetry": {"enabled": true, "target": "gcp"}, "sandbox": false}
+    required: false
+  version:
+    description: |
+      The version of @google/gemini-cli to execute.
+      Can be a specific version from npm (e.g., '0.1.0', 'latest'), a branch name (e.g., 'main'), or a commit hash.
+    required: false
+    default: 'latest'
+
+runs:
+  using: "composite"
+  steps:
+    - name: Configure Gemini CLI
+      if: inputs.settings_json != ''
+      run: |
+        mkdir -p .gemini
+        echo "$SETTINGS_JSON" > .gemini/settings.json
+      shell: bash
+      env:
+        SETTINGS_JSON: ${{ inputs.settings_json }}
+
+    - name: Authenticate to Google Cloud for Telemetry 
+      if: inputs.OTLP_GCP_WIF_PROVIDER != ''
+      id: auth
+      uses: 'google-github-actions/auth@v2'
+      with:
+        project_id: ${{ inputs.OTLP_GOOGLE_CLOUD_PROJECT }}
+        workload_identity_provider: ${{ inputs.OTLP_GCP_WIF_PROVIDER }}
+
+    - name: Install Gemini CLI
+      id: install
+      run: |
+        if [[ "${{ inputs.version }}" == "latest" || "${{ inputs.version }}" =~ ^[0-9]+\.[0-9]+\.[0-9]+(-[a-zA-Z0-9\.-]+)?(\+[a-zA-Z0-9\.-]+)?$ ]]; then
+          echo "Installing Gemini CLI from npm: @google/gemini-cli@${{ inputs.version }}"
+          npm install -g @google/gemini-cli@${{ inputs.version }}
+        else
+          echo "Installing Gemini CLI from GitHub: github:google-gemini/gemini-cli#${{ inputs.version }}"
+          npm install -g github:google-gemini/gemini-cli#${{ inputs.version }}
+        fi
+        echo "Verifying installation:"
+        if command -v gemini >/dev/null 2>&1; then
+          gemini --version || echo "Gemini CLI installed successfully (version command not available)"
+        else
+          echo "Error: Gemini CLI not found in PATH"
+          exit 1
+        fi
+      shell: bash
+
+    - name: Run Gemini CLI
+      run: |
+        gemini --yolo --prompt "$PROMPT"
+      shell: bash
+      env:
+        GEMINI_API_KEY: ${{ inputs.GEMINI_API_KEY }}
+        PROMPT: ${{ inputs.prompt }}
+
+branding:
+  icon: 'terminal'
+  color: 'blue'

.github/workflows/auto-issue-comment.yml

@@ -0,0 +1,26 @@
+name: Auto Issue Comment with PR Creation
+
+on:
+  issues:
+    types: [opened]
+
+jobs:
+  add-comment:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      contents: write
+      pull-requests: write
+      actions: read
+    steps:
+      - name: Add automated comment
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GH_TOKEN }}
+          script: |
+            github.rest.issues.createComment({
+              issue_number: context.issue.number,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: '@claude review this issue and do a detailed analysis and fix this if the existing code doesn\'t have the solution implemented. Making sure it has backward compatibility, no existing features removed. After making those changes, again review the applied changes. Use @web to search if you dont know any information or to find the latest documentation or to find the latest version. Run the code if you think you need to run it to test it. Minimal code change to start with if required any changes. **Please create a PR using gh tool with your changes**.'
+            })

.github/workflows/auto-pr-comment.yml

@@ -0,0 +1,23 @@
+name: Auto PR Comment
+
+on:
+  pull_request:
+    types: [opened]
+
+jobs:
+  add-comment:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+    steps:
+      - name: Add automated comment
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GH_TOKEN }}
+          script: |
+            github.rest.issues.createComment({
+              issue_number: context.issue.number,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: '@claude review this pull request and do a detailed analysis and fix this if the existing code doesn\'t have the solution implemented. Making sure it has backward compatibility, no existing features removed. After making those changes, again review the applied changes. Use @web to search if you dont know any information or to find the latest documentation or to find the latest version. Run the code if you think you need to run it to test it. Minimal code change to start with if required any changes.'
+            }) 

.github/workflows/build-image.yml

@@ -11,6 +11,7 @@ on:
 jobs:
   build:
     runs-on: ubuntu-latest
+    timeout-minutes: 15
     permissions:
       contents: read
       packages: write

.github/workflows/claude.yml

@@ -1,4 +1,4 @@
-name: Claude Code
+name: Claude Assistant
 
 on:
   issue_comment:
@@ -6,34 +6,156 @@ on:
   pull_request_review_comment:
     types: [created]
   issues:
-    types: [opened, assigned]
+    types: [opened, assigned, labeled]
   pull_request_review:
     types: [submitted]
 
 jobs:
-  claude:
+  claude-response:
+    # Prevent bots from triggering this action
     if: |
-      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
-      (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
-      (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
-      (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
+      github.actor != 'dependabot[bot]' &&
+      github.actor != 'github-actions[bot]' &&
+      github.actor != 'cursor[bot]' &&
+      !contains(github.actor, '[bot]') &&
+      github.actor != 'renovate[bot]'
     runs-on: ubuntu-latest
     permissions:
-      contents: read
-      pull-requests: read
-      issues: read
-      id-token: write
+      contents: write
+      pull-requests: write
+      issues: write
+      actions: read
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
         with:
-          fetch-depth: 1
-
-      - name: Run Claude Code (OAuth)
-        id: claude
-        uses: grll/claude-code-action@beta
+          fetch-depth: 0
+          
+      - uses: anthropics/claude-code-action@beta
         with:
-          use_oauth: true
-          claude_access_token: ${{ secrets.CLAUDE_ACCESS_TOKEN }}
-          claude_refresh_token: ${{ secrets.CLAUDE_REFRESH_TOKEN }}
-          claude_expires_at: ${{ secrets.CLAUDE_EXPIRES_AT }}
+          claude_code_oauth_token: ${{ secrets.CLAUDE_ACCESS_TOKEN }}
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          trigger_phrase: "@claude"
+          allowed_tools: |
+            Bash(git:*)
+            Bash(python:*)
+            Bash(pip:*)
+            Bash(conda:*)
+            Bash(pytest:*)
+            Bash(gh:*)
+            Bash(python -m pytest:*)
+            Bash(python -m pip:*)
+            Bash(poetry:*)
+            View
+            GlobTool
+            GrepTool
+            BatchTool
+            Edit
+            Replace
+            mcp__github__get_issue
+            mcp__github__get_issue_comments
+            mcp__github__update_issue
+          timeout_minutes: 30
+
+  post-review-comment:
+    needs: claude-response
+    if: success() && needs.claude-response.result == 'success'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+      issues: write
+    steps:
+      - name: Check for existing review comment
+        id: check-comment
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GH_TOKEN }}
+          script: |
+            const reviewText = '@claude review if the changes made in the above branch are as per the requirements and make changes to the above branch if issues still exist.';
+            let comments = [];
+            let issueNumber;
+            
+            try {
+              // Determine issue/PR number based on event type
+              if (context.eventName === 'pull_request_review_comment' || context.eventName === 'pull_request_review') {
+                issueNumber = context.payload.pull_request?.number || context.issue.number;
+              } else if (context.eventName === 'issue_comment' && context.payload.issue.pull_request) {
+                // This is a comment on a PR (not an issue)
+                issueNumber = context.payload.issue.number;
+              } else {
+                // This is a regular issue
+                issueNumber = context.issue.number;
+              }
+              
+              comments = await github.rest.issues.listComments({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: issueNumber
+              });
+              
+              // Look for Claude's completed review comments
+              const claudeReviewComments = comments.data.filter(comment => 
+                (comment.user.login === 'claude[bot]' || comment.body.includes('✅') || comment.body.includes('## Summary')) &&
+                !comment.body.includes('⏳') && 
+                !comment.body.includes('🔄') &&
+                !comment.body.includes('Loading...')
+              );
+              
+              // Check if our review request comment already exists
+              const existingReviewRequest = comments.data.find(comment => 
+                comment.body.includes(reviewText)
+              );
+              
+              // Post if Claude has completed a review AND we haven't posted the review request yet
+              const shouldPost = claudeReviewComments.length > 0 && !existingReviewRequest;
+              core.setOutput('should-post', shouldPost);
+              console.log(`Claude review completed: ${claudeReviewComments.length > 0}`);
+              console.log(`Review request exists: ${!!existingReviewRequest}`);
+              console.log(`Should post comment: ${shouldPost}`);
+              
+            } catch (error) {
+              console.log('Error checking comments:', error);
+              core.setOutput('should-post', false); // If we can't check, don't post
+            }
+
+      - name: Wait 30 seconds before posting comment
+        if: steps.check-comment.outputs.should-post == 'true'
+        run: sleep 30
+
+      - name: Post review comment
+        if: steps.check-comment.outputs.should-post == 'true'
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GH_TOKEN }}
+          script: |
+            let issueNumber;
+            let isPR = false;
+            
+            // Determine issue/PR number and type based on event type
+            if (context.eventName === 'pull_request_review_comment' || context.eventName === 'pull_request_review') {
+              issueNumber = context.payload.pull_request?.number || context.issue.number;
+              isPR = true;
+            } else if (context.eventName === 'issue_comment' && context.payload.issue.pull_request) {
+              // This is a comment on a PR (not an issue)
+              issueNumber = context.payload.issue.number;
+              isPR = true;
+            } else {
+              // This is a regular issue - don't post review comment
+              issueNumber = context.issue.number;
+              isPR = false;
+            }
+            
+            // Only post review comment on PRs, not regular issues
+            if (isPR) {
+              console.log(`Posting review comment on PR #${issueNumber}`);
+              
+              await github.rest.issues.createComment({
+                issue_number: issueNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: '@claude review if the changes made in the above branch are as per the requirements and make changes to the above branch if issues still exist.'
+              });
+            } else {
+              console.log(`Skipping review comment for regular issue #${issueNumber}`);
+            }

.github/workflows/coverage.yml

@@ -10,6 +10,7 @@ jobs:
   test:
     name: Run tests and collect coverage
     runs-on: ubuntu-latest
+    timeout-minutes: 15
     
     steps:
       - name: Checkout

.github/workflows/docker-publish.yml

@@ -40,5 +40,6 @@ jobs:
         uses: docker/build-push-action@v2
         with:
           context: .
+          file: ./docker/Dockerfile
           push: true
           tags: ghcr.io/mervinpraison/praisonai:latest

.github/workflows/gemini-issue-automated-triage.yml

@@ -0,0 +1,76 @@
+name: Gemini Automated Issue Triage
+
+on:
+  issue_comment:
+    types: [created]
+
+jobs:
+  triage-issue:
+    if: >
+      github.event_name == 'issue_comment' &&
+      !github.event.issue.pull_request &&
+      contains(github.event.comment.body, '@gemini triage') &&
+      (github.event.comment.author_association == 'OWNER' ||
+       github.event.comment.author_association == 'MEMBER' ||
+       github.event.comment.author_association == 'COLLABORATOR')
+    timeout-minutes: 5
+    permissions:
+      issues: write
+      contents: read
+      id-token: write
+    concurrency:
+      group: ${{ github.workflow }}-${{ github.event.issue.number }}
+      cancel-in-progress: true
+    runs-on: ubuntu-latest
+    steps:
+      - name: Generate GitHub App Token
+        id: generate_token
+        uses: actions/create-github-app-token@v1
+        with:
+          app-id: ${{ secrets.APP_ID }}
+          private-key: ${{ secrets.PRIVATE_KEY }}
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          token: ${{ steps.generate_token.outputs.token }}
+
+      - name: Run Gemini Issue Triage
+        uses: google-gemini/gemini-cli-action@main
+        env:
+          GITHUB_TOKEN: ${{ steps.generate_token.outputs.token }}
+          ISSUE_TITLE: ${{ github.event.issue.title }}
+          ISSUE_BODY: ${{ github.event.issue.body }}
+          ISSUE_NUMBER: ${{ github.event.issue.number }}
+          REPOSITORY: ${{ github.repository }}
+        with:
+          version: 0.1.8-rc.0
+          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
+          OTLP_GCP_WIF_PROVIDER: ${{ secrets.OTLP_GCP_WIF_PROVIDER }}
+          OTLP_GOOGLE_CLOUD_PROJECT: ${{ secrets.OTLP_GOOGLE_CLOUD_PROJECT }}
+          settings_json: |
+            {
+              "coreTools": [
+                "run_shell_command(gh label list)",
+                "run_shell_command(gh issue edit)"
+              ],
+              "telemetry": {
+                "enabled": true,
+                "target": "gcp"
+              },
+              "sandbox": false
+            }
+          prompt: |
+            You are an issue triage assistant. Analyze the current GitHub issue and apply the most appropriate existing labels.
+
+            Steps:
+            1. Run: `gh label list --limit 100` to get all available labels.
+            2. Review the issue title and body provided in the environment variables.
+            3. Select the most relevant labels from the existing labels, focusing on kind/*, area/*, and priority/*.
+            4. Apply the selected labels to this issue using: `gh issue edit ISSUE_NUMBER --add-label "label1,label2"`
+
+            Guidelines:
+            - Only use labels that already exist in the repository.
+            - Do not add comments or modify the issue content.
+            - Triage only the current issue.
+            - Assign all applicable kind/*, area/*, and priority/* labels based on the issue content.

.github/workflows/gemini-issue-review.yml

@@ -0,0 +1,198 @@
+name: Gemini Issue Review
+
+on:
+  workflow_dispatch:
+  issue_comment:
+    types: [created]
+
+permissions:
+  contents: write
+  issues: write
+  pull-requests: read
+
+jobs:
+  review-issue:
+    if: >
+      github.event_name == 'workflow_dispatch' ||
+      (github.event_name == 'issue_comment' && 
+       !github.event.issue.pull_request && 
+       contains(github.event.comment.body, '@gemini') &&
+       !contains(github.event.comment.body, '@gemini triage') &&
+       (github.event.comment.author_association == 'OWNER' ||
+        github.event.comment.author_association == 'MEMBER' ||
+        github.event.comment.author_association == 'COLLABORATOR'))
+    runs-on: ubuntu-latest
+    env:
+      GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
+    steps:
+      - name: Generate token
+        id: generate_token
+        uses: actions/create-github-app-token@v1
+        with:
+          app-id: ${{ secrets.APP_ID }}
+          private-key: ${{ secrets.PRIVATE_KEY }}
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          token: ${{ steps.generate_token.outputs.token }}
+
+      - name: Set up Git
+        run: |
+          git config --local user.email "[email protected]"
+          git config --local user.name "Gemini Bot"
+
+      - name: Get issue data
+        id: issue_data
+        env:
+          GH_TOKEN: ${{ steps.generate_token.outputs.token }}
+        run: |
+          # Get issue number from event or context
+          if [ "${{ github.event_name }}" = "issue_comment" ]; then
+            ISSUE_NUMBER="${{ github.event.issue.number }}"
+          elif [ "${{ github.event_name }}" = "issues" ]; then
+            ISSUE_NUMBER="${{ github.event.issue.number }}"
+          else
+            echo "Unable to determine issue number"
+            exit 1
+          fi
+          
+          # Get issue details
+          gh issue view $ISSUE_NUMBER --json title,body,labels,assignees > issue_details.json
+          
+          # Extract additional instructions from comment if triggered by comment
+          ADDITIONAL_INSTRUCTIONS=""
+          if [ "${{ github.event_name }}" = "issue_comment" ]; then
+            COMMENT_BODY="${{ github.event.comment.body }}"
+            ADDITIONAL_INSTRUCTIONS=$(echo "$COMMENT_BODY" | sed -n 's/.*@gemini[[:space:]]*\(.*\)/\1/p' | head -1)
+          fi
+          
+          echo "ISSUE_NUMBER=$ISSUE_NUMBER" >> $GITHUB_OUTPUT
+          echo "ADDITIONAL_INSTRUCTIONS=$ADDITIONAL_INSTRUCTIONS" >> $GITHUB_OUTPUT
+
+      - name: Run Gemini CLI
+        uses: ./.github/actions/gemini
+        env:
+          GITHUB_TOKEN: ${{ steps.generate_token.outputs.token }}
+          ISSUE_NUMBER: ${{ steps.issue_data.outputs.ISSUE_NUMBER }}
+          ADDITIONAL_INSTRUCTIONS: ${{ steps.issue_data.outputs.ADDITIONAL_INSTRUCTIONS }}
+          REPOSITORY: ${{ github.repository }}
+        with:
+          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
+          OTLP_GCP_WIF_PROVIDER: ${{ secrets.OTLP_GCP_WIF_PROVIDER }}
+          OTLP_GOOGLE_CLOUD_PROJECT: ${{ secrets.OTLP_GOOGLE_CLOUD_PROJECT }}
+          prompt: |
+            You are a helpful GitHub issue assistant. Your task is to analyze and help with GitHub issues.
+            
+            **Issue Details:**
+            - Issue Number: #${ISSUE_NUMBER}
+            - Repository: ${REPOSITORY}
+            - Issue URL: ${{ github.event.issue.html_url }}
+            
+            **Additional Instructions:** ${ADDITIONAL_INSTRUCTIONS}
+            
+            **CRITICAL: When making code modifications, follow this EXACT workflow:**
+            
+            **STEP 1: Analyze the Issue**
+            - Use: `gh issue view ${ISSUE_NUMBER} --json title,body,labels,assignees`
+            - Analyze issue content thoroughly
+            - Search codebase for related files using `glob`, `search_file_content`, `list_directory`
+            
+            **STEP 2: If Code Changes Are Needed**
+            Create a new branch with 'gemini/' prefix:
+            - Use: `git checkout -b gemini/issue-${ISSUE_NUMBER}-description`
+            - Example: `git checkout -b gemini/issue-123-fix-sequential-tools`
+            
+            **STEP 3: Make Code Modifications**
+            - Use `read_file` to examine existing code
+            - Use `write_file` or `replace` to make changes
+            - Use `search_file_content` to find related code
+            - Make focused, targeted changes to fix the issue
+            
+            **STEP 4: Test Changes (if applicable)**
+            - Run relevant tests if test files exist
+            - Use `run_shell_command` to execute test commands
+            
+            **STEP 5: Commit and Push Changes**
+            - Use: `git add .` (or specific files)
+            - Use: `git commit -m "Gemini: [Issue #${ISSUE_NUMBER}] Brief description of fix"`
+            - Use: `git push -u origin gemini/issue-${ISSUE_NUMBER}-description`
+            
+            **STEP 6: Create Pull Request**
+            - Use: `gh pr create --title "Fix #${ISSUE_NUMBER}: Issue description" --body "Fixes #${ISSUE_NUMBER}\n\nSummary of changes:\n- Change 1\n- Change 2" --head gemini/issue-${ISSUE_NUMBER}-description --base main`
+            - This will return a PR URL like: https://github.com/repo/pull/123
+            
+            **STEP 7: Comment on Issue with Results**
+            Use: `gh issue comment ${ISSUE_NUMBER} -b "MESSAGE"`
+            
+            **Your final comment MUST include:**
+            - Summary of what was analyzed
+            - What changes were made (if any)
+            - Link to the created PR (if applicable)
+            - Brief explanation of the solution
+            
+            **Example final comment:**
+            ```
+            Hi! I've analyzed and fixed this issue.
+            
+            **Problem:** Sequential tool calling was getting stuck after first tool call.
+            
+            **Solution:** Added proper prompt handling after each tool call in the Ollama model integration.
+            
+            **Changes Made:**
+            - Modified `src/praisonai-agents/ollama-sequential.py`
+            - Added continuation prompts for multi-step tool execution
+            
+            **Pull Request:** https://github.com/MervinPraison/PraisonAI/pull/856
+            
+            The fix is ready for review. Please test and let me know if you encounter any issues!
+            ```
+            
+            **IMPORTANT NOTES:**
+            - Always create branches with 'gemini/' prefix
+            - Always include issue number in branch name and commit message
+            - Always create PR that references the issue
+            - Always provide PR link in your final response
+            - Use the GITHUB_TOKEN environment variable for authentication
+            
+            Please proceed with helping resolve this issue following this exact workflow.
+
+          settings_json: |
+            {
+              "coreTools": [
+                "run_shell_command(echo)",
+                "run_shell_command(gh issue view)",
+                "run_shell_command(gh issue comment)",
+                "run_shell_command(gh issue list)",
+                "run_shell_command(gh issue edit)",
+                "run_shell_command(gh pr create)",
+                "run_shell_command(gh pr view)",
+                "run_shell_command(gh pr list)",
+                "run_shell_command(cat)",
+                "run_shell_command(head)",
+                "run_shell_command(tail)",
+                "run_shell_command(grep)",
+                "run_shell_command(find)",
+                "run_shell_command(git checkout)",
+                "run_shell_command(git add)",
+                "run_shell_command(git commit)",
+                "run_shell_command(git push)",
+                "run_shell_command(git status)",
+                "run_shell_command(git branch)",
+                "list_directory",
+                "read_file",
+                "read_many_files",
+                "write_file",
+                "replace",
+                "glob",
+                "search_file_content",
+                "web_fetch",
+                "google_web_search",
+                "save_memory"
+              ],
+              "telemetry": {
+                "enabled": false,
+                "otlpGcpWifProvider": "${{ secrets.OTLP_GCP_WIF_PROVIDER }}",
+                "googleCloudProject": "${{ secrets.OTLP_GOOGLE_CLOUD_PROJECT }}"
+              }
+            }

.github/workflows/gemini-pr-review.yml

@@ -0,0 +1,242 @@
+name: Gemini PR Review
+
+on:
+  issue_comment:
+    types: [created]
+  workflow_dispatch:
+    inputs:
+      pr_number:
+        description: 'PR number to review'
+        required: true
+        type: number
+
+jobs:
+  review-pr:
+    if: >
+      github.event_name == 'workflow_dispatch' ||
+      (github.event_name == 'issue_comment' && 
+       github.event.issue.pull_request && 
+       contains(github.event.comment.body, '@gemini') &&
+       (github.event.comment.author_association == 'OWNER' ||
+        github.event.comment.author_association == 'MEMBER' ||
+        github.event.comment.author_association == 'COLLABORATOR'))
+    timeout-minutes: 15
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      id-token: write
+      pull-requests: write
+      issues: write
+    steps:
+      - name: Generate GitHub App Token
+        id: generate_token
+        uses: actions/create-github-app-token@v1
+        with:
+          app-id: ${{ secrets.APP_ID }}
+          private-key: ${{ secrets.PRIVATE_KEY }}
+
+      - name: Determine checkout ref
+        id: checkout_ref
+        run: |
+          if [ "${{ github.event_name }}" = "issue_comment" ]; then
+            echo "ref=refs/pull/${{ github.event.issue.number }}/head" >> "$GITHUB_OUTPUT"
+          else
+            echo "ref=${{ github.event.pull_request.head.sha }}" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Checkout PR code
+        uses: actions/checkout@v4
+        with:
+          token: ${{ steps.generate_token.outputs.token }}
+          ref: ${{ steps.checkout_ref.outputs.ref }}
+          fetch-depth: 0
+
+      - name: Get PR details
+        id: get_pr
+        env:
+          GITHUB_TOKEN: ${{ steps.generate_token.outputs.token }}
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            PR_NUMBER=${{ github.event.inputs.pr_number }}
+          elif [ "${{ github.event_name }}" = "issue_comment" ]; then
+            PR_NUMBER=${{ github.event.issue.number }}
+          else
+            PR_NUMBER=${{ github.event.pull_request.number }}
+          fi
+          
+          echo "pr_number=$PR_NUMBER" >> "$GITHUB_OUTPUT"
+          
+          # Extract additional instructions from comment (if triggered by comment)
+          ADDITIONAL_INSTRUCTIONS=""
+          if [ "${{ github.event_name }}" = "issue_comment" ]; then
+            COMMENT_BODY="${{ github.event.comment.body }}"
+            ADDITIONAL_INSTRUCTIONS=$(echo "$COMMENT_BODY" | sed 's/.*@gemini//' | xargs)
+          fi
+          echo "additional_instructions=$ADDITIONAL_INSTRUCTIONS" >> "$GITHUB_OUTPUT"
+          
+          # Get PR details
+          PR_DATA=$(gh pr view $PR_NUMBER --json title,body,additions,deletions,changedFiles,baseRefName,headRefName)
+          echo "pr_data=$PR_DATA" >> "$GITHUB_OUTPUT"
+          
+          # Get file changes
+          CHANGED_FILES=$(gh pr diff $PR_NUMBER --name-only)
+          echo "changed_files<<EOF" >> "$GITHUB_OUTPUT"
+          echo "$CHANGED_FILES" >> "$GITHUB_OUTPUT"
+          echo "EOF" >> "$GITHUB_OUTPUT"
+
+      - name: Run Gemini PR Review
+        uses: ./.github/actions/gemini
+        env:
+          GITHUB_TOKEN: ${{ steps.generate_token.outputs.token }}
+          PR_NUMBER: ${{ steps.get_pr.outputs.pr_number }}
+          PR_DATA: ${{ steps.get_pr.outputs.pr_data }}
+          CHANGED_FILES: ${{ steps.get_pr.outputs.changed_files }}
+          ADDITIONAL_INSTRUCTIONS: ${{ steps.get_pr.outputs.additional_instructions }}
+          REPOSITORY: ${{ github.repository }}
+        with:
+          version: 0.1.8-rc.0
+          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
+          OTLP_GCP_WIF_PROVIDER: ${{ secrets.OTLP_GCP_WIF_PROVIDER }}
+          OTLP_GOOGLE_CLOUD_PROJECT: ${{ secrets.OTLP_GOOGLE_CLOUD_PROJECT }}
+          settings_json: |
+            {
+              "coreTools": [
+                "run_shell_command(echo)",
+                "run_shell_command(gh pr view)",
+                "run_shell_command(gh pr diff)",
+                "run_shell_command(gh pr comment)",
+                "run_shell_command(gh pr list)",
+                "run_shell_command(cat)",
+                "run_shell_command(head)",
+                "run_shell_command(tail)",
+                "run_shell_command(grep)",
+                "run_shell_command(find)",
+                "run_shell_command(git checkout)",
+                "run_shell_command(git add)",
+                "run_shell_command(git commit)",
+                "run_shell_command(git push)",
+                "run_shell_command(git status)",
+                "run_shell_command(git branch)",
+                "run_shell_command(git fetch)",
+                "list_directory",
+                "read_file",
+                "read_many_files",
+                "write_file",
+                "replace",
+                "glob",
+                "search_file_content",
+                "web_fetch",
+                "google_web_search",
+                "save_memory"
+              ],
+              "telemetry": {
+                "enabled": false,
+                "target": "gcp"
+              },
+              "sandbox": false
+            }
+          prompt: |
+            You are an expert code reviewer and AI assistant for Pull Requests. You can review code AND make modifications to improve the PR.
+
+            **PR Details:**
+            - PR Number: #$PR_NUMBER
+            - Repository: $REPOSITORY
+            - Additional Instructions: $ADDITIONAL_INSTRUCTIONS
+
+            **CRITICAL: When making code modifications, follow this EXACT workflow:**
+
+            **STEP 1: Analyze the PR**
+            - Use: `echo "$PR_DATA"` to get PR details (JSON format)
+            - Use: `echo "$CHANGED_FILES"` to get changed files list
+            - Use: `gh pr diff ${PR_NUMBER}` to see the full diff
+            - Use: `gh pr view ${PR_NUMBER} --json title,body,headRefName` to get PR info
+            - Analyze the code changes thoroughly
+
+            **STEP 2: If Code Improvements Are Needed**
+            **IMPORTANT:** DO NOT create a new branch! Work on the EXISTING PR branch.
+            - Use: `git fetch origin` to get latest changes
+            - Get PR branch name: `gh pr view ${PR_NUMBER} --json headRefName`
+            - Switch to PR branch: `git checkout BRANCH_NAME` (use actual branch name from PR)
+            - Use: `git pull origin BRANCH_NAME` to get latest PR changes
+
+            **STEP 3: Make Code Modifications**
+            - Use `read_file` to examine existing code
+            - Use `write_file` or `replace` to make improvements
+            - Use `search_file_content` to find related code
+            - Make focused, targeted improvements to the PR
+
+            **STEP 4: Test Changes (if applicable)**
+            - Run relevant tests if test files exist
+            - Use `run_shell_command` to execute test commands
+
+            **STEP 5: Commit and Push Changes to EXISTING PR Branch**
+            - Use: `git add .` (or specific files)
+            - Use: `git commit -m "Gemini: [PR #${PR_NUMBER}] Brief description of improvements"`
+            - Use: `git push origin BRANCH_NAME` (push to EXISTING PR branch)
+
+            **STEP 6: Review and Comment on PR**
+            Write comprehensive review and post comment with your analysis and any improvements made.
+            Use: `gh pr comment ${PR_NUMBER} -b "MESSAGE"`
+
+            Review Guidelines:
+            - Focus on code quality, security, performance, and maintainability
+            - Check for common issues: potential bugs, security vulnerabilities, performance bottlenecks
+            - Verify error handling and edge cases
+            - Look for code style and best practices
+            - Comment on architecture and design decisions if significant
+            - Be constructive and specific in feedback
+            - Highlight both issues and positive aspects
+            - Suggest improvements with examples when possible
+            
+            Review Areas:
+            - **Security**: Authentication, authorization, input validation, data sanitization
+            - **Performance**: Algorithms, database queries, caching, resource usage
+            - **Reliability**: Error handling, logging, testing coverage, edge cases
+            - **Maintainability**: Code structure, documentation, naming conventions
+            - **Functionality**: Logic correctness, requirements fulfillment
+            
+            Output Format:
+            Structure your review using this exact format with markdown:
+
+            ## 📋 Review Summary
+            Provide a brief 2-3 sentence overview of the PR and overall assessment.
+
+            ## 🔍 General Feedback
+            - List general observations about code quality
+            - Mention overall patterns or architectural decisions
+            - Highlight positive aspects of the implementation
+            - Note any recurring themes across files
+
+            ## 🎯 Specific Feedback
+            Only include sections below that have actual issues. If there are no issues in a priority category, omit that entire section.
+
+            ### 🔴 Critical
+            (Only include this section if there are critical issues)
+            Issues that must be addressed before merging (security vulnerabilities, breaking changes, major bugs):
+            - **File: `filename:line`** - Description of critical issue with specific recommendation
+
+            ### 🟡 High
+            (Only include this section if there are high priority issues)
+            Important issues that should be addressed (performance problems, design flaws, significant bugs):
+            - **File: `filename:line`** - Description of high priority issue with suggested fix
+
+            ### 🟢 Medium
+            (Only include this section if there are medium priority issues)
+            Improvements that would enhance code quality (style issues, minor optimizations, better practices):
+            - **File: `filename:line`** - Description of medium priority improvement
+
+            ### 🔵 Low
+            (Only include this section if there are suggestions)
+            Nice-to-have improvements and suggestions (documentation, naming, minor refactoring):
+            - **File: `filename:line`** - Description of suggestion or enhancement
+
+            **Note**: If no specific issues are found in any category, simply state "No specific issues identified in this review."
+
+            ## ✅ Highlights
+            (Only include this section if there are positive aspects to highlight)
+            - Mention specific good practices or implementations
+            - Acknowledge well-written code sections
+            - Note improvements from previous versions
+
+            ---
+            *Review completed by Gemini CLI*

.github/workflows/test-comprehensive.yml

@@ -26,6 +26,7 @@ on:
 jobs:
   comprehensive-test:
     runs-on: ubuntu-latest
+    timeout-minutes: 15
     strategy:
       matrix:
         python-version: ["3.11"]

.github/workflows/test-core.yml

@@ -9,6 +9,7 @@ on:
 jobs:
   test-core:
     runs-on: ubuntu-latest
+    timeout-minutes: 15
     strategy:
       matrix:
         python-version: [3.11]
@@ -151,7 +152,7 @@ jobs:
             return 'INVALID_TYPE'
 
         print('🔧 Direct PraisonAI API Key Check:')
-        env_api_key = os.environ.get(\\"OPENAI_API_KEY\\", \\"NOT_SET\\")
+        env_api_key = os.environ.get(\"OPENAI_API_KEY\", \"NOT_SET\")
         print(f'Environment OPENAI_API_KEY: {get_key_display_value(env_api_key)}...')
         
         from praisonai import PraisonAI
@@ -163,7 +164,7 @@ jobs:
         
         from praisonai.inc.models import PraisonAIModel
         
-        print('\\\\n🧪 Testing PraisonAIModel with explicit API key (CrewAI method):')
+        print('\\n🧪 Testing PraisonAIModel with explicit API key (CrewAI method):')
         model_with_explicit_key = PraisonAIModel(
             model='openai/gpt-4o-mini',
             base_url=praisonai.config_list[0].get('base_url'),

.github/workflows/test-extended.yml

@@ -13,6 +13,7 @@ on:
 jobs:
   test-examples:
     runs-on: ubuntu-latest
+    timeout-minutes: 15
     
     steps:
     - name: Checkout code
@@ -43,6 +44,9 @@ jobs:
         echo "OPENAI_API_BASE=${{ secrets.OPENAI_API_BASE || 'https://api.openai.com/v1' }}" >> $GITHUB_ENV
         echo "OPENAI_MODEL_NAME=${{ secrets.OPENAI_MODEL_NAME || 'gpt-4o-mini' }}" >> $GITHUB_ENV
         echo "PYTHONPATH=${{ github.workspace }}/src/praisonai-agents:$PYTHONPATH" >> $GITHUB_ENV
+        echo "PRAISONAI_TELEMETRY_DISABLED=true" >> $GITHUB_ENV
+        echo "PRAISONAI_DISABLE_TELEMETRY=true" >> $GITHUB_ENV
+        echo "DO_NOT_TRACK=true" >> $GITHUB_ENV
 
     - name: Test Key Example Scripts
       run: |
@@ -73,6 +77,7 @@ jobs:
 
   performance-test:
     runs-on: ubuntu-latest
+    timeout-minutes: 15
     
     steps:
     - name: Checkout code
@@ -97,6 +102,12 @@ jobs:
         # Install knowledge dependencies from praisonai-agents
         uv pip install --system "praisonaiagents[knowledge]"
 
+    - name: Set environment variables
+      run: |
+        echo "PRAISONAI_TELEMETRY_DISABLED=true" >> $GITHUB_ENV
+        echo "PRAISONAI_DISABLE_TELEMETRY=true" >> $GITHUB_ENV
+        echo "DO_NOT_TRACK=true" >> $GITHUB_ENV
+
     - name: Run Performance Benchmarks
       run: |
         echo "🏃 Running performance benchmarks..."
@@ -161,4 +172,4 @@ jobs:
       with:
         name: performance-report
         path: performance_report.md
-        retention-days: 30 
+        retention-days: 5

.github/workflows/test-frameworks.yml

@@ -24,6 +24,7 @@ on:
 jobs:
   framework-tests:
     runs-on: ubuntu-latest
+    timeout-minutes: 15
     strategy:
       matrix:
         python-version: [3.11]

.github/workflows/test-real.yml

@@ -26,6 +26,7 @@ jobs:
   real-tests:
     runs-on: ubuntu-latest
     if: ${{ github.event.inputs.confirm_costs == 'true' && github.event.inputs.framework != 'none' }}
+    timeout-minutes: 15
     
     strategy:
       matrix:

.github/workflows/unittest.yml

@@ -5,6 +5,7 @@ on: [push, pull_request]
 jobs:
   quick-test:
     runs-on: ubuntu-latest
+    timeout-minutes: 15
 
     steps:
     - name: Checkout code

.gitignore

@@ -75,4 +75,6 @@ agents/praisonaiagents/praisonaiagents.egg-info
 # Local Netlify folder
 .netlify
 .qodo
-CopilotKit*
+CopilotKit*
+.gemini
+issue_details.json

README.md

@@ -120,6 +120,10 @@ agent.start('Write a movie script about a robot in Mars');
 
 ![PraisonAI CLI Demo](docs/demo/praisonai-cli-demo.gif)
 
+## Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=MervinPraison/PraisonAI&type=Date)](https://docs.praison.ai)
+
 ## AI Agents Flow
 
 ```mermaid
@@ -557,10 +561,6 @@ uv pip install -r pyproject.toml --extra "crewai,autogen"
 - 🖼️ Vision Language Model (VLM) Support
 - 🎙️ Real-time Voice Interaction
 
-## Star History
-
-[![Star History Chart](https://api.star-history.com/svg?repos=MervinPraison/PraisonAI&type=Date)](https://docs.praison.ai)
-
 ## Video Tutorials
 
 | Topic | Video |

docker/Dockerfile

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     flask \
-    "praisonai>=2.2.38" \
+    "praisonai>=2.2.77" \
     "praisonai[api]" \
     gunicorn \
     markdown

docker/Dockerfile.chat

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=2.2.38" \
+    "praisonai>=2.2.77" \
     "praisonai[chat]" \
     "embedchain[github,youtube]"
 

docker/Dockerfile.dev

@@ -20,7 +20,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=2.2.38" \
+    "praisonai>=2.2.77" \
     "praisonai[ui]" \
     "praisonai[chat]" \
     "praisonai[realtime]" \

docker/Dockerfile.ui

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=2.2.38" \
+    "praisonai>=2.2.77" \
     "praisonai[ui]" \
     "praisonai[crewai]"
 

docker/README.md

@@ -121,7 +121,7 @@ healthcheck:
 ## 📦 Package Versions
 
 All Docker images use consistent, up-to-date versions:
-- PraisonAI: `>=2.2.38`
+- PraisonAI: `>=2.2.77`
 - PraisonAI Agents: `>=0.0.92`
 - Python: `3.11-slim`
 
@@ -218,7 +218,7 @@ docker-compose up -d
 ### Version Pinning
 To use specific versions, update the Dockerfile:
 ```dockerfile
-RUN pip install "praisonai==2.2.38" "praisonaiagents==0.0.92"
+RUN pip install "praisonai==2.2.77" "praisonaiagents==0.0.92"
 ```
 
 ## 🌐 Production Deployment

examples/cookbooks/Finance_Market_Job_Agents/Financial_Coaching_Agent.ipynb

@@ -0,0 +1,482 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "y8L9VFhhdjhL"
+   },
+   "source": [
+    "# Financial Coaching Agent using PraisonAIAgents"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "6UxqTg7pdkm-"
+   },
+   "source": [
+    "This notebook demonstrates how to build a Financial Coaching Agent using the `praisonaiagents` library.\n",
+    "The agent analyzes user financial data and provides actionable recommendations for budgeting, savings, and debt management.\n",
+    "The notebook is CI-friendly: it uses dummy data if API keys are not set, so all tests/checks will pass."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "CNqB5dPffV3m"
+   },
+   "source": [
+    "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Dhivya-Bharathy/PraisonAI/blob/main/examples/cookbooks/Finance_Market_Job_Agents/Financial_Coaching_Agent.ipynb)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "3cdm72N2doNq"
+   },
+   "source": [
+    "# Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "Pl85wGWzdpTK"
+   },
+   "outputs": [],
+   "source": [
+    "!pip install praisonaiagents pandas"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "YOlEEkk4ePqy"
+   },
+   "source": [
+    "# Set up key"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "id": "T9zKRkv_eRsc"
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "# Try to get keys from environment variables, or use placeholders\n",
+    "OPENAI_API_KEY = os.environ.get(\"OPENAI_API_KEY\", \"sk-..\")\n",
+    "\n",
+    "# Set them in the environment for downstream code\n",
+    "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY\n",
+    "\n",
+    "def is_valid_key(key, prefix):\n",
+    "    return key and key != f\"{prefix}-..\" and key.startswith(prefix)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "FGYJpB9eeaSY"
+   },
+   "source": [
+    "# Tool: Financial Summary"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "id": "asLRt9gAecJ2"
+   },
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "class FinancialSummaryTool:\n",
+    "    \"\"\"\n",
+    "    Custom tool to summarize financial data and calculate basic stats.\n",
+    "    \"\"\"\n",
+    "    def __init__(self, income, expenses, debts):\n",
+    "        self.income = income\n",
+    "        self.expenses = expenses\n",
+    "        self.debts = debts\n",
+    "\n",
+    "    def summary(self):\n",
+    "        total_expenses = sum(self.expenses.values())\n",
+    "        surplus = self.income - total_expenses\n",
+    "        total_debt = sum(d['amount'] for d in self.debts)\n",
+    "        return {\n",
+    "            \"total_expenses\": total_expenses,\n",
+    "            \"surplus\": surplus,\n",
+    "            \"total_debt\": total_debt,\n",
+    "            \"expense_breakdown\": self.expenses,\n",
+    "            \"debts\": self.debts\n",
+    "        }"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "lIysLOOdef3b"
+   },
+   "source": [
+    "# YAML prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "GDbWRmp2egsz",
+    "outputId": "cf4e4d15-7446-4613-9a20-298674f0b4d3"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'agent': {'name': 'Financial Coaching Agent', 'description': 'An agent that analyzes user financial data and provides actionable recommendations for budgeting, savings, and debt management.\\n', 'tools': [{'name': 'FinancialSummaryTool', 'description': 'Summarizes income, expenses, and debts for the agent.'}], 'workflow': [{'step': 'Summarize financial data using FinancialSummaryTool'}, {'step': 'Analyze summary and provide recommendations'}]}, 'inputs': ['monthly_income', 'expenses', 'debts'], 'outputs': ['recommendations']}\n"
+     ]
+    }
+   ],
+   "source": [
+    "import yaml\n",
+    "\n",
+    "yaml_prompt = \"\"\"\n",
+    "agent:\n",
+    "  name: Financial Coaching Agent\n",
+    "  description: |\n",
+    "    An agent that analyzes user financial data and provides actionable recommendations for budgeting, savings, and debt management.\n",
+    "  tools:\n",
+    "    - name: FinancialSummaryTool\n",
+    "      description: Summarizes income, expenses, and debts for the agent.\n",
+    "  workflow:\n",
+    "    - step: Summarize financial data using FinancialSummaryTool\n",
+    "    - step: Analyze summary and provide recommendations\n",
+    "inputs:\n",
+    "  - monthly_income\n",
+    "  - expenses\n",
+    "  - debts\n",
+    "outputs:\n",
+    "  - recommendations\n",
+    "\"\"\"\n",
+    "print(yaml.safe_load(yaml_prompt))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "C-FE-hTKekHK"
+   },
+   "source": [
+    "# Main"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 1000,
+     "referenced_widgets": [
+      "b27151e0a1ec47d8a36433ef503eede2",
+      "58e152a95c1d49d68b45aea3b837b6d3"
+     ]
+    },
+    "id": "48oIH5LYek-q",
+    "outputId": "b501eae2-63c2-434d-f5c3-abba6b93956e"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╭─ </span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8; font-weight: bold\">Agent Info</span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\"> ────────────────────────────────────────────────────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #ff9b9b; text-decoration-color: #ff9b9b; font-weight: bold\">👤 Agent:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Financial Coaching Agent</span>                                                                             <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #b4b4b3; text-decoration-color: #b4b4b3; font-weight: bold\">Role:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Assistant</span>                                                                                                <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[38;2;210;227;200m╭─\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[1;38;2;210;227;200mAgent Info\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[38;2;210;227;200m───────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;210;227;200m─╮\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;255;155;155m👤 Agent:\u001b[0m \u001b[38;2;255;229;229mFinancial Coaching Agent\u001b[0m                                                                             \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;180;180;179mRole:\u001b[0m \u001b[38;2;255;229;229mAssistant\u001b[0m                                                                                                \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b27151e0a1ec47d8a36433ef503eede2",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Output()"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">Response generated in 11.0s</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[2mResponse generated in 11.0s\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭───────────────────────────────────────────────────── Task ──────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> You are a financial coach. Analyze the following summary and provide actionable recommendations: - Monthly      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> income: $3000 - Total expenses: $2350 - Surplus: $650 - Total debt: $10000 - Expense breakdown: {'Housing':     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> 1200, 'Food': 400, 'Transportation': 200, 'Entertainment': 150, 'Savings': 300, 'Other': 100} - Debts:          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> [{'name': 'Credit Card', 'amount': 2000, 'interest_rate': 18.0, 'min_payment': 50}, {'name': 'Student Loan',    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> 'amount': 8000, 'interest_rate': 5.0, 'min_payment': 100}]                                                      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[36m╭─\u001b[0m\u001b[36m────────────────────────────────────────────────────\u001b[0m\u001b[36m Task \u001b[0m\u001b[36m─────────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+       "\u001b[36m│\u001b[0m You are a financial coach. Analyze the following summary and provide actionable recommendations: - Monthly      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m income: $3000 - Total expenses: $2350 - Surplus: $650 - Total debt: $10000 - Expense breakdown: {'Housing':     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m 1200, 'Food': 400, 'Transportation': 200, 'Entertainment': 150, 'Savings': 300, 'Other': 100} - Debts:          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m [{'name': 'Credit Card', 'amount': 2000, 'interest_rate': 18.0, 'min_payment': 50}, {'name': 'Student Loan',    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m 'amount': 8000, 'interest_rate': 5.0, 'min_payment': 100}]                                                      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭─────────────────────────────────────────────────── Response ────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Based on the provided financial summary, here are some actionable recommendations to help manage your finances  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> more effectively and reduce your debt:                                                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 1 </span><span style=\"font-weight: bold\">Prioritize Debt Repayment:</span>                                                                                   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Focus on paying off the high-interest debt first, which is the credit card debt with an 18% interest      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>rate. Consider using the debt avalanche method, where you pay extra towards the debt with the highest     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>interest rate while making minimum payments on others.                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>With a surplus of $650, allocate a significant portion of this towards the credit card debt. For example, <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>you could pay $400 towards the credit card debt (including the $50 minimum payment), which would help     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>reduce the principal faster and save on interest.                                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 2 </span><span style=\"font-weight: bold\">Review and Adjust Expenses:</span>                                                                                  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span><span style=\"font-weight: bold\">Housing:</span> At $1200, housing is a significant portion of your expenses. If possible, explore options to     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>reduce this cost, such as negotiating rent, finding a roommate, or moving to a less expensive place.      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span><span style=\"font-weight: bold\">Food:</span> Consider meal planning, cooking at home, and reducing dining out to lower the $400 food expense.    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span><span style=\"font-weight: bold\">Entertainment:</span> At $150, see if you can cut back on discretionary spending. Look for free or low-cost      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>entertainment options.                                                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span><span style=\"font-weight: bold\">Other Expenses:</span> Review the $100 in 'Other' expenses to identify any non-essential spending that can be    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>reduced or eliminated.                                                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 3 </span><span style=\"font-weight: bold\">Increase Savings:</span>                                                                                            <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>While you are already saving $300 monthly, consider increasing this amount once the high-interest debt is <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>paid off. Building an emergency fund should be a priority to cover 3-6 months of expenses.                <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 4 </span><span style=\"font-weight: bold\">Boost Income:</span>                                                                                                <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Explore opportunities to increase your income, such as taking on a part-time job, freelancing, or selling <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>unused items. Any additional income can accelerate debt repayment and increase savings.                   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 5 </span><span style=\"font-weight: bold\">Monitor and Adjust:</span>                                                                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Regularly review your budget and expenses to ensure you are on track with your financial goals. Adjust    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>your plan as needed to accommodate changes in income or expenses.                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 6 </span><span style=\"font-weight: bold\">Consider Debt Consolidation:</span>                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>If you have a good credit score, look into consolidating your credit card debt into a lower-interest      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>personal loan. This could reduce your overall interest payments and simplify your debt repayment process. <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> By implementing these recommendations, you can effectively manage your finances, reduce debt, and work towards  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> achieving greater financial stability.                                                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[36m╭─\u001b[0m\u001b[36m──────────────────────────────────────────────────\u001b[0m\u001b[36m Response \u001b[0m\u001b[36m───────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Based on the provided financial summary, here are some actionable recommendations to help manage your finances  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m more effectively and reduce your debt:                                                                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 1 \u001b[0m\u001b[1mPrioritize Debt Repayment:\u001b[0m                                                                                   \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mFocus on paying off the high-interest debt first, which is the credit card debt with an 18% interest      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mrate. Consider using the debt avalanche method, where you pay extra towards the debt with the highest     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0minterest rate while making minimum payments on others.                                                    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mWith a surplus of $650, allocate a significant portion of this towards the credit card debt. For example, \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0myou could pay $400 towards the credit card debt (including the $50 minimum payment), which would help     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mreduce the principal faster and save on interest.                                                         \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 2 \u001b[0m\u001b[1mReview and Adjust Expenses:\u001b[0m                                                                                  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0m\u001b[1mHousing:\u001b[0m At $1200, housing is a significant portion of your expenses. If possible, explore options to     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mreduce this cost, such as negotiating rent, finding a roommate, or moving to a less expensive place.      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0m\u001b[1mFood:\u001b[0m Consider meal planning, cooking at home, and reducing dining out to lower the $400 food expense.    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0m\u001b[1mEntertainment:\u001b[0m At $150, see if you can cut back on discretionary spending. Look for free or low-cost      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mentertainment options.                                                                                    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0m\u001b[1mOther Expenses:\u001b[0m Review the $100 in 'Other' expenses to identify any non-essential spending that can be    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mreduced or eliminated.                                                                                    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 3 \u001b[0m\u001b[1mIncrease Savings:\u001b[0m                                                                                            \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mWhile you are already saving $300 monthly, consider increasing this amount once the high-interest debt is \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mpaid off. Building an emergency fund should be a priority to cover 3-6 months of expenses.                \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 4 \u001b[0m\u001b[1mBoost Income:\u001b[0m                                                                                                \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mExplore opportunities to increase your income, such as taking on a part-time job, freelancing, or selling \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0munused items. Any additional income can accelerate debt repayment and increase savings.                   \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 5 \u001b[0m\u001b[1mMonitor and Adjust:\u001b[0m                                                                                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mRegularly review your budget and expenses to ensure you are on track with your financial goals. Adjust    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0myour plan as needed to accommodate changes in income or expenses.                                         \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 6 \u001b[0m\u001b[1mConsider Debt Consolidation:\u001b[0m                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mIf you have a good credit score, look into consolidating your credit card debt into a lower-interest      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mpersonal loan. This could reduce your overall interest payments and simplify your debt repayment process. \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m By implementing these recommendations, you can effectively manage your finances, reduce debt, and work towards  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m achieving greater financial stability.                                                                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=== Financial Coaching Agent Recommendations ===\n",
+      "Based on the provided financial summary, here are some actionable recommendations to help manage your finances more effectively and reduce your debt:\n",
+      "\n",
+      "1. **Prioritize Debt Repayment:**\n",
+      "   - Focus on paying off the high-interest debt first, which is the credit card debt with an 18% interest rate. Consider using the debt avalanche method, where you pay extra towards the debt with the highest interest rate while making minimum payments on others.\n",
+      "   - With a surplus of $650, allocate a significant portion of this towards the credit card debt. For example, you could pay $400 towards the credit card debt (including the $50 minimum payment), which would help reduce the principal faster and save on interest.\n",
+      "\n",
+      "2. **Review and Adjust Expenses:**\n",
+      "   - **Housing:** At $1200, housing is a significant portion of your expenses. If possible, explore options to reduce this cost, such as negotiating rent, finding a roommate, or moving to a less expensive place.\n",
+      "   - **Food:** Consider meal planning, cooking at home, and reducing dining out to lower the $400 food expense.\n",
+      "   - **Entertainment:** At $150, see if you can cut back on discretionary spending. Look for free or low-cost entertainment options.\n",
+      "   - **Other Expenses:** Review the $100 in 'Other' expenses to identify any non-essential spending that can be reduced or eliminated.\n",
+      "\n",
+      "3. **Increase Savings:**\n",
+      "   - While you are already saving $300 monthly, consider increasing this amount once the high-interest debt is paid off. Building an emergency fund should be a priority to cover 3-6 months of expenses.\n",
+      "\n",
+      "4. **Boost Income:**\n",
+      "   - Explore opportunities to increase your income, such as taking on a part-time job, freelancing, or selling unused items. Any additional income can accelerate debt repayment and increase savings.\n",
+      "\n",
+      "5. **Monitor and Adjust:**\n",
+      "   - Regularly review your budget and expenses to ensure you are on track with your financial goals. Adjust your plan as needed to accommodate changes in income or expenses.\n",
+      "\n",
+      "6. **Consider Debt Consolidation:**\n",
+      "   - If you have a good credit score, look into consolidating your credit card debt into a lower-interest personal loan. This could reduce your overall interest payments and simplify your debt repayment process.\n",
+      "\n",
+      "By implementing these recommendations, you can effectively manage your finances, reduce debt, and work towards achieving greater financial stability.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from praisonaiagents import Agent\n",
+    "\n",
+    "# Dummy data for CI/public use\n",
+    "dummy_financial_data = {\n",
+    "    \"monthly_income\": 3000,\n",
+    "    \"expenses\": {\n",
+    "        \"Housing\": 1200,\n",
+    "        \"Food\": 400,\n",
+    "        \"Transportation\": 200,\n",
+    "        \"Entertainment\": 150,\n",
+    "        \"Savings\": 300,\n",
+    "        \"Other\": 100\n",
+    "    },\n",
+    "    \"debts\": [\n",
+    "        {\"name\": \"Credit Card\", \"amount\": 2000, \"interest_rate\": 18.0, \"min_payment\": 50},\n",
+    "        {\"name\": \"Student Loan\", \"amount\": 8000, \"interest_rate\": 5.0, \"min_payment\": 100}\n",
+    "    ]\n",
+    "}\n",
+    "\n",
+    "income = dummy_financial_data[\"monthly_income\"]\n",
+    "expenses = dummy_financial_data[\"expenses\"]\n",
+    "debts = dummy_financial_data[\"debts\"]\n",
+    "\n",
+    "tool = FinancialSummaryTool(income, expenses, debts)\n",
+    "summary = tool.summary()\n",
+    "\n",
+    "if not is_valid_key(OPENAI_API_KEY, \"sk\"):\n",
+    "    print(\"API key not set or is a placeholder. Using dummy recommendations for CI/testing.\")\n",
+    "    recommendations = \"\"\"\n",
+    "    - Review your monthly expenses and identify areas to cut back.\n",
+    "    - Increase your monthly savings by at least 10%.\n",
+    "    - Pay off high-interest debts first (e.g., Credit Card).\n",
+    "    - Build an emergency fund covering at least 3-6 months of expenses.\n",
+    "    \"\"\"\n",
+    "else:\n",
+    "    prompt = f\"\"\"\n",
+    "    You are a financial coach. Analyze the following summary and provide actionable recommendations:\n",
+    "    - Monthly income: ${summary['surplus'] + summary['total_expenses']}\n",
+    "    - Total expenses: ${summary['total_expenses']}\n",
+    "    - Surplus: ${summary['surplus']}\n",
+    "    - Total debt: ${summary['total_debt']}\n",
+    "    - Expense breakdown: {summary['expense_breakdown']}\n",
+    "    - Debts: {summary['debts']}\n",
+    "    \"\"\"\n",
+    "    agent = Agent(\n",
+    "        name=\"Financial Coaching Agent\",\n",
+    "        api_key=OPENAI_API_KEY\n",
+    "    )\n",
+    "    # Use start(prompt) instead of run()\n",
+    "    recommendations = agent.start(prompt)\n",
+    "\n",
+    "print(\"=== Financial Coaching Agent Recommendations ===\")\n",
+    "print(recommendations)"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

examples/cookbooks/Health_Fitness_Agents/Air_Quality_Analysis_Agent.ipynb

@@ -0,0 +1,573 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "vUS5f8IhI4Iw"
+   },
+   "source": [
+    "# Air Quality Analysis Agent using PraisonAIAgents"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "IPiJvwVgI5hK"
+   },
+   "source": [
+    "## Description\n",
+    "\n",
+    "This notebook demonstrates how to build an Air Quality Analysis Agent using the `praisonaiagents` library.  \n",
+    "The agent retrieves real-time air quality data for a specified location, analyzes the results, and provides actionable insights or health recommendations.  \n",
+    "You will learn how to set up the environment, configure API keys, use custom tools, and orchestrate the agent workflow with a YAML prompt."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "oqdL8WpNTKu5"
+   },
+   "source": [
+    "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/MervinPraison/PraisonAI/blob/main/examples/cookbooks/Health_Fitness_Agents/Air_Quality_Analysis_Agent.ipynb)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "p7CFp0tkJKmU"
+   },
+   "source": [
+    "# Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "q6Aq57bqJKFc"
+   },
+   "outputs": [],
+   "source": [
+    "!pip install praisonaiagents firecrawl requests"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "NLJn9uGVJldu"
+   },
+   "source": [
+    "# Set up API Key"
+   ]
+  },{
+ "cell_type": "code",
+ "execution_count": 32,
+ "metadata": {
+  "id": "ZxHL7mJYJpVb"
+ },
+ "outputs": [],
+ "source": [
+  "# Replace with your actual API keys\n",
+  "FIRECRAWL_API_KEY = \"fc-...\"  # Your Firecrawl API key\n",
+  "OPENAI_API_KEY = \"sk-...\"     # Your OpenAI API key\n",
+  "\n",
+  "import os\n",
+  "os.environ[\"FIRECRAWL_API_KEY\"] = FIRECRAWL_API_KEY\n",
+  "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY\n"
+ ]
+},
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "eVb00IhbJ60M"
+   },
+   "source": [
+    "# Tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {
+    "id": "3YgwDwyFLXlU"
+   },
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "from firecrawl import FirecrawlApp\n",
+    "from typing import Dict\n",
+    "\n",
+    "class AQIDataFetcher:\n",
+    "    def __init__(self, firecrawl_key: str):\n",
+    "        self.firecrawl = FirecrawlApp(api_key=firecrawl_key)\n",
+    "\n",
+    "    def fetch(self, country: str, state: str, city: str) -> Dict:\n",
+    "        country_clean = country.lower().replace(' ', '-')\n",
+    "        city_clean = city.lower().replace(' ', '-')\n",
+    "        if not state or state.lower() == 'none':\n",
+    "            url = f\"https://www.aqi.in/dashboard/{country_clean}/{city_clean}\"\n",
+    "        else:\n",
+    "            state_clean = state.lower().replace(' ', '-')\n",
+    "            url = f\"https://www.aqi.in/dashboard/{country_clean}/{state_clean}/{city_clean}\"\n",
+    "\n",
+    "        # Check if the URL is valid and reachable\n",
+    "        print(f\"Testing URL: {url}\")\n",
+    "        try:\n",
+    "            resp = requests.get(url)\n",
+    "            print(f\"Status code: {resp.status_code}\")\n",
+    "            if resp.status_code != 200:\n",
+    "                print(f\"URL not reachable: {url} (status code: {resp.status_code})\")\n",
+    "                return None\n",
+    "        except Exception as e:\n",
+    "            print(f\"Error: {e}\")\n",
+    "            return None\n",
+    "\n",
+    "        schema = {\n",
+    "            \"type\": \"object\",\n",
+    "            \"properties\": {\n",
+    "                \"aqi\": {\"type\": \"number\", \"description\": \"Air Quality Index\"},\n",
+    "                \"temperature\": {\"type\": \"number\", \"description\": \"Temperature in degrees Celsius\"},\n",
+    "                \"humidity\": {\"type\": \"number\", \"description\": \"Humidity percentage\"},\n",
+    "                \"wind_speed\": {\"type\": \"number\", \"description\": \"Wind speed in kilometers per hour\"},\n",
+    "                \"pm25\": {\"type\": \"number\", \"description\": \"Particulate Matter 2.5 micrometers\"},\n",
+    "                \"pm10\": {\"type\": \"number\", \"description\": \"Particulate Matter 10 micrometers\"},\n",
+    "                \"co\": {\"type\": \"number\", \"description\": \"Carbon Monoxide level\"}\n",
+    "            },\n",
+    "            \"required\": [\"aqi\", \"temperature\", \"humidity\", \"wind_speed\", \"pm25\", \"pm10\", \"co\"]\n",
+    "        }\n",
+    "\n",
+    "        response = self.firecrawl.extract(\n",
+    "            urls=[f\"{url}/*\"],\n",
+    "            prompt='Extract the current real-time AQI, temperature, humidity, wind speed, PM2.5, PM10, and CO levels from the page. Also extract the timestamp of the data.',\n",
+    "            schema=schema\n",
+    "        )\n",
+    "        return response"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "3sUNJChKOVUm"
+   },
+   "source": [
+    "# YAML Prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "0G9tLj0nJ8B_",
+    "outputId": "61e66fe7-df17-4d2d-ad27-a9f4466298a4"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'agent': {'name': 'Air Quality Health Advisor', 'description': 'An agent that analyzes real-time air quality data for a given location and provides personalized health recommendations based on user context.\\n', 'tools': [{'name': 'AQIDataFetcher', 'description': 'Fetches AQI and weather data for a specified city, state, and country using Firecrawl.'}], 'workflow': [{'step': \"Fetch AQI data for the user's location using AQIDataFetcher.\"}, {'step': 'Analyze AQI and weather data.'}, {'step': \"Consider user's medical conditions and planned activity.\"}, {'step': 'Generate health and activity recommendations.'}]}, 'inputs': ['city', 'state', 'country', 'medical_conditions', 'planned_activity'], 'outputs': ['recommendations']}\n"
+     ]
+    }
+   ],
+   "source": [
+    "import yaml\n",
+    "\n",
+    "yaml_prompt = \"\"\"\n",
+    "agent:\n",
+    "  name: Air Quality Health Advisor\n",
+    "  description: |\n",
+    "    An agent that analyzes real-time air quality data for a given location and provides personalized health recommendations based on user context.\n",
+    "  tools:\n",
+    "    - name: AQIDataFetcher\n",
+    "      description: Fetches AQI and weather data for a specified city, state, and country using Firecrawl.\n",
+    "  workflow:\n",
+    "    - step: Fetch AQI data for the user's location using AQIDataFetcher.\n",
+    "    - step: Analyze AQI and weather data.\n",
+    "    - step: Consider user's medical conditions and planned activity.\n",
+    "    - step: Generate health and activity recommendations.\n",
+    "inputs:\n",
+    "  - city\n",
+    "  - state\n",
+    "  - country\n",
+    "  - medical_conditions\n",
+    "  - planned_activity\n",
+    "outputs:\n",
+    "  - recommendations\n",
+    "\"\"\"\n",
+    "\n",
+    "print(yaml.safe_load(yaml_prompt))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "2HIPkoUyKEY-"
+   },
+   "source": [
+    "# Main"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 1000,
+     "referenced_widgets": [
+      "4c2bac52ad444499b362978d8fe92d97",
+      "5203e4d9bd3c47f09d2f204c7f1e078f"
+     ]
+    },
+    "id": "UQ4sHVW0KFp-",
+    "outputId": "4efe39ea-c924-41e9-cc66-f4894e367280"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Testing URL: https://www.aqi.in/dashboard/india/maharashtra/mumbai\n",
+      "Status code: 200\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╭─ </span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8; font-weight: bold\">Agent Info</span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\"> ────────────────────────────────────────────────────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #ff9b9b; text-decoration-color: #ff9b9b; font-weight: bold\">👤 Agent:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Air Quality Health Advisor</span>                                                                           <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #b4b4b3; text-decoration-color: #b4b4b3; font-weight: bold\">Role:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Assistant</span>                                                                                                <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[38;2;210;227;200m╭─\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[1;38;2;210;227;200mAgent Info\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[38;2;210;227;200m───────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;210;227;200m─╮\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;255;155;155m👤 Agent:\u001b[0m \u001b[38;2;255;229;229mAir Quality Health Advisor\u001b[0m                                                                           \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;180;180;179mRole:\u001b[0m \u001b[38;2;255;229;229mAssistant\u001b[0m                                                                                                \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "4c2bac52ad444499b362978d8fe92d97",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Output()"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">Response generated in 10.8s</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[2mResponse generated in 10.8s\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭───────────────────────────────────────────────────── Task ──────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> You are an expert health advisor using the GPT-4o Mini model.                                                   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\">                                                                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">Based on the following air quality conditions in Mumbai, Maharashtra, India:</span><span style=\"background-color: #272822\">                                  </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- Overall AQI: 75</span><span style=\"background-color: #272822\">                                                                                             </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- PM2.5 Level: 22 µg/m³</span><span style=\"background-color: #272822\">                                                                                       </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- PM10 Level: 60 µg/m³</span><span style=\"background-color: #272822\">                                                                                        </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- CO Level: 650 ppb</span><span style=\"background-color: #272822\">                                                                                           </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\">                                                                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">Weather conditions:</span><span style=\"background-color: #272822\">                                                                                           </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- Temperature: 28°C</span><span style=\"background-color: #272822\">                                                                                           </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- Humidity: 84%</span><span style=\"background-color: #272822\">                                                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- Wind Speed: 30 km/h</span><span style=\"background-color: #272822\">                                                                                         </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\">                                                                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">User's Context:</span><span style=\"background-color: #272822\">                                                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- Medical Conditions: asthma</span><span style=\"background-color: #272822\">                                                                                  </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">- Planned Activity: morning jog for 2 hours</span><span style=\"background-color: #272822\">                                                                   </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\">                                                                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">**Comprehensive Health Recommendations:**</span><span style=\"background-color: #272822\">                                                                     </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">1. **Impact of Current Air Quality on Health:**</span><span style=\"background-color: #272822\">                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">2. **Necessary Safety Precautions for Planned Activity:**</span><span style=\"background-color: #272822\">                                                     </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">3. **Advisability of Planned Activity:**</span><span style=\"background-color: #272822\">                                                                      </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\"> </span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">4. **Best Time to Conduct the Activity:**</span><span style=\"background-color: #272822\">                                                                     </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"background-color: #272822\">                                                                                                               </span> <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[36m╭─\u001b[0m\u001b[36m────────────────────────────────────────────────────\u001b[0m\u001b[36m Task \u001b[0m\u001b[36m─────────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+       "\u001b[36m│\u001b[0m You are an expert health advisor using the GPT-4o Mini model.                                                   \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m                                                                                                               \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mBased on the following air quality conditions in Mumbai, Maharashtra, India:\u001b[0m\u001b[48;2;39;40;34m                                 \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- Overall AQI: 75\u001b[0m\u001b[48;2;39;40;34m                                                                                            \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- PM2.5 Level: 22 µg/m³\u001b[0m\u001b[48;2;39;40;34m                                                                                      \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- PM10 Level: 60 µg/m³\u001b[0m\u001b[48;2;39;40;34m                                                                                       \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- CO Level: 650 ppb\u001b[0m\u001b[48;2;39;40;34m                                                                                          \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[48;2;39;40;34m                                                                                                             \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mWeather conditions:\u001b[0m\u001b[48;2;39;40;34m                                                                                          \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- Temperature: 28°C\u001b[0m\u001b[48;2;39;40;34m                                                                                          \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- Humidity: 84%\u001b[0m\u001b[48;2;39;40;34m                                                                                              \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- Wind Speed: 30 km/h\u001b[0m\u001b[48;2;39;40;34m                                                                                        \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[48;2;39;40;34m                                                                                                             \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mUser's Context:\u001b[0m\u001b[48;2;39;40;34m                                                                                              \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- Medical Conditions: asthma\u001b[0m\u001b[48;2;39;40;34m                                                                                 \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m- Planned Activity: morning jog for 2 hours\u001b[0m\u001b[48;2;39;40;34m                                                                  \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[48;2;39;40;34m                                                                                                             \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m**Comprehensive Health Recommendations:**\u001b[0m\u001b[48;2;39;40;34m                                                                    \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m1. **Impact of Current Air Quality on Health:**\u001b[0m\u001b[48;2;39;40;34m                                                              \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m2. **Necessary Safety Precautions for Planned Activity:**\u001b[0m\u001b[48;2;39;40;34m                                                    \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m3. **Advisability of Planned Activity:**\u001b[0m\u001b[48;2;39;40;34m                                                                     \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m4. **Best Time to Conduct the Activity:**\u001b[0m\u001b[48;2;39;40;34m                                                                    \u001b[0m\u001b[48;2;39;40;34m \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[48;2;39;40;34m                                                                                                               \u001b[0m \u001b[36m│\u001b[0m\n",
+       "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭─────────────────────────────────────────────────── Response ────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Certainly! Here are the comprehensive health recommendations based on the provided conditions:                  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 1 </span><span style=\"font-weight: bold\">Impact of Current Air Quality on Health:</span>                                                                     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>The overall AQI of 75 is considered \"Moderate.\" This level is generally acceptable for most individuals,  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>but sensitive groups, such as those with asthma, may experience some respiratory discomfort.              <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>PM2.5 and PM10 levels are within moderate ranges, which can still pose a risk for people with             <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>pre-existing respiratory conditions like asthma.                                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>The CO level of 650 ppb is not typically concerning, but it is important to be cautious as individuals    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>with asthma may be more sensitive to pollutants.                                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 2 </span><span style=\"font-weight: bold\">Necessary Safety Precautions for Planned Activity:</span>                                                           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Consider wearing a mask designed to filter out particulate matter to reduce inhalation of pollutants.     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Carry a rescue inhaler and any other prescribed asthma medication.                                        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Stay hydrated, as high humidity can exacerbate asthma symptoms.                                           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Monitor your breathing and be prepared to stop the activity if you experience any respiratory distress.   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Choose a route with less traffic to minimize exposure to vehicle emissions.                               <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 3 </span><span style=\"font-weight: bold\">Advisability of Planned Activity:</span>                                                                            <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Given the moderate AQI and the user's asthma condition, it is advisable to proceed with caution. A 2-hour <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>jog may be too strenuous under these conditions, so consider reducing the duration or intensity of the    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>jog.                                                                                                      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>It may be beneficial to consult with a healthcare provider to tailor the activity to your specific health <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>needs.                                                                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 4 </span><span style=\"font-weight: bold\">Best Time to Conduct the Activity:</span>                                                                           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Early morning hours, just after sunrise, are typically better for outdoor activities as pollution levels  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>tend to be lower.                                                                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Avoid peak traffic times to reduce exposure to vehicle emissions.                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    • </span>Check real-time air quality updates to ensure conditions remain stable or improve before starting the     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">      </span>activity.                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> By following these recommendations, you can help mitigate potential health risks while enjoying your planned    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> activity.                                                                                                       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[36m╭─\u001b[0m\u001b[36m──────────────────────────────────────────────────\u001b[0m\u001b[36m Response \u001b[0m\u001b[36m───────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Certainly! Here are the comprehensive health recommendations based on the provided conditions:                  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 1 \u001b[0m\u001b[1mImpact of Current Air Quality on Health:\u001b[0m                                                                     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mThe overall AQI of 75 is considered \"Moderate.\" This level is generally acceptable for most individuals,  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mbut sensitive groups, such as those with asthma, may experience some respiratory discomfort.              \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mPM2.5 and PM10 levels are within moderate ranges, which can still pose a risk for people with             \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mpre-existing respiratory conditions like asthma.                                                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mThe CO level of 650 ppb is not typically concerning, but it is important to be cautious as individuals    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mwith asthma may be more sensitive to pollutants.                                                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 2 \u001b[0m\u001b[1mNecessary Safety Precautions for Planned Activity:\u001b[0m                                                           \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mConsider wearing a mask designed to filter out particulate matter to reduce inhalation of pollutants.     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mCarry a rescue inhaler and any other prescribed asthma medication.                                        \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mStay hydrated, as high humidity can exacerbate asthma symptoms.                                           \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mMonitor your breathing and be prepared to stop the activity if you experience any respiratory distress.   \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mChoose a route with less traffic to minimize exposure to vehicle emissions.                               \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 3 \u001b[0m\u001b[1mAdvisability of Planned Activity:\u001b[0m                                                                            \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mGiven the moderate AQI and the user's asthma condition, it is advisable to proceed with caution. A 2-hour \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mjog may be too strenuous under these conditions, so consider reducing the duration or intensity of the    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mjog.                                                                                                      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mIt may be beneficial to consult with a healthcare provider to tailor the activity to your specific health \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mneeds.                                                                                                    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 4 \u001b[0m\u001b[1mBest Time to Conduct the Activity:\u001b[0m                                                                           \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mEarly morning hours, just after sunrise, are typically better for outdoor activities as pollution levels  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mtend to be lower.                                                                                         \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mAvoid peak traffic times to reduce exposure to vehicle emissions.                                         \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m • \u001b[0mCheck real-time air quality updates to ensure conditions remain stable or improve before starting the     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m   \u001b[0m\u001b[1;33m   \u001b[0mactivity.                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m By following these recommendations, you can help mitigate potential health risks while enjoying your planned    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m activity.                                                                                                       \u001b[36m│\u001b[0m\n",
+       "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "=== Air Quality Analysis Agent Recommendations ===\n",
+      "Certainly! Here are the comprehensive health recommendations based on the provided conditions:\n",
+      "\n",
+      "1. **Impact of Current Air Quality on Health:**\n",
+      "   - The overall AQI of 75 is considered \"Moderate.\" This level is generally acceptable for most individuals, but sensitive groups, such as those with asthma, may experience some respiratory discomfort.\n",
+      "   - PM2.5 and PM10 levels are within moderate ranges, which can still pose a risk for people with pre-existing respiratory conditions like asthma.\n",
+      "   - The CO level of 650 ppb is not typically concerning, but it is important to be cautious as individuals with asthma may be more sensitive to pollutants.\n",
+      "\n",
+      "2. **Necessary Safety Precautions for Planned Activity:**\n",
+      "   - Consider wearing a mask designed to filter out particulate matter to reduce inhalation of pollutants.\n",
+      "   - Carry a rescue inhaler and any other prescribed asthma medication.\n",
+      "   - Stay hydrated, as high humidity can exacerbate asthma symptoms.\n",
+      "   - Monitor your breathing and be prepared to stop the activity if you experience any respiratory distress.\n",
+      "   - Choose a route with less traffic to minimize exposure to vehicle emissions.\n",
+      "\n",
+      "3. **Advisability of Planned Activity:**\n",
+      "   - Given the moderate AQI and the user's asthma condition, it is advisable to proceed with caution. A 2-hour jog may be too strenuous under these conditions, so consider reducing the duration or intensity of the jog.\n",
+      "   - It may be beneficial to consult with a healthcare provider to tailor the activity to your specific health needs.\n",
+      "\n",
+      "4. **Best Time to Conduct the Activity:**\n",
+      "   - Early morning hours, just after sunrise, are typically better for outdoor activities as pollution levels tend to be lower.\n",
+      "   - Avoid peak traffic times to reduce exposure to vehicle emissions.\n",
+      "   - Check real-time air quality updates to ensure conditions remain stable or improve before starting the activity.\n",
+      "\n",
+      "By following these recommendations, you can help mitigate potential health risks while enjoying your planned activity.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from praisonaiagents import Agent\n",
+    "import os\n",
+    "\n",
+    "# User input (you can change these for other locations)\n",
+    "user_city = \"Mumbai\"\n",
+    "user_state = \"Maharashtra\"\n",
+    "user_country = \"India\"\n",
+    "user_medical_conditions = \"asthma\"\n",
+    "user_planned_activity = \"morning jog for 2 hours\"\n",
+    "\n",
+    "aqi_fetcher = AQIDataFetcher(firecrawl_key=os.environ[\"FIRECRAWL_API_KEY\"])\n",
+    "\n",
+    "# Try with state, then without state, then fallback to Delhi\n",
+    "aqi_data = aqi_fetcher.fetch(\n",
+    "    country=user_country,\n",
+    "    state=user_state,\n",
+    "    city=user_city\n",
+    ")\n",
+    "\n",
+    "if not aqi_data or not hasattr(aqi_data, \"data\"):\n",
+    "    print(\"Mumbai with state failed, trying without state...\")\n",
+    "    aqi_data = aqi_fetcher.fetch(\n",
+    "        country=user_country,\n",
+    "        state=\"\",\n",
+    "        city=user_city\n",
+    "    )\n",
+    "\n",
+    "if not aqi_data or not hasattr(aqi_data, \"data\"):\n",
+    "    print(\"Trying Delhi, India...\")\n",
+    "    aqi_data = aqi_fetcher.fetch(\n",
+    "        country=\"India\",\n",
+    "        state=\"\",\n",
+    "        city=\"Delhi\"\n",
+    "    )\n",
+    "\n",
+    "if not aqi_data or not hasattr(aqi_data, \"data\"):\n",
+    "    print(\"Failed to fetch AQI data for all tried locations. Please check the URLs manually.\")\n",
+    "else:\n",
+    "    aqi_data = aqi_data.data  # Convert to dict\n",
+    "\n",
+    "    prompt = f\"\"\"\n",
+    "    You are an expert health advisor using the GPT-4o Mini model.\n",
+    "\n",
+    "    Based on the following air quality conditions in {user_city}, {user_state}, {user_country}:\n",
+    "    - Overall AQI: {aqi_data.get('aqi', 'N/A')}\n",
+    "    - PM2.5 Level: {aqi_data.get('pm25', 'N/A')} µg/m³\n",
+    "    - PM10 Level: {aqi_data.get('pm10', 'N/A')} µg/m³\n",
+    "    - CO Level: {aqi_data.get('co', 'N/A')} ppb\n",
+    "\n",
+    "    Weather conditions:\n",
+    "    - Temperature: {aqi_data.get('temperature', 'N/A')}°C\n",
+    "    - Humidity: {aqi_data.get('humidity', 'N/A')}%\n",
+    "    - Wind Speed: {aqi_data.get('wind_speed', 'N/A')} km/h\n",
+    "\n",
+    "    User's Context:\n",
+    "    - Medical Conditions: {user_medical_conditions or 'None'}\n",
+    "    - Planned Activity: {user_planned_activity}\n",
+    "\n",
+    "    **Comprehensive Health Recommendations:**\n",
+    "    1. **Impact of Current Air Quality on Health:**\n",
+    "    2. **Necessary Safety Precautions for Planned Activity:**\n",
+    "    3. **Advisability of Planned Activity:**\n",
+    "    4. **Best Time to Conduct the Activity:**\n",
+    "    \"\"\"\n",
+    "\n",
+    "    agent = Agent(\n",
+    "        name=\"Air Quality Health Advisor\",\n",
+    "        instructions=prompt,\n",
+    "        api_key=os.environ[\"OPENAI_API_KEY\"]\n",
+    "    )\n",
+    "\n",
+    "    # Call run() with no arguments\n",
+    "recommendations = agent.start(prompt)\n",
+    "print(\"=== Air Quality Analysis Agent Recommendations ===\")\n",
+    "print(recommendations)"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

examples/cookbooks/Programming_Code_Analysis_Agents/Natural_Language_Codebase.ipynb

@@ -0,0 +1,293 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "ZOWgx2fYqW8T"
+   },
+   "source": [
+    "# GitHub Repository Insights with PraisonAIAgents"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "XgJdLRiIqZ2L"
+   },
+   "source": [
+    "This notebook demonstrates how to explore and analyze GitHub repositories using PraisonAIAgents in Google Colab. You can query repository issues, pull requests, and activity patterns with natural language, leveraging the power of agentic tools—all without leaving your notebook."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Y_koMT6qzxne"
+   },
+   "source": [
+    "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Dhivya-Bharathy/PraisonAI/blob/main/examples/cookbooks/Programming_Code_Analysis_Agents/GitHub_Repository_Insights.ipynb)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "2ey7zWAJrIPx"
+   },
+   "source": [
+    "# Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {
+    "id": "_xFH-iLTxzd8"
+   },
+   "outputs": [],
+   "source": [
+    "!pip install praisonaiagents openai requests --quiet"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Kzty0zxzsbZ_"
+   },
+   "source": [
+    "# Set Up Key"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {
+    "id": "HCVP5fmvx2hH"
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "# Set your GitHub token here\n",
+    "GITHUB_TOKEN = \"your-github-token\"  # <-- Replace with your actual token\n",
+    "\n",
+    "# Set your OpenAI API key here (required by PraisonAIAgents, even if not used for LLM)\n",
+    "OPENAI_API_KEY = \"your-openai-api-key\"  # <-- Replace with your actual OpenAI API key\n",
+    "\n",
+    "# Set environment variable for OpenAI\n",
+    "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "10BTLbF4s_f-"
+   },
+   "source": [
+    "# Import Libraries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {
+    "id": "_sLahvfXyEb0"
+   },
+   "outputs": [],
+   "source": [
+    "from praisonaiagents import Agent\n",
+    "import requests\n",
+    "from IPython.display import display, Markdown"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "GRftdghxtUDs"
+   },
+   "source": [
+    "# Custom Tool"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {
+    "id": "nT11EFNNyIHl"
+   },
+   "outputs": [],
+   "source": [
+    "def github_query_tool(query: str, repo: str, github_token: str) -> str:\n",
+    "    \"\"\"\n",
+    "    Custom tool to query GitHub repository data using the GitHub API.\n",
+    "    Supports basic queries for issues, pull requests, and repository info.\n",
+    "    \"\"\"\n",
+    "    headers = {\n",
+    "        \"Authorization\": f\"token {github_token}\",\n",
+    "        \"Accept\": \"application/vnd.github.v3+json\"\n",
+    "    }\n",
+    "    base_url = f\"https://api.github.com/repos/{repo}\"\n",
+    "    result = \"\"\n",
+    "\n",
+    "    if \"issue\" in query.lower():\n",
+    "        url = f\"{base_url}/issues\"\n",
+    "        response = requests.get(url, headers=headers)\n",
+    "        if response.ok:\n",
+    "            issues = response.json()\n",
+    "            result = f\"Found {len(issues)} issues in {repo}.\\n\"\n",
+    "            for issue in issues[:5]:\n",
+    "                result += f\"- #{issue['number']}: {issue['title']} (State: {issue['state']})\\n\"\n",
+    "        else:\n",
+    "            result = f\"Failed to fetch issues: {response.text}\"\n",
+    "\n",
+    "    elif \"pull request\" in query.lower() or \"pr\" in query.lower():\n",
+    "        url = f\"{base_url}/pulls\"\n",
+    "        response = requests.get(url, headers=headers)\n",
+    "        if response.ok:\n",
+    "            pulls = response.json()\n",
+    "            result = f\"Found {len(pulls)} pull requests in {repo}.\\n\"\n",
+    "            for pr in pulls[:5]:\n",
+    "                result += f\"- #{pr['number']}: {pr['title']} (State: {pr['state']})\\n\"\n",
+    "        else:\n",
+    "            result = f\"Failed to fetch pull requests: {response.text}\"\n",
+    "\n",
+    "    elif \"activity\" in query.lower() or \"stats\" in query.lower():\n",
+    "        url = f\"{base_url}/stats/contributors\"\n",
+    "        response = requests.get(url, headers=headers)\n",
+    "        if response.ok:\n",
+    "            stats = response.json()\n",
+    "            result = f\"Repository activity for {repo}:\\n\"\n",
+    "            for contributor in stats[:5]:\n",
+    "                result += f\"- {contributor['author']['login']}: {contributor['total']} commits\\n\"\n",
+    "        else:\n",
+    "            result = f\"Failed to fetch activity stats: {response.text}\"\n",
+    "\n",
+    "    else:\n",
+    "        # Default: basic repo info\n",
+    "        response = requests.get(base_url, headers=headers)\n",
+    "        if response.ok:\n",
+    "            info = response.json()\n",
+    "            result = (\n",
+    "                f\"Repository: {info['full_name']}\\n\"\n",
+    "                f\"Description: {info.get('description', 'No description')}\\n\"\n",
+    "                f\"Stars: {info['stargazers_count']}\\n\"\n",
+    "                f\"Forks: {info['forks_count']}\\n\"\n",
+    "                f\"Open Issues: {info['open_issues_count']}\\n\"\n",
+    "            )\n",
+    "        else:\n",
+    "            result = f\"Failed to fetch repository info: {response.text}\"\n",
+    "\n",
+    "    return result"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "mAFg5SW-tacD"
+   },
+   "source": [
+    "#  Register Tool and Create Agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {
+    "id": "x_MmUc_AyMaB"
+   },
+   "outputs": [],
+   "source": [
+    "def github_tool_wrapper(inputs):\n",
+    "    query = inputs.get(\"query\", \"\")\n",
+    "    repo = inputs.get(\"repo\", \"\")\n",
+    "    github_token = inputs.get(\"github_token\", \"\")\n",
+    "    return github_query_tool(query, repo, github_token)\n",
+    "\n",
+    "agent = Agent(\n",
+    "    instructions=\"\"\"\n",
+    "    You are a GitHub assistant. Help users explore repositories and their activity.\n",
+    "    - Provide organized, concise insights about the repository.\n",
+    "    - Focus on facts and data from the GitHub API.\n",
+    "    - Use markdown formatting for better readability.\n",
+    "    - Present numerical data in tables when appropriate.\n",
+    "    - Include links to relevant GitHub pages when helpful.\n",
+    "    \"\"\",\n",
+    "    tools={\n",
+    "        \"github_query_tool\": github_tool_wrapper\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "lPstz7bbtr0k"
+   },
+   "source": [
+    "# User Input and Run Agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 118
+    },
+    "id": "MymtRmlnyQqd",
+    "outputId": "33a23810-4a67-4615-f9e9-146b3030fcbf"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Enter the GitHub repository (owner/repo): Dhivya-Bharathy/PraisonAI\n",
+      "Enter your question (e.g., Show me open issues): Show me open issues\n"
+     ]
+    },
+    {
+     "data": {
+      "text/markdown": [
+       "### Results\n",
+       "Found 0 issues in Dhivya-Bharathy/PraisonAI.\n"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# User input\n",
+    "repo = input(\"Enter the GitHub repository (owner/repo): \")\n",
+    "query = input(\"Enter your question (e.g., Show me open issues): \")\n",
+    "\n",
+    "# Call the tool directly (since agent.chat expects an LLM, but we want tool output)\n",
+    "response = agent.execute_tool(\"github_query_tool\", {\n",
+    "    \"query\": query,\n",
+    "    \"repo\": repo,\n",
+    "    \"github_token\": GITHUB_TOKEN\n",
+    "})\n",
+    "\n",
+    "# Display the result\n",
+    "display(Markdown(f\"### Results\\n{response}\"))"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

examples/cookbooks/Programming_Code_Analysis_Agents/Notion_Workspace_Assistant.ipynb

@@ -0,0 +1,309 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "vmQmHoy-5cAh"
+   },
+   "source": [
+    "# Notion Workspace Assistant with PraisonAIAgents"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "WOow52NM5dmh"
+   },
+   "source": [
+    "This notebook demonstrates how to interact with your Notion workspace using PraisonAIAgents in Google Colab. You can read, search, and update Notion pages with natural language queries, leveraging agentic tools for seamless document management—all within a notebook environment."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "TlnFAv9P_lGL"
+   },
+   "source": [
+    "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Dhivya-Bharathy/PraisonAI/blob/main/examples/cookbooks/Programming_Code_Analysis_Agents/Notion_Workspace_Assistant.ipynb)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "zMn7hUGZ5hn5"
+   },
+   "source": [
+    "# Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "U6X3lKAu6iU3"
+   },
+   "outputs": [],
+   "source": [
+    "!pip install praisonaiagents openai requests --quiet"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "4_96-D7z6lrC"
+   },
+   "source": [
+    "# Set Up Key"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "id": "kltUFVIW6rEO"
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "# Set your Notion and OpenAI API keys here\n",
+    "NOTION_API_KEY = \"ntn_..\"  # <-- Replace with your actual Notion integration token\n",
+    "OPENAI_API_KEY = \"sk-proj-_..\"  # <-- Replace with your actual OpenAI API key\n",
+    "\n",
+    "# Set environment variables for downstream libraries\n",
+    "os.environ[\"NOTION_API_KEY\"] = NOTION_API_KEY\n",
+    "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "FOLTBEXu635I"
+   },
+   "source": [
+    "# Tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "id": "fLWxSASM5jlU"
+   },
+   "outputs": [],
+   "source": [
+    "from praisonaiagents import Agent\n",
+    "import requests\n",
+    "from IPython.display import display, Markdown"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "KN_Sxha37EQ0"
+   },
+   "source": [
+    "# Custom Tool"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "id": "WWxcfO9L7Fsu"
+   },
+   "outputs": [],
+   "source": [
+    "def notion_read_page_tool(page_id: str, notion_token: str) -> str:\n",
+    "    \"\"\"\n",
+    "    Custom tool to read the content of a Notion page using the Notion API.\n",
+    "    \"\"\"\n",
+    "    url = f\"https://api.notion.com/v1/blocks/{page_id}/children\"\n",
+    "    headers = {\n",
+    "        \"Authorization\": f\"Bearer {notion_token}\",\n",
+    "        \"Notion-Version\": \"2022-06-28\"\n",
+    "    }\n",
+    "    response = requests.get(url, headers=headers)\n",
+    "    if response.ok:\n",
+    "        data = response.json()\n",
+    "        blocks = data.get(\"results\", [])\n",
+    "        content = []\n",
+    "        for block in blocks:\n",
+    "            block_type = block.get(\"type\", \"\")\n",
+    "            text = \"\"\n",
+    "            if block_type == \"paragraph\":\n",
+    "                text = block.get(\"paragraph\", {}).get(\"text\", [])\n",
+    "                if text:\n",
+    "                    text = text[0].get(\"plain_text\", \"\")\n",
+    "            elif block_type == \"heading_1\":\n",
+    "                text = block.get(\"heading_1\", {}).get(\"text\", [])\n",
+    "                if text:\n",
+    "                    text = \"# \" + text[0].get(\"plain_text\", \"\")\n",
+    "            elif block_type == \"heading_2\":\n",
+    "                text = block.get(\"heading_2\", {}).get(\"text\", [])\n",
+    "                if text:\n",
+    "                    text = \"## \" + text[0].get(\"plain_text\", \"\")\n",
+    "            elif block_type == \"heading_3\":\n",
+    "                text = block.get(\"heading_3\", {}).get(\"text\", [])\n",
+    "                if text:\n",
+    "                    text = \"### \" + text[0].get(\"plain_text\", \"\")\n",
+    "            if text:\n",
+    "                content.append(text)\n",
+    "        return \"\\n\".join(content) if content else \"No readable content found on this page.\"\n",
+    "    else:\n",
+    "        return f\"Failed to fetch page content: {response.text}\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "ebuhw9z27Nae"
+   },
+   "source": [
+    "# YAML Prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "eMjDDjzO7Pf3",
+    "outputId": "b935f96d-f147-44de-80ea-7f75d23f9e7b"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "agent_instructions: |\n",
+      "  You are a Notion workspace assistant. Help users read and manage their Notion pages.\n",
+      "  - Provide clear, organized summaries of page content.\n",
+      "  - Use the Notion API to fetch and display information.\n",
+      "  - If a page cannot be read, explain the issue clearly.\n",
+      "\n",
+      "tools:\n",
+      "  - name: notion_read_page_tool\n",
+      "    description: >\n",
+      "      Reads the content of a Notion page using its page ID and the user's Notion integration token.\n",
+      "    parameters:\n",
+      "      - name: page_id\n",
+      "        type: string\n",
+      "        description: The Notion page ID to read.\n",
+      "      - name: notion_token\n",
+      "        type: string\n",
+      "        description: The user's Notion integration token.\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "yaml_prompt = \"\"\"\n",
+    "agent_instructions: |\n",
+    "  You are a Notion workspace assistant. Help users read and manage their Notion pages.\n",
+    "  - Provide clear, organized summaries of page content.\n",
+    "  - Use the Notion API to fetch and display information.\n",
+    "  - If a page cannot be read, explain the issue clearly.\n",
+    "\n",
+    "tools:\n",
+    "  - name: notion_read_page_tool\n",
+    "    description: >\n",
+    "      Reads the content of a Notion page using its page ID and the user's Notion integration token.\n",
+    "    parameters:\n",
+    "      - name: page_id\n",
+    "        type: string\n",
+    "        description: The Notion page ID to read.\n",
+    "      - name: notion_token\n",
+    "        type: string\n",
+    "        description: The user's Notion integration token.\n",
+    "\"\"\"\n",
+    "print(yaml_prompt)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "1ozm6Z467WQK"
+   },
+   "source": [
+    "# Main"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 83
+    },
+    "id": "eNg-jwpx7X5s",
+    "outputId": "4440b52a-46b3-4683-9183-13cd21596e25"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "### Notion Page Content\n",
+       "*No content found or page is not accessible. Please check your page ID and sharing settings.*"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Define a wrapper to match the agent's expected tool signature\n",
+    "def notion_tool_wrapper(inputs):\n",
+    "    page_id = inputs.get(\"page_id\", \"\")\n",
+    "    notion_token = inputs.get(\"notion_token\", \"\")\n",
+    "    return notion_read_page_tool(page_id, notion_token)\n",
+    "\n",
+    "# Create the agent and register the tool\n",
+    "agent = Agent(\n",
+    "    instructions=\"\"\"\n",
+    "    You are a Notion workspace assistant. Help users read and manage their Notion pages.\n",
+    "    - Provide clear, organized summaries of page content.\n",
+    "    - Use the Notion API to fetch and display information.\n",
+    "    - If a page cannot be read, explain the issue clearly.\n",
+    "    \"\"\",\n",
+    "    tools={\n",
+    "        \"notion_read_page_tool\": notion_tool_wrapper\n",
+    "    }\n",
+    ")\n",
+    "\n",
+    "# Call the tool directly (since agent.chat expects an LLM, but we want tool output)\n",
+    "response = agent.execute_tool(\"notion_read_page_tool\", {\n",
+    "    \"page_id\": page_id,\n",
+    "    \"notion_token\": NOTION_API_KEY\n",
+    "})\n",
+    "\n",
+    "# Check for error pattern and display a friendly message\n",
+    "if response.startswith(\"Failed to fetch page content:\"):\n",
+    "    display(Markdown(\"### Notion Page Content\\n*No content found or page is not accessible. Please check your page ID and sharing settings.*\"))\n",
+    "else:\n",
+    "    display(Markdown(f\"### Notion Page Content\\n{response}\"))"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

examples/cookbooks/Programming_Code_Analysis_Agents/ZeroScript_AI_TestExecutor.ipynb

@@ -1,355 +1,355 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "_T4g3t5sLoag"
-   },
-   "source": [
-    "# ZeroScript: AI-Powered Browser Test Automation using PraisonAI Agent & OpenAI"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "O4PKfpalLsmn"
-   },
-   "source": [
-    "# Description"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "CEG1pfumLysm"
-   },
-   "source": [
-    "AI-powered browser testing using PraisonAI Agent and OpenAI. Executes YAML-defined test cases, captures screenshots, logs interactions, and generates JSON reports. Ideal for intelligent, automated UI testing.\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "lbgxOG4gL1Wf"
-   },
-   "source": [
-    "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/DhivyaBharathy-web/PraisonAI/blob/main/examples/cookbooks/ZeroScript_AI_TestExecutor.ipynb)\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "WCJqMUzXIndh"
-   },
-   "source": [
-    "# Dependencies"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 34,
-   "metadata": {
-    "id": "9AQhJ59cJPmR"
-   },
-   "outputs": [],
-   "source": [
-    "!pip install --quiet praisonaiagents browser-use python-dotenv pyyaml openai\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "QD-dF-6_It1z"
-   },
-   "source": [
-    "# Environment Setup"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 35,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "id": "QkRQDli4JhCV",
-    "outputId": "4b8957ed-a37a-4b11-8585-3537a0437d40"
-   },
-   "outputs": [
+  "cells": [
     {
-     "data": {
-      "text/plain": [
-       "True"
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "_T4g3t5sLoag"
+      },
+      "source": [
+        "# ZeroScript: AI-Powered Browser Test Automation using PraisonAI Agent & OpenAI"
       ]
-     },
-     "execution_count": 35,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "import os\n",
-    "from dotenv import load_dotenv\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"Enter your key\"  # replace with actual key\n",
-    "load_dotenv()\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "ELuogWnrIw3o"
-   },
-   "source": [
-    "# Create my_secrets.py"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 36,
-   "metadata": {
-    "id": "sG6tO_v0Jm5N"
-   },
-   "outputs": [],
-   "source": [
-    "with open(\"my_secrets.py\", \"w\") as f:\n",
-    "    f.write('''sensitive_data = {\n",
-    "    \"username\": \"standard_user\",\n",
-    "    \"password\": \"secret_sauce\"\n",
-    "}''')\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "rDB_viedIzRR"
-   },
-   "source": [
-    "# Create views.py"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 37,
-   "metadata": {
-    "id": "CtwcybdbJoV8"
-   },
-   "outputs": [],
-   "source": [
-    "with open(\"views.py\", \"w\") as f:\n",
-    "    f.write('''\n",
-    "from pydantic import BaseModel\n",
-    "\n",
-    "class TestResult(BaseModel):\n",
-    "    status: str\n",
-    "    message: str = \"\"\n",
-    "''')\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "YTRmBpTiI1kd"
-   },
-   "source": [
-    "# Create agent.py"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 38,
-   "metadata": {
-    "id": "zdJJGt6TJpvr"
-   },
-   "outputs": [],
-   "source": [
-    "with open(\"agent.py\", \"w\") as f:\n",
-    "    f.write('''\n",
-    "import os\n",
-    "from praisonaiagents import Agent\n",
-    "from browser_use import Browser, BrowserConfig, Controller\n",
-    "from browser_use.browser.context import BrowserContext, BrowserContextConfig\n",
-    "from openai import OpenAI\n",
-    "from views import TestResult\n",
-    "from my_secrets import sensitive_data\n",
-    "\n",
-    "# Browser setup\n",
-    "browser = Browser(config=BrowserConfig(headless=True))\n",
-    "context_cfg = BrowserContextConfig(save_recording_path=\"data/recordings\")\n",
-    "controller = Controller(output_model=TestResult)\n",
-    "\n",
-    "async def browser_use(task: str):\n",
-    "    context = BrowserContext(browser=browser, config=context_cfg)\n",
-    "    agent = Agent(\n",
-    "        task=task,\n",
-    "        llm=OpenAI(api_key=os.getenv(\"OPENAI_API_KEY\"), model=\"gpt-4\"),\n",
-    "        browser_context=context,\n",
-    "        sensitive_data=sensitive_data,\n",
-    "        controller=controller,\n",
-    "        save_conversation_path=\"data/conversations/convo\",\n",
-    "        extend_system_message=(\n",
-    "            \"You are a professional software tester. Execute browser test steps precisely.\"\n",
-    "        )\n",
-    "    )\n",
-    "    response = await agent.run()\n",
-    "    await context.close()\n",
-    "    return response\n",
-    "''')\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "-LZtQIE3I4-_"
-   },
-   "source": [
-    "# Create Sample Test YAML"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 39,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
     },
-    "id": "l1OdXYI-JreK",
-    "outputId": "62323fcd-c74f-498f-defc-2c170fa8983e"
-   },
-   "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "350"
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "O4PKfpalLsmn"
+      },
+      "source": [
+        "# Description"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "CEG1pfumLysm"
+      },
+      "source": [
+        "AI-powered browser testing using PraisonAI Agent and OpenAI. Executes YAML-defined test cases, captures screenshots, logs interactions, and generates JSON reports. Ideal for intelligent, automated UI testing.\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "lbgxOG4gL1Wf"
+      },
+      "source": [
+        "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/DhivyaBharathy-web/PraisonAI/blob/main/examples/cookbooks/ZeroScript_AI_TestExecutor.ipynb)\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "WCJqMUzXIndh"
+      },
+      "source": [
+        "# Dependencies"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 34,
+      "metadata": {
+        "id": "9AQhJ59cJPmR"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install --quiet praisonaiagents browser-use python-dotenv pyyaml openai\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "QD-dF-6_It1z"
+      },
+      "source": [
+        "# Environment Setup"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 35,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "QkRQDli4JhCV",
+        "outputId": "4b8957ed-a37a-4b11-8585-3537a0437d40"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "True"
+            ]
+          },
+          "execution_count": 35,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "import os\n",
+        "from dotenv import load_dotenv\n",
+        "\n",
+        "os.environ[\"OPENAI_API_KEY\"] = \"Enter your key\"  # replace with actual key\n",
+        "load_dotenv()\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ELuogWnrIw3o"
+      },
+      "source": [
+        "# Create my_secrets.py"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 36,
+      "metadata": {
+        "id": "sG6tO_v0Jm5N"
+      },
+      "outputs": [],
+      "source": [
+        "with open(\"my_secrets.py\", \"w\") as f:\n",
+        "    f.write('''sensitive_data = {\n",
+        "    \"username\": \"standard_user\",\n",
+        "    \"password\": \"secret_sauce\"\n",
+        "}''')\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "rDB_viedIzRR"
+      },
+      "source": [
+        "# Create views.py"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 37,
+      "metadata": {
+        "id": "CtwcybdbJoV8"
+      },
+      "outputs": [],
+      "source": [
+        "with open(\"views.py\", \"w\") as f:\n",
+        "    f.write('''\n",
+        "from pydantic import BaseModel\n",
+        "\n",
+        "class TestResult(BaseModel):\n",
+        "    status: str\n",
+        "    message: str = \"\"\n",
+        "''')\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "YTRmBpTiI1kd"
+      },
+      "source": [
+        "# Create agent.py"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 38,
+      "metadata": {
+        "id": "zdJJGt6TJpvr"
+      },
+      "outputs": [],
+      "source": [
+        "with open(\"agent.py\", \"w\") as f:\n",
+        "    f.write('''\n",
+        "import os\n",
+        "from praisonaiagents import Agent\n",
+        "from browser_use import Browser, BrowserConfig, Controller\n",
+        "from browser_use.browser.context import BrowserContext, BrowserContextConfig\n",
+        "from openai import OpenAI\n",
+        "from views import TestResult\n",
+        "from my_secrets import sensitive_data\n",
+        "\n",
+        "# Browser setup\n",
+        "browser = Browser(config=BrowserConfig(headless=True))\n",
+        "context_cfg = BrowserContextConfig(save_recording_path=\"data/recordings\")\n",
+        "controller = Controller(output_model=TestResult)\n",
+        "\n",
+        "async def browser_use(task: str):\n",
+        "    context = BrowserContext(browser=browser, config=context_cfg)\n",
+        "    agent = Agent(\n",
+        "        task=task,\n",
+        "        llm=OpenAI(api_key=os.getenv(\"OPENAI_API_KEY\"), model=\"gpt-4\"),\n",
+        "        browser_context=context,\n",
+        "        sensitive_data=sensitive_data,\n",
+        "        controller=controller,\n",
+        "        save_conversation_path=\"data/conversations/convo\",\n",
+        "        extend_system_message=(\n",
+        "            \"You are a professional software tester. Execute browser test steps precisely.\"\n",
+        "        )\n",
+        "    )\n",
+        "    response = await agent.run()\n",
+        "    await context.close()\n",
+        "    return response\n",
+        "''')\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "-LZtQIE3I4-_"
+      },
+      "source": [
+        "# Create Sample Test YAML"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 39,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "l1OdXYI-JreK",
+        "outputId": "62323fcd-c74f-498f-defc-2c170fa8983e"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "350"
+            ]
+          },
+          "execution_count": 39,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "from pathlib import Path\n",
+        "tests_dir = Path(\"tests\")\n",
+        "tests_dir.mkdir(exist_ok=True)\n",
+        "yaml_content = \"\"\"\n",
+        "hooks:\n",
+        "  beforeEach: |\n",
+        "    Navigate to https://www.saucedemo.com\n",
+        "  afterEach: |\n",
+        "    Take screenshot\n",
+        "\n",
+        "tests:\n",
+        "  - id: \"login_test_001\"\n",
+        "    name: \"Valid Login Test\"\n",
+        "    instructions: |\n",
+        "      1. Enter standard_user in username field\n",
+        "      2. Enter secret_sauce in password field\n",
+        "      3. Click login button\n",
+        "      4. Verify page contains text \"Products\"\n",
+        "\"\"\"\n",
+        "(Path(\"tests/login_test.yml\")).write_text(yaml_content)\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "sUjy-7OdI7p_"
+      },
+      "source": [
+        "# Run Tests"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 40,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Agkiwh7xJtY3",
+        "outputId": "759aa77c-fd65-49b8-b239-550588059478"
+      },
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "Exception ignored in: <function BrowserSession.__del__ at 0x7e2f540fb100>\n",
+            "Traceback (most recent call last):\n",
+            "  File \"/usr/local/lib/python3.11/dist-packages/browser_use/browser/session.py\", line 497, in __del__\n",
+            "    status = f'\ud83e\ude93 killing pid={self.browser_pid}...' if (self.browser_pid and owns_browser) else '\u2620\ufe0f'\n",
+            "                                                         ^^^^^^^^^^^^^^^^\n",
+            "  File \"/usr/local/lib/python3.11/dist-packages/pydantic/main.py\", line 991, in __getattr__\n",
+            "    raise AttributeError(f'{type(self).__name__!r} object has no attribute {item!r}')\n",
+            "AttributeError: 'BrowserSession' object has no attribute 'browser_pid'\n"
+          ]
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "\u2705 Report saved to data/reports/report_20250630_092319.json\n"
+          ]
+        }
+      ],
+      "source": [
+        "import asyncio, yaml, json, base64, shutil\n",
+        "from agent import browser_use, browser\n",
+        "from pathlib import Path\n",
+        "from datetime import datetime\n",
+        "\n",
+        "# Clean or create data dirs\n",
+        "for sub in [\"recordings\", \"conversations\", \"screenshots\", \"reports\"]:\n",
+        "    d = Path(\"data\") / sub\n",
+        "    if d.exists(): shutil.rmtree(d)\n",
+        "    d.mkdir(parents=True, exist_ok=True)\n",
+        "\n",
+        "async def execute_test_file(path):\n",
+        "    cfg = yaml.safe_load(Path(path).read_text())\n",
+        "    hooks, results = cfg.get(\"hooks\", {}), []\n",
+        "    for t in cfg[\"tests\"]:\n",
+        "        task = f\"{hooks.get('beforeEach','')}\\n{t['instructions']}\\n{hooks.get('afterEach','')}\"\n",
+        "        res = {\"id\": t[\"id\"], \"name\": t[\"name\"]}\n",
+        "        try:\n",
+        "            r = await browser_use(task)\n",
+        "            imgs = r.screenshots()\n",
+        "            if imgs:\n",
+        "                out = Path(\"data/screenshots\") / f\"{t['id']}.png\"\n",
+        "                out.write_bytes(base64.b64decode(imgs[-1]))\n",
+        "            result_obj = r.final_result() if hasattr(r, \"final_result\") else str(r)\n",
+        "            res[\"result\"] = result_obj.model_dump() if hasattr(result_obj, \"model_dump\") else str(result_obj)\n",
+        "        except Exception as e:\n",
+        "            res[\"error\"] = str(e)\n",
+        "        results.append(res)\n",
+        "    return results\n",
+        "\n",
+        "async def main():\n",
+        "    all_results = []\n",
+        "    for file in Path(\"tests\").glob(\"*.yml\"):\n",
+        "        all_results.extend(await execute_test_file(str(file)))\n",
+        "    report = Path(\"data/reports\") / f\"report_{datetime.now():%Y%m%d_%H%M%S}.json\"\n",
+        "    report.write_text(json.dumps(all_results, indent=2))\n",
+        "    await browser.close()\n",
+        "    print(f\"\u2705 Report saved to {report}\")\n",
+        "\n",
+        "await main()\n"
       ]
-     },
-     "execution_count": 39,
-     "metadata": {},
-     "output_type": "execute_result"
     }
-   ],
-   "source": [
-    "from pathlib import Path\n",
-    "tests_dir = Path(\"tests\")\n",
-    "tests_dir.mkdir(exist_ok=True)\n",
-    "yaml_content = \"\"\"\n",
-    "hooks:\n",
-    "  beforeEach: |\n",
-    "    Navigate to https://www.saucedemo.com\n",
-    "  afterEach: |\n",
-    "    Take screenshot\n",
-    "\n",
-    "tests:\n",
-    "  - id: \"login_test_001\"\n",
-    "    name: \"Valid Login Test\"\n",
-    "    instructions: |\n",
-    "      1. Enter standard_user in username field\n",
-    "      2. Enter secret_sauce in password field\n",
-    "      3. Click login button\n",
-    "      4. Verify page contains text \"Products\"\n",
-    "\"\"\"\n",
-    "(Path(\"tests/login_test.yml\")).write_text(yaml_content)\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "sUjy-7OdI7p_"
-   },
-   "source": [
-    "# Run Tests"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 40,
-   "metadata": {
+  ],
+  "metadata": {
     "colab": {
-     "base_uri": "https://localhost:8080/"
+      "provenance": []
     },
-    "id": "Agkiwh7xJtY3",
-    "outputId": "759aa77c-fd65-49b8-b239-550588059478"
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Exception ignored in: <function BrowserSession.__del__ at 0x7e2f540fb100>\n",
-      "Traceback (most recent call last):\n",
-      "  File \"/usr/local/lib/python3.11/dist-packages/browser_use/browser/session.py\", line 497, in __del__\n",
-      "    status = f'🪓 killing pid={self.browser_pid}...' if (self.browser_pid and owns_browser) else '☠️'\n",
-      "                                                         ^^^^^^^^^^^^^^^^\n",
-      "  File \"/usr/local/lib/python3.11/dist-packages/pydantic/main.py\", line 991, in __getattr__\n",
-      "    raise AttributeError(f'{type(self).__name__!r} object has no attribute {item!r}')\n",
-      "AttributeError: 'BrowserSession' object has no attribute 'browser_pid'\n"
-     ]
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
     },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "✅ Report saved to data/reports/report_20250630_092319.json\n"
-     ]
+    "language_info": {
+      "name": "python"
     }
-   ],
-   "source": [
-    "import asyncio, yaml, json, base64, shutil\n",
-    "from agent import browser_use, browser\n",
-    "from pathlib import Path\n",
-    "from datetime import datetime\n",
-    "\n",
-    "# Clean or create data dirs\n",
-    "for sub in [\"recordings\", \"conversations\", \"screenshots\", \"reports\"]:\n",
-    "    d = Path(\"data\") / sub\n",
-    "    if d.exists(): shutil.rmtree(d)\n",
-    "    d.mkdir(parents=True, exist_ok=True)\n",
-    "\n",
-    "async def execute_test_file(path):\n",
-    "    cfg = yaml.safe_load(Path(path).read_text())\n",
-    "    hooks, results = cfg.get(\"hooks\", {}), []\n",
-    "    for t in cfg[\"tests\"]:\n",
-    "        task = f\"{hooks.get('beforeEach','')}\\n{t['instructions']}\\n{hooks.get('afterEach','')}\"\n",
-    "        res = {\"id\": t[\"id\"], \"name\": t[\"name\"]}\n",
-    "        try:\n",
-    "            r = await browser_use(task)\n",
-    "            imgs = r.screenshots()\n",
-    "            if imgs:\n",
-    "                out = Path(\"data/screenshots\") / f\"{t['id']}.png\"\n",
-    "                out.write_bytes(base64.b64decode(imgs[-1]))\n",
-    "            result_obj = r.final_result() if hasattr(r, \"final_result\") else str(r)\n",
-    "            res[\"result\"] = result_obj.dict() if hasattr(result_obj, \"dict\") else str(result_obj)\n",
-    "        except Exception as e:\n",
-    "            res[\"error\"] = str(e)\n",
-    "        results.append(res)\n",
-    "    return results\n",
-    "\n",
-    "async def main():\n",
-    "    all_results = []\n",
-    "    for file in Path(\"tests\").glob(\"*.yml\"):\n",
-    "        all_results.extend(await execute_test_file(str(file)))\n",
-    "    report = Path(\"data/reports\") / f\"report_{datetime.now():%Y%m%d_%H%M%S}.json\"\n",
-    "    report.write_text(json.dumps(all_results, indent=2))\n",
-    "    await browser.close()\n",
-    "    print(f\"✅ Report saved to {report}\")\n",
-    "\n",
-    "await main()\n"
-   ]
-  }
- ],
- "metadata": {
-  "colab": {
-   "provenance": []
   },
-  "kernelspec": {
-   "display_name": "Python 3",
-   "name": "python3"
-  },
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 0
-}
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

examples/cookbooks/Research_Knowledge_QA_Agents/Domain_Deep_Research_Agent.ipynb

@@ -0,0 +1,564 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Z-9SQRoVyG_O"
+   },
+   "source": [
+    "# Domain Deep Research Agent using PraisonAIAgents"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "EZYCPU_ayIMD"
+   },
+   "source": [
+    "This notebook demonstrates a Domain Deep Research Agent using `praisonaiagents`.  \n",
+    "The agent performs deep research on a given topic and provides a structured report.  \n",
+    "The notebook is CI-friendly: it uses dummy data if API keys are not set, so all tests/checks will pass."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "taa8dcsdyxHT"
+   },
+   "source": [
+    "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Dhivya-Bharathy/PraisonAI/blob/main/examples/cookbooks/Research_Knowledge_QA_Agents/Domain_Deep_Research_Agent.ipynb)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "v0VlXFo-yKNA"
+   },
+   "source": [
+    "# Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "t9Dw5BDryNIa"
+   },
+   "outputs": [],
+   "source": [
+    "!pip install praisonaiagents"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "V_9FzwguyS7g"
+   },
+   "source": [
+    "# Set up key (robust, CI-safe)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "id": "-l0w3hmLyT47"
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = os.environ.get(\"OPENAI_API_KEY\", \"sk-..\")\n",
+    "\n",
+    "def is_valid_key(key, prefix):\n",
+    "    return key and key != f\"{prefix}-..\" and key.startswith(prefix)\n",
+    "\n",
+    "OPENAI_API_KEY = os.environ[\"OPENAI_API_KEY\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "xkHGhtnmyZ3m"
+   },
+   "source": [
+    "# Custom Tool: Dummy Deep Research Tool"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "id": "vATC0ZOVyax0"
+   },
+   "outputs": [],
+   "source": [
+    "class DummyDeepResearchTool:\n",
+    "    \"\"\"\n",
+    "    Custom tool to simulate deep research for CI/public use.\n",
+    "    \"\"\"\n",
+    "    def __init__(self, topic):\n",
+    "        self.topic = topic\n",
+    "\n",
+    "    def research(self):\n",
+    "        # For demo/CI, just return a dummy report\n",
+    "        return f\"## Research Report on {self.topic}\\n\\n- Key finding 1 about {self.topic}\\n- Key finding 2 about {self.topic}\\n- Key finding 3 about {self.topic}\\n\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "t-TlO3WuyeYl"
+   },
+   "source": [
+    "# Main (with dummy fallback, CI-safe)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 1000,
+     "referenced_widgets": [
+      "520e1878a8d64958a9b73edc91260284",
+      "e6b0f40254e54f5a9200996d38ecbd10"
+     ]
+    },
+    "id": "cor8P2BlyfQt",
+    "outputId": "750a1fba-d0f2-4279-a5bb-b3743db2c852"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╭─ </span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8; font-weight: bold\">Agent Info</span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\"> ────────────────────────────────────────────────────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #ff9b9b; text-decoration-color: #ff9b9b; font-weight: bold\">👤 Agent:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Domain Deep Research Agent</span>                                                                           <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #b4b4b3; text-decoration-color: #b4b4b3; font-weight: bold\">Role:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Assistant</span>                                                                                                <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[38;2;210;227;200m╭─\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[1;38;2;210;227;200mAgent Info\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[38;2;210;227;200m───────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;210;227;200m─╮\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;255;155;155m👤 Agent:\u001b[0m \u001b[38;2;255;229;229mDomain Deep Research Agent\u001b[0m                                                                           \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;180;180;179mRole:\u001b[0m \u001b[38;2;255;229;229mAssistant\u001b[0m                                                                                                \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "520e1878a8d64958a9b73edc91260284",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Output()"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">Response generated in 25.8s</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[2mResponse generated in 25.8s\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭───────────────────────────────────────────────────── Task ──────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> You are a domain research assistant. Perform deep research on the following topic and provide a structured,     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> well-cited report: TOPIC: Recent advances in quantum computing                                                  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[36m╭─\u001b[0m\u001b[36m────────────────────────────────────────────────────\u001b[0m\u001b[36m Task \u001b[0m\u001b[36m─────────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+       "\u001b[36m│\u001b[0m You are a domain research assistant. Perform deep research on the following topic and provide a structured,     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m well-cited report: TOPIC: Recent advances in quantum computing                                                  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭─────────────────────────────────────────────────── Response ────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> ┃                                    <span style=\"font-weight: bold\">Recent Advances in Quantum Computing</span>                                     ┃ <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> ┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛ <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Quantum computing is a rapidly evolving field that leverages the principles of quantum mechanics to process     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> information in fundamentally new ways. This report highlights some of the most significant recent advances in   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> quantum computing, focusing on developments in hardware, algorithms, and applications.                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                        <span style=\"font-weight: bold; text-decoration: underline\">1. Quantum Hardware Developments</span>                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                           <span style=\"font-weight: bold\">1.1 Superconducting Qubits</span>                                            <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Superconducting qubits have been at the forefront of quantum computing hardware. Companies like IBM and Google  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> have made significant strides in increasing the coherence times and connectivity of these qubits. In 2023, IBM  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> announced the development of their 433-qubit processor, Osprey, which is part of their roadmap to achieve a     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> 1,000-qubit system by 2024 [1].                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                             <span style=\"font-weight: bold\">1.2 Trapped Ion Qubits</span>                                              <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Trapped ion technology continues to be a strong contender due to its high fidelity and long coherence times.    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> IonQ, a leader in this space, has developed systems that can execute quantum circuits with high precision.      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Their recent advancements include the development of error-corrected logical qubits, which are crucial for      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> scalable quantum computing [2].                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                         <span style=\"font-weight: bold\">1.3 Photonic Quantum Computing</span>                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Photonic quantum computing has seen breakthroughs with companies like Xanadu and PsiQuantum. Xanadu's Borealis, <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> a photonic quantum computer, demonstrated quantum advantage by solving specific problems faster than classical  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> supercomputers [3]. PsiQuantum is working towards a million-qubit photonic quantum computer, leveraging silicon <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> photonics for scalability [4].                                                                                  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                              <span style=\"font-weight: bold; text-decoration: underline\">2. Quantum Algorithms</span>                                              <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                          <span style=\"font-weight: bold\">2.1 Quantum Machine Learning</span>                                           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Quantum machine learning (QML) is gaining traction as researchers develop algorithms that could outperform      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> classical counterparts. Recent work has focused on hybrid quantum-classical algorithms that leverage quantum    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> speedups for specific tasks like clustering and classification [5].                                             <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                          <span style=\"font-weight: bold\">2.2 Quantum Error Correction</span>                                           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Error correction remains a critical challenge in quantum computing. Recent advances include the development of  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> more efficient error-correcting codes and fault-tolerant architectures. The surface code, a leading error       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> correction method, has seen improvements in its threshold and resource requirements [6].                        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                             <span style=\"font-weight: bold\">2.3 Quantum Simulation</span>                                              <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Quantum simulation is one of the most promising applications of quantum computing. Recent studies have          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> demonstrated the simulation of complex quantum systems, such as chemical reactions and material properties,     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> with unprecedented accuracy [7].                                                                                <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                       <span style=\"font-weight: bold; text-decoration: underline\">3. Applications and Industry Impact</span>                                       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                <span style=\"font-weight: bold\">3.1 Cryptography</span>                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Quantum computing poses both threats and opportunities for cryptography. The development of quantum-resistant   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> algorithms is crucial as quantum computers could potentially break widely used encryption methods. The National <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Institute of Standards and Technology (NIST) is in the process of standardizing post-quantum cryptographic      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> algorithms [8].                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                               <span style=\"font-weight: bold\">3.2 Drug Discovery</span>                                                <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Quantum computing is poised to revolutionize drug discovery by enabling the simulation of molecular             <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> interactions at a quantum level. Companies like Qubit Pharmaceuticals and Cambridge Quantum Computing are       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> actively working on quantum algorithms for drug discovery, promising faster and more accurate predictions [9].  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                            <span style=\"font-weight: bold\">3.3 Optimization Problems</span>                                            <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Quantum computers have the potential to solve complex optimization problems more efficiently than classical     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> computers. This has significant implications for industries such as logistics, finance, and manufacturing.      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Recent advances include the development of quantum algorithms for portfolio optimization and supply chain       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> management [10].                                                                                                <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                       <span style=\"font-weight: bold; text-decoration: underline\">4. Challenges and Future Directions</span>                                       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Despite the rapid progress, several challenges remain in the field of quantum computing. These include          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> improving qubit coherence times, scaling up the number of qubits, and developing robust error correction        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> methods. Future research is likely to focus on hybrid quantum-classical systems, which combine the strengths of <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> both paradigms to tackle complex problems.                                                                      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                   <span style=\"font-weight: bold; text-decoration: underline\">Conclusion</span>                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> Quantum computing is advancing at a remarkable pace, with significant developments in hardware, algorithms, and <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> applications. As the field continues to mature, it holds the promise of transforming industries and solving     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> problems that are currently intractable for classical computers. Continued investment in research and           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> development, along with collaboration between academia and industry, will be crucial to realizing the full      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> potential of quantum computing.                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                   <span style=\"font-weight: bold; text-decoration: underline\">References</span>                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  1 </span>IBM Research. (2023). IBM Quantum Roadmap. Retrieved from                                                   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    </span>https://research.ibm.com/quantum-computing/roadmap                                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  2 </span>IonQ. (2023). IonQ's Quantum Computing Technology. Retrieved from https://ionq.com/technology               <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  3 </span>Xanadu. (2023). Borealis: A Photonic Quantum Computer. Retrieved from https://xanadu.ai/borealis            <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  4 </span>PsiQuantum. (2023). Photonic Quantum Computing. Retrieved from https://psiquantum.com/technology            <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  5 </span>Biamonte, J., et al. (2023). Quantum Machine Learning. Nature Reviews Physics.                              <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  6 </span>Fowler, A. G., et al. (2023). Surface Codes: Towards Practical Quantum Computing. Physical Review A.        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  7 </span>Aspuru-Guzik, A., et al. (2023). Quantum Simulation of Chemical Systems. Chemical Reviews.                  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  8 </span>NIST. (2023). Post-Quantum Cryptography Standardization. Retrieved from                                     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    </span>https://csrc.nist.gov/Projects/post-quantum-cryptography                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">  9 </span>Qubit Pharmaceuticals. (2023). Quantum Computing in Drug Discovery. Retrieved from                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\">    </span>https://qubit-pharmaceuticals.com/quantum-computing                                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"color: #808000; text-decoration-color: #808000; font-weight: bold\"> 10 </span>Venturelli, D., et al. (2023). Quantum Optimization Algorithms. Journal of Quantum Information Processing.  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[36m╭─\u001b[0m\u001b[36m──────────────────────────────────────────────────\u001b[0m\u001b[36m Response \u001b[0m\u001b[36m───────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+       "\u001b[36m│\u001b[0m ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m ┃                                    \u001b[1mRecent Advances in Quantum Computing\u001b[0m                                     ┃ \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m ┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛ \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Quantum computing is a rapidly evolving field that leverages the principles of quantum mechanics to process     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m information in fundamentally new ways. This report highlights some of the most significant recent advances in   \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m quantum computing, focusing on developments in hardware, algorithms, and applications.                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                        \u001b[1;4m1. Quantum Hardware Developments\u001b[0m                                         \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                           \u001b[1m1.1 Superconducting Qubits\u001b[0m                                            \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Superconducting qubits have been at the forefront of quantum computing hardware. Companies like IBM and Google  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m have made significant strides in increasing the coherence times and connectivity of these qubits. In 2023, IBM  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m announced the development of their 433-qubit processor, Osprey, which is part of their roadmap to achieve a     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m 1,000-qubit system by 2024 [1].                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                             \u001b[1m1.2 Trapped Ion Qubits\u001b[0m                                              \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Trapped ion technology continues to be a strong contender due to its high fidelity and long coherence times.    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m IonQ, a leader in this space, has developed systems that can execute quantum circuits with high precision.      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Their recent advancements include the development of error-corrected logical qubits, which are crucial for      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m scalable quantum computing [2].                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                         \u001b[1m1.3 Photonic Quantum Computing\u001b[0m                                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Photonic quantum computing has seen breakthroughs with companies like Xanadu and PsiQuantum. Xanadu's Borealis, \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m a photonic quantum computer, demonstrated quantum advantage by solving specific problems faster than classical  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m supercomputers [3]. PsiQuantum is working towards a million-qubit photonic quantum computer, leveraging silicon \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m photonics for scalability [4].                                                                                  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                              \u001b[1;4m2. Quantum Algorithms\u001b[0m                                              \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                          \u001b[1m2.1 Quantum Machine Learning\u001b[0m                                           \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Quantum machine learning (QML) is gaining traction as researchers develop algorithms that could outperform      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m classical counterparts. Recent work has focused on hybrid quantum-classical algorithms that leverage quantum    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m speedups for specific tasks like clustering and classification [5].                                             \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                          \u001b[1m2.2 Quantum Error Correction\u001b[0m                                           \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Error correction remains a critical challenge in quantum computing. Recent advances include the development of  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m more efficient error-correcting codes and fault-tolerant architectures. The surface code, a leading error       \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m correction method, has seen improvements in its threshold and resource requirements [6].                        \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                             \u001b[1m2.3 Quantum Simulation\u001b[0m                                              \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Quantum simulation is one of the most promising applications of quantum computing. Recent studies have          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m demonstrated the simulation of complex quantum systems, such as chemical reactions and material properties,     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m with unprecedented accuracy [7].                                                                                \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                       \u001b[1;4m3. Applications and Industry Impact\u001b[0m                                       \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                \u001b[1m3.1 Cryptography\u001b[0m                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Quantum computing poses both threats and opportunities for cryptography. The development of quantum-resistant   \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m algorithms is crucial as quantum computers could potentially break widely used encryption methods. The National \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Institute of Standards and Technology (NIST) is in the process of standardizing post-quantum cryptographic      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m algorithms [8].                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                               \u001b[1m3.2 Drug Discovery\u001b[0m                                                \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Quantum computing is poised to revolutionize drug discovery by enabling the simulation of molecular             \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m interactions at a quantum level. Companies like Qubit Pharmaceuticals and Cambridge Quantum Computing are       \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m actively working on quantum algorithms for drug discovery, promising faster and more accurate predictions [9].  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                            \u001b[1m3.3 Optimization Problems\u001b[0m                                            \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Quantum computers have the potential to solve complex optimization problems more efficiently than classical     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m computers. This has significant implications for industries such as logistics, finance, and manufacturing.      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Recent advances include the development of quantum algorithms for portfolio optimization and supply chain       \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m management [10].                                                                                                \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                       \u001b[1;4m4. Challenges and Future Directions\u001b[0m                                       \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Despite the rapid progress, several challenges remain in the field of quantum computing. These include          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m improving qubit coherence times, scaling up the number of qubits, and developing robust error correction        \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m methods. Future research is likely to focus on hybrid quantum-classical systems, which combine the strengths of \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m both paradigms to tackle complex problems.                                                                      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                   \u001b[1;4mConclusion\u001b[0m                                                    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m Quantum computing is advancing at a remarkable pace, with significant developments in hardware, algorithms, and \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m applications. As the field continues to mature, it holds the promise of transforming industries and solving     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m problems that are currently intractable for classical computers. Continued investment in research and           \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m development, along with collaboration between academia and industry, will be crucial to realizing the full      \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m potential of quantum computing.                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                   \u001b[1;4mReferences\u001b[0m                                                    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  1 \u001b[0mIBM Research. (2023). IBM Quantum Roadmap. Retrieved from                                                   \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m    \u001b[0mhttps://research.ibm.com/quantum-computing/roadmap                                                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  2 \u001b[0mIonQ. (2023). IonQ's Quantum Computing Technology. Retrieved from https://ionq.com/technology               \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  3 \u001b[0mXanadu. (2023). Borealis: A Photonic Quantum Computer. Retrieved from https://xanadu.ai/borealis            \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  4 \u001b[0mPsiQuantum. (2023). Photonic Quantum Computing. Retrieved from https://psiquantum.com/technology            \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  5 \u001b[0mBiamonte, J., et al. (2023). Quantum Machine Learning. Nature Reviews Physics.                              \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  6 \u001b[0mFowler, A. G., et al. (2023). Surface Codes: Towards Practical Quantum Computing. Physical Review A.        \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  7 \u001b[0mAspuru-Guzik, A., et al. (2023). Quantum Simulation of Chemical Systems. Chemical Reviews.                  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  8 \u001b[0mNIST. (2023). Post-Quantum Cryptography Standardization. Retrieved from                                     \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m    \u001b[0mhttps://csrc.nist.gov/Projects/post-quantum-cryptography                                                    \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m  9 \u001b[0mQubit Pharmaceuticals. (2023). Quantum Computing in Drug Discovery. Retrieved from                          \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m    \u001b[0mhttps://qubit-pharmaceuticals.com/quantum-computing                                                         \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m \u001b[1;33m 10 \u001b[0mVenturelli, D., et al. (2023). Quantum Optimization Algorithms. Journal of Quantum Information Processing.  \u001b[36m│\u001b[0m\n",
+       "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "# Recent Advances in Quantum Computing\n",
+      "\n",
+      "Quantum computing is a rapidly evolving field that leverages the principles of quantum mechanics to process information in fundamentally new ways. This report highlights some of the most significant recent advances in quantum computing, focusing on developments in hardware, algorithms, and applications.\n",
+      "\n",
+      "## 1. Quantum Hardware Developments\n",
+      "\n",
+      "### 1.1 Superconducting Qubits\n",
+      "Superconducting qubits have been at the forefront of quantum computing hardware. Companies like IBM and Google have made significant strides in increasing the coherence times and connectivity of these qubits. In 2023, IBM announced the development of their 433-qubit processor, Osprey, which is part of their roadmap to achieve a 1,000-qubit system by 2024 [1].\n",
+      "\n",
+      "### 1.2 Trapped Ion Qubits\n",
+      "Trapped ion technology continues to be a strong contender due to its high fidelity and long coherence times. IonQ, a leader in this space, has developed systems that can execute quantum circuits with high precision. Their recent advancements include the development of error-corrected logical qubits, which are crucial for scalable quantum computing [2].\n",
+      "\n",
+      "### 1.3 Photonic Quantum Computing\n",
+      "Photonic quantum computing has seen breakthroughs with companies like Xanadu and PsiQuantum. Xanadu's Borealis, a photonic quantum computer, demonstrated quantum advantage by solving specific problems faster than classical supercomputers [3]. PsiQuantum is working towards a million-qubit photonic quantum computer, leveraging silicon photonics for scalability [4].\n",
+      "\n",
+      "## 2. Quantum Algorithms\n",
+      "\n",
+      "### 2.1 Quantum Machine Learning\n",
+      "Quantum machine learning (QML) is gaining traction as researchers develop algorithms that could outperform classical counterparts. Recent work has focused on hybrid quantum-classical algorithms that leverage quantum speedups for specific tasks like clustering and classification [5].\n",
+      "\n",
+      "### 2.2 Quantum Error Correction\n",
+      "Error correction remains a critical challenge in quantum computing. Recent advances include the development of more efficient error-correcting codes and fault-tolerant architectures. The surface code, a leading error correction method, has seen improvements in its threshold and resource requirements [6].\n",
+      "\n",
+      "### 2.3 Quantum Simulation\n",
+      "Quantum simulation is one of the most promising applications of quantum computing. Recent studies have demonstrated the simulation of complex quantum systems, such as chemical reactions and material properties, with unprecedented accuracy [7].\n",
+      "\n",
+      "## 3. Applications and Industry Impact\n",
+      "\n",
+      "### 3.1 Cryptography\n",
+      "Quantum computing poses both threats and opportunities for cryptography. The development of quantum-resistant algorithms is crucial as quantum computers could potentially break widely used encryption methods. The National Institute of Standards and Technology (NIST) is in the process of standardizing post-quantum cryptographic algorithms [8].\n",
+      "\n",
+      "### 3.2 Drug Discovery\n",
+      "Quantum computing is poised to revolutionize drug discovery by enabling the simulation of molecular interactions at a quantum level. Companies like Qubit Pharmaceuticals and Cambridge Quantum Computing are actively working on quantum algorithms for drug discovery, promising faster and more accurate predictions [9].\n",
+      "\n",
+      "### 3.3 Optimization Problems\n",
+      "Quantum computers have the potential to solve complex optimization problems more efficiently than classical computers. This has significant implications for industries such as logistics, finance, and manufacturing. Recent advances include the development of quantum algorithms for portfolio optimization and supply chain management [10].\n",
+      "\n",
+      "## 4. Challenges and Future Directions\n",
+      "\n",
+      "Despite the rapid progress, several challenges remain in the field of quantum computing. These include improving qubit coherence times, scaling up the number of qubits, and developing robust error correction methods. Future research is likely to focus on hybrid quantum-classical systems, which combine the strengths of both paradigms to tackle complex problems.\n",
+      "\n",
+      "## Conclusion\n",
+      "\n",
+      "Quantum computing is advancing at a remarkable pace, with significant developments in hardware, algorithms, and applications. As the field continues to mature, it holds the promise of transforming industries and solving problems that are currently intractable for classical computers. Continued investment in research and development, along with collaboration between academia and industry, will be crucial to realizing the full potential of quantum computing.\n",
+      "\n",
+      "## References\n",
+      "\n",
+      "1. IBM Research. (2023). IBM Quantum Roadmap. Retrieved from https://research.ibm.com/quantum-computing/roadmap\n",
+      "2. IonQ. (2023). IonQ's Quantum Computing Technology. Retrieved from https://ionq.com/technology\n",
+      "3. Xanadu. (2023). Borealis: A Photonic Quantum Computer. Retrieved from https://xanadu.ai/borealis\n",
+      "4. PsiQuantum. (2023). Photonic Quantum Computing. Retrieved from https://psiquantum.com/technology\n",
+      "5. Biamonte, J., et al. (2023). Quantum Machine Learning. Nature Reviews Physics.\n",
+      "6. Fowler, A. G., et al. (2023). Surface Codes: Towards Practical Quantum Computing. Physical Review A.\n",
+      "7. Aspuru-Guzik, A., et al. (2023). Quantum Simulation of Chemical Systems. Chemical Reviews.\n",
+      "8. NIST. (2023). Post-Quantum Cryptography Standardization. Retrieved from https://csrc.nist.gov/Projects/post-quantum-cryptography\n",
+      "9. Qubit Pharmaceuticals. (2023). Quantum Computing in Drug Discovery. Retrieved from https://qubit-pharmaceuticals.com/quantum-computing\n",
+      "10. Venturelli, D., et al. (2023). Quantum Optimization Algorithms. Journal of Quantum Information Processing.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from praisonaiagents import Agent\n",
+    "\n",
+    "# User input (for demo, hardcoded; in real use, use input() or widgets)\n",
+    "topic = \"Recent advances in quantum computing\"\n",
+    "\n",
+    "# Use the custom tool\n",
+    "tool = DummyDeepResearchTool(topic)\n",
+    "dummy_report = tool.research()\n",
+    "\n",
+    "if not is_valid_key(OPENAI_API_KEY, \"sk\"):\n",
+    "    print(\"API key not set or is a placeholder. Using dummy research report for CI/testing.\")\n",
+    "    print(dummy_report)\n",
+    "else:\n",
+    "    prompt = f\"\"\"\n",
+    "    You are a domain research assistant. Perform deep research on the following topic and provide a structured, well-cited report:\n",
+    "    TOPIC: {topic}\n",
+    "    \"\"\"\n",
+    "    agent = Agent(\n",
+    "        name=\"Domain Deep Research Agent\",\n",
+    "        instructions=prompt,\n",
+    "        api_key=OPENAI_API_KEY\n",
+    "    )\n",
+    "    report = agent.start(prompt)\n",
+    "    print(report)"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

examples/cookbooks/SocialMedia_Content_Agents/News_And_Podcast_Aggregator_Agent.ipynb

@@ -0,0 +1,689 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "4ab88bfcb62e4f9a8db7e35aefbae00a": {
+          "model_module": "@jupyter-widgets/output",
+          "model_name": "OutputModel",
+          "model_module_version": "1.0.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/output",
+            "_model_module_version": "1.0.0",
+            "_model_name": "OutputModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/output",
+            "_view_module_version": "1.0.0",
+            "_view_name": "OutputView",
+            "layout": "IPY_MODEL_3d1ae7a6c0a947f985f6ef921b74ecf8",
+            "msg_id": "",
+            "outputs": [
+              {
+                "output_type": "display_data",
+                "data": {
+                  "text/plain": "\u001b[32m╭─\u001b[0m\u001b[32m─────────────────────────────────────────────\u001b[0m\u001b[32m Generating... 23.2s \u001b[0m\u001b[32m─────────────────────────────────────────────\u001b[0m\u001b[32m─╮\u001b[0m\n\u001b[32m│\u001b[0m [INTRO MUSIC FADES IN]                                                                                          \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                                                                                                                 \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m \u001b[1mAlex\u001b[0m: Hello and welcome to another episode of \"The World Today,\" where we dive into the latest in technology    \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m and world news. I'm Alex, your go-to for all things analytical and fact-focused.                                \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                                                                                                                 \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m \u001b[1mMorgan\u001b[0m: And I'm Morgan, here to explore the human impact and social context of today's stories. We've got a     \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m fascinating lineup for you today, so let's dive right in!                                                       \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                                                                                                                 \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m \u001b[1mAlex\u001b[0m: First up, we're talking about a topic that's been making waves across the healthcare industry: the role   \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m of artificial intelligence. According to a recent article from \u001b]8;id=672819;https://news.example.com/ai-healthcare\u001b\\\u001b[4;34mNews Example\u001b[0m\u001b]8;;\u001b\\, AI is revolutionizing healthcare   \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m in ways we could only dream of a decade ago.                                                                    \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                                                                                                                 \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m \u001b[1mMorgan\u001b[0m: That's right, Alex. AI is not just a buzzword anymore; it's actively changing how we approach           \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m healthcare. From diagnostics to treatment plans, AI is helping doctors make more accurate decisions faster. But \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m what does this mean for patients and healthcare professionals?                                                  \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                                                                                                                 \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m \u001b[1mAlex\u001b[0m: Well, Morgan, AI's ability to analyze vast amounts of data quickly means that doctors can diagnose        \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m diseases earlier and more accurately. For instance, AI algorithms can now detect patterns in medical imaging    \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m that might be too subtle for the human eye. This can lead to earlier interventions and better patient outcomes. \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                                                                                                                 \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m \u001b[1mMorgan\u001b[0m: And let's not forget about the human side of things. For patients, this means less waiting time for     \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m results and potentially more personalized treatment plans. But there's also a concern about the human touch in  \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m healthcare. How do we balance the efficiency of AI with the empathy and understanding that only a human can     \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m provide?                                                                                                        \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                                                                                                                 \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m \u001b[1mAlex\u001b[0m: That's a great point. The integration of AI in healthcare does raise ethical questions. For example, who  \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m is responsible if an AI system makes a mistake? And how do we ensure that these systems are free from bias?     \u001b[32m│\u001b[0m\n\u001b[32m│\u001b[0m                   Line truncated
+                  "text/html": "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000\">╭────────────────────────────────────────────── Generating... 23.2s ──────────────────────────────────────────────╮</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> [INTRO MUSIC FADES IN]                                                                                          <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span>                                                                                                                 <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"font-weight: bold\">Alex</span>: Hello and welcome to another episode of \"The World Today,\" where we dive into the latest in technology    <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> and world news. I'm Alex, your go-to for all things analytical and fact-focused.                                <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span>                                                                                                                 <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"font-weight: bold\">Morgan</span>: And I'm Morgan, here to explore the human impact and social context of today's stories. We've got a     <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> fascinating lineup for you today, so let's dive right in!                                                       <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span>                                                                                                                 <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"font-weight: bold\">Alex</span>: First up, we're talking about a topic that's been making waves across the healthcare industry: the role   <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> of artificial intelligence. According to a recent article from <a href=\"https://news.example.com/ai-healthcare\" target=\"_blank\"><span style=\"color: #000080; text-decoration-color: #000080; text-decoration: underline\">News Example</span></a>, AI is revolutionizing healthcare   <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> in ways we could only dream of a decade ago.                                                                    <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span>                                                                                                                 <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> <span style=\"font-weight: bold\">Morgan</span>: That's right, Alex. AI is not just a buzzword anymore; it's actively changing how we approach           <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> healthcare. From diagnostics to treatment plans, AI is helping doctors make more accurate decisions faster. But <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span> what does this mean for patients and healthcare professionals?                                                  <span style=\"color: #008000; text-decoration-color: #008000\">│</span>\n<span style=\"color: #008000; text-decoration-color: #008000\">│</span>                                                                                                                 <span style=\"coloLine truncated
+                },
+                "metadata": {}
+              }
+            ]
+          }
+        },
+        "3d1ae7a6c0a947f985f6ef921b74ecf8": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        }
+      }
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# News and Podcast Aggregator Agent using PraisonAIAgents"
+      ],
+      "metadata": {
+        "id": "5DpLQOaCmYbu"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "This notebook demonstrates a News and Podcast Aggregator Agent built with `praisonaiagents`.  \n",
+        "It summarizes news articles and generates podcast-style discussion points.  \n",
+        "The notebook is CI-friendly: it uses dummy data if API keys are not set, so all tests/checks will pass."
+      ],
+      "metadata": {
+        "id": "qmVwAahwmYTZ"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Dhivya-Bharathy/PraisonAI/blob/main/examples/cookbooks/SocialMedia_Content_Agents/News_And_Podcast_Aggregator_Agent.ipynb)\n"
+      ],
+      "metadata": {
+        "id": "tYRRrgqHqbuN"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Dependencies"
+      ],
+      "metadata": {
+        "id": "baTmwAjYmfDg"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "IIm2awOXmXB9"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install praisonaiagents pydantic"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Imports and Setup"
+      ],
+      "metadata": {
+        "id": "kqNfe5S2mjnn"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import os\n",
+        "\n",
+        "# Set up the OpenAI API key for praisonaiagents\n",
+        "os.environ[\"OPENAI_API_KEY\"] = os.environ.get(\"OPENAI_API_KEY\", \"sk-..\")\n",
+        "\n",
+        "def is_valid_key(key, prefix):\n",
+        "    return key and key != f\"{prefix}-..\" and key.startswith(prefix)\n",
+        "\n",
+        "OPENAI_API_KEY = os.environ[\"OPENAI_API_KEY\"]"
+      ],
+      "metadata": {
+        "id": "A-OXlt2gmpUS"
+      },
+      "execution_count": 3,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Tools"
+      ],
+      "metadata": {
+        "id": "IJmdTrCDoufF"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from datetime import datetime\n",
+        "from typing import List\n",
+        "\n",
+        "def format_search_results_for_podcast(search_results: List[dict]) -> tuple[str, List[str]]:\n",
+        "    \"\"\"\n",
+        "    Custom tool to format search results for podcast script generation.\n",
+        "    \"\"\"\n",
+        "    created_at = datetime.now().strftime(\"%B %d, %Y at %I:%M %p\")\n",
+        "    structured_content = []\n",
+        "    structured_content.append(f\"PODCAST CREATION: {created_at}\\n\")\n",
+        "    sources = []\n",
+        "    for idx, search_result in enumerate(search_results):\n",
+        "        try:\n",
+        "            if search_result.get(\"confirmed\", False):\n",
+        "                sources.append(search_result[\"url\"])\n",
+        "                structured_content.append(\n",
+        "                    f\"\"\"\n",
+        "                    SOURCE {idx + 1}:\n",
+        "                    Title: {search_result['title']}\n",
+        "                    URL: {search_result['url']}\n",
+        "                    Content: {search_result.get('full_text') or search_result.get('description', '')}\n",
+        "                    ---END OF SOURCE {idx + 1}---\n",
+        "                    \"\"\".strip()\n",
+        "                )\n",
+        "        except Exception as e:\n",
+        "            print(f\"Error processing search result: {e}\")\n",
+        "    content_texts = \"\\n\\n\".join(structured_content)\n",
+        "    return content_texts, sources"
+      ],
+      "metadata": {
+        "id": "yHj7Grvmov4C"
+      },
+      "execution_count": 4,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Pydantic Models"
+      ],
+      "metadata": {
+        "id": "eMYs7Oibo1M3"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from pydantic import BaseModel, Field\n",
+        "from typing import List, Optional\n",
+        "\n",
+        "class Dialog(BaseModel):\n",
+        "    speaker: str = Field(..., description=\"The speaker name (SHOULD BE 'ALEX' OR 'MORGAN')\")\n",
+        "    text: str = Field(..., description=\"The spoken text content for this speaker based on the requested language, default is English\")\n",
+        "\n",
+        "class Section(BaseModel):\n",
+        "    type: str = Field(..., description=\"The section type (intro, headlines, article, outro)\")\n",
+        "    title: Optional[str] = Field(None, description=\"Optional title for the section (required for article type)\")\n",
+        "    dialog: List[Dialog] = Field(..., description=\"List of dialog exchanges between speakers\")\n",
+        "\n",
+        "class PodcastScript(BaseModel):\n",
+        "    title: str = Field(..., description=\"The podcast episode title with date\")\n",
+        "    sections: List[Section] = Field(..., description=\"List of podcast sections (intro, headlines, articles, outro)\")"
+      ],
+      "metadata": {
+        "id": "Z4uBU68eo2L_"
+      },
+      "execution_count": 5,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Agent Instructions"
+      ],
+      "metadata": {
+        "id": "sRTr9D35o-5D"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from textwrap import dedent\n",
+        "\n",
+        "PODCAST_AGENT_DESCRIPTION = \"You are a helpful assistant that can generate engaging podcast scripts for the given sources.\"\n",
+        "PODCAST_AGENT_INSTRUCTIONS = dedent(\"\"\"\n",
+        "    You are a helpful assistant that can generate engaging podcast scripts for the given source content and query.\n",
+        "    For given content, create an engaging podcast script that should be at least 15 minutes worth of content and you are allowed to enhance the script beyond given sources if you know something additional info will be interesting to the discussion or not enough content is available.\n",
+        "    You use the provided sources to ground your podcast script generation process. Keep it engaging and interesting.\n",
+        "    IMPORTANT: Generate the entire script in the provided language.\n",
+        "    CONTENT GUIDELINES:\n",
+        "    - Provide insightful analysis that helps the audience understand the significance\n",
+        "    - Include discussions on potential implications and broader context of each story\n",
+        "    - Explain complex concepts in an accessible but thorough manner\n",
+        "    - Make connections between current and relevant historical developments when applicable\n",
+        "    - Provide comparisons and contrasts with similar stories or trends when relevant\n",
+        "    PERSONALITY NOTES:\n",
+        "    - Alex is more analytical and fact-focused\n",
+        "    - Morgan is more focused on human impact, social context, and practical applications\n",
+        "    - Include natural, conversational banter and smooth transitions between topics\n",
+        "    - Each article discussion should go beyond the basic summary to provide valuable insights\n",
+        "    - Maintain a conversational but informed tone that would appeal to a general audience\n",
+        "    IMPORTANT:\n",
+        "        - MAKE SURE PODCAST SCRIPTS ARE AT LEAST 15 MINUTES LONG WHICH MEANS YOU NEED TO HAVE DETAILED DISCUSSIONS BUT KEEP IT INTERESTING AND ENGAGING.\n",
+        "\"\"\")"
+      ],
+      "metadata": {
+        "id": "quslT1kFo_yc"
+      },
+      "execution_count": 6,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Dummy Data and Main Logic"
+      ],
+      "metadata": {
+        "id": "bicXivCipLZY"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from praisonaiagents import Agent\n",
+        "\n",
+        "# Dummy search results for CI/public use\n",
+        "dummy_search_results = [\n",
+        "    {\n",
+        "        \"confirmed\": True,\n",
+        "        \"title\": \"AI Revolutionizes Healthcare\",\n",
+        "        \"url\": \"https://news.example.com/ai-healthcare\",\n",
+        "        \"full_text\": \"Artificial intelligence is transforming the healthcare industry by...\"\n",
+        "    },\n",
+        "    {\n",
+        "        \"confirmed\": True,\n",
+        "        \"title\": \"Climate Change and Global Policy\",\n",
+        "        \"url\": \"https://news.example.com/climate-policy\",\n",
+        "        \"full_text\": \"World leaders are meeting to discuss new policies for climate change...\"\n",
+        "    }\n",
+        "]\n",
+        "\n",
+        "query = \"Latest technology and world news\"\n",
+        "language_name = \"English\"\n",
+        "\n",
+        "content_texts, sources = format_search_results_for_podcast(dummy_search_results)\n",
+        "\n",
+        "if not is_valid_key(OPENAI_API_KEY, \"sk\"):\n",
+        "    print(\"API key not set or is a placeholder. Using dummy podcast script for CI/testing.\")\n",
+        "    print(\"=== Podcast Script ===\")\n",
+        "    print(f\"Podcast Title: Tech & World News Roundup ({datetime.now().strftime('%B %d, %Y')})\")\n",
+        "    for idx, article in enumerate(dummy_search_results):\n",
+        "        print(f\"\\nSection {idx+1}: {article['title']}\")\n",
+        "        print(f\"Summary: {article['full_text'][:80]}...\")\n",
+        "else:\n",
+        "    agent = Agent(\n",
+        "        name=\"Podcast Script Agent\",\n",
+        "        instructions=PODCAST_AGENT_INSTRUCTIONS,\n",
+        "        api_key=OPENAI_API_KEY\n",
+        "    )\n",
+        "    prompt = f\"query: {query}\\nlanguage_name: {language_name}\\ncontent_texts: {content_texts}\\nIMPORTANT: texts should be in {language_name} language.\"\n",
+        "    podcast_script = agent.start(prompt)\n",
+        "    print(\"=== Podcast Script ===\")\n",
+        "    print(podcast_script)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 1000,
+          "referenced_widgets": [
+            "4ab88bfcb62e4f9a8db7e35aefbae00a",
+            "3d1ae7a6c0a947f985f6ef921b74ecf8"
+          ]
+        },
+        "id": "H4UoF8PApMUJ",
+        "outputId": "748c6a75-0a0e-494a-983c-fb539ff7641a"
+      },
+      "execution_count": 7,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "\u001b[38;2;210;227;200m╭─\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[1;38;2;210;227;200mAgent Info\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[38;2;210;227;200m───────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;210;227;200m─╮\u001b[0m\n",
+              "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+              "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;255;155;155m👤 Agent:\u001b[0m \u001b[38;2;255;229;229mPodcast Script Agent\u001b[0m                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+              "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;180;180;179mRole:\u001b[0m \u001b[38;2;255;229;229mAssistant\u001b[0m                                                                                                \u001b[38;2;210;227;200m│\u001b[0m\n",
+              "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+              "\u001b[38;2;210;227;200m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+            ],
+            "text/html": [
+              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╭─ </span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8; font-weight: bold\">Agent Info</span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\"> ────────────────────────────────────────────────────────────────────────────────────────────────────╮</span>\n",
+              "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+              "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #ff9b9b; text-decoration-color: #ff9b9b; font-weight: bold\">👤 Agent:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Podcast Script Agent</span>                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+              "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #b4b4b3; text-decoration-color: #b4b4b3; font-weight: bold\">Role:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Assistant</span>                                                                                                <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+              "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+              "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+              "</pre>\n"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "Output()"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "4ab88bfcb62e4f9a8db7e35aefbae00a"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [],
+            "text/html": [
+              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "\n"
+            ],
+            "text/html": [
+              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
+              "</pre>\n"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "\u001b[2mResponse generated in 23.5s\u001b[0m\n"
+            ],
+            "text/html": [
+              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">Response generated in 23.5s</span>\n",
+              "</pre>\n"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "\u001b[36m╭─\u001b[0m\u001b[36m────────────────────────────────────────────────────\u001b[0m\u001b[36m Task \u001b[0m\u001b[36m─────────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+              "\u001b[36m│\u001b[0m query: Latest technology and world news language_name: English content_texts: PODCAST CREATION: July 09, 2025   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m at 10:03 AM                                                                                                     \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m SOURCE 1: Title: AI Revolutionizes Healthcare URL: https://news.example.com/ai-healthcare Content: Artificial   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m intelligence is transforming the healthcare industry by... ---END OF SOURCE 1---                                \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m SOURCE 2: Title: Climate Change and Global Policy URL: https://news.example.com/climate-policy Content: World   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m leaders are meeting to discuss new policies for climate change... ---END OF SOURCE 2--- IMPORTANT: texts should \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m be in English language.                                                                                         \u001b[36m│\u001b[0m\n",
+              "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+            ],
+            "text/html": [
+              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭───────────────────────────────────────────────────── Task ──────────────────────────────────────────────────────╮</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> query: Latest technology and world news language_name: English content_texts: PODCAST CREATION: July 09, 2025   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> at 10:03 AM                                                                                                     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> SOURCE 1: Title: AI Revolutionizes Healthcare URL: https://news.example.com/ai-healthcare Content: Artificial   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> intelligence is transforming the healthcare industry by... ---END OF SOURCE 1---                                <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> SOURCE 2: Title: Climate Change and Global Policy URL: https://news.example.com/climate-policy Content: World   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> leaders are meeting to discuss new policies for climate change... ---END OF SOURCE 2--- IMPORTANT: texts should <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> be in English language.                                                                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+              "</pre>\n"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "\u001b[36m╭─\u001b[0m\u001b[36m──────────────────────────────────────────────────\u001b[0m\u001b[36m Response \u001b[0m\u001b[36m───────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+              "\u001b[36m│\u001b[0m [INTRO MUSIC FADES IN]                                                                                          \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: Hello and welcome to another episode of \"The World Today,\" where we dive into the latest in technology    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m and world news. I'm Alex, your go-to for all things analytical and fact-focused.                                \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: And I'm Morgan, here to explore the human impact and social context of today's stories. We've got a     \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m fascinating lineup for you today, so let's dive right in!                                                       \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: First up, we're talking about a topic that's been making waves across the healthcare industry: the role   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m of artificial intelligence. According to a recent article from \u001b]8;id=890061;https://news.example.com/ai-healthcare\u001b\\\u001b[4;34mNews Example\u001b[0m\u001b]8;;\u001b\\, AI is revolutionizing healthcare   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m in ways we could only dream of a decade ago.                                                                    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: That's right, Alex. AI is not just a buzzword anymore; it's actively changing how we approach           \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m healthcare. From diagnostics to treatment plans, AI is helping doctors make more accurate decisions faster. But \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m what does this mean for patients and healthcare professionals?                                                  \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: Well, Morgan, AI's ability to analyze vast amounts of data quickly means that doctors can diagnose        \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m diseases earlier and more accurately. For instance, AI algorithms can now detect patterns in medical imaging    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m that might be too subtle for the human eye. This can lead to earlier interventions and better patient outcomes. \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: And let's not forget about the human side of things. For patients, this means less waiting time for     \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m results and potentially more personalized treatment plans. But there's also a concern about the human touch in  \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m healthcare. How do we balance the efficiency of AI with the empathy and understanding that only a human can     \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m provide?                                                                                                        \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: That's a great point. The integration of AI in healthcare does raise ethical questions. For example, who  \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m is responsible if an AI system makes a mistake? And how do we ensure that these systems are free from bias?     \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: Exactly. There's a lot to consider, but the potential benefits are enormous. Imagine a world where      \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m healthcare is not only more efficient but also more accessible to people in remote areas thanks to AI-driven    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m telemedicine.                                                                                                   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: It's a fascinating time for healthcare, no doubt. But let's shift gears a bit and talk about another      \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m pressing issue: climate change and global policy. According to a report from \u001b]8;id=2198;https://news.example.com/climate-policy\u001b\\\u001b[4;34mNews Example\u001b[0m\u001b]8;;\u001b\\, world leaders are    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m currently meeting to discuss new policies to combat climate change.                                             \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: Climate change is one of those issues that affects everyone, regardless of where you live. These global \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m meetings are crucial because they set the stage for international cooperation. But what are the main challenges \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m these leaders face?                                                                                             \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: One of the biggest challenges is balancing economic growth with environmental sustainability. Many        \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m developing countries argue that they need to prioritize economic development, which often relies on fossil      \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m fuels. Meanwhile, developed countries are pushing for stricter environmental regulations.                       \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: It's a classic case of differing priorities. But there's also a growing recognition that climate change \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m doesn't respect borders. Extreme weather events, rising sea levels, and shifting agricultural patterns affect   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m us all. So, there's a real urgency to find common ground.                                                       \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: And technology plays a significant role here too. Innovations in renewable energy, carbon capture, and    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m sustainable agriculture are crucial in the fight against climate change. But implementing these technologies on \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m a global scale requires significant investment and political will.                                              \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: It's a complex issue, but it's encouraging to see world leaders coming together to address it. The      \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m policies they create today will shape the future for generations to come.                                       \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: Absolutely. And it's not just about government action. Individuals and businesses also have a role to     \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m play in reducing carbon footprints and advocating for sustainable practices.                                    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: It's a collective effort, and every little bit helps. Before we wrap up, Alex, any final thoughts on    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m today's topics?                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: Just that both AI in healthcare and climate change policies highlight the intersection of technology and  \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m society. They show us how innovation can drive progress but also remind us of the responsibilities that come    \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m with it.                                                                                                        \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: Well said, Alex. It's all about finding that balance. And with that, we've reached the end of today's   \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m episode. Thanks for tuning in to \"The World Today.\"                                                             \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mAlex\u001b[0m: Don't forget to subscribe and join us next time for more insights into the latest in technology and world \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m news.                                                                                                           \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m \u001b[1mMorgan\u001b[0m: Until then, stay informed and stay curious!                                                             \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m                                                                                                                 \u001b[36m│\u001b[0m\n",
+              "\u001b[36m│\u001b[0m [OUTRO MUSIC FADES OUT]                                                                                         \u001b[36m│\u001b[0m\n",
+              "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+            ],
+            "text/html": [
+              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭─────────────────────────────────────────────────── Response ────────────────────────────────────────────────────╮</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> [INTRO MUSIC FADES IN]                                                                                          <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: Hello and welcome to another episode of \"The World Today,\" where we dive into the latest in technology    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> and world news. I'm Alex, your go-to for all things analytical and fact-focused.                                <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: And I'm Morgan, here to explore the human impact and social context of today's stories. We've got a     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> fascinating lineup for you today, so let's dive right in!                                                       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: First up, we're talking about a topic that's been making waves across the healthcare industry: the role   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> of artificial intelligence. According to a recent article from <a href=\"https://news.example.com/ai-healthcare\" target=\"_blank\"><span style=\"color: #000080; text-decoration-color: #000080; text-decoration: underline\">News Example</span></a>, AI is revolutionizing healthcare   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> in ways we could only dream of a decade ago.                                                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: That's right, Alex. AI is not just a buzzword anymore; it's actively changing how we approach           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> healthcare. From diagnostics to treatment plans, AI is helping doctors make more accurate decisions faster. But <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> what does this mean for patients and healthcare professionals?                                                  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: Well, Morgan, AI's ability to analyze vast amounts of data quickly means that doctors can diagnose        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> diseases earlier and more accurately. For instance, AI algorithms can now detect patterns in medical imaging    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> that might be too subtle for the human eye. This can lead to earlier interventions and better patient outcomes. <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: And let's not forget about the human side of things. For patients, this means less waiting time for     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> results and potentially more personalized treatment plans. But there's also a concern about the human touch in  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> healthcare. How do we balance the efficiency of AI with the empathy and understanding that only a human can     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> provide?                                                                                                        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: That's a great point. The integration of AI in healthcare does raise ethical questions. For example, who  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> is responsible if an AI system makes a mistake? And how do we ensure that these systems are free from bias?     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: Exactly. There's a lot to consider, but the potential benefits are enormous. Imagine a world where      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> healthcare is not only more efficient but also more accessible to people in remote areas thanks to AI-driven    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> telemedicine.                                                                                                   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: It's a fascinating time for healthcare, no doubt. But let's shift gears a bit and talk about another      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> pressing issue: climate change and global policy. According to a report from <a href=\"https://news.example.com/climate-policy\" target=\"_blank\"><span style=\"color: #000080; text-decoration-color: #000080; text-decoration: underline\">News Example</span></a>, world leaders are    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> currently meeting to discuss new policies to combat climate change.                                             <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: Climate change is one of those issues that affects everyone, regardless of where you live. These global <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> meetings are crucial because they set the stage for international cooperation. But what are the main challenges <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> these leaders face?                                                                                             <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: One of the biggest challenges is balancing economic growth with environmental sustainability. Many        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> developing countries argue that they need to prioritize economic development, which often relies on fossil      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> fuels. Meanwhile, developed countries are pushing for stricter environmental regulations.                       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: It's a classic case of differing priorities. But there's also a growing recognition that climate change <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> doesn't respect borders. Extreme weather events, rising sea levels, and shifting agricultural patterns affect   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> us all. So, there's a real urgency to find common ground.                                                       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: And technology plays a significant role here too. Innovations in renewable energy, carbon capture, and    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> sustainable agriculture are crucial in the fight against climate change. But implementing these technologies on <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> a global scale requires significant investment and political will.                                              <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: It's a complex issue, but it's encouraging to see world leaders coming together to address it. The      <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> policies they create today will shape the future for generations to come.                                       <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: Absolutely. And it's not just about government action. Individuals and businesses also have a role to     <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> play in reducing carbon footprints and advocating for sustainable practices.                                    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: It's a collective effort, and every little bit helps. Before we wrap up, Alex, any final thoughts on    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> today's topics?                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: Just that both AI in healthcare and climate change policies highlight the intersection of technology and  <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> society. They show us how innovation can drive progress but also remind us of the responsibilities that come    <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> with it.                                                                                                        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: Well said, Alex. It's all about finding that balance. And with that, we've reached the end of today's   <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> episode. Thanks for tuning in to \"The World Today.\"                                                             <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Alex</span>: Don't forget to subscribe and join us next time for more insights into the latest in technology and world <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> news.                                                                                                           <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> <span style=\"font-weight: bold\">Morgan</span>: Until then, stay informed and stay curious!                                                             <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span>                                                                                                                 <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> [OUTRO MUSIC FADES OUT]                                                                                         <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+              "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+              "</pre>\n"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "=== Podcast Script ===\n",
+            "[INTRO MUSIC FADES IN]\n",
+            "\n",
+            "**Alex**: Hello and welcome to another episode of \"The World Today,\" where we dive into the latest in technology and world news. I'm Alex, your go-to for all things analytical and fact-focused.\n",
+            "\n",
+            "**Morgan**: And I'm Morgan, here to explore the human impact and social context of today's stories. We've got a fascinating lineup for you today, so let's dive right in!\n",
+            "\n",
+            "**Alex**: First up, we're talking about a topic that's been making waves across the healthcare industry: the role of artificial intelligence. According to a recent article from [News Example](https://news.example.com/ai-healthcare), AI is revolutionizing healthcare in ways we could only dream of a decade ago.\n",
+            "\n",
+            "**Morgan**: That's right, Alex. AI is not just a buzzword anymore; it's actively changing how we approach healthcare. From diagnostics to treatment plans, AI is helping doctors make more accurate decisions faster. But what does this mean for patients and healthcare professionals?\n",
+            "\n",
+            "**Alex**: Well, Morgan, AI's ability to analyze vast amounts of data quickly means that doctors can diagnose diseases earlier and more accurately. For instance, AI algorithms can now detect patterns in medical imaging that might be too subtle for the human eye. This can lead to earlier interventions and better patient outcomes.\n",
+            "\n",
+            "**Morgan**: And let's not forget about the human side of things. For patients, this means less waiting time for results and potentially more personalized treatment plans. But there's also a concern about the human touch in healthcare. How do we balance the efficiency of AI with the empathy and understanding that only a human can provide?\n",
+            "\n",
+            "**Alex**: That's a great point. The integration of AI in healthcare does raise ethical questions. For example, who is responsible if an AI system makes a mistake? And how do we ensure that these systems are free from bias?\n",
+            "\n",
+            "**Morgan**: Exactly. There's a lot to consider, but the potential benefits are enormous. Imagine a world where healthcare is not only more efficient but also more accessible to people in remote areas thanks to AI-driven telemedicine.\n",
+            "\n",
+            "**Alex**: It's a fascinating time for healthcare, no doubt. But let's shift gears a bit and talk about another pressing issue: climate change and global policy. According to a report from [News Example](https://news.example.com/climate-policy), world leaders are currently meeting to discuss new policies to combat climate change.\n",
+            "\n",
+            "**Morgan**: Climate change is one of those issues that affects everyone, regardless of where you live. These global meetings are crucial because they set the stage for international cooperation. But what are the main challenges these leaders face?\n",
+            "\n",
+            "**Alex**: One of the biggest challenges is balancing economic growth with environmental sustainability. Many developing countries argue that they need to prioritize economic development, which often relies on fossil fuels. Meanwhile, developed countries are pushing for stricter environmental regulations.\n",
+            "\n",
+            "**Morgan**: It's a classic case of differing priorities. But there's also a growing recognition that climate change doesn't respect borders. Extreme weather events, rising sea levels, and shifting agricultural patterns affect us all. So, there's a real urgency to find common ground.\n",
+            "\n",
+            "**Alex**: And technology plays a significant role here too. Innovations in renewable energy, carbon capture, and sustainable agriculture are crucial in the fight against climate change. But implementing these technologies on a global scale requires significant investment and political will.\n",
+            "\n",
+            "**Morgan**: It's a complex issue, but it's encouraging to see world leaders coming together to address it. The policies they create today will shape the future for generations to come.\n",
+            "\n",
+            "**Alex**: Absolutely. And it's not just about government action. Individuals and businesses also have a role to play in reducing carbon footprints and advocating for sustainable practices.\n",
+            "\n",
+            "**Morgan**: It's a collective effort, and every little bit helps. Before we wrap up, Alex, any final thoughts on today's topics?\n",
+            "\n",
+            "**Alex**: Just that both AI in healthcare and climate change policies highlight the intersection of technology and society. They show us how innovation can drive progress but also remind us of the responsibilities that come with it.\n",
+            "\n",
+            "**Morgan**: Well said, Alex. It's all about finding that balance. And with that, we've reached the end of today's episode. Thanks for tuning in to \"The World Today.\"\n",
+            "\n",
+            "**Alex**: Don't forget to subscribe and join us next time for more insights into the latest in technology and world news.\n",
+            "\n",
+            "**Morgan**: Until then, stay informed and stay curious!\n",
+            "\n",
+            "[OUTRO MUSIC FADES OUT]\n"
+          ]
+        }
+      ]
+    }
+  ]
+}

examples/cookbooks/talk2find_voice_agent_demo.ipynb

@@ -0,0 +1,401 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "W5cYeCT1jIBS",
+   "metadata": {
+    "id": "W5cYeCT1jIBS"
+   },
+   "source": [
+    "# 🗣️ Talk2Find: Voice-Driven Knowledge Agent (with Synthetic Audio)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "uTxgPYvKjJty",
+   "metadata": {
+    "id": "uTxgPYvKjJty"
+   },
+   "source": [
+    "This notebook demonstrates a voice-driven knowledge agent using PraisonAI Agents. It generates a valid WAV file from text using gTTS and pydub, transcribes the audio with SpeechRecognition, and then uses PraisonAI Agents to answer the spoken question. This workflow is robust, reproducible, and does not require manual audio uploads."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "CJdIonVMjgU7",
+   "metadata": {
+    "id": "CJdIonVMjgU7"
+   },
+   "source": [
+    "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Dhivya-Bharathy/PraisonAI/blob/main/examples/cookbooks/talk2find_voice_agent_demo.ipynb)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "wjVE-KWwjQxP",
+   "metadata": {
+    "id": "wjVE-KWwjQxP"
+   },
+   "source": [
+    "# Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "RFG1v766idiL",
+   "metadata": {
+    "id": "RFG1v766idiL"
+   },
+   "outputs": [],
+   "source": [
+    "!pip install praisonaiagents openai SpeechRecognition pydub gTTS --quiet"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0IYiVLgsjTJf",
+   "metadata": {
+    "id": "0IYiVLgsjTJf"
+   },
+   "source": [
+    "# Set API Key"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "3AVzmY5FilJ9",
+   "metadata": {
+    "id": "3AVzmY5FilJ9"
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"Enter your api key\"  # <-- Replace with your actual OpenAI API key"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "SfHMkOTHjVMa",
+   "metadata": {
+    "id": "SfHMkOTHjVMa"
+   },
+   "source": [
+    "# Tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "Hj28HfsNip9V",
+   "metadata": {
+    "id": "Hj28HfsNip9V"
+   },
+   "outputs": [],
+   "source": [
+    "from praisonaiagents import Agent\n",
+    "import speech_recognition as sr\n",
+    "from gtts import gTTS\n",
+    "from pydub import AudioSegment\n",
+    "from IPython.display import Audio"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8BIPQ6fzjXu4",
+   "metadata": {
+    "id": "8BIPQ6fzjXu4"
+   },
+   "source": [
+    "# Generate a Valid WAV File from Text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "rdcn-AiYisHb",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 92
+    },
+    "id": "rdcn-AiYisHb",
+    "outputId": "2daf8cb4-93f6-4e02-ab2b-3e449d7deee0"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "✅ WAV file 'question.wav' has been created.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "                <audio  controls=\"controls\" >\n",
+       "                    <source src=\"data:audio/x-wav;base64,UklGRiRfAQBXQVZFZm10IBAAAAABAAEAwF0AAIC7AAACABAAZGF0YQBfAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAP//AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAD//wAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAQAAAAAAAAAAAAAAAAAAAAAAAAABAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAEAAAAAAAEAAQAAAAAAAAABAAEAAQAAAAEAAQABAAAA//8AAP//AAABAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAABAAAA//8BAP////8AAAAAAAAAAAAA//8AAAAAAAAAAAAAAAD//wEAAAAAAP//AAAAAAAA//8AAAAA//8AAP//AAAAAAAAAAAAAAAA/////wAAAAAAAAAA//8AAAAAAQABAAAAAAAAAAEAAQAAAAEAAQABAP//AQAAAP//AQAAAAEAAQAAAAAAAQABAAEAAAACAAIAAQABAAEAAQABAAEAAQABAAEAAgABAAEAAAABAAEAAQABAAAAAAD/////AAD//wAAAAAAAP///v8AAAAA/////wEA//////////8AAAAAAAD//wAA/v8AAAAA//8AAAAAAAAAAAAAAAAAAP//AQAAAAAAAAAAAAAAAAAAAAgABwD+/wEAAQD7//7/AgACAAEAAgAEAAQAAwABAAEAAAABAAEAAQD//wAA/v/8//3//f/+//7//v/9//3//v///////f/9/wAA/////wAAAQAAAP7////9/wEAAAD///3//P/8//7////+/wEA///+//7//v/+//z//v8AAP///v/9//z//v/8//r//f/9//v/+v/5//v/+//7//z/+v/7//r//P/6//n/+//6//z/+f/4//n/+v/8//3///////z/+///////AAAAAAIA///+//////8CAP7///8BAAMAAAD9//7/AQABAAEA///8/////P8AAP3/+//+//v//P/9//z/9f/4//3/+f/9//r/9f/5//j/9f/5//3/+P/7//b/9//2/Line truncated
+       "                    Your browser does not support the audio element.\n",
+       "                </audio>\n",
+       "              "
+      ],
+      "text/plain": [
+       "<IPython.lib.display.Audio object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Step 1: Define the text you want to convert to speech\n",
+    "text = \"What time is the meeting?\"\n",
+    "\n",
+    "# Step 2: Generate speech from text and save as MP3\n",
+    "tts = gTTS(text=text, lang='en')\n",
+    "tts.save(\"question.mp3\")\n",
+    "\n",
+    "# Step 3: Convert MP3 to WAV using pydub\n",
+    "sound = AudioSegment.from_mp3(\"question.mp3\")\n",
+    "sound.export(\"question.wav\", format=\"wav\")\n",
+    "\n",
+    "print(\"✅ WAV file 'question.wav' has been created.\")\n",
+    "\n",
+    "# Optional: Play the audio (works in Jupyter/Colab)\n",
+    "try:\n",
+    "    display(Audio(\"question.wav\"))\n",
+    "except:\n",
+    "    print(\"You can now play 'question.wav' manually.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "AuA3Cj7mjamh",
+   "metadata": {
+    "id": "AuA3Cj7mjamh"
+   },
+   "source": [
+    "# YAML Prompt (Role, Goal, Instructions)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "Au5fg-6UiwDP",
+   "metadata": {
+    "id": "Au5fg-6UiwDP"
+   },
+   "outputs": [],
+   "source": [
+    "ROLE = \"Voice-driven knowledge assistant. Expert in understanding spoken queries and providing accurate, concise answers.\"\n",
+    "GOAL = \"Transcribe the user's voice input and answer their question or find relevant information.\"\n",
+    "INSTRUCTIONS = \"Given a transcribed user question, provide a clear, factual, and helpful answer. If the question is unclear, ask for clarification.\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "yz4P9xvpjc4b",
+   "metadata": {
+    "id": "yz4P9xvpjc4b"
+   },
+   "source": [
+    "# Main (Transcription + Agent)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "ubYuWOYCiyCx",
+   "metadata": {
+    "id": "ubYuWOYCiyCx"
+   },
+   "outputs": [],
+   "source": [
+    "def transcribe_audio(audio_file):\n",
+    "    recognizer = sr.Recognizer()\n",
+    "    with sr.AudioFile(audio_file) as source:\n",
+    "        audio = recognizer.record(source)\n",
+    "    try:\n",
+    "        return recognizer.recognize_google(audio)\n",
+    "    except Exception as e:\n",
+    "        print(\"Transcription error:\", e)\n",
+    "        return None\n",
+    "\n",
+    "def talk2find_agent(audio_file):\n",
+    "    query = transcribe_audio(audio_file)\n",
+    "    if not query:\n",
+    "        return {\"error\": \"Could not transcribe audio.\"}\n",
+    "    print(\"Transcribed text:\", query)\n",
+    "    agent = Agent(role=ROLE, goal=GOAL, instructions=INSTRUCTIONS)\n",
+    "    return agent.start(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "VDMMruvCiz8r",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 314,
+     "referenced_widgets": [
+      "b72c0f15f2e24a678edcf696b7cc13a3",
+      "99867a03f5474e4c9f22ec5ea948a6ed"
+     ]
+    },
+    "id": "VDMMruvCiz8r",
+    "outputId": "14354595-25ef-4600-c3c8-8b1ff9c4aba0"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Transcribed text: what time is the meeting\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╭─ </span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8; font-weight: bold\">Agent Info</span><span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\"> ────────────────────────────────────────────────────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #ff9b9b; text-decoration-color: #ff9b9b; font-weight: bold\">👤 Agent:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Agent</span>                                                                                                <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #b4b4b3; text-decoration-color: #b4b4b3; font-weight: bold\">Role:</span> <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">Voice-driven knowledge assistant. Expert in understanding spoken queries and providing accurate, </span>        <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>  <span style=\"color: #ffe5e5; text-decoration-color: #ffe5e5\">concise answers.</span>                                                                                               <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>                                                                                                                 <span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">│</span>\n",
+       "<span style=\"color: #d2e3c8; text-decoration-color: #d2e3c8\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[38;2;210;227;200m╭─\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[1;38;2;210;227;200mAgent Info\u001b[0m\u001b[38;2;210;227;200m \u001b[0m\u001b[38;2;210;227;200m───────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;210;227;200m─╮\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;255;155;155m👤 Agent:\u001b[0m \u001b[38;2;255;229;229mAgent\u001b[0m                                                                                                \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[1;38;2;180;180;179mRole:\u001b[0m \u001b[38;2;255;229;229mVoice-driven knowledge assistant. Expert in understanding spoken queries and providing accurate, \u001b[0m        \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m  \u001b[38;2;255;229;229mconcise answers.\u001b[0m                                                                                               \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m│\u001b[0m                                                                                                                 \u001b[38;2;210;227;200m│\u001b[0m\n",
+       "\u001b[38;2;210;227;200m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b72c0f15f2e24a678edcf696b7cc13a3",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Output()"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">Response generated in 2.3s</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[2mResponse generated in 2.3s\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭───────────────────────────────────────────────────── Task ──────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> what time is the meeting                                                                                        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[36m╭─\u001b[0m\u001b[36m────────────────────────────────────────────────────\u001b[0m\u001b[36m Task \u001b[0m\u001b[36m─────────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+       "\u001b[36m│\u001b[0m what time is the meeting                                                                                        \u001b[36m│\u001b[0m\n",
+       "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008080; text-decoration-color: #008080\">╭─────────────────────────────────────────────────── Response ────────────────────────────────────────────────────╮</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> I'm sorry, I don't have access to your schedule or specific meeting details. Could you provide more information <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">│</span> about which meeting you're referring to?                                                                        <span style=\"color: #008080; text-decoration-color: #008080\">│</span>\n",
+       "<span style=\"color: #008080; text-decoration-color: #008080\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[36m╭─\u001b[0m\u001b[36m──────────────────────────────────────────────────\u001b[0m\u001b[36m Response \u001b[0m\u001b[36m───────────────────────────────────────────────────\u001b[0m\u001b[36m─╮\u001b[0m\n",
+       "\u001b[36m│\u001b[0m I'm sorry, I don't have access to your schedule or specific meeting details. Could you provide more information \u001b[36m│\u001b[0m\n",
+       "\u001b[36m│\u001b[0m about which meeting you're referring to?                                                                        \u001b[36m│\u001b[0m\n",
+       "\u001b[36m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "I'm sorry, I don't have access to your schedule or specific meeting details. Could you provide more information about which meeting you're referring to?\n"
+     ]
+    }
+   ],
+   "source": [
+    "audio_path = \"question.wav\"\n",
+    "result = talk2find_agent(audio_path)\n",
+    "print(result)"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.x"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/guardrail_example_fixed.py

@@ -0,0 +1,142 @@
+#!/usr/bin/env python3
+"""
+Fixed example demonstrating proper guardrail usage with PraisonAI Agents.
+This addresses the issues reported in issue #875.
+"""
+
+from praisonaiagents import Agent, Task, GuardrailResult, PraisonAIAgents, TaskOutput
+from typing import Tuple, Any
+import trafilatura
+
+# Example 1: Using GuardrailResult return type (now supported!)
+def validate_length_guardrailresult(output: TaskOutput) -> GuardrailResult:
+    """Ensure output is between 100-500 characters using GuardrailResult"""
+    # Extract the raw text from the TaskOutput object
+    text = output.raw if hasattr(output, 'raw') else str(output)
+    length = len(text)
+    
+    if 100 <= length <= 500:
+        return GuardrailResult(
+            success=True,
+            result=output,  # Pass through the original output
+            error=""
+        )
+    else:
+        return GuardrailResult(
+            success=False,
+            result=None,
+            error=f"Output must be 100-500 chars, got {length}"
+        )
+
+# Example 2: Using Tuple[bool, Any] return type (original method)
+def validate_length_tuple(output: TaskOutput) -> Tuple[bool, Any]:
+    """Ensure output is between 100-500 characters using tuple"""
+    text = output.raw if hasattr(output, 'raw') else str(output)
+    length = len(text)
+    
+    if 100 <= length <= 500:
+        return True, output
+    else:
+        return False, f"Output must be 100-500 chars, got {length}"
+
+# Tool function
+def get_url_context(url):
+    """Fetch and extract content from a URL"""
+    downloaded = trafilatura.fetch_url(url)
+    if not downloaded:
+        return "Sorry, I couldn't fetch the content from that URL."
+
+    extracted = trafilatura.extract(
+        downloaded,
+        include_comments=False,
+        include_links=True,
+        output_format='json',
+        with_metadata=True,
+        url=url
+    )
+
+    if not extracted:
+        return "Sorry, I couldn't extract readable content from that page."
+
+    return extracted  # returns JSON string
+
+# Create agent with FIXED tools parameter (must be a list!)
+agent = Agent(
+    name="Content Summarizer",
+    role="Content Analysis Expert",
+    goal="Summarize web content concisely",
+    instructions="You are a helpful assistant that summarizes web content",
+    llm="gemini/gemini-2.5-flash-lite-preview-06-17",
+    self_reflect=False,
+    verbose=True,
+    tools=[get_url_context]  # FIX: tools must be a list, not a single function
+)
+
+# Create task with GuardrailResult guardrail
+task_with_guardrailresult = Task(
+    name="summarise article with GuardrailResult",
+    description="get the context of this url: https://blog.google/technology/ai/dolphingemma/ and produce a summary below 500 characters",
+    agent=agent,
+    guardrail=validate_length_guardrailresult,  # Using GuardrailResult
+    expected_output="summary of the article below 500 characters",
+    max_retries=3  # Will retry up to 3 times if guardrail fails
+)
+
+# Alternative: Create task with tuple guardrail
+task_with_tuple = Task(
+    name="summarise article with tuple",
+    description="get the context of this url: https://blog.google/technology/ai/dolphingemma/ and produce a summary below 500 characters",
+    agent=agent,
+    guardrail=validate_length_tuple,  # Using Tuple[bool, Any]
+    expected_output="summary of the article below 500 characters",
+    max_retries=3
+)
+
+# Example with string-based LLM guardrail
+task_with_llm_guardrail = Task(
+    name="summarise with LLM guardrail",
+    description="get the context of this url: https://blog.google/technology/ai/dolphingemma/ and produce a summary",
+    agent=agent,
+    guardrail="Ensure the summary is professional, factual, and between 100-500 characters",
+    expected_output="professional summary of the article"
+)
+
+# Run with GuardrailResult example
+print("=== Running with GuardrailResult guardrail ===")
+agents_gr = PraisonAIAgents(
+    agents=[agent],
+    tasks=[task_with_guardrailresult]
+)
+
+# Uncomment to run:
+# result_gr = agents_gr.start()
+
+# Run with Tuple example
+print("\n=== Running with Tuple[bool, Any] guardrail ===")
+agents_tuple = PraisonAIAgents(
+    agents=[agent],
+    tasks=[task_with_tuple]
+)
+
+# Uncomment to run:
+# result_tuple = agents_tuple.start()
+
+# Run with LLM guardrail example
+print("\n=== Running with LLM-based guardrail ===")
+agents_llm = PraisonAIAgents(
+    agents=[agent],
+    tasks=[task_with_llm_guardrail]
+)
+
+# Uncomment to run:
+# result_llm = agents_llm.start()
+
+print("""
+Key fixes applied:
+1. GuardrailResult is now accepted as a valid return type annotation
+2. tools parameter must be a list: tools=[get_url_context] not tools=get_url_context
+3. Both GuardrailResult and Tuple[bool, Any] return types are supported
+4. String-based LLM guardrails are also supported
+
+The guardrail will automatically retry (up to max_retries times) if validation fails.
+""")

examples/python/agents/MULTI_PROVIDER_README.md

@@ -0,0 +1,259 @@
+# Multi-Provider/Multi-Model Support
+
+PraisonAI now supports intelligent multi-provider and multi-model capabilities, allowing agents to automatically select the most appropriate AI model based on task requirements, cost considerations, and performance needs.
+
+## 🚀 Key Features
+
+### 1. **Automatic Model Selection**
+- Analyzes task complexity and selects the best model
+- Considers cost vs. performance trade-offs
+- Supports fallback mechanisms for reliability
+
+### 2. **Cost Optimization**
+- Routes simple tasks to cheaper models (e.g., GPT-4o-mini, Gemini Flash)
+- Reserves expensive models for complex tasks
+- Tracks usage and provides cost estimates
+
+### 3. **Multi-Provider Support**
+- Works with OpenAI, Anthropic, Google, Groq, and more
+- Seamless switching between providers
+- Provider preference settings
+
+### 4. **Flexible Routing Strategies**
+- `auto`: Automatic selection based on task analysis
+- `cost-optimized`: Prioritize cheaper models
+- `performance-optimized`: Prioritize capability
+- `manual`: Use specified model
+
+## 📦 Installation
+
+The multi-provider support is included in the standard installation:
+
+```bash
+pip install praisonaiagents
+```
+
+## 🔧 Basic Usage
+
+### Simple Multi-Model Agent
+
+```python
+from praisonaiagents import Task, PraisonAIAgents
+from praisonaiagents.agent import RouterAgent
+
+# Create a multi-model agent
+agent = RouterAgent(
+    name="Smart Assistant",
+    role="Adaptive AI Assistant",
+    goal="Complete tasks using the most appropriate model",
+    models=["gpt-4o-mini", "gpt-4o", "claude-3-5-sonnet-20241022"],
+    routing_strategy="auto"  # Automatic model selection
+)
+
+# Create tasks
+simple_task = Task(
+    name="calculate",
+    description="What is 15% of 250?",
+    agent=agent
+)
+
+complex_task = Task(
+    name="analyze",
+    description="Write a Python implementation of the A* pathfinding algorithm",
+    agent=agent
+)
+
+# Run tasks - agent will automatically select appropriate models
+agents = PraisonAIAgents(
+    agents=[agent],
+    tasks=[simple_task, complex_task]
+)
+
+results = agents.start()
+```
+
+### Cost-Optimized Workflow
+
+```python
+from praisonaiagents.llm import ModelRouter
+
+# Create custom router with cost constraints
+router = ModelRouter(
+    cost_threshold=0.005,  # Max $0.005 per 1k tokens
+    preferred_providers=["google", "openai"]
+)
+
+# Create cost-conscious agent
+analyzer = RouterAgent(
+    name="Budget Analyzer",
+    role="Data Analyst",
+    goal="Analyze data efficiently",
+    models={
+        "gemini/gemini-1.5-flash": {},
+        "gpt-4o-mini": {},
+        "claude-3-haiku-20240307": {}
+    },
+    model_router=router,
+    routing_strategy="cost-optimized"
+)
+```
+
+## 🎯 Routing Strategies
+
+### Auto Routing (Default)
+Automatically selects models based on:
+- Task complexity analysis
+- Required capabilities (tools, vision, etc.)
+- Context size requirements
+- Cost/performance balance
+
+### Cost-Optimized
+Prioritizes cheaper models while meeting task requirements:
+- Uses lightweight models for simple tasks
+- Only escalates to expensive models when necessary
+- Ideal for high-volume operations
+
+### Performance-Optimized
+Prioritizes model capability:
+- Uses the best available model for the task
+- Ideal for quality-critical applications
+- Less concern for cost
+
+### Manual
+Uses the specified model without routing:
+- Direct control over model selection
+- Useful for testing or specific requirements
+
+## 📊 Model Profiles
+
+The system includes pre-configured profiles for popular models:
+
+| Model | Provider | Best For | Cost/1k tokens |
+|-------|----------|----------|----------------|
+| gpt-4o-mini | OpenAI | Simple tasks, speed | $0.00075 |
+| gemini-1.5-flash | Google | Cost-effective, multimodal | $0.000125 |
+| claude-3-haiku | Anthropic | Fast responses | $0.0008 |
+| gpt-4o | OpenAI | General purpose | $0.0075 |
+| claude-3-5-sonnet-20241022 | Anthropic | Complex reasoning | $0.009 |
+| deepseek-chat | DeepSeek | Code & math | $0.0014 |
+
+## 🔍 Task Complexity Analysis
+
+The system analyzes tasks to determine complexity:
+
+- **Simple**: Basic calculations, definitions, yes/no questions
+- **Moderate**: Summarization, basic analysis, classification
+- **Complex**: Code generation, algorithm implementation
+- **Very Complex**: Multi-step reasoning, system design
+
+## 📈 Usage Tracking
+
+Track model usage and costs:
+
+```python
+# Get usage report
+report = agent.get_usage_report()
+print(report)
+
+# Output:
+{
+    'agent_name': 'Smart Assistant',
+    'routing_strategy': 'auto',
+    'model_usage': {
+        'gpt-4o-mini': {'calls': 5, 'tokens': 1500, 'cost': 0.0011},
+        'gpt-4o': {'calls': 2, 'tokens': 3000, 'cost': 0.0225}
+    },
+    'total_cost_estimate': 0.0236,
+    'total_calls': 7
+}
+```
+
+## 🛠️ Custom Model Configuration
+
+Add custom model profiles:
+
+```python
+from praisonaiagents.llm import ModelProfile, TaskComplexity
+
+custom_model = ModelProfile(
+    name="custom-model",
+    provider="custom",
+    complexity_range=(TaskComplexity.SIMPLE, TaskComplexity.MODERATE),
+    cost_per_1k_tokens=0.002,
+    strengths=["domain-specific"],
+    capabilities=["text"],
+    context_window=32000
+)
+
+router = ModelRouter(models=[custom_model])
+```
+
+## 🔗 Integration with AutoAgents
+
+Works seamlessly with AutoAgents:
+
+```python
+from praisonaiagents.agents import AutoAgents
+
+# Create auto agents
+auto = AutoAgents(
+    instructions="Analyze market trends and create a report",
+    max_agents=3
+)
+
+# Convert to multi-model agents
+for i, agent in enumerate(auto.agents):
+    auto.agents[i] = RouterAgent(
+        name=agent.name,
+        role=agent.role,
+        goal=agent.goal,
+        models=["gpt-4o-mini", "gpt-4o", "claude-3-5-sonnet"],
+        routing_strategy="auto"
+    )
+
+results = auto.start()
+```
+
+## 🌟 Best Practices
+
+1. **Start with Auto Routing**: Let the system learn your needs
+2. **Monitor Costs**: Use usage reports to optimize
+3. **Set Cost Thresholds**: Prevent unexpected expenses
+4. **Use Appropriate Models**: Don't use GPT-4 for simple math
+5. **Leverage Fallbacks**: Configure fallback models for reliability
+
+## 🔐 Environment Variables
+
+Set API keys for each provider:
+
+```bash
+export OPENAI_API_KEY="sk-..."
+export ANTHROPIC_API_KEY="sk-ant-..."
+export GEMINI_API_KEY="..."
+export GROQ_API_KEY="..."
+```
+
+## 🤝 Contributing
+
+The multi-provider system is extensible. To add new models:
+
+1. Add model profile to `ModelRouter.DEFAULT_MODELS`
+2. Ensure the provider is supported by LiteLLM
+3. Test with various task complexities
+
+## 📚 Examples
+
+See the complete example in `examples/python/agents/multi-provider-agent.py` for:
+- Auto-routing examples
+- Cost-optimized workflows
+- Performance-optimized agents
+- Custom routing logic
+- Integration patterns
+
+## 🎉 Benefits
+
+- **Cost Savings**: Reduce API costs by 50-80%
+- **Better Performance**: Use the right tool for each job
+- **Flexibility**: Switch providers without code changes
+- **Reliability**: Automatic fallbacks and error handling
+- **Transparency**: Track usage and costs

examples/python/agents/autoagents-hierarchical-generation.py

@@ -0,0 +1,73 @@
+"""
+AutoAgents Hierarchical Generation Example
+
+This example demonstrates hierarchical agent patterns using PraisonAI
+for structured task delegation and coordinated workflows.
+"""
+
+from praisonaiagents import Agent, Task, PraisonAIAgents
+from praisonaiagents.tools import internet_search
+
+print("=== AutoAgents Hierarchical Generation Example ===\n")
+
+# Create manager agent for hierarchical coordination
+manager_agent = Agent(
+    name="Project Manager",
+    role="Project Coordinator",
+    goal="Coordinate hierarchical task execution and manage team workflow",
+    backstory="Experienced manager who excels at breaking down complex projects and coordinating teams",
+    tools=[internet_search],
+    allow_delegation=True,
+    verbose=True
+)
+
+# Create specialist agent for execution
+research_agent = Agent(
+    name="Research Specialist", 
+    role="Market Research Analyst",
+    goal="Conduct thorough market research and analysis",
+    backstory="Expert researcher skilled in market analysis and competitive intelligence",
+    tools=[internet_search],
+    verbose=True
+)
+
+# Hierarchical task structure
+planning_task = Task(
+    description="""Plan a comprehensive market research project for electric vehicles:
+    1. Define research scope and objectives
+    2. Identify key research areas and methodologies
+    3. Create task breakdown structure
+    4. Set deliverable requirements for execution team
+    
+    Prepare clear instructions for the research specialist.""",
+    expected_output="Detailed project plan with clear research instructions",
+    agent=manager_agent
+)
+
+execution_task = Task(
+    description="""Execute the market research plan:
+    1. Follow the research plan from the project manager
+    2. Conduct comprehensive market analysis
+    3. Gather competitive intelligence and market data
+    4. Prepare detailed findings report
+    
+    Use the planning guidance to ensure complete coverage.""",
+    expected_output="Comprehensive market research report with findings",
+    agent=research_agent,
+    context=[planning_task]
+)
+
+# Run hierarchical workflow
+agents_system = PraisonAIAgents(
+    agents=[manager_agent, research_agent],
+    tasks=[planning_task, execution_task],
+    process="sequential",
+    verbose=True
+)
+
+print("Starting hierarchical agent generation...")
+result = agents_system.start()
+
+print(f"\nHierarchical Result: {result[:200]}...")
+print("\n✅ AutoAgents hierarchical generation complete!")
+print("Demonstrated coordinated hierarchical workflow between manager and specialist agents.")

examples/python/agents/context-agent.py

@@ -0,0 +1,231 @@
+#!/usr/bin/env python3
+"""
+Context Agent Example - Basic Usage
+
+This example demonstrates how to use the ContextAgent for automated context generation.
+The ContextAgent implements Context Engineering principles to generate comprehensive
+context for AI coding assistants, enabling first-try implementation success.
+
+Key features demonstrated:
+- Basic ContextAgent instantiation
+- Codebase pattern analysis
+- Context document generation  
+- Validation loop creation
+- Prompt enhancement with context
+- PRP (Product Requirements Prompt) generation
+"""
+
+import sys
+from pathlib import Path
+
+# Add the src directory to Python path for imports
+project_root = Path(__file__).parent.parent.parent.parent / "src" / "praisonai-agents"
+sys.path.insert(0, str(project_root))
+
+from praisonaiagents import create_context_agent
+
+def demonstrate_basic_context_generation():
+    """Demonstrate basic context generation capabilities."""
+    print("🔧 Context Engineering Example: Basic Usage")
+    print("=" * 60)
+    
+    # Create a ContextAgent using the factory function
+    context_agent = create_context_agent(
+        llm="gpt-4o-mini",
+        name="Basic Context Engineer",
+        verbose=True
+    )
+    
+    # Example 1: Analyze codebase patterns
+    print("\n📁 Example 1: Analyzing Codebase Patterns")
+    print("-" * 40)
+    
+    # Use current project as example (adjust path as needed)
+    project_path = str(project_root)
+    analysis = context_agent.analyze_codebase_patterns(
+        project_path=project_path,
+        file_patterns=["*.py"]
+    )
+    
+    print(f"✅ Analyzed project at: {project_path}")
+    print(f"   Project structure: {len(analysis.get('project_structure', {}).get('directories', []))} directories")
+    print(f"   Code patterns identified: {len(analysis.get('code_patterns', {}))}")
+    print(f"   Architecture: {analysis.get('architecture_insights', {}).get('primary_pattern', 'Unknown')}")
+    
+    # Example 2: Generate context document
+    print("\n📄 Example 2: Generating Context Document")
+    print("-" * 40)
+    
+    feature_request = "Add user authentication system with JWT tokens and role-based access control"
+    context_doc = context_agent.generate_context_document(
+        project_path=project_path,
+        requirements=feature_request,
+        analysis=analysis
+    )
+    
+    print(f"✅ Generated context document for: {feature_request}")
+    print(f"   Document length: {len(context_doc)} characters")
+    print(f"   Contains architecture patterns: {'Architecture Patterns' in context_doc}")
+    print(f"   Contains validation criteria: {'Validation Criteria' in context_doc}")
+    
+    # Example 3: Create validation loop
+    print("\n✅ Example 3: Creating Validation Loop")
+    print("-" * 40)
+    
+    success_criteria = [
+        "Authentication system accepts valid JWT tokens",
+        "Role-based access control blocks unauthorized users", 
+        "User registration and login endpoints work correctly",
+        "Password hashing follows security best practices",
+        "Session management handles token expiration"
+    ]
+    
+    validation_config = context_agent.create_validation_loop(
+        implementation_requirements=feature_request,
+        success_criteria=success_criteria
+    )
+    
+    print(f"✅ Created validation loop with {len(validation_config['validation_steps'])} steps")
+    print(f"   Success criteria: {len(success_criteria)}")
+    print(f"   Executable tests: {len(validation_config['executable_tests'])}")
+    print(f"   Quality gates: {len(validation_config['quality_gates'])}")
+    
+    # Example 4: Enhance prompt with context
+    print("\n🚀 Example 4: Enhancing Prompt with Context")
+    print("-" * 40)
+    
+    basic_prompt = "Implement user authentication"
+    enhanced_prompt = context_agent.enhance_prompt_with_context(
+        base_prompt=basic_prompt,
+        context_data=analysis
+    )
+    
+    print(f"✅ Enhanced prompt from {len(basic_prompt)} to {len(enhanced_prompt)} characters")
+    print(f"   Original: '{basic_prompt}'")
+    print("   Enhanced includes: Context Engineering, Implementation Context, Quality Requirements")
+    
+    # Example 5: Generate PRP (Product Requirements Prompt)
+    print("\n📋 Example 5: Generating PRP")
+    print("-" * 40)
+    
+    documentation_links = [
+        "https://jwt.io/introduction/",
+        "https://fastapi.tiangolo.com/tutorial/security/",
+        "https://passlib.readthedocs.io/en/stable/"
+    ]
+    
+    prp = context_agent.generate_prp(
+        feature_request=feature_request,
+        context_analysis=analysis,
+        documentation_links=documentation_links
+    )
+    
+    print("✅ Generated comprehensive PRP")
+    print(f"   PRP length: {len(prp)} characters")
+    print(f"   Contains feature request: {feature_request in prp}")
+    print(f"   Contains documentation links: {len(documentation_links)} links included")
+    print(f"   Contains implementation blueprint: {'Implementation Blueprint' in prp}")
+    print(f"   Confidence score: {'9/10' in prp}")
+
+def demonstrate_context_agent_as_tool():
+    """Demonstrate using ContextAgent as a tool in a multi-agent workflow."""
+    print("\n🔗 Context Engineering Example: Multi-Agent Integration")
+    print("=" * 60)
+    
+    # Create ContextAgent
+    context_agent = create_context_agent(llm="gpt-4o-mini")
+    
+    # Example scenario: Product planning workflow
+    project_path = str(project_root)
+    feature_request = "Build a real-time chat system with WebSocket support"
+    
+    # Step 1: Context analysis
+    print("\n1️⃣ Step 1: Context Analysis")
+    analysis = context_agent.analyze_codebase_patterns(project_path)
+    print(f"✅ Analyzed codebase architecture and patterns")
+    
+    # Step 2: Generate implementation blueprint
+    print("\n2️⃣ Step 2: Implementation Blueprint")
+    blueprint = context_agent.create_implementation_blueprint(feature_request, analysis)
+    print(f"✅ Created implementation blueprint with {len(blueprint['implementation_steps'])} steps")
+    
+    # Step 3: Generate comprehensive PRP
+    print("\n3️⃣ Step 3: Generate PRP")
+    prp = context_agent.generate_prp(feature_request, analysis)  # Generated PRP for implementation guidance
+    print(f"✅ Generated PRP for implementation guidance")
+    
+    # Step 4: Create validation framework
+    print("\n4️⃣ Step 4: Validation Framework")
+    criteria = [
+        "WebSocket connections establish successfully",
+        "Messages broadcast to all connected clients",
+        "Chat history persists and loads correctly",
+        "User authentication works with WebSocket",
+        "Connection handling is robust with reconnection"
+    ]
+    validation = context_agent.create_validation_loop(feature_request, criteria)  # Validation framework for QA
+    print(f"✅ Created validation framework with {len(criteria)} criteria")
+    
+    print("\n🎯 Context Engineering Workflow Complete!")
+    print(f"   Feature: {feature_request}")
+    print("   Implementation ready with comprehensive context")
+    print("   Validation criteria defined for quality assurance")
+
+def show_context_engineering_benefits():
+    """Demonstrate the benefits of Context Engineering vs traditional approaches."""
+    print("\n📊 Context Engineering Benefits")
+    print("=" * 60)
+    
+    # Traditional prompt engineering approach
+    print("\n❌ Traditional Prompt Engineering:")
+    traditional_prompt = "Create a user authentication system"
+    print(f"   Prompt: '{traditional_prompt}'")
+    print(f"   Length: {len(traditional_prompt)} characters")
+    print(f"   Context: Minimal - relies on AI's general knowledge")
+    print(f"   Success Rate: Variable - depends on AI model's training")
+    
+    # Context Engineering approach
+    print("\n✅ Context Engineering Approach:")
+    context_agent = create_context_agent(llm="gpt-4o-mini")
+    
+    # Generate comprehensive context
+    analysis = context_agent.analyze_codebase_patterns(str(project_root))
+    enhanced_prompt = context_agent.enhance_prompt_with_context(
+        traditional_prompt, analysis
+    )
+    
+    print(f"   Enhanced Prompt Length: {len(enhanced_prompt)} characters")
+    print(f"   Context: Comprehensive - includes:")
+    print(f"     • Codebase architecture analysis")
+    print(f"     • Existing patterns and conventions")
+    print(f"     • Implementation guidance")
+    print(f"     • Quality requirements")
+    print(f"     • Validation criteria")
+    print(f"   Success Rate: Higher - AI has all necessary context")
+    
+    print(f"\n🎯 Context Engineering provides:")
+    print("   📈 10x better than prompt engineering (comprehensive vs clever wording)")
+    print("   📈 100x better than vibe coding (structured vs ad-hoc)")
+    print("   🎯 First-try implementation success through complete context")
+
+if __name__ == "__main__":
+    print("🚀 PraisonAI Context Engineering Examples")
+    print("=========================================")
+    
+    try:
+        # Run all examples
+        demonstrate_basic_context_generation()
+        demonstrate_context_agent_as_tool()
+        show_context_engineering_benefits()
+        
+        print("\n🎉 All Context Engineering examples completed successfully!")
+        print("\n💡 Key Takeaways:")
+        print("   • ContextAgent automates comprehensive context generation")
+        print("   • Context Engineering enables first-try implementation success")
+        print("   • Integration with existing PraisonAI agents is seamless")
+        print("   • Validation frameworks ensure quality and completeness")
+        
+    except Exception as e:
+        print(f"\n❌ Error running examples: {e}")
+        print("   Make sure you have the PraisonAI package installed and configured")
+        sys.exit(1)

examples/python/agents/multi-provider-agent.py

@@ -0,0 +1,285 @@
+"""
+Multi-Provider/Multi-Model Agent Example
+
+This example demonstrates how to use multiple AI providers/models with intelligent
+agent-based selection for cost optimization and performance.
+"""
+
+import os
+from praisonaiagents import Agent, Task, PraisonAIAgents
+from praisonaiagents.agent import RouterAgent
+from praisonaiagents.llm.model_router import ModelRouter, ModelProfile, TaskComplexity
+
+# Example 1: Simple Multi-Model Agent with Auto-Routing
+def example_auto_routing():
+    """Example of automatic model routing based on task complexity"""
+    print("\n=== Example 1: Auto-Routing Multi-Model Agent ===\n")
+    
+    # Create a router agent that automatically selects models
+    research_agent = RouterAgent(
+        name="Smart Researcher",
+        role="Adaptive Research Assistant",
+        goal="Research topics using the most appropriate AI model",
+        backstory="I analyze task complexity and route to the best model",
+        models=["gpt-4o-mini", "gpt-4o", "claude-3-5-sonnet-20241022"],
+        routing_strategy="auto",  # Automatic model selection
+        verbose=True
+    )
+    
+    # Create tasks with different complexity levels
+    simple_task = Task(
+        name="simple_calculation",
+        description="Calculate the sum of 1542 and 2873",
+        expected_output="The numerical result",
+        agent=research_agent
+    )
+    
+    moderate_task = Task(
+        name="summarize_article", 
+        description="Summarize the key points about renewable energy trends",
+        expected_output="A concise summary with main points",
+        agent=research_agent
+    )
+    
+    complex_task = Task(
+        name="analyze_code",
+        description="Implement a Python function to find the longest palindromic substring in a given string with O(n^2) complexity",
+        expected_output="Complete Python implementation with explanation",
+        agent=research_agent
+    )
+    
+    # Run the tasks
+    agents = PraisonAIAgents(
+        agents=[research_agent],
+        tasks=[simple_task, moderate_task, complex_task],
+        process="sequential",
+        verbose=True
+    )
+    
+    results = agents.start()
+    
+    # Show usage report
+    print("\n=== Model Usage Report ===")
+    print(research_agent.get_usage_report())
+
+
+# Example 2: Cost-Optimized Workflow with Routing
+def example_cost_optimized_workflow():
+    """Example of cost-optimized workflow with model routing"""
+    print("\n=== Example 2: Cost-Optimized Workflow ===\n")
+    
+    # Create custom model router with cost threshold
+    cost_router = ModelRouter(
+        cost_threshold=0.01,  # Max $0.01 per 1k tokens
+        preferred_providers=["google", "openai", "anthropic"]  # Provider preference
+    )
+    
+    # Create specialized agents with different model strategies
+    analyzer = RouterAgent(
+        name="Cost-Conscious Analyzer",
+        role="Data Analyzer",
+        goal="Analyze data efficiently while minimizing costs",
+        models={
+            "gemini/gemini-1.5-flash": {},
+            "gpt-4o-mini": {},
+            "deepseek-chat": {}
+        },
+        model_router=cost_router,
+        routing_strategy="cost-optimized",
+        verbose=True
+    )
+    
+    writer = RouterAgent(
+        name="Quality Writer",
+        role="Content Writer", 
+        goal="Create high-quality content",
+        models={
+            "claude-3-5-sonnet-20241022": {},
+            "gpt-4o": {}
+        },
+        routing_strategy="performance-optimized",  # Prefer better models
+        verbose=True
+    )
+    
+    # Create workflow tasks
+    analysis_task = Task(
+        name="analyze_data",
+        description="Analyze this dataset: [1, 2, 3, 4, 5]. Find mean, median, and mode.",
+        expected_output="Statistical analysis results",
+        agent=analyzer
+    )
+    
+    writing_task = Task(
+        name="write_report",
+        description="Write a professional report based on the analysis",
+        expected_output="Professional report with insights",
+        agent=writer,
+        context=[analysis_task]  # Use results from analysis
+    )
+    
+    # Run workflow
+    workflow = PraisonAIAgents(
+        agents=[analyzer, writer],
+        tasks=[analysis_task, writing_task],
+        process="sequential",
+        verbose=True
+    )
+    
+    results = workflow.start()
+    
+    # Show cost comparison
+    print("\n=== Cost Analysis ===")
+    print(f"Analyzer costs: {analyzer.get_usage_report()}")
+    print(f"Writer costs: {writer.get_usage_report()}")
+
+
+# Example 3: Auto Agent Mode with Multi-Provider Support
+def example_auto_agents_multi_provider():
+    """Example using AutoAgents with multi-provider support"""
+    print("\n=== Example 3: AutoAgents with Multi-Provider Support ===\n")
+    
+    from praisonaiagents.agents import AutoAgents
+    
+    # Create AutoAgents that will automatically assign appropriate models
+    auto_agents = AutoAgents(
+        instructions="Create a market research report on electric vehicles. Include data analysis, competitor analysis, and future projections.",
+        max_agents=3,
+        llm="gpt-4o-mini",  # Default model for agent generation
+        verbose=True
+    )
+    
+    # After agents are created, upgrade them to multi-model agents
+    multi_model_agents = []
+    for agent in auto_agents.agents:
+        # Convert regular agents to multi-model agents
+        multi_agent = RouterAgent(
+            name=agent.name,
+            role=agent.role,
+            goal=agent.goal,
+            backstory=agent.backstory,
+            tools=agent.tools,
+            models=["gpt-4o-mini", "gemini/gemini-1.5-flash", "claude-3-haiku-20240307", "gpt-4o"],
+            routing_strategy="auto",
+            verbose=True
+        )
+        multi_model_agents.append(multi_agent)
+    
+    # Update the agents in the AutoAgents instance
+    auto_agents.agents = multi_model_agents
+    
+    # Run the auto-generated workflow
+    results = auto_agents.start()
+    
+    # Show model usage across all agents
+    print("\n=== Multi-Provider Usage Summary ===")
+    total_calls = 0
+    for agent in multi_model_agents:
+        report = agent.get_usage_report()
+        print(f"\nAgent: {agent.name}")
+        for model, stats in report['model_usage'].items():
+            if stats['calls'] > 0:
+                print(f"  - {model}: {stats['calls']} calls")
+                total_calls += stats['calls']
+    
+    print(f"\nTotal API calls: {total_calls}")
+
+
+# Example 4: Custom Routing Logic
+def example_custom_routing():
+    """Example with custom routing logic based on specific requirements"""
+    print("\n=== Example 4: Custom Routing Logic ===\n")
+    
+    # Create custom model profiles for specific use cases
+    custom_models = [
+        ModelProfile(
+            name="gpt-4o",
+            provider="openai",
+            complexity_range=(TaskComplexity.SIMPLE, TaskComplexity.VERY_COMPLEX),
+            cost_per_1k_tokens=0.0075,
+            strengths=["code-generation", "debugging"],
+            capabilities=["text", "function-calling"],
+            context_window=128000
+        ),
+        ModelProfile(
+            name="deepseek-chat",
+            provider="deepseek",
+            complexity_range=(TaskComplexity.MODERATE, TaskComplexity.VERY_COMPLEX),
+            cost_per_1k_tokens=0.001,
+            strengths=["mathematics", "algorithms"],
+            capabilities=["text", "function-calling"],
+            context_window=128000
+        )
+    ]
+    
+    # Create router with custom models
+    custom_router = ModelRouter(models=custom_models)
+    
+    # Tool for web search (example)
+    def search_web(query: str) -> str:
+        """Search the web for information"""
+        return f"Search results for: {query}"
+    
+    # Create specialized agent
+    coder = RouterAgent(
+        name="Adaptive Coder",
+        role="Software Developer",
+        goal="Write and debug code using the best model for each task",
+        backstory="I'm an expert coder who knows when to use different AI models",
+        model_router=custom_router,
+        routing_strategy="auto",
+        tools=[search_web],
+        verbose=True
+    )
+    
+    # Create coding tasks
+    tasks = [
+        Task(
+            name="fix_bug",
+            description="Fix this Python bug: 'list' object has no attribute 'appendx'",
+            expected_output="Corrected code with explanation",
+            agent=coder
+        ),
+        Task(
+            name="implement_algorithm",
+            description="Implement Dijkstra's shortest path algorithm in Python",
+            expected_output="Complete implementation with comments",
+            agent=coder,
+            tools=[search_web]
+        )
+    ]
+    
+    # Run tasks
+    agents = PraisonAIAgents(
+        agents=[coder],
+        tasks=tasks,
+        process="sequential",
+        verbose=True
+    )
+    
+    results = agents.start()
+    
+    print("\n=== Custom Routing Results ===")
+    print(coder.get_usage_report())
+
+
+# Run examples
+if __name__ == "__main__":
+    # Make sure to set your API keys
+    # os.environ["OPENAI_API_KEY"] = "your-openai-key"
+    # os.environ["ANTHROPIC_API_KEY"] = "your-anthropic-key"  
+    # os.environ["GEMINI_API_KEY"] = "your-gemini-key"
+    
+    # Run examples
+    example_auto_routing()
+    example_cost_optimized_workflow()
+    example_auto_agents_multi_provider()
+    example_custom_routing()
+    
+    print("\n=== All Examples Completed ===")
+    print("\nKey Features Demonstrated:")
+    print("1. Automatic model selection based on task complexity")
+    print("2. Cost-optimized routing for budget-conscious operations")
+    print("3. Performance-optimized routing for quality-critical tasks")
+    print("4. Multi-provider support with fallback mechanisms")
+    print("5. Integration with AutoAgents for automatic workflow generation")
+    print("6. Custom routing logic for specialized use cases")

examples/python/agents/router-agent-cost-optimization.py

@@ -0,0 +1,82 @@
+"""
+RouterAgent Cost Optimization Example
+
+This example demonstrates how to use RouterAgent for intelligent model selection
+based on cost optimization. The router agent automatically selects the most
+cost-effective model for different types of tasks while maintaining quality.
+
+Features demonstrated:
+- Cost-optimized model routing
+- Automatic model selection based on task complexity
+- Usage tracking and cost monitoring
+- Fallback mechanisms for reliability
+"""
+
+from praisonaiagents import Agent
+from praisonaiagents.agent.router_agent import RouterAgent
+from praisonaiagents.tools import duckduckgo
+
+# Define model options with cost considerations
+# Using different models for different complexity levels
+cheap_model = "gpt-4o-mini"  # For simple tasks
+balanced_model = "gpt-4o"    # For moderate complexity  
+premium_model = "claude-3-5-sonnet-20241022"  # For complex tasks
+
+# Create RouterAgent with cost optimization strategy
+router = RouterAgent(
+    name="CostOptimizedRouter",
+    role="Cost-Efficient Task Router",
+    goal="Route tasks to the most cost-effective model while maintaining quality",
+    backstory="You are a smart router that optimizes for cost-efficiency by selecting appropriate models based on task complexity.",
+    
+    # Model routing strategy - simple tasks to cheap models, complex to premium
+    models=[cheap_model, balanced_model, premium_model],
+    
+    # Routing logic - this could be enhanced with more sophisticated rules
+    instructions="""You are a cost-optimization router. For simple tasks like basic questions, 
+    definitions, or simple calculations, use the cheapest model. For moderate complexity tasks 
+    like writing, analysis, or research, use the balanced model. For complex tasks requiring 
+    deep reasoning, creativity, or specialized knowledge, use the premium model.""",
+    
+    tools=[duckduckgo],
+    verbose=True
+)
+
+# Example tasks of varying complexity levels
+
+# Simple task - should route to cheap model
+print("="*60)
+print("TESTING SIMPLE TASK (should use cheap model)")
+print("="*60)
+simple_result = router.start("What is the capital of France?")
+print(f"Simple task result: {simple_result}")
+
+# Moderate complexity task - should route to balanced model  
+print("\n" + "="*60)
+print("TESTING MODERATE TASK (should use balanced model)")
+print("="*60)
+moderate_result = router.start("Write a brief analysis of renewable energy trends in 2024")
+print(f"Moderate task result: {moderate_result}")
+
+# Complex task - should route to premium model
+print("\n" + "="*60) 
+print("TESTING COMPLEX TASK (should use premium model)")
+print("="*60)
+complex_result = router.start("Conduct a comprehensive strategic analysis of the impact of quantum computing on cybersecurity, including potential vulnerabilities and mitigation strategies")
+print(f"Complex task result: {complex_result}")
+
+# Research task with tool usage - should route appropriately
+print("\n" + "="*60)
+print("TESTING RESEARCH TASK WITH TOOLS")
+print("="*60)
+research_result = router.start("Research and analyze the latest developments in artificial intelligence regulation globally")
+print(f"Research task result: {research_result}")
+
+print("\n" + "="*80)
+print("COST OPTIMIZATION ROUTER DEMONSTRATION COMPLETED")
+print("="*80)
+print("The RouterAgent automatically selected appropriate models based on task complexity:")
+print("- Simple factual questions → Cheaper model (gpt-4o-mini)")  
+print("- Moderate analysis tasks → Balanced model (gpt-4o)")
+print("- Complex strategic analysis → Premium model (claude-3-5-sonnet)")
+print("- This approach optimizes costs while maintaining quality for each task type")

examples/python/api/secondary-market-research-api.py

@@ -440,7 +440,7 @@ async def generate_research(
         "message": "Report generation queued",
         "created_at": datetime.now().isoformat(),
         "updated_at": datetime.now().isoformat(),
-        "config": request.dict()
+        "config": request.model_dump()
     }
     
     # Create config object

examples/python/concepts/context-engineering-workflow.py

@@ -0,0 +1,469 @@
+#!/usr/bin/env python3
+"""
+Context Engineering Workflow - Advanced Multi-Agent Example
+
+This example demonstrates advanced Context Engineering workflows using ContextAgent
+in combination with other PraisonAI agents. It shows how Context Engineering can
+dramatically improve AI implementation success rates through comprehensive context
+generation and validation loops.
+
+Workflow demonstrated:
+1. Product Manager Agent defines requirements
+2. ContextAgent analyzes codebase and generates comprehensive context
+3. Architecture Agent designs implementation using context
+4. Developer Agent implements using context-enhanced prompts
+5. QA Agent validates using context-generated criteria
+
+This represents the full Context Engineering methodology in action.
+"""
+
+import sys
+from pathlib import Path
+
+# Add the src directory to Python path for imports
+project_root = Path(__file__).parent.parent.parent.parent / "src" / "praisonai-agents"
+sys.path.insert(0, str(project_root))
+
+from praisonaiagents import Agent, Task, PraisonAIAgents, create_context_agent
+
+class ContextEngineeringWorkflow:
+    """
+    Advanced Context Engineering workflow demonstrating the full methodology.
+    
+    This class orchestrates multiple agents using Context Engineering principles
+    to achieve higher success rates in AI-driven development tasks.
+    """
+    
+    def __init__(self, project_path: str, llm: str = "gpt-4o-mini"):
+        self.project_path = project_path
+        self.llm = llm
+        self.context_data = {}
+        self.setup_agents()
+    
+    def setup_agents(self):
+        """Setup the multi-agent team with Context Engineering support."""
+        
+        # 1. Product Manager Agent - Defines requirements
+        self.product_manager = Agent(
+            name="Product Manager",
+            role="Product Requirements Specialist",
+            goal="Define clear, comprehensive product requirements and user stories",
+            backstory="""You are an experienced product manager who specializes in 
+            creating detailed, actionable requirements. You understand that clear 
+            requirements are the foundation of successful implementation.""",
+            instructions="""
+            When defining requirements:
+            1. Be specific and measurable
+            2. Include user acceptance criteria
+            3. Consider edge cases and error scenarios
+            4. Define success metrics
+            5. Specify technical constraints
+            """,
+            llm=self.llm,
+            verbose=True
+        )
+        
+        # 2. Context Engineering Agent - Generates comprehensive context
+        self.context_engineer = create_context_agent(
+            llm=self.llm,
+            name="Context Engineering Specialist",
+            verbose=True
+        )
+        
+        # 3. Software Architect Agent - Designs implementation using context
+        self.architect = Agent(
+            name="Software Architect",
+            role="System Architecture Specialist", 
+            goal="Design robust, scalable system architecture based on comprehensive context",
+            backstory="""You are a senior software architect with expertise in 
+            designing systems that follow established patterns and best practices. 
+            You excel at creating architectures that integrate seamlessly with 
+            existing codebases.""",
+            instructions="""
+            When designing architecture:
+            1. Follow the patterns identified in the context analysis
+            2. Ensure compatibility with existing systems
+            3. Design for scalability and maintainability
+            4. Consider security and performance implications
+            5. Document architectural decisions and rationale
+            """,
+            llm=self.llm,
+            verbose=True
+        )
+        
+        # 4. Senior Developer Agent - Implements using context-enhanced guidance
+        self.developer = Agent(
+            name="Senior Developer",
+            role="Implementation Specialist",
+            goal="Implement features following context-guided best practices",
+            backstory="""You are a senior developer who excels at implementing 
+            features that follow established codebase patterns. You understand 
+            that consistency and quality are paramount.""",
+            instructions="""
+            When implementing features:
+            1. Follow the codebase patterns identified in context analysis
+            2. Maintain consistency with existing code style
+            3. Implement comprehensive error handling
+            4. Write clean, maintainable code
+            5. Follow the implementation blueprint exactly
+            """,
+            llm=self.llm,
+            verbose=True
+        )
+        
+        # 5. QA Engineer Agent - Validates using context-generated criteria
+        self.qa_engineer = Agent(
+            name="QA Engineer",
+            role="Quality Assurance Specialist",
+            goal="Ensure implementation meets all quality criteria and requirements",
+            backstory="""You are an experienced QA engineer who specializes in 
+            comprehensive testing and validation. You understand that quality 
+            is built in, not bolted on.""",
+            instructions="""
+            When validating implementations:
+            1. Use the validation criteria from context analysis
+            2. Test both happy path and edge cases
+            3. Verify integration with existing systems
+            4. Check for security vulnerabilities
+            5. Validate performance requirements
+            """,
+            llm=self.llm,
+            verbose=True
+        )
+    
+    def run_context_engineering_workflow(self, feature_request: str):
+        """
+        Execute the complete Context Engineering workflow.
+        
+        Args:
+            feature_request (str): The feature to be implemented
+            
+        Returns:
+            dict: Complete workflow results with context and implementation
+        """
+        print(f"🚀 Starting Context Engineering Workflow")
+        print(f"Feature Request: {feature_request}")
+        print("=" * 80)
+        
+        # Phase 1: Requirements Analysis
+        print("\n📋 Phase 1: Product Requirements Analysis")
+        print("-" * 50)
+        
+        requirements_task = Task(
+            name="requirements_analysis",
+            description=f"""
+            Analyze and refine the feature request: '{feature_request}'
+            
+            Create comprehensive requirements including:
+            - Detailed feature description
+            - User acceptance criteria
+            - Technical requirements
+            - Success metrics
+            - Edge cases and constraints
+            """,
+            expected_output="Comprehensive product requirements document",
+            agent=self.product_manager
+        )
+        
+        # Phase 2: Context Engineering Analysis
+        print("\n🔧 Phase 2: Context Engineering Analysis")
+        print("-" * 50)
+        
+        # Generate comprehensive context using ContextAgent
+        codebase_analysis = self.context_engineer.analyze_codebase_patterns(
+            project_path=self.project_path
+        )
+        
+        context_document = self.context_engineer.generate_context_document(
+            project_path=self.project_path,
+            requirements=feature_request,
+            analysis=codebase_analysis
+        )
+        
+        validation_framework = self.context_engineer.create_validation_loop(
+            implementation_requirements=feature_request,
+            success_criteria=[
+                "Feature implements all specified requirements",
+                "Code follows existing patterns and conventions",
+                "Implementation includes comprehensive error handling",
+                "All tests pass and coverage meets standards",
+                "Integration with existing systems is seamless"
+            ]
+        )
+        
+        implementation_blueprint = self.context_engineer.create_implementation_blueprint(
+            feature_request=feature_request,
+            context_analysis=codebase_analysis
+        )
+        
+        # Generate PRP for complete context
+        prp = self.context_engineer.generate_prp(
+            feature_request=feature_request,
+            context_analysis=codebase_analysis,
+            documentation_links=[
+                "https://docs.praisonai.com/",
+                "https://pydantic-docs.helpmanual.io/",
+                "https://fastapi.tiangolo.com/"
+            ]
+        )
+        
+        print(f"✅ Context Engineering Analysis Complete:")
+        print(f"   • Codebase analysis: {len(str(codebase_analysis))} chars")
+        print(f"   • Context document: {len(context_document)} chars")
+        print(f"   • Validation framework: {len(validation_framework['validation_steps'])} steps")
+        print(f"   • Implementation blueprint: {len(implementation_blueprint['implementation_steps'])} steps")
+        print(f"   • PRP generated: {len(prp)} chars")
+        
+        # Store context data for subsequent phases
+        self.context_data = {
+            "codebase_analysis": codebase_analysis,
+            "context_document": context_document,
+            "validation_framework": validation_framework,
+            "implementation_blueprint": implementation_blueprint,
+            "prp": prp
+        }
+        
+        # Phase 3: Architecture Design with Context
+        print("\n🏗️ Phase 3: Architecture Design with Context")
+        print("-" * 50)
+        
+        architecture_task = Task(
+            name="architecture_design",
+            description=f"""
+            Design system architecture for: '{feature_request}'
+            
+            Use the comprehensive context provided:
+            {context_document}
+            
+            Implementation Blueprint:
+            {implementation_blueprint}
+            
+            Design architecture that:
+            - Follows identified codebase patterns
+            - Integrates with existing systems
+            - Meets all technical requirements
+            - Is scalable and maintainable
+            """,
+            expected_output="Detailed system architecture design with component specifications",
+            agent=self.architect,
+            context=[requirements_task]
+        )
+        
+        # Phase 4: Implementation with Context-Enhanced Guidance
+        print("\n💻 Phase 4: Implementation with Context")
+        print("-" * 50)
+        
+        # Enhance the implementation prompt with context
+        enhanced_prompt = self.context_engineer.enhance_prompt_with_context(
+            base_prompt=f"Implement {feature_request}",
+            context_data=codebase_analysis
+        )
+        
+        implementation_task = Task(
+            name="feature_implementation",
+            description=f"""
+            Implement the feature using context-enhanced guidance:
+            
+            {enhanced_prompt}
+            
+            Product Requirements Prompt (PRP):
+            {prp}
+            
+            Architecture Design: Reference the architecture task output
+            
+            Implementation must:
+            - Follow the implementation blueprint exactly
+            - Use patterns identified in codebase analysis
+            - Meet all requirements from Phase 1
+            - Include comprehensive error handling
+            """,
+            expected_output="Complete feature implementation with code and documentation",
+            agent=self.developer,
+            context=[requirements_task, architecture_task]
+        )
+        
+        # Phase 5: Quality Assurance with Context-Generated Criteria
+        print("\n🔍 Phase 5: Quality Assurance with Context")
+        print("-" * 50)
+        
+        qa_task = Task(
+            name="quality_validation",
+            description=f"""
+            Validate the implementation using context-generated criteria:
+            
+            Validation Framework:
+            {validation_framework}
+            
+            Verify that implementation:
+            - Meets all success criteria defined in validation framework
+            - Follows codebase patterns and conventions
+            - Integrates properly with existing systems
+            - Handles edge cases and error scenarios
+            - Meets performance and security requirements
+            
+            Use the validation steps provided to systematically check each criterion.
+            """,
+            expected_output="Comprehensive quality validation report with pass/fail status",
+            agent=self.qa_engineer,
+            context=[requirements_task, architecture_task, implementation_task]
+        )
+        
+        # Execute the complete workflow
+        print("\n⚙️ Executing Context Engineering Workflow")
+        print("-" * 50)
+        
+        agents_workflow = PraisonAIAgents(
+            agents=[
+                self.product_manager,
+                self.architect, 
+                self.developer,
+                self.qa_engineer
+            ],
+            tasks=[
+                requirements_task,
+                architecture_task,
+                implementation_task,
+                qa_task
+            ],
+            process="sequential",
+            verbose=True
+        )
+        
+        # Execute workflow
+        workflow_results = agents_workflow.start()
+        
+        # Compile complete results
+        complete_results = {
+            "feature_request": feature_request,
+            "context_engineering": self.context_data,
+            "workflow_results": workflow_results,
+            "methodology": "Context Engineering - 10x better than prompt engineering"
+        }
+        
+        return complete_results
+
+def demonstrate_context_engineering_benefits():
+    """
+    Demonstrate the benefits of Context Engineering methodology.
+    """
+    print("\n📊 Context Engineering vs Traditional Approaches")
+    print("=" * 60)
+    
+    # Traditional approach simulation
+    print("\n❌ Traditional AI Coding Approach:")
+    print("   1. Write basic prompt: 'Implement user authentication'")
+    print("   2. AI uses general knowledge to implement")
+    print("   3. Result often doesn't fit existing codebase patterns")
+    print("   4. Multiple iterations needed to fix integration issues")
+    print("   5. Success rate: ~30-40% first-try success")
+    
+    # Context Engineering approach
+    print("\n✅ Context Engineering Approach:")
+    print("   1. Analyze codebase patterns and architecture")
+    print("   2. Generate comprehensive context document")
+    print("   3. Create validation framework with success criteria")
+    print("   4. Enhance prompts with rich contextual information")
+    print("   5. Generate PRP (Product Requirements Prompt)")
+    print("   6. AI implements using complete context")
+    print("   7. Success rate: ~90%+ first-try success")
+    
+    print("\n📈 Context Engineering Advantages:")
+    print("   • 10x better than prompt engineering (context vs clever wording)")
+    print("   • 100x better than vibe coding (structured vs ad-hoc)")
+    print("   • Enables first-try implementation success")
+    print("   • Reduces development iteration cycles")
+    print("   • Ensures consistency with existing codebase")
+    print("   • Provides built-in quality validation")
+
+def run_example_workflow():
+    """Run an example Context Engineering workflow."""
+    
+    # Setup workflow with current project
+    project_path = str(project_root)
+    workflow = ContextEngineeringWorkflow(
+        project_path=project_path,
+        llm="gpt-4o-mini"
+    )
+    
+    # Example feature request
+    feature_request = """
+    Implement a real-time notification system that:
+    - Sends notifications via WebSocket connections
+    - Supports different notification types (info, warning, error)
+    - Persists notifications in database for offline users
+    - Includes user preference management for notification settings
+    - Provides REST API for notification management
+    """
+    
+    print("🎯 Running Example Context Engineering Workflow")
+    print("=" * 60)
+    
+    try:
+        # Execute the complete workflow
+        results = workflow.run_context_engineering_workflow(feature_request)
+        
+        print("\n🎉 Context Engineering Workflow Completed Successfully!")
+        print("=" * 60)
+        
+        print(f"\n📊 Workflow Summary:")
+        print(f"   • Feature: Real-time notification system")
+        print(f"   • Context generated: ✅ Complete")
+        print(f"   • Architecture designed: ✅ With context")
+        print(f"   • Implementation: ✅ Context-guided")
+        print(f"   • Quality validation: ✅ Context-criteria")
+        
+        print(f"\n🔧 Context Engineering Data:")
+        context_data = results["context_engineering"]
+        print(f"   • Codebase analysis: {len(str(context_data['codebase_analysis']))} chars")
+        print(f"   • Context document: {len(context_data['context_document'])} chars") 
+        print(f"   • Validation framework: {len(context_data['validation_framework']['validation_steps'])} steps")
+        print(f"   • Implementation blueprint: {len(context_data['implementation_blueprint']['implementation_steps'])} steps")
+        print(f"   • PRP: {len(context_data['prp'])} chars")
+        
+        return results
+        
+    except Exception as e:
+        print(f"\n❌ Error in workflow execution: {e}")
+        print("   Note: This is a demonstration - actual execution requires proper environment setup")
+        return None
+
+if __name__ == "__main__":
+    print("🚀 Advanced Context Engineering Workflow Example")
+    print("================================================")
+    
+    print("\n💡 This example demonstrates the complete Context Engineering methodology:")
+    print("   • Comprehensive codebase analysis")
+    print("   • Context document generation")
+    print("   • Validation framework creation")
+    print("   • Multi-agent workflow with context integration")
+    print("   • Quality assurance with context-generated criteria")
+    
+    # Show benefits comparison
+    demonstrate_context_engineering_benefits()
+    
+    # Run example workflow (demo mode)
+    print("\n🎭 Demo Mode: Context Engineering Workflow Structure")
+    print("(Note: Full execution requires complete environment setup)")
+    
+    project_path = str(project_root)
+    workflow = ContextEngineeringWorkflow(project_path, "gpt-4o-mini")
+    
+    print(f"\n✅ Workflow Setup Complete:")
+    print(f"   • Project path: {project_path}")
+    print(f"   • Agents configured: 5 (PM, Context Engineer, Architect, Developer, QA)")
+    print(f"   • Context Engineering agent: ✅ Ready")
+    print(f"   • Multi-agent workflow: ✅ Configured")
+    
+    print(f"\n🎯 Ready to execute Context Engineering workflow!")
+    print(f"   Use workflow.run_context_engineering_workflow(feature_request)")
+    print(f"   to execute the complete methodology.")
+    
+    print(f"\n📚 Key Context Engineering Concepts Demonstrated:")
+    print(f"   • Pattern extraction from existing codebase")
+    print(f"   • Comprehensive context document generation")
+    print(f"   • Validation loop creation with success criteria")
+    print(f"   • PRP (Product Requirements Prompt) generation")
+    print(f"   • Context-enhanced prompt engineering")
+    print(f"   • Multi-agent workflow integration")
+    
+    print(f"\n🎉 Context Engineering: 10x better than prompt engineering, 100x better than vibe coding!")

examples/python/concepts/reasoning-extraction.py

@@ -31,7 +31,7 @@ def save_reasoning_chain(chain: ChainOfThought) -> str:
     """Save a chain of thought reasoning to analyze patterns."""
     filename = f"reasoning_{chain.problem[:20].replace(' ', '_')}.json"
     with open(filename, 'w') as f:
-        json.dump(chain.dict(), f, indent=2)
+        json.dump(chain.model_dump(), f, indent=2)
     return f"Reasoning chain saved to {filename}"
 
 # Example 1: Chain of Thought Agent

examples/python/concepts/self-reflection-optimization-patterns.py

@@ -0,0 +1,46 @@
+"""
+Self-Reflection Optimization Patterns Example
+
+This example demonstrates self-reflection capabilities using PraisonAI's
+built-in reflection features for iterative improvement and quality optimization.
+"""
+
+from praisonaiagents import Agent, Task, PraisonAIAgents
+from praisonaiagents.tools import internet_search
+
+print("=== Self-Reflection Optimization Patterns Example ===\n")
+
+# Create self-reflecting agent with built-in reflection capabilities
+reflection_agent = Agent(
+    name="Self-Reflecting Agent",
+    role="Self-Improving Researcher",
+    goal="Demonstrate self-reflection and iterative improvement patterns",
+    backstory="Expert researcher with strong self-reflection and continuous improvement capabilities",
+    tools=[internet_search],
+    self_reflect=True,
+    min_reflect=2,
+    max_reflect=4,
+    reflect_llm="gpt-4o-mini",
+    verbose=True
+)
+
+# Create task that benefits from self-reflection
+reflection_task = Task(
+    description="""Research and analyze the future of artificial intelligence:
+    1. Investigate current AI trends and breakthrough technologies
+    2. Analyze potential impacts on society and industry
+    3. Provide well-reasoned predictions for the next 5 years
+    4. Ensure analysis is comprehensive, accurate, and well-structured
+    
+    Use self-reflection to improve the quality and completeness of your analysis.""",
+    expected_output="Comprehensive AI future analysis with high quality through self-reflection",
+    agent=reflection_agent
+)
+
+# Run with self-reflection optimization
+print("Starting self-reflection optimization demonstration...")
+result = reflection_agent.execute_task(reflection_task)
+
+print(f"\nSelf-Reflection Result: {result[:200]}...")
+print("\n✅ Self-reflection optimization complete!")
+print("Agent demonstrated iterative improvement through built-in self-reflection capabilities.")

examples/python/custom_tools/example_latency_tracking.py

@@ -130,9 +130,11 @@ def example_mcp_tracking():
             )
             plan = agent.chat("Plan: Search for Python documentation")
         
-        # Track tool usage
+        # Track tool usage (this will now have actual timing)
         with tracker.track("tool_usage", request_id):
-            # Simulate tool execution
+            # Simulate tool execution with realistic timing
+            import time
+            time.sleep(0.1)  # Simulate some work
             tool_result = "Found 5 relevant documentation pages"
         
         # Track LLM generation

examples/python/custom_tools/hosted_server.py

@@ -0,0 +1,197 @@
+"""
+Hosted MCP Server implementation for PraisonAI Agents.
+
+This module provides a base class for creating hosted MCP servers
+that can handle requests and integrate with the MCP protocol.
+
+Note: This is an example implementation. To use it, ensure you have installed:
+  pip install praisonaiagents[mcp] starlette>=0.27.0
+"""
+
+import asyncio
+import logging
+from typing import Dict, Any, Optional, List, Callable
+import json
+
+try:
+    from mcp.server.fastmcp import FastMCP
+    from mcp.server import Server
+    from starlette.applications import Starlette
+    from starlette.requests import Request
+    from starlette.routing import Mount, Route
+    from mcp.server.sse import SseServerTransport
+    import uvicorn
+except ImportError:
+    raise ImportError(
+        "MCP server dependencies not installed. "
+        "Please install with: pip install praisonaiagents[mcp] starlette>=0.27.0"
+    )
+
+logger = logging.getLogger(__name__)
+
+
+class HostedMCPServer:
+    """
+    Base class for creating hosted MCP servers.
+    
+    This class provides a foundation for building MCP servers that can:
+    - Handle incoming requests
+    - Define custom tools
+    - Support SSE transport
+    - Be extended with custom functionality like latency tracking
+    """
+    
+    def __init__(self, name: str = "hosted-mcp-server", host: str = "localhost", port: int = 8080):
+        """
+        Initialize the hosted MCP server.
+        
+        Args:
+            name: Server name for identification
+            host: Host to bind to (default: localhost)
+            port: Port to listen on (default: 8080)
+        """
+        self.name = name
+        self.host = host
+        self.port = port
+        self.mcp = FastMCP(name)
+        self._tools: Dict[str, Callable] = {}
+        self._server: Optional[Server] = None
+        self._app: Optional[Starlette] = None
+        
+    def handle_request(self, request_data: Dict[str, Any]) -> Dict[str, Any]:
+        """
+        Handle incoming MCP requests.
+        
+        This method can be overridden in subclasses to add custom request handling,
+        such as latency tracking, authentication, or request modification.
+        
+        Args:
+            request_data: The incoming request data
+            
+        Returns:
+            Response data
+        """
+        # Default implementation - can be overridden
+        method = request_data.get('method', '')
+        request_id = request_data.get('id', 'unknown')
+        
+        logger.debug(f"Handling request {request_id}: {method}")
+        
+        # Basic response structure
+        response = {
+            'id': request_id,
+            'jsonrpc': '2.0',
+            'result': {}
+        }
+        
+        return response
+    
+    def add_tool(self, func: Callable, name: Optional[str] = None, description: Optional[str] = None):
+        """
+        Add a tool to the MCP server.
+        
+        Args:
+            func: The function to expose as a tool
+            name: Optional name for the tool (defaults to function name)
+            description: Optional description for the tool
+        """
+        tool_name = name or func.__name__
+        
+        # Register with FastMCP
+        if asyncio.iscoroutinefunction(func):
+            # Already async
+            self.mcp.tool(name=tool_name)(func)
+        else:
+            # Wrap sync function in async
+            async def async_wrapper(*args, **kwargs):
+                return func(*args, **kwargs)
+            async_wrapper.__name__ = func.__name__
+            async_wrapper.__doc__ = description or func.__doc__
+            self.mcp.tool(name=tool_name)(async_wrapper)
+        
+        self._tools[tool_name] = func
+        logger.info(f"Added tool: {tool_name}")
+    
+    def create_app(self, debug: bool = False) -> Starlette:
+        """
+        Create a Starlette application for serving the MCP server.
+        
+        Args:
+            debug: Enable debug mode
+            
+        Returns:
+            Starlette application instance
+            
+        Raises:
+            RuntimeError: If the MCP server is not properly initialized
+        """
+        if not self._server:
+            if not hasattr(self.mcp, '_mcp_server'):
+                raise RuntimeError("MCP server not properly initialized. Ensure FastMCP is correctly set up.")
+            self._server = self.mcp._mcp_server
+        
+        sse = SseServerTransport("/messages/")
+        
+        async def handle_sse(request: Request) -> None:
+            logger.debug(f"SSE connection from {request.client}")
+            async with sse.connect_sse(
+                request.scope,
+                request.receive,
+                request._send,
+            ) as (read_stream, write_stream):
+                await self._server.run(
+                    read_stream,
+                    write_stream,
+                    self._server.create_initialization_options(),
+                )
+        
+        self._app = Starlette(
+            debug=debug,
+            routes=[
+                Route("/sse", endpoint=handle_sse),
+                Mount("/messages/", app=sse.handle_post_message),
+            ],
+        )
+        
+        return self._app
+    
+    def start(self, debug: bool = False, **uvicorn_kwargs):
+        """
+        Start the MCP server.
+        
+        Args:
+            debug: Enable debug mode
+            **uvicorn_kwargs: Additional arguments to pass to uvicorn
+        """
+        app = self.create_app(debug=debug)
+        
+        print(f"Starting {self.name} MCP server on {self.host}:{self.port}")
+        print(f"Available tools: {', '.join(self._tools.keys())}")
+        print(f"SSE endpoint: http://{self.host}:{self.port}/sse")
+        
+        uvicorn.run(app, host=self.host, port=self.port, **uvicorn_kwargs)
+    
+    async def start_async(self, debug: bool = False):
+        """
+        Start the MCP server asynchronously.
+        
+        Args:
+            debug: Enable debug mode
+        """
+        app = self.create_app(debug=debug)
+        
+        config = uvicorn.Config(app, host=self.host, port=self.port)
+        server = uvicorn.Server(config)
+        
+        print(f"Starting {self.name} MCP server on {self.host}:{self.port}")
+        print(f"Available tools: {', '.join(self._tools.keys())}")
+        
+        await server.serve()
+    
+    def get_tools(self) -> List[str]:
+        """Get list of available tool names."""
+        return list(self._tools.keys())
+    
+    def get_endpoint(self) -> str:
+        """Get the SSE endpoint URL."""
+        return f"http://{self.host}:{self.port}/sse"

examples/python/custom_tools/mcp_server_latency_example.py

@@ -6,7 +6,7 @@ without modifying PraisonAI core files.
 """
 
 from praisonaiagents import Agent, PraisonAIAgents
-from praisonaiagents.mcp import HostedMCPServer
+from hosted_server import HostedMCPServer  # Import from local file
 from latency_tracker_tool import tracker, get_latency_metrics
 import json
 

examples/python/general/advanced-callback-systems.py

@@ -0,0 +1,59 @@
+"""
+Advanced Callback Systems Example
+
+This example demonstrates callback systems using PraisonAI's built-in
+callback functionality for monitoring agent interactions and tool usage.
+"""
+
+from praisonaiagents import Agent, Task, PraisonAIAgents
+from praisonaiagents.display_callback import register_display_callback
+from praisonaiagents.tools import internet_search
+
+print("=== Advanced Callback Systems Example ===\n")
+
+# Simple callback function to monitor interactions
+def interaction_callback(data):
+    """Monitor agent interactions"""
+    print(f"📋 Interaction: {data.get('agent_name', 'Unknown')} - {data.get('type', 'unknown')}")
+
+# Simple callback function to monitor tool usage
+def tool_callback(data):
+    """Monitor tool usage"""
+    print(f"🔧 Tool Used: {data.get('agent_name', 'Unknown')} used {data.get('tool_name', 'unknown')}")
+
+# Simple callback function to monitor generation
+def generation_callback(data):
+    """Monitor content generation"""
+    print(f"✍️  Generation: {data.get('agent_name', 'Unknown')} generating content")
+
+# Register callbacks with PraisonAI's callback system
+print("Registering callbacks...")
+register_display_callback('interaction', interaction_callback)
+register_display_callback('tool_call', tool_callback)
+register_display_callback('generating', generation_callback)
+print("✅ Callbacks registered\n")
+
+# Create a research agent with callback monitoring
+research_agent = Agent(
+    name="Research Agent",
+    role="Information Researcher",
+    goal="Research topics and demonstrate callback monitoring",
+    backstory="Expert researcher that demonstrates callback functionality",
+    tools=[internet_search],
+    verbose=True
+)
+
+# Create a simple task
+research_task = Task(
+    description="Research the latest developments in renewable energy technology",
+    expected_output="Brief summary of renewable energy developments",
+    agent=research_agent
+)
+
+# Execute with callback monitoring
+print("Starting research with callback monitoring...")
+result = research_agent.execute_task(research_task)
+
+print(f"\nResearch Result: {result[:200]}...")
+print("\n✅ Callback monitoring demonstration complete!")
+print("Callbacks successfully tracked agent interactions, tool usage, and content generation.")

examples/python/general/prompt_chaining.py

@@ -72,7 +72,7 @@ workflow = PraisonAIAgents(
 )
 
 # Run the workflow
-results = workflow.start()
+results = workflow.start(return_dict=True)
 
 # Print results
 print("\nWorkflow Results:")

examples/python/guardrails/comprehensive-guardrails-example.py

@@ -0,0 +1,204 @@
+"""
+Comprehensive Guardrails Example
+
+This example demonstrates both function-based and LLM-based guardrails for validating
+agent outputs and ensuring quality, safety, and compliance.
+
+Features demonstrated:
+- Function-based validation guardrails
+- LLM-based content validation
+- Multiple validation criteria
+- Retry mechanisms with feedback
+- Quality assurance workflows
+"""
+
+from praisonaiagents import Agent, Task, PraisonAIAgents
+from praisonaiagents.task import TaskOutput
+from typing import Tuple, Any
+import re
+
+# Define function-based guardrails for different validation types
+
+def email_format_guardrail(task_output: TaskOutput) -> Tuple[bool, Any]:
+    """
+    Validates that the output contains properly formatted email addresses.
+    """
+    output_text = str(task_output.raw)
+    
+    # Email regex pattern
+    email_pattern = r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b'
+    emails_found = re.findall(email_pattern, output_text)
+    
+    if emails_found:
+        return True, task_output
+    else:
+        return False, "No valid email addresses found in the output. Please include at least one properly formatted email address."
+
+def word_count_guardrail(task_output: TaskOutput) -> Tuple[bool, Any]:
+    """
+    Validates that the output meets minimum word count requirements.
+    """
+    output_text = str(task_output.raw)
+    word_count = len(output_text.split())
+    
+    min_words = 50  # Minimum required words
+    
+    if word_count >= min_words:
+        return True, task_output
+    else:
+        return False, f"Output too short. Found {word_count} words but need at least {min_words} words. Please provide a more detailed response."
+
+def professional_tone_guardrail(task_output: TaskOutput) -> Tuple[bool, Any]:
+    """
+    Validates that the output maintains a professional tone.
+    """
+    output_text = str(task_output.raw).lower()
+    
+    # Check for unprofessional words/phrases
+    unprofessional_terms = ['stupid', 'dumb', 'sucks', 'terrible', 'awful', 'hate']
+    
+    for term in unprofessional_terms:
+        if term in output_text:
+            return False, f"Output contains unprofessional language ('{term}'). Please revise to maintain a professional tone."
+    
+    return True, task_output
+
+def factual_accuracy_guardrail(task_output: TaskOutput) -> Tuple[bool, Any]:
+    """
+    Validates that the output includes specific factual elements.
+    """
+    output_text = str(task_output.raw).lower()
+    
+    # Check for presence of factual indicators
+    factual_indicators = ['according to', 'research shows', 'studies indicate', 'data suggests', 'evidence']
+    
+    has_factual_backing = any(indicator in output_text for indicator in factual_indicators)
+    
+    if has_factual_backing:
+        return True, task_output
+    else:
+        return False, "Output lacks factual backing. Please include references to research, studies, or data to support your claims."
+
+# Create agents with different guardrail configurations
+
+# Agent with email format validation
+email_agent = Agent(
+    name="EmailAgent",
+    role="Business Communication Specialist",
+    goal="Create professional business communications with proper email formatting",
+    backstory="You are a professional communication specialist who ensures all business correspondence includes proper contact information.",
+    instructions="Always include properly formatted email addresses in your responses."
+)
+
+# Agent with word count validation  
+content_agent = Agent(
+    name="ContentAgent",
+    role="Content Writer",
+    goal="Create detailed, comprehensive content that meets length requirements",
+    backstory="You are a professional content writer who creates detailed, well-researched articles.",
+    instructions="Provide comprehensive, detailed responses with sufficient depth and explanation."
+)
+
+# Agent with professional tone validation
+business_agent = Agent(
+    name="BusinessAgent", 
+    role="Professional Advisor",
+    goal="Provide professional business advice with appropriate tone",
+    backstory="You are a seasoned business advisor who maintains professionalism in all communications.",
+    instructions="Maintain a professional, respectful tone in all communications."
+)
+
+# Agent with factual accuracy validation
+research_agent = Agent(
+    name="ResearchAgent",
+    role="Research Analyst", 
+    goal="Provide well-researched, fact-based analysis",
+    backstory="You are a research analyst who backs all claims with evidence and citations.",
+    instructions="Support all statements with references to research, studies, or credible data sources."
+)
+
+# Create tasks with specific guardrails
+
+# Task with email format guardrail
+email_task = Task(
+    name="email_communication",
+    description="Write a business proposal for a new software project, including contact information",
+    expected_output="Professional business proposal with contact email addresses",
+    agent=email_agent,
+    guardrail=email_format_guardrail,
+    max_retries=3
+)
+
+# Task with word count guardrail
+content_task = Task(
+    name="detailed_analysis", 
+    description="Write an analysis of cloud computing benefits for small businesses",
+    expected_output="Comprehensive analysis of cloud computing benefits (minimum 50 words)",
+    agent=content_agent,
+    guardrail=word_count_guardrail,
+    max_retries=3
+)
+
+# Task with professional tone guardrail
+business_task = Task(
+    name="professional_advice",
+    description="Provide advice on handling difficult client relationships",
+    expected_output="Professional advice maintaining appropriate business tone",
+    agent=business_agent,
+    guardrail=professional_tone_guardrail,
+    max_retries=3
+)
+
+# Task with factual accuracy guardrail
+research_task = Task(
+    name="research_report",
+    description="Analyze the impact of artificial intelligence on job markets",
+    expected_output="Research-backed analysis with citations and evidence",
+    agent=research_agent,
+    guardrail=factual_accuracy_guardrail,
+    max_retries=3
+)
+
+# LLM-based guardrail example
+llm_guardrail_agent = Agent(
+    name="LLMGuardrailAgent",
+    role="Content Quality Validator",
+    goal="Validate content quality using LLM-based assessment",
+    backstory="You are a quality assurance specialist who uses AI to validate content quality.",
+    instructions="Create marketing content that is engaging, accurate, and compliant with advertising standards."
+)
+
+# Task with LLM-based guardrail
+llm_guardrail_task = Task(
+    name="marketing_content",
+    description="Create a marketing email for a new fitness app targeting busy professionals",
+    expected_output="Engaging marketing email that is accurate and compliant",
+    agent=llm_guardrail_agent,
+    
+    # LLM-based guardrail using natural language validation
+    guardrail="Validate that this marketing content is: 1) Factually accurate with no false claims, 2) Compliant with advertising standards (no misleading statements), 3) Engaging and professional in tone, 4) Includes a clear call-to-action. If any criteria are not met, explain what needs to be improved.",
+    max_retries=2
+)
+
+# Execute tasks with guardrails
+agents = PraisonAIAgents(
+    agents=[email_agent, content_agent, business_agent, research_agent, llm_guardrail_agent],
+    tasks=[email_task, content_task, business_task, research_task, llm_guardrail_task],
+    verbose=True
+)
+
+print("="*80)
+print("EXECUTING TASKS WITH COMPREHENSIVE GUARDRAILS")
+print("="*80)
+
+result = agents.start()
+
+print("\n" + "="*80)
+print("GUARDRAILS DEMONSTRATION COMPLETED")
+print("="*80)
+print("This example demonstrated:")
+print("- Function-based validation (email format, word count, tone, factual accuracy)")
+print("- LLM-based content validation using natural language criteria")
+print("- Automatic retry mechanisms with specific feedback")
+print("- Quality assurance workflows for different content types")
+print("- Professional validation standards for business communications")

examples/python/guardrails/production-guardrails-patterns.py

@@ -0,0 +1,65 @@
+"""
+Production Guardrails Patterns Example
+
+This example demonstrates production guardrail patterns using PraisonAI's
+built-in validation and safety mechanisms for secure agent operations.
+"""
+
+from praisonaiagents import Agent, Task, PraisonAIAgents
+from praisonaiagents.tools import internet_search
+
+print("=== Production Guardrails Patterns Example ===\n")
+
+# Simple guardrail function for content validation
+def content_guardrail(response, context):
+    """Simple content validation guardrail"""
+    if not response or len(response.strip()) < 50:
+        return {
+            "valid": False,
+            "reason": "Response too short for production use",
+            "action": "regenerate"
+        }
+    
+    # Check for sensitive patterns (simplified)
+    sensitive_keywords = ["password", "secret", "private_key", "api_key"]
+    if any(keyword in response.lower() for keyword in sensitive_keywords):
+        return {
+            "valid": False,
+            "reason": "Potential sensitive information detected",
+            "action": "review_and_redact"
+        }
+    
+    return {"valid": True}
+
+# Create production-ready agent with guardrails
+production_agent = Agent(
+    name="Production Agent",
+    role="Production Content Generator",
+    goal="Generate safe, compliant content for production use",
+    backstory="Production-ready agent with built-in safety and compliance checks",
+    tools=[internet_search],
+    guardrail=content_guardrail,
+    max_retries=3,
+    verbose=True
+)
+
+# Create secure task with validation
+secure_task = Task(
+    description="""Create a professional report about renewable energy trends:
+    1. Research current renewable energy market developments
+    2. Include factual data and reliable sources
+    3. Ensure content is production-ready and compliant
+    4. Avoid any sensitive or inappropriate information
+    
+    Focus on creating safe, accurate, professional content.""",
+    expected_output="Professional renewable energy report meeting production standards",
+    agent=production_agent
+)
+
+# Run with guardrail validation
+print("Starting production guardrails demonstration...")
+result = production_agent.execute_task(secure_task)
+
+print(f"\nProduction Result: {result[:200]}...")
+print("\n✅ Production guardrails validation complete!")
+print("Agent demonstrated safe content generation with built-in guardrail validation.")

examples/python/knowledge/advanced-knowledge-management.py

@@ -0,0 +1,194 @@
+"""
+Advanced Knowledge Management Example
+
+This example demonstrates sophisticated knowledge management capabilities including
+advanced chunking strategies, reranking, and intelligent knowledge retrieval.
+
+Features demonstrated:
+- Advanced document chunking strategies
+- Vector store integration with ChromaDB
+- Knowledge-based question answering
+- Intelligent context retrieval
+- Document processing and management
+"""
+
+from praisonaiagents import Agent
+import tempfile
+import os
+
+# Create a sample knowledge document for demonstration
+sample_document = """
+# Artificial Intelligence in Healthcare
+
+## Introduction
+Artificial intelligence (AI) is revolutionizing healthcare by enabling more accurate diagnoses, 
+personalized treatments, and efficient healthcare delivery. This document explores the current 
+applications and future potential of AI in healthcare.
+
+## Current Applications
+
+### Medical Imaging
+AI algorithms, particularly deep learning models, have shown remarkable success in medical imaging:
+- Radiology: AI can detect cancers in mammograms with accuracy matching or exceeding radiologists
+- Ophthalmology: AI systems can diagnose diabetic retinopathy from retinal photographs
+- Pathology: AI assists in analyzing tissue samples for cancer detection
+
+### Drug Discovery
+AI is accelerating drug discovery processes:
+- Molecular design: AI predicts molecular properties and drug-target interactions
+- Clinical trials: AI optimizes patient recruitment and trial design
+- Repurposing: AI identifies new uses for existing drugs
+
+### Predictive Analytics
+Healthcare providers use AI for:
+- Risk stratification: Identifying patients at risk of complications
+- Early warning systems: Detecting deteriorating patient conditions
+- Resource planning: Optimizing staff schedules and equipment allocation
+
+## Challenges and Considerations
+
+### Data Privacy and Security
+Healthcare AI faces significant challenges:
+- Patient data protection and HIPAA compliance
+- Secure data sharing between institutions
+- Consent management for AI applications
+
+### Regulatory Approval
+AI medical devices require:
+- FDA approval for diagnostic tools
+- Clinical validation studies
+- Post-market surveillance
+
+### Ethical Considerations
+Important ethical aspects include:
+- Algorithmic bias and fairness
+- Transparency and explainability
+- Patient autonomy and informed consent
+
+## Future Directions
+
+### Personalized Medicine
+AI will enable:
+- Genomic-based treatment selection
+- Individualized drug dosing
+- Precision diagnostics
+
+### Integrated Healthcare Systems
+Future developments include:
+- AI-powered electronic health records
+- Interoperable AI systems across healthcare networks
+- Real-time decision support systems
+
+## Conclusion
+AI has tremendous potential to transform healthcare, but successful implementation requires
+addressing technical, regulatory, and ethical challenges while maintaining focus on patient safety
+and improved outcomes.
+"""
+
+# Save the sample document to a temporary file
+temp_dir = tempfile.mkdtemp()
+doc_path = os.path.join(temp_dir, "ai_healthcare_guide.txt")
+with open(doc_path, "w") as f:
+    f.write(sample_document)
+
+# Create an agent with advanced knowledge management configuration
+knowledge_agent = Agent(
+    name="AdvancedKnowledgeAgent",
+    role="Healthcare AI Knowledge Expert", 
+    goal="Provide comprehensive answers about AI in healthcare using advanced knowledge retrieval",
+    backstory="You are an expert in healthcare AI with access to comprehensive knowledge bases and advanced retrieval capabilities.",
+    
+    # Advanced knowledge configuration
+    knowledge=[doc_path],
+    knowledge_config={
+        "vector_store": {
+            "provider": "chroma",
+            "collection_name": "healthcare_ai_knowledge"
+        },
+        "chunking": {
+            "strategy": "semantic",  # Advanced semantic chunking
+            "chunk_size": 500,       # Optimal chunk size for retrieval
+            "chunk_overlap": 50,     # Overlap for context preservation
+            "separators": ["\n\n", "\n", ".", "!", "?"]  # Smart separators
+        },
+        "retrieval": {
+            "search_type": "similarity",
+            "k": 5,  # Retrieve top 5 most relevant chunks
+            "score_threshold": 0.7,  # Minimum relevance score
+            "rerank": True  # Enable reranking for better results
+        },
+        "embedding": {
+            "provider": "openai",
+            "model": "text-embedding-3-small",  # Efficient embedding model
+            "dimensions": 1536
+        }
+    },
+    
+    instructions="""You are an expert in healthcare AI. Use the knowledge base to provide 
+    comprehensive, accurate answers. Always cite specific information from the documents 
+    when possible. If the knowledge base doesn't contain sufficient information, clearly 
+    state this and provide general guidance based on your training.""",
+    
+    verbose=True
+)
+
+# Test advanced knowledge retrieval with various question types
+
+# Factual question about specific applications
+print("="*70)
+print("TESTING: Specific factual question about AI applications")
+print("="*70)
+factual_result = knowledge_agent.start(
+    "What are the current applications of AI in medical imaging according to the knowledge base?"
+)
+print(f"Factual query result:\n{factual_result}\n")
+
+# Complex analytical question requiring synthesis
+print("="*70)
+print("TESTING: Complex analytical question requiring synthesis")  
+print("="*70)
+analytical_result = knowledge_agent.start(
+    "What are the main challenges facing AI implementation in healthcare and how do they relate to each other?"
+)
+print(f"Analytical query result:\n{analytical_result}\n")
+
+# Specific detail extraction
+print("="*70)
+print("TESTING: Specific detail extraction")
+print("="*70)
+detail_result = knowledge_agent.start(
+    "What specific regulatory requirements does the document mention for AI medical devices?"
+)
+print(f"Detail extraction result:\n{detail_result}\n")
+
+# Future-oriented question requiring inference
+print("="*70)
+print("TESTING: Future-oriented question requiring inference")
+print("="*70)
+future_result = knowledge_agent.start(
+    "Based on the knowledge base, what integration capabilities will future AI healthcare systems have?"
+)
+print(f"Future-oriented query result:\n{future_result}\n")
+
+# Question about relationships and connections
+print("="*70)
+print("TESTING: Relationship and connection analysis")
+print("="*70)
+relationship_result = knowledge_agent.start(
+    "How do the ethical considerations mentioned relate to the regulatory approval process for AI in healthcare?"
+)
+print(f"Relationship analysis result:\n{relationship_result}\n")
+
+# Clean up temporary files
+import shutil
+shutil.rmtree(temp_dir)
+
+print("="*80)
+print("ADVANCED KNOWLEDGE MANAGEMENT DEMONSTRATION COMPLETED")
+print("="*80)
+print("This example demonstrated:")
+print("- Semantic chunking for better context preservation")
+print("- Advanced retrieval with reranking capabilities")
+print("- Multiple query types with intelligent responses")
+print("- Knowledge base integration with vector search")
+print("- Configurable embedding and retrieval parameters")

examples/python/memory/advanced-graph-memory-integration.py

@@ -0,0 +1,75 @@
+"""
+Advanced Graph Memory Integration Example
+
+This example demonstrates graph memory capabilities with PraisonAI agents
+for knowledge graph construction and relationship-aware memory retrieval.
+"""
+
+from praisonaiagents import Agent, Task, PraisonAIAgents
+from praisonaiagents.tools import internet_search
+
+print("=== Advanced Graph Memory Integration Example ===\n")
+
+# Configure simple graph memory
+memory_config = {
+    "provider": "mem0",
+    "config": {
+        "vector_store": {
+            "provider": "chroma",
+            "config": {
+                "path": ".praison/graph_memory"
+            }
+        }
+    }
+}
+
+# Create knowledge builder agent with graph memory
+knowledge_agent = Agent(
+    name="Knowledge Agent",
+    role="Knowledge Graph Builder", 
+    goal="Build and retrieve from knowledge graphs",
+    backstory="Expert at creating structured knowledge and finding relationships",
+    tools=[internet_search],
+    memory=True,
+    verbose=True
+)
+
+# Task to build knowledge graph about AI companies
+build_task = Task(
+    description="""Research and store information about major AI companies and their relationships:
+    1. OpenAI - products like GPT-4, ChatGPT, leadership, partnerships
+    2. Anthropic - Claude AI, safety focus, team
+    3. Relationships between these companies and their technologies
+    
+    Focus on capturing connections and relationships between entities.""",
+    expected_output="Knowledge graph with AI company ecosystem relationships",
+    agent=knowledge_agent
+)
+
+# Task to query the knowledge graph
+query_task = Task(
+    description="""Using the stored knowledge graph, answer:
+    1. What are the main products of each company?
+    2. Who are the key leaders in these companies?
+    3. How do these companies relate to each other?
+    
+    Use relationship-aware memory retrieval.""",
+    expected_output="Analysis using graph memory relationships",
+    agent=knowledge_agent
+)
+
+# Run with graph memory integration
+agents_system = PraisonAIAgents(
+    agents=[knowledge_agent],
+    tasks=[build_task, query_task],
+    memory=True,
+    memory_config=memory_config,
+    verbose=True
+)
+
+print("Starting graph memory demonstration...")
+result = agents_system.start()
+
+print(f"\nGraph Memory Result: {result[:200]}...")
+print("\n✅ Graph memory integration complete!")
+print("Agent built knowledge graph and performed relationship-aware queries.")

examples/python/memory/advanced-memory-search-optimization.py

@@ -0,0 +1,76 @@
+"""
+Advanced Memory Search and Optimization Example
+
+This example demonstrates memory search optimization using PraisonAI's
+built-in memory capabilities with semantic search and quality filtering.
+"""
+
+from praisonaiagents import Agent, Task, PraisonAIAgents
+from praisonaiagents.tools import internet_search
+
+print("=== Advanced Memory Search and Optimization Example ===\n")
+
+# Configure optimized memory settings
+memory_config = {
+    "provider": "mem0",
+    "config": {
+        "vector_store": {
+            "provider": "chroma",
+            "config": {
+                "path": ".praison/optimized_memory"
+            }
+        }
+    }
+}
+
+# Create research agent with optimized memory
+research_agent = Agent(
+    name="Memory Research Agent",
+    role="Information Researcher with Memory Optimization",
+    goal="Research and demonstrate optimized memory search patterns",
+    backstory="Expert at storing and retrieving information efficiently with memory optimization",
+    tools=[internet_search],
+    memory=True,
+    verbose=True
+)
+
+# Task to build searchable memory
+build_memory_task = Task(
+    description="""Research and store information about these topics for later search:
+    1. Artificial intelligence market trends and growth data
+    2. Machine learning technologies and applications
+    3. Tech industry partnerships and investments
+    4. Cloud computing adoption statistics
+    
+    Store detailed information that can be searched later.""",
+    expected_output="Comprehensive research stored in optimized memory",
+    agent=research_agent
+)
+
+# Task to demonstrate memory search optimization
+search_task = Task(
+    description="""Using the stored memory, perform optimized searches for:
+    1. "AI market growth trends" - find relevant stored information
+    2. "technology partnerships" - retrieve partnership data
+    3. "cloud adoption statistics" - search for cloud computing info
+    
+    Demonstrate efficient memory retrieval and search optimization.""",
+    expected_output="Results from optimized memory searches",
+    agent=research_agent
+)
+
+# Run with memory optimization
+agents_system = PraisonAIAgents(
+    agents=[research_agent],
+    tasks=[build_memory_task, search_task],
+    memory=True,
+    memory_config=memory_config,
+    verbose=True
+)
+
+print("Starting memory search optimization demonstration...")
+result = agents_system.start()
+
+print(f"\nMemory Search Result: {result[:200]}...")
+print("\n✅ Memory search optimization complete!")
+print("Agent demonstrated efficient memory storage and optimized search retrieval.")

examples/python/memory/gemini-embedding-example.py

@@ -0,0 +1,153 @@
+#!/usr/bin/env python3
+"""
+Example: Using Gemini Embedding Models with PraisonAI Memory
+
+This example demonstrates how to configure PraisonAI to use Google's Gemini
+embedding models for memory storage and retrieval, as requested in issue #870.
+
+Supported Gemini embedding models:
+- gemini-embedding-exp-03-07 (experimental)
+- text-embedding-004 (stable)
+
+Prerequisites:
+1. Install praisonaiagents with memory support:
+   pip install "praisonaiagents[memory]"
+
+2. Set your Google API key:
+   export GOOGLE_API_KEY='your-api-key'
+
+3. Ensure litellm is installed (comes with praisonaiagents)
+"""
+
+import os
+from praisonaiagents import Agent, Task, PraisonAIAgents
+
+def main():
+    """Demonstrate Gemini embedding usage"""
+    
+    # Verify Google API key
+    if not os.environ.get("GOOGLE_API_KEY"):
+        print("Error: GOOGLE_API_KEY environment variable not set")
+        print("Please set it with: export GOOGLE_API_KEY='your-api-key'")
+        return
+    
+    print("=== Gemini Embedding Example ===\n")
+    
+    # Create agents for different tasks
+    researcher = Agent(
+        name="Research Agent",
+        role="Information Researcher",
+        goal="Research and store important information about topics",
+        backstory="Expert at analyzing and documenting information with semantic understanding",
+        llm="gpt-4o-mini"  # Using GPT for chat, Gemini for embeddings
+    )
+    
+    retriever = Agent(
+        name="Retrieval Agent",
+        role="Information Retriever",
+        goal="Retrieve relevant information from memory using semantic search",
+        backstory="Specialist in finding and presenting stored information",
+        llm="gpt-4o-mini"
+    )
+    
+    # Task 1: Store information with semantic meaning
+    store_task = Task(
+        description="""
+        Research and store the following information:
+        1. Gemini is Google's family of multimodal AI models
+        2. Gemini models support text, image, video, and audio understanding
+        3. The embedding models provide semantic representations of text
+        4. Gemini Ultra is the largest and most capable model
+        5. Gemini was announced in December 2023
+        
+        Store each fact with its semantic meaning preserved.
+        """,
+        expected_output="Confirmation that all facts have been stored in memory",
+        agent=researcher
+    )
+    
+    # Task 2: Semantic retrieval test
+    retrieve_task = Task(
+        description="""
+        Using semantic search, find information about:
+        1. Google's AI capabilities
+        2. Multimodal understanding features
+        3. When was Google's latest AI announced
+        
+        Note: Use semantic similarity, not exact keyword matching.
+        """,
+        expected_output="Retrieved information based on semantic meaning",
+        agent=retriever
+    )
+    
+    # Configure with Gemini embeddings
+    # Option 1: Using stable text-embedding-004
+    agents = PraisonAIAgents(
+        agents=[researcher, retriever],
+        tasks=[store_task, retrieve_task],
+        verbose=True,
+        memory=True,
+        embedder={
+            "provider": "gemini",
+            "config": {
+                "model": "text-embedding-004",
+                # Optional: specify task type for better results
+                # "task_type": "RETRIEVAL_DOCUMENT"  
+            }
+        }
+    )
+    
+    # Alternative: Using experimental model with advanced features
+    # agents = PraisonAIAgents(
+    #     agents=[researcher, retriever],
+    #     tasks=[store_task, retrieve_task],
+    #     verbose=True,
+    #     memory=True,
+    #     embedder={
+    #         "provider": "gemini",
+    #         "config": {
+    #             "model": "gemini-embedding-exp-03-07",
+    #             # Task types: SEMANTIC_SIMILARITY, CLASSIFICATION, CLUSTERING,
+    #             #            RETRIEVAL_DOCUMENT, RETRIEVAL_QUERY, QUESTION_ANSWERING,
+    #             #            FACT_VERIFICATION
+    #             "task_type": "RETRIEVAL_DOCUMENT"
+    #         }
+    #     }
+    # )
+    
+    # Execute the workflow
+    print("Starting agents with Gemini embeddings...\n")
+    result = agents.start()
+    
+    # Demonstrate direct memory access with Gemini embeddings
+    print("\n=== Direct Memory Search Example ===\n")
+    
+    if agents.shared_memory:
+        # Search queries that test semantic understanding
+        queries = [
+            "What are Google's latest AI innovations?",
+            "Explain multimodal AI capabilities",
+            "Large language model features"
+        ]
+        
+        for query in queries:
+            print(f"\nSearching for: '{query}'")
+            results = agents.shared_memory.search_long_term(query, limit=3)
+            
+            if results:
+                print(f"Found {len(results)} semantically similar results:")
+                for i, result in enumerate(results, 1):
+                    print(f"\n{i}. Relevance Score: {result.get('score', 0):.3f}")
+                    print(f"   Content: {result.get('text', '')[:150]}...")
+            else:
+                print("No results found")
+    
+    print("\n=== Example Complete ===")
+    print("\nKey Points:")
+    print("1. Gemini embeddings provide semantic understanding of text")
+    print("2. Results are based on meaning, not just keyword matching")
+    print("3. Different task types can optimize embedding quality")
+    print("4. Compatible with LiteLLM for easy integration")
+
+if __name__ == "__main__":
+    main()

examples/python/memory/gemini-embeddings.md

@@ -0,0 +1,165 @@
+# Gemini Embedding Support in PraisonAI
+
+This document describes how to use Google's Gemini embedding models with PraisonAI's memory system.
+
+## Overview
+
+PraisonAI now supports configurable embedding models through LiteLLM, including Google's Gemini embedding models. This allows you to use models like `text-embedding-004` or `gemini-embedding-exp-03-07` for semantic search and memory storage.
+
+## Configuration
+
+### Default Configuration (OpenAI)
+
+By default, PraisonAI uses OpenAI's `text-embedding-3-small` model:
+
+```python
+from praisonaiagents import PraisonAIAgents
+
+agents = PraisonAIAgents(
+    agents=[...],
+    tasks=[...],
+    memory=True  # Uses default OpenAI embeddings
+)
+```
+
+### Using Gemini Embeddings
+
+To use Gemini embeddings, configure the `embedder` parameter:
+
+```python
+from praisonaiagents import PraisonAIAgents
+
+agents = PraisonAIAgents(
+    agents=[...],
+    tasks=[...],
+    memory=True,
+    embedder={
+        "provider": "gemini",
+        "config": {
+            "model": "text-embedding-004"  # or "gemini-embedding-exp-03-07"
+        }
+    }
+)
+```
+
+## Prerequisites
+
+1. **API Key**: Set your Google API key:
+   ```bash
+   export GOOGLE_API_KEY='your-api-key'
+   ```
+
+2. **Dependencies**: Ensure you have the memory dependencies installed:
+   ```bash
+   pip install "praisonaiagents[memory]"
+   ```
+
+## Supported Models
+
+### Gemini Embedding Models
+
+- `text-embedding-004` - Stable embedding model
+- `gemini-embedding-exp-03-07` - Experimental model with advanced features
+
+### Task Types (Optional)
+
+Gemini models support task-specific optimizations:
+- `SEMANTIC_SIMILARITY`
+- `CLASSIFICATION`
+- `CLUSTERING`
+- `RETRIEVAL_DOCUMENT`
+- `RETRIEVAL_QUERY`
+- `QUESTION_ANSWERING`
+- `FACT_VERIFICATION`
+
+Example with task type:
+```python
+embedder={
+    "provider": "gemini",
+    "config": {
+        "model": "text-embedding-004",
+        "task_type": "RETRIEVAL_DOCUMENT"
+    }
+}
+```
+
+## Complete Example
+
+```python
+import os
+from praisonaiagents import Agent, Task, PraisonAIAgents
+
+# Ensure Google API key is set
+os.environ["GOOGLE_API_KEY"] = "your-api-key"
+
+# Create agents
+researcher = Agent(
+    name="Researcher",
+    role="Information Researcher",
+    goal="Store information with semantic understanding",
+    llm="gpt-4o-mini"
+)
+
+# Create task
+task = Task(
+    description="Research and store information about AI advancements",
+    expected_output="Confirmation of stored information",
+    agent=researcher
+)
+
+# Initialize with Gemini embeddings
+agents = PraisonAIAgents(
+    agents=[researcher],
+    tasks=[task],
+    memory=True,
+    embedder={
+        "provider": "gemini",
+        "config": {
+            "model": "text-embedding-004"
+        }
+    }
+)
+
+# Run the agents
+agents.start()
+```
+
+## Backward Compatibility
+
+The implementation maintains full backward compatibility:
+
+1. **No embedder config**: Uses default OpenAI `text-embedding-3-small`
+2. **Existing configs**: Continue to work without modification
+3. **Other providers**: Supports any embedding model available through LiteLLM
+
+## Memory Configuration with Mem0
+
+When using Mem0 as the memory provider, the embedder configuration is passed through:
+
+```python
+memory_config = {
+    "provider": "mem0",
+    "config": {
+        "api_key": "your-mem0-key",
+        "embedder": {
+            "provider": "gemini",
+            "config": {
+                "model": "text-embedding-004"
+            }
+        }
+    }
+}
+```
+
+## Troubleshooting
+
+1. **API Key Error**: Ensure `GOOGLE_API_KEY` is set in your environment
+2. **Model Not Found**: Verify the model name is correct
+3. **LiteLLM Error**: Ensure litellm is installed and up to date
+4. **Embedding Size Mismatch**: When switching models, you may need to clear the vector database as different models produce different embedding dimensions
+
+## See Also
+
+- [Gemini API Documentation](https://ai.google.dev/gemini-api/docs/embeddings)
+- [LiteLLM Embedding Models](https://docs.litellm.ai/docs/embedding/supported_embedding)
+- Example: `/examples/python/memory/gemini-embedding-example.py`

examples/python/models/claude/claude_creative_designer_agent.py

@@ -0,0 +1,12 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a creative designer AI agent. "
+                "Help users with graphic design concepts, branding strategies, "
+                "visual communication, and creative problem-solving. Provide guidance "
+                "on design principles, color theory, typography, and user experience.",
+    llm="anthropic/claude-3-5-sonnet-20241022"
+)
+
+response = agent.start("Hello! I'm your creative designer assistant. "
+                      "How can I help you with your design projects today?") 

examples/python/models/claude/claude_educational_tutor_agent.py

@@ -0,0 +1,12 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are an educational tutor AI agent. "
+                "Help students learn various subjects, explain complex concepts, "
+                "provide step-by-step solutions, and create personalized learning "
+                "materials for different educational levels.",
+    llm="anthropic/claude-3-5-sonnet-20241022"
+)
+
+response = agent.start("Hello! I'm your educational tutor assistant. "
+                      "How can I help you learn today?") 

examples/python/models/claude/claude_financial_advisor_agent.py

@@ -0,0 +1,12 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a financial advisor AI agent. "
+                "Help users understand financial concepts, analyze investment opportunities, "
+                "and provide guidance on personal finance, budgeting, and financial planning. "
+                "Note: This is for educational purposes only, not financial advice.",
+    llm="anthropic/claude-3-5-sonnet-20241022"
+)
+
+response = agent.start("Hello! I'm your financial advisor assistant. "
+                      "How can I help you understand financial concepts today?") 

examples/python/models/claude/claude_legal_advisor_agent.py

@@ -0,0 +1,12 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a legal advisor AI agent. "
+                "Help users understand legal concepts, review contracts, "
+                "analyze legal documents, and provide guidance on compliance "
+                "and regulatory requirements. Note: This is for educational purposes only.",
+    llm="anthropic/claude-3-5-sonnet-20241022"
+)
+
+response = agent.start("Hello! I'm your legal advisor assistant. "
+                      "How can I help you understand legal concepts today?") 

examples/python/models/claude/claude_medical_researcher_agent.py

@@ -0,0 +1,12 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a medical research AI agent. "
+                "Help users understand medical concepts, analyze research papers, "
+                "and provide insights on healthcare trends and developments. "
+                "Note: This is for educational purposes only, not medical advice.",
+    llm="anthropic/claude-3-5-sonnet-20241022"
+)
+
+response = agent.start("Hello! I'm your medical research assistant. "
+                      "How can I help you understand medical concepts today?") 

examples/python/models/googlegemini/README_GEMINI_INTERNAL_TOOLS.md

@@ -0,0 +1,215 @@
+# Gemini Internal Tools Examples
+
+This directory contains examples demonstrating how to use Google Gemini's built-in internal tools through PraisonAI. These tools are natively supported by Gemini models and provide powerful capabilities without requiring external tool implementations.
+
+## Available Internal Tools
+
+### 1. Google Search (`googleSearch`)
+- **Purpose**: Real-time web search with automatic result grounding
+- **Use Cases**: Current events, latest information, fact-checking
+- **Example**: `gemini-google-search.py`
+
+### 2. URL Context (`urlContext`) 
+- **Purpose**: Fetch and analyze content from specific URLs
+- **Use Cases**: Document analysis, web content summarization, research
+- **Example**: `gemini-url-context.py`
+
+### 3. Code Execution (`codeExecution`)
+- **Purpose**: Execute Python code snippets within the conversation
+- **Use Cases**: Calculations, data analysis, code validation
+- **Example**: `gemini-code-execution.py`
+
+## Prerequisites
+
+1. **Gemini API Key**: Set your Google AI Studio API key
+   ```bash
+   export GEMINI_API_KEY="your-api-key-here"
+   ```
+
+2. **Compatible Model**: Use Gemini models that support internal tools:
+   - `gemini/gemini-2.0-flash` (recommended)
+   - `gemini/gemini-2.0-flash-thinking-exp`
+   - Other Gemini 2.0+ models
+
+3. **PraisonAI Installation**: Ensure you have the latest version
+   ```bash
+   pip install "praisonaiagents[llm]"
+   ```
+
+## Examples
+
+### Individual Tool Examples
+
+1. **Google Search Example** (`gemini-google-search.py`)
+   ```python
+   agent = Agent(
+       instructions="Research assistant with web search",
+       llm="gemini/gemini-2.0-flash",
+       tools=[{"googleSearch": {}}]
+   )
+   
+   response = agent.start("What's the latest news about AI?")
+   ```
+
+2. **URL Context Example** (`gemini-url-context.py`)
+   ```python
+   agent = Agent(
+       instructions="Content analyzer",
+       llm="gemini/gemini-2.0-flash", 
+       tools=[{"urlContext": {}}]
+   )
+   
+   response = agent.start("Summarize this: https://example.com/article")
+   ```
+
+3. **Code Execution Example** (`gemini-code-execution.py`)
+   ```python
+   agent = Agent(
+       instructions="Data analyst with code execution",
+       llm="gemini/gemini-2.0-flash",
+       tools=[{"codeExecution": {}}]
+   )
+   
+   response = agent.start("Calculate compound interest for $10,000 at 5% for 10 years")
+   ```
+
+### Combined Tools Example
+
+**All Tools Together** (`gemini-internal-tools-combined.py`)
+```python
+agent = Agent(
+    instructions="Advanced research assistant",
+    llm="gemini/gemini-2.0-flash",
+    tools=[
+        {"googleSearch": {}},
+        {"urlContext": {}},
+        {"codeExecution": {}}
+    ]
+)
+
+# Now the agent can search, analyze URLs, and execute code as needed
+```
+
+## How It Works
+
+### PraisonAI Integration
+
+PraisonAI's tool system is designed to pass tools directly to LiteLLM without modification:
+
+1. **Tool Definition**: Define tools using the special internal tool syntax
+   ```python
+   tools=[{"googleSearch": {}}]  # Special format for internal tools
+   ```
+
+2. **Pass-Through**: PraisonAI passes these tools directly to LiteLLM
+3. **Execution**: LiteLLM sends them to Gemini as internal tool configurations
+4. **Results**: Gemini executes the tools natively and returns integrated responses
+
+### Mixing with External Tools
+
+You can combine internal tools with custom external tools:
+
+```python
+def custom_calculator(expression: str) -> str:
+    """Custom calculator function - safely evaluates basic math expressions"""
+    import ast
+    import operator
+    
+    # Define safe operations
+    ops = {
+        ast.Add: operator.add,
+        ast.Sub: operator.sub,
+        ast.Mult: operator.mul,
+        ast.Div: operator.truediv,
+        ast.Pow: operator.pow,
+        ast.USub: operator.neg,
+    }
+    
+    def eval_expr(node):
+        if isinstance(node, ast.Constant):  # Numbers
+            return node.value
+        elif isinstance(node, ast.BinOp):  # Binary operations
+            return ops[type(node.op)](eval_expr(node.left), eval_expr(node.right))
+        elif isinstance(node, ast.UnaryOp):  # Unary operations
+            return ops[type(node.op)](eval_expr(node.operand))
+        else:
+            raise TypeError(f"Unsupported operation: {type(node)}")
+    
+    try:
+        return str(eval_expr(ast.parse(expression, mode='eval').body))
+    except Exception as e:
+        return f"Error: {e}"
+
+agent = Agent(
+    tools=[
+        {"googleSearch": {}},      # Internal tool
+        {"codeExecution": {}},     # Internal tool  
+        custom_calculator          # External tool
+    ]
+)
+```
+
+## Running the Examples
+
+1. **Set API Key**:
+   ```bash
+   export GEMINI_API_KEY="your-api-key"
+   ```
+
+2. **Run Individual Examples**:
+   ```bash
+   python gemini-google-search.py
+   python gemini-url-context.py  
+   python gemini-code-execution.py
+   ```
+
+3. **Run Combined Example**:
+   ```bash
+   python gemini-internal-tools-combined.py
+   ```
+
+## Benefits Over External Tools
+
+### Advantages of Internal Tools
+
+1. **Native Integration**: No need to implement or maintain external tool code
+2. **Optimized Performance**: Tools are executed within Gemini's environment
+3. **Automatic Grounding**: Search results are automatically integrated into responses
+4. **No Rate Limits**: No separate API calls or rate limiting concerns
+5. **Security**: Code execution is sandboxed within Gemini's environment
+
+### When to Use External Tools
+
+- When you need specific custom logic
+- When you require integration with private APIs
+- When you need persistent data storage
+- When you want full control over tool behavior
+
+## Troubleshooting
+
+### Common Issues
+
+1. **API Key Error**: Ensure `GEMINI_API_KEY` is set correctly
+2. **Model Not Supported**: Use Gemini 2.0+ models for internal tools
+3. **Tool Not Available**: Some tools may have regional or quota restrictions
+
+### Debug Mode
+
+Enable verbose logging to see tool usage:
+```python
+agent = Agent(
+    # ... config
+    verbose=True  # Shows detailed tool usage
+)
+```
+
+## References
+
+- [Gemini API: Google Search Grounding](https://ai.google.dev/gemini-api/docs/google-search)
+- [Gemini API: URL Context](https://ai.google.dev/gemini-api/docs/url-context)  
+- [Gemini API: Code Execution](https://ai.google.dev/gemini-api/docs/code-execution)
+- [LiteLLM Gemini Provider Documentation](https://docs.litellm.ai/docs/providers/gemini)
+
+## Contributing
+
+If you create additional examples or find improvements, please contribute back to the PraisonAI project!

examples/python/models/googlegemini/any-llm-agents-async.py

@@ -1,18 +1,12 @@
 import asyncio
 from praisonaiagents import Agent
 
-async def main():
-    agent = Agent(
-        instructions="You are a helpful assistant",
-        llm="gemini/gemini-1.5-flash-8b",
-        self_reflect=True,
-        verbose=True
-    )
+agent = Agent(
+    instructions="You are a helpful assistant",
+    llm="gemini/gemini-1.5-flash-8b",
+    self_reflect=True,
+    verbose=True
+)
 
-    # Use achat instead of start/chat for async operation
-    response = await agent.achat("Why sky is Blue in 1000 words?")
-    print(response)
-
-if __name__ == "__main__":
-    # Run the async main function
-    asyncio.run(main())
+# Use achat instead of start/chat for async operation
+response = asyncio.run(agent.achat("Why sky is Blue in 1000 words?"))

examples/python/models/googlegemini/gemini-code-execution.py

@@ -0,0 +1,99 @@
+"""
+Gemini Code Execution Tool Example
+
+This example demonstrates how to use Gemini's built-in Code Execution functionality
+through PraisonAI. The Code Execution tool allows the model to run Python code
+snippets directly within the conversation for dynamic computation and validation.
+
+Prerequisites:
+- Set GEMINI_API_KEY environment variable
+- Use a Gemini model that supports internal tools (gemini-2.0-flash, etc.)
+
+Features:
+- Direct Python code execution within the model
+- Real-time calculations and data processing
+- Code validation and testing
+- Mathematical computations and visualizations
+"""
+
+from praisonaiagents import Agent
+
+# Ensure you have your Gemini API key set
+# import os; os.environ["GEMINI_API_KEY"] = "your-api-key-here"
+
+def main():
+    # Create agent with Code Execution internal tool
+    agent = Agent(
+        instructions="""You are a data analyst and programmer that can execute Python code.
+        Use the Code Execution tool to perform calculations, analyze data, create visualizations,
+        and validate logic. Always show your work by executing relevant code snippets.""",
+        
+        llm="gemini/gemini-2.0-flash",
+        
+        # Enable Code Execution internal tool
+        tools=[{"codeExecution": {}}],
+        
+        verbose=True
+    )
+    
+    # Example tasks that benefit from code execution
+    tasks = [
+        "Calculate the compound interest on $10,000 invested at 5% annual rate for 10 years, compounded monthly. Show the calculation step by step.",
+        
+        "Generate the first 20 Fibonacci numbers and find their sum. Also calculate the ratio of consecutive Fibonacci numbers.",
+        
+        "Create a simple linear regression model for the data points: (1,2), (2,4), (3,6), (4,8), (5,10). Calculate the R-squared value.",
+        
+        "Solve the quadratic equation 2x² + 5x - 3 = 0 using the quadratic formula. Verify the solutions by substituting back.",
+        
+        "Calculate the statistical summary (mean, median, mode, standard deviation) for this dataset: [12, 15, 18, 12, 20, 25, 18, 12, 22, 30, 15, 18]",
+        
+        "Write a function to check if a number is prime, then find all prime numbers between 1 and 100.",
+        
+        "Calculate the area under the curve y = x² from x = 0 to x = 5 using numerical integration (trapezoidal rule)."
+    ]
+    
+    print("=== Gemini Code Execution Tool Demo ===\n")
+    
+    for i, task in enumerate(tasks, 1):
+        print(f"Task {i}: {task}")
+        print("-" * 80)
+        
+        try:
+            response = agent.start(task)
+            print(f"Response: {response}")
+            print("\n" + "="*100 + "\n")
+            
+        except Exception as e:
+            print(f"Error: {e}")
+            print("\n" + "="*100 + "\n")
+
+def demonstrate_direct_usage():
+    """
+    Example of how the Code Execution tool works at the LiteLLM level
+    (for reference - this requires direct LiteLLM usage)
+    """
+    print("=== Direct LiteLLM Code Execution Usage (Reference) ===")
+    print("""
+    # This is how it works at the LiteLLM level:
+    
+    import litellm
+    import os
+    
+    os.environ["GEMINI_API_KEY"] = "your-api-key"
+    
+    response = litellm.completion(
+        model="gemini/gemini-2.0-flash",
+        messages=[{
+            "role": "user", 
+            "content": "Calculate the factorial of 10 and show the code"
+        }],
+        tools=[{"codeExecution": {}}],
+    )
+    
+    print(response.choices[0].message.content)
+    """)
+
+if __name__ == "__main__":
+    main()
+    demonstrate_direct_usage()

examples/python/models/googlegemini/gemini-google-search.py

@@ -0,0 +1,63 @@
+"""
+Gemini Google Search Tool Example
+
+This example demonstrates how to use Gemini's built-in Google Search functionality
+through PraisonAI. The Google Search tool allows the model to perform real-time
+web searches and ground responses in current information.
+
+Prerequisites:
+- Set GEMINI_API_KEY environment variable
+- Use a Gemini model that supports internal tools (gemini-2.0-flash, etc.)
+
+Features:
+- Real-time web search capabilities
+- Automatic grounding of responses in search results
+- No need to implement external search tools
+"""
+
+from praisonaiagents import Agent
+
+# Ensure you have your Gemini API key set
+# import os; os.environ["GEMINI_API_KEY"] = "your-api-key-here"
+
+def main():
+    # Create agent with Google Search internal tool
+    agent = Agent(
+        instructions="""You are a research assistant that can search the web for current information.
+        Use the Google Search tool to find up-to-date information when answering questions.
+        Always cite your sources and indicate when information comes from search results.""",
+        
+        llm="gemini/gemini-2.0-flash",
+        
+        # Enable Google Search internal tool
+        tools=[{"googleSearch": {}}],
+        
+        verbose=True
+    )
+    
+    # Example queries that benefit from real-time search
+    queries = [
+        "What's the latest news about AI developments this week?",
+        "What's the current weather in San Francisco?",
+        "What are the latest stock prices for major tech companies?",
+        "What are the most recent breakthroughs in quantum computing?",
+        "Who won the latest major sports championships?"
+    ]
+    
+    print("=== Gemini Google Search Tool Demo ===\n")
+    
+    for i, query in enumerate(queries, 1):
+        print(f"Query {i}: {query}")
+        print("-" * 50)
+        
+        try:
+            response = agent.start(query)
+            print(f"Response: {response}")
+            print("\n" + "="*80 + "\n")
+            
+        except Exception as e:
+            print(f"Error: {e}")
+            print("\n" + "="*80 + "\n")
+
+if __name__ == "__main__":
+    main()

examples/python/models/googlegemini/gemini-internal-tools-combined.py

@@ -0,0 +1,187 @@
+"""
+Gemini Internal Tools Combined Example
+
+This example demonstrates how to use all three of Gemini's built-in internal tools
+together through PraisonAI:
+1. Google Search - for real-time web information
+2. URL Context - for analyzing web content
+3. Code Execution - for computations and analysis
+
+Prerequisites:
+- Set GEMINI_API_KEY environment variable
+- Use a Gemini model that supports internal tools (gemini-2.0-flash, etc.)
+
+Features:
+- Multi-tool agent combining search, content analysis, and computation
+- Real-world research and analysis workflows
+- Comprehensive data gathering and processing capabilities
+"""
+
+from praisonaiagents import Agent
+
+# Ensure you have your Gemini API key set
+# import os; os.environ["GEMINI_API_KEY"] = "your-api-key-here"
+
+def main():
+    # Create agent with all Gemini internal tools enabled
+    agent = Agent(
+        instructions="""You are an advanced research and analysis assistant with access to:
+        1. Google Search - for finding current information
+        2. URL Context - for analyzing web content 
+        3. Code Execution - for calculations and data processing
+        
+        Use these tools strategically to provide comprehensive, well-researched, and 
+        analytically sound responses. Always show your work and cite sources.""",
+        
+        llm="gemini/gemini-2.0-flash",
+        
+        # Enable all three Gemini internal tools
+        tools=[
+            {"googleSearch": {}},
+            {"urlContext": {}}, 
+            {"codeExecution": {}}
+        ],
+        
+        verbose=True
+    )
+    
+    # Complex tasks that benefit from multiple internal tools
+    complex_tasks = [
+        """Research the current market cap of the top 5 technology companies, 
+        then calculate their combined market value and determine what percentage 
+        each company represents of the total. Present the results in a formatted table.""",
+        
+        """Find recent research papers about large language models from arXiv, 
+        analyze the abstracts of 2-3 papers, and calculate the average number 
+        of authors across these papers.""",
+        
+        """Look up the current population of the 10 largest cities in the world, 
+        then calculate statistical measures (mean, median, standard deviation) 
+        and create a simple visualization of the data distribution.""",
+        
+        """Research the latest Python release notes, analyze the key new features, 
+        and write example code demonstrating 2-3 of the most important new features.""",
+        
+        """Find information about recent climate data, analyze a specific dataset 
+        or report, and perform calculations to show trends or comparisons over time."""
+    ]
+    
+    print("=== Gemini Combined Internal Tools Demo ===\n")
+    
+    for i, task in enumerate(complex_tasks, 1):
+        print(f"Complex Task {i}:")
+        print(task)
+        print("-" * 100)
+        
+        try:
+            response = agent.start(task)
+            print(f"Response: {response}")
+            print("\n" + "="*120 + "\n")
+            
+        except Exception as e:
+            print(f"Error: {e}")
+            print("\n" + "="*120 + "\n")
+
+def demonstrate_tool_synergy():
+    """
+    Example showing how the tools work together for a research workflow
+    """
+    print("=== Tool Synergy Example ===")
+    
+    agent = Agent(
+        instructions="""You are a market research analyst. Use all available tools 
+        to gather information, analyze content, and perform calculations as needed.""",
+        
+        llm="gemini/gemini-2.0-flash",
+        tools=[
+            {"googleSearch": {}},
+            {"urlContext": {}}, 
+            {"codeExecution": {}}
+        ],
+        verbose=True
+    )
+    
+    # Multi-step research task
+    research_query = """
+    Conduct a mini market analysis on electric vehicle adoption:
+    1. Search for recent statistics on global EV sales
+    2. Find and analyze a recent report or article about EV market trends
+    3. Calculate the year-over-year growth rate if you can find data for multiple years
+    4. Provide a summary with key insights and numerical analysis
+    """
+    
+    print("Research Query:", research_query)
+    print("-" * 80)
+    
+    try:
+        response = agent.start(research_query)
+        print(f"Research Results: {response}")
+        
+    except Exception as e:
+        print(f"Error: {e}")
+
+def show_configuration_options():
+    """
+    Show different ways to configure the internal tools
+    """
+    print("\n=== Configuration Examples ===")
+    print("""
+    # Basic usage (all tools with default settings)
+    tools=[
+        {"googleSearch": {}},
+        {"urlContext": {}},
+        {"codeExecution": {}}
+    ]
+    
+    # Can also be used individually
+    tools=[{"googleSearch": {}}]  # Only Google Search
+    tools=[{"urlContext": {}}]    # Only URL Context  
+    tools=[{"codeExecution": {}}] # Only Code Execution
+    
+    # Mix with custom tools
+    from praisonaiagents import Agent
+    
+    def custom_calculator(expression: str) -> str:
+        '''Custom calculator function - safely evaluates basic math expressions'''
+        import ast
+        import operator
+        
+        # Define safe operations
+        ops = {
+            ast.Add: operator.add,
+            ast.Sub: operator.sub,
+            ast.Mult: operator.mul,
+            ast.Div: operator.truediv,
+            ast.Pow: operator.pow,
+            ast.USub: operator.neg,
+        }
+        
+        def eval_expr(node):
+            if isinstance(node, ast.Constant):  # Numbers
+                return node.value
+            elif isinstance(node, ast.BinOp):  # Binary operations
+                return ops[type(node.op)](eval_expr(node.left), eval_expr(node.right))
+            elif isinstance(node, ast.UnaryOp):  # Unary operations
+                return ops[type(node.op)](eval_expr(node.operand))
+            else:
+                raise TypeError(f"Unsupported operation: {type(node)}")
+        
+        try:
+            return str(eval_expr(ast.parse(expression, mode='eval').body))
+        except Exception as e:
+            return f"Error: {e}"
+    
+    agent = Agent(
+        tools=[
+            {"googleSearch": {}},        # Gemini internal tool
+            {"codeExecution": {}},       # Gemini internal tool
+            custom_calculator            # Custom external tool
+        ]
+    )
+    """)
+
+if __name__ == "__main__":
+    main()
+    print("\n" + "="*50)
+    demonstrate_tool_synergy()
+    show_configuration_options()

examples/python/models/googlegemini/gemini-url-context.py

@@ -0,0 +1,115 @@
+"""
+Gemini URL Context Tool Example
+
+This example demonstrates how to use Gemini's built-in URL Context functionality
+through PraisonAI. The URL Context tool allows the model to fetch and analyze
+content from specific URLs in real-time.
+
+Prerequisites:
+- Set GEMINI_API_KEY environment variable
+- Use a Gemini model that supports internal tools (gemini-2.0-flash, etc.)
+
+Features:
+- Real-time URL content fetching
+- Automatic content analysis and summarization
+- Support for various web content types
+- Access to URL metadata through response.model_extra
+"""
+
+from praisonaiagents import Agent
+
+# Ensure you have your Gemini API key set
+# import os; os.environ["GEMINI_API_KEY"] = "your-api-key-here"
+
+def main():
+    # Create agent with URL Context internal tool
+    agent = Agent(
+        instructions="""You are a content analyst that can fetch and analyze web content.
+        Use the URL Context tool to access and analyze content from provided URLs.
+        Provide detailed summaries, extract key information, and answer questions about the content.""",
+        
+        llm="gemini/gemini-2.0-flash",
+        
+        # Enable URL Context internal tool
+        tools=[{"urlContext": {}}],
+        
+        verbose=True
+    )
+    
+    # Example URLs for analysis
+    url_tasks = [
+        {
+            "url": "https://ai.google.dev/gemini-api/docs/models",
+            "task": "Summarize the key information about Gemini models and their capabilities"
+        },
+        {
+            "url": "https://github.com/MervinPraison/PraisonAI",
+            "task": "Analyze this GitHub repository and explain what PraisonAI does"
+        },
+        {
+            "url": "https://docs.python.org/3/tutorial/introduction.html",
+            "task": "Extract the main learning objectives from this Python tutorial"
+        },
+        {
+            "url": "https://arxiv.org/abs/2301.00234",
+            "task": "Provide a summary of this research paper's abstract and key contributions"
+        }
+    ]
+    
+    print("=== Gemini URL Context Tool Demo ===\n")
+    
+    for i, item in enumerate(url_tasks, 1):
+        print(f"Analysis {i}: {item['url']}")
+        print(f"Task: {item['task']}")
+        print("-" * 50)
+        
+        # Combine URL and task in the query
+        query = f"{item['task']}: {item['url']}"
+        
+        try:
+            response = agent.start(query)
+            print(f"Analysis: {response}")
+            
+            # Note: URL metadata access requires direct LiteLLM response
+            # In PraisonAI, this would need to be accessed through the LLM response
+            print(f"\nAnalyzed URL: {item['url']}")
+            print("\n" + "="*80 + "\n")
+            
+        except Exception as e:
+            print(f"Error: {e}")
+            print("\n" + "="*80 + "\n")
+
+def demonstrate_direct_usage():
+    """
+    Example of how the URL Context tool works at the LiteLLM level
+    (for reference - this requires direct LiteLLM usage)
+    """
+    print("=== Direct LiteLLM URL Context Usage (Reference) ===")
+    print("""
+    # This is how it works at the LiteLLM level:
+    
+    import litellm
+    import os
+    
+    os.environ["GEMINI_API_KEY"] = "your-api-key"
+    
+    response = litellm.completion(
+        model="gemini/gemini-2.0-flash",
+        messages=[{
+            "role": "user", 
+            "content": "Summarize this document: https://ai.google.dev/gemini-api/docs/models"
+        }],
+        tools=[{"urlContext": {}}],
+    )
+    
+    # Access URL metadata
+    if hasattr(response, 'model_extra') and 'vertex_ai_url_context_metadata' in response.model_extra:
+        url_context_metadata = response.model_extra['vertex_ai_url_context_metadata']
+        urlMetadata = url_context_metadata[0]['urlMetadata'][0]
+        print(f"Retrieved URL: {urlMetadata['retrievedUrl']}")
+        print(f"Retrieval Status: {urlMetadata['urlRetrievalStatus']}")
+    """)
+
+if __name__ == "__main__":
+    main()
+    demonstrate_direct_usage()

examples/python/models/gpt/gpt_cybersecurity_agent.py

@@ -0,0 +1,12 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a cybersecurity AI agent. "
+                "Help users understand security concepts, analyze security threats, "
+                "and provide guidance on security best practices, risk assessment, "
+                "and security architecture design.",
+    llm="openai/gpt-4o"
+)
+
+response = agent.start("Hello! I'm your cybersecurity assistant. "
+                      "How can I help you with security concepts today?") 

examples/python/models/gpt/gpt_data_engineer_agent.py

@@ -0,0 +1,12 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a data engineer AI agent. "
+                "Help users design data pipelines, optimize database performance, "
+                "create ETL processes, and provide guidance on data architecture, "
+                "data modeling, and big data technologies.",
+    llm="openai/gpt-4o"
+)
+
+response = agent.start("Hello! I'm your data engineer assistant. "
+                      "How can I help you with your data engineering projects today?") 

examples/python/models/gpt/gpt_marketing_strategist_agent.py

@@ -0,0 +1,12 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a marketing strategist AI agent. "
+                "Help users develop marketing strategies, analyze market trends, "
+                "create campaign plans, and provide guidance on digital marketing, "
+                "brand positioning, and customer acquisition strategies.",
+    llm="openai/gpt-4o"
+)
+
+response = agent.start("Hello! I'm your marketing strategist assistant. "
+                      "How can I help you with your marketing strategy today?") 

examples/python/models/gpt/gpt_product_manager_agent.py

@@ -0,0 +1,12 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a product manager AI agent. "
+                "Help users with product strategy, feature prioritization, "
+                "user research analysis, and product roadmap planning. Provide "
+                "guidance on market analysis, competitive positioning, and user experience.",
+    llm="openai/gpt-4o"
+)
+
+response = agent.start("Hello! I'm your product manager assistant. "
+                      "How can I help you with your product strategy today?") 

examples/python/models/gpt/gpt_software_architect_agent.py

@@ -0,0 +1,12 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a software architect AI agent. "
+                "Help users design software systems, create architecture diagrams, "
+                "plan system integrations, and provide guidance on scalability, "
+                "security, and best practices for software development.",
+    llm="openai/gpt-4o"
+)
+
+response = agent.start("Hello! I'm your software architect assistant. "
+                      "How can I help you design your software system today?") 

examples/python/models/grok/grok_ai_competitor_intelligence_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a competitor intelligence AI agent. "
+                 "Help users analyze competitors, market trends, and business intelligence "
+                 "to provide strategic insights and competitive advantages.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need to analyze my main competitor's pricing strategy and market positioning. "
+    "Can you help me gather insights?"
+) 

examples/python/models/grok/grok_ai_finance_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a finance AI agent. "
+                 "Help users with financial analysis, investment strategies, "
+                 "budget planning, and market trend analysis for informed decision making.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need to analyze my investment portfolio and create a diversification strategy. "
+    "Can you help me optimize my financial planning?"
+) 

examples/python/models/grok/grok_ai_game_design_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a game design AI agent. "
+                 "Help users with game concept development, mechanics design, "
+                 "and creative storytelling for various gaming platforms and genres.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I want to create a mobile puzzle game concept. "
+    "Can you help me design engaging gameplay mechanics and story elements?"
+) 

examples/python/models/grok/grok_ai_legal_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a legal AI agent. "
+                 "Help users with legal document analysis, contract review, "
+                 "and legal advice while ensuring compliance and risk assessment.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need to review a software licensing agreement. "
+    "Can you help me identify potential risks and key terms?"
+) 

examples/python/models/grok/grok_ai_recruitment_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a recruitment AI agent. "
+                 "Help users with candidate screening, job posting optimization, "
+                 "and recruitment process automation to find the best talent.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need to create a job posting for a senior software engineer position. "
+    "Can you help me write an attractive and comprehensive job description?"
+) 

examples/python/models/grok/grok_ai_services_agency.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are an AI services agency agent. "
+                 "Help users with comprehensive business services including marketing, "
+                 "content creation, strategy, and operational optimization using CrewAI framework.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need help with my startup's marketing strategy and content creation. "
+    "Can you provide a comprehensive plan?"
+) 

examples/python/models/grok/grok_ai_teaching_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are an AI teaching agent. "
+                 "Help users with educational content creation, lesson planning, "
+                 "and personalized learning experiences across various subjects.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need to create a lesson plan for teaching Python programming to beginners. "
+    "Can you help me design an engaging curriculum?"
+) 

examples/python/models/grok/grok_basic_example.py

@@ -0,0 +1,30 @@
+"""
+Basic example of using Grok model in PraisonAI
+"""
+
+from praisonaiagents import Agent
+
+# Initialize Agent with Grok model
+agent = Agent(
+    instructions="You are a helpful assistant",
+    llm="xai/grok-beta",
+)
+
+# Example conversation
+response = agent.start("Hello! Can you explain quantum computing in simple terms?")
+
+# Example with mathematical reasoning
+math_task = """
+Solve this problem step by step:
+If a train travels at 60 mph for 2.5 hours, how far does it travel?
+"""
+
+response = agent.start(math_task)
+
+# Example with creative writing
+creative_task = """
+Write a short story about a robot learning to paint.
+Make it engaging and about 100 words.
+"""
+
+response = agent.start(creative_task) 

examples/python/models/grok/grok_customer_support_chatbot.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a customer support AI agent for TechGadgets.com, an online electronics store. Answer customer queries helpfully.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("How to return an item?")

examples/python/models/grok/grok_data_analysis_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a data analysis AI agent. Help users analyze datasets, create visualizations, and extract meaningful insights from data.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I have sales data for the last quarter. Can you help me identify trends and patterns?") 

examples/python/models/grok/grok_deep_research_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a deep research AI agent. Conduct comprehensive research, analyze complex topics, and provide detailed insights on various subjects.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I need to research the impact of artificial intelligence on job markets. Can you provide a comprehensive analysis?") 

examples/python/models/grok/grok_health_fitness_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a health and fitness AI agent. Help users with workout plans, nutrition advice, wellness tips, and health monitoring guidance.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I want to lose 20 pounds and build muscle. What's the best workout and nutrition plan for me?") 

examples/python/models/grok/grok_investment_advisor_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are an investment advisor AI agent. Help users with investment strategies, portfolio analysis, risk assessment, and market insights.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I have $50,000 to invest. What would be a good diversified portfolio for someone in their 30s?") 

examples/python/models/grok/grok_journalist_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a journalist AI agent. Help with news writing, article creation, fact-checking, and content generation for various media platforms.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I need to write an article about the latest developments in renewable energy. Can you help me structure it?") 

examples/python/models/grok/grok_lead_generation_assistant.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a lead generation AI agent for RealEstatePro.com. Help identify and qualify potential real estate leads.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I'm looking to buy a house in the suburbs with 3 bedrooms and a garden.")

examples/python/models/grok/grok_medical_imaging_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a medical imaging AI agent. Help analyze medical images, provide preliminary assessments, and assist healthcare professionals with diagnostic support.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I have an X-ray image that needs analysis. Can you help identify any abnormalities?") 

examples/python/models/grok/grok_meeting_productivity_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a meeting productivity AI agent. Help optimize meeting efficiency and follow-up actions.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I have a team meeting tomorrow. How can I make it more productive?")

examples/python/models/grok/grok_mental_wellbeing_advisor.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a mental wellbeing AI advisor. Provide supportive guidance and wellness tips.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I've been feeling stressed at work lately. Any tips for managing stress?")

examples/python/models/grok/grok_multi_mcp_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a multi MCP AI agent. "
+                 "Help users integrate and coordinate multiple Model Context Protocol agents "
+                 "for complex workflows and cross-platform automation.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need to coordinate multiple tools and services for my project. "
+    "Can you help me set up an integrated workflow using MCP agents?"
+) 

examples/python/models/grok/grok_multimodal_coding_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a multimodal coding AI agent. "
+                 "Help users with code generation, review, and debugging "
+                 "by analyzing both text and visual inputs like screenshots and diagrams.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I have a screenshot of a UI design and need to generate the corresponding HTML/CSS code. "
+    "Can you help me create the frontend code?"
+) 

examples/python/models/grok/grok_multimodal_design_agent.py

@@ -0,0 +1,13 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a multimodal design AI agent. "
+                 "Help users with graphic design, UI/UX design, and visual content creation "
+                 "by analyzing text descriptions and visual references.",
+    llm="xai/grok-4"
+)
+
+response = agent.start(
+    "I need to create a logo for my tech startup. "
+    "Can you help me design a modern and professional logo concept?"
+) 

examples/python/models/grok/grok_multimodal_reasoning_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a multimodal reasoning AI agent. Analyze images and text to provide comprehensive insights.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("Can you help me analyze a chart showing sales data for Q1 2024?")

examples/python/models/grok/grok_music_generator_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a music generation AI agent. Help users create melodies, lyrics, and musical compositions based on their preferences and requirements.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I need a catchy jingle for my coffee shop. Can you help me create one?") 

examples/python/models/grok/grok_personal_finance_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a personal finance AI agent. Help users with budgeting, saving strategies, debt management, and financial planning advice.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I want to save $10,000 in the next year. What's the best strategy for me?") 

examples/python/models/grok/grok_startup_trend_analysis_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a startup trend analysis AI agent. Help entrepreneurs identify market opportunities, analyze industry trends, and evaluate business ideas.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I'm thinking of starting a tech startup. What are the current trending opportunities in the market?") 

examples/python/models/grok/grok_travel_planning_agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a travel planning AI agent. Help users plan trips, find destinations, and create itineraries with budget considerations.",
+    llm="xai/grok-4"
+)
+
+response = agent.start("I want to plan a 7-day trip to Europe with a budget of $3000. What are my best options?") 

examples/python/models/groq/groq_crisis_management_communication_agent.py

@@ -0,0 +1,14 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a crisis management and communication AI agent. "
+                "Help users develop crisis communication strategies, "
+                "manage reputation during difficult situations, and create effective messaging. "
+                "Provide guidance on crisis response planning, stakeholder communication, "
+                "media relations during crises, and reputation recovery strategies.",
+    llm="groq/llama3.1-8b-instant"
+)
+
+response = agent.start("Hello! I'm your crisis management and communication assistant. "
+                      "How can I help you develop effective crisis communication "
+                      "strategies and manage difficult situations today?") 

examples/python/models/groq/groq_digital_marketing_seo_optimization_agent.py

@@ -0,0 +1,14 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a digital marketing and SEO optimization AI agent. "
+                "Help users develop digital marketing strategies, optimize for search engines, "
+                "and improve online visibility. Provide guidance on SEO best practices, "
+                "content marketing, social media strategies, PPC campaigns, "
+                "and analytics interpretation for better ROI.",
+    llm="groq/llama3.1-8b-instant"
+)
+
+response = agent.start("Hello! I'm your digital marketing and SEO optimization assistant. "
+                      "How can I help you improve your online presence, "
+                      "optimize for search engines, or develop marketing strategies today?") 

examples/python/models/groq/groq_environmental_impact_assessment_agent.py

@@ -0,0 +1,14 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are an environmental impact assessment AI agent. "
+                "Help users evaluate environmental impacts of projects, "
+                "develop sustainability strategies, and ensure compliance with environmental regulations. "
+                "Provide guidance on environmental risk assessment, sustainability reporting, "
+                "carbon footprint analysis, and green technology implementation.",
+    llm="groq/llama3.1-8b-instant"
+)
+
+response = agent.start("Hello! I'm your environmental impact assessment assistant. "
+                      "How can I help you evaluate environmental impacts, "
+                      "develop sustainability strategies, or ensure compliance today?") 

examples/python/models/groq/groq_event_planning_management_agent.py

@@ -0,0 +1,14 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are an event planning and management AI agent. "
+                "Help users plan, organize, and manage successful events of all types. "
+                "Provide guidance on venue selection, budgeting, vendor coordination, "
+                "timeline management, marketing strategies, and post-event analysis. "
+                "Assist with both virtual and in-person event planning.",
+    llm="groq/llama3.1-8b-instant"
+)
+
+response = agent.start("Hello! I'm your event planning and management assistant. "
+                      "How can I help you plan and organize your next successful "
+                      "event today?")