Merge pull request #504 from MervinPraison/develop

Update Python version format in GitHub Actions workflow

.cursorrules

@@ -0,0 +1,8 @@
+1. Make minimal code changes as possible
+2. if you are creating function, make sure to name it in more easy, user friendly , optimised manner. 
+3. Never copy the exact code if presented with a code from other location or file or codebase, just make it optimised
+4. Always Follow the principle LESS IS MORE
+5. Make it minimal change as possible
+6. Firstly try not to make any modification to the existing code as possible
+7. Only modify the existing code if its highly required, without that if it cant be done, then add new code section. 
+8. If you are adding new code, make sure to add it in a way that it can be easily integrated with the existing codebase. 

.github/workflows/claude.yml

@@ -0,0 +1,37 @@
+name: Claude Code
+
+on:
+  issue_comment:
+    types: [created]
+  pull_request_review_comment:
+    types: [created]
+  issues:
+    types: [opened, assigned]
+  pull_request_review:
+    types: [submitted]
+
+jobs:
+  claude:
+    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')))
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code
+        id: claude
+        uses: anthropics/claude-code-action@beta
+        with:
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+

.github/workflows/python-package.yml

@@ -19,9 +19,9 @@ jobs:
         python-version: ["3.10", "3.11"]
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v3
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies

.github/workflows/python-publish.yml

@@ -21,9 +21,9 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Set up Python
-      uses: actions/setup-python@v3
+      uses: actions/setup-python@v5
       with:
         python-version: '3.x'
     - name: Install dependencies

.github/workflows/release.yml

@@ -0,0 +1,524 @@
+name: Release Workflow
+
+on:
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Tag to create release with (e.g., v2.0.10)'
+        required: true
+      fork_owner:
+        description: 'GitHub username of the fork owner'
+        required: true
+        default: 'tosin2013'
+
+jobs:
+  test-ubuntu:
+    strategy:
+      matrix:
+        os: [ubuntu-22.04, ubuntu-24.04]
+        framework: ['crewai', 'autogen']
+      fail-fast: false
+
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 90
+
+    steps:
+    # First checkout the upstream repo at the specified tag
+    - name: Checkout upstream repo
+      uses: actions/checkout@v4
+      with:
+        repository: MervinPraison/PraisonAI
+        ref: ${{ github.event.inputs.tag }}
+        fetch-depth: 0
+
+    # Get the commit hash from the tag
+    - name: Get commit hash
+      id: get_commit
+      run: |
+        COMMIT_HASH=$(git rev-parse HEAD)
+        echo "commit_hash=$COMMIT_HASH" >> $GITHUB_OUTPUT
+        echo "Found commit: $COMMIT_HASH for tag ${{ github.event.inputs.tag }}"
+
+    # Now checkout the fork at main branch
+    - name: Checkout fork
+      uses: actions/checkout@v4
+      with:
+        repository: ${{ github.event.inputs.fork_owner }}/PraisonAI
+        ref: main
+        fetch-depth: 0
+        clean: true
+
+    # Sync with upstream commit
+    - name: Sync with upstream
+      run: |
+        git config --global user.name "GitHub Actions"
+        git config --global user.email "[email protected]"
+        
+        # Add upstream remote
+        git remote add upstream https://github.com/MervinPraison/PraisonAI.git
+        
+        # Fetch from upstream
+        git fetch upstream --tags --force
+        
+        # Reset to upstream commit
+        git reset --hard ${{ steps.get_commit.outputs.commit_hash }}
+
+    - name: Setup Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.11'
+        cache: 'pip'
+
+    - name: Install Poetry
+      run: |
+        curl -sSL https://install.python-poetry.org | python3 -
+        echo "$HOME/.local/bin" >> $GITHUB_PATH
+        poetry config virtualenvs.in-project true
+        poetry config virtualenvs.create true
+        poetry --version
+        poetry config --list
+
+    - name: Install Dependencies
+      run: |
+        poetry lock #--no-update
+        poetry install --all-extras
+        poetry env info
+        # Verify venv exists
+        test -d .venv || { echo "Virtual environment not created!"; exit 1; }
+        test -f .venv/bin/activate || { echo "Activation script not found!"; exit 1; }
+
+    - name: Run setup script
+      timeout-minutes: 20
+      run: |
+        set -e  # Exit on any error
+        curl -OL https://raw.githubusercontent.com/tosin2013/PraisonAI/refs/heads/main/setup.sh
+        chmod +x setup.sh
+        ./setup.sh --all --cicd || { echo "Setup script failed"; exit 1; }
+      env:
+        OPENAI_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        OPENAI_MODEL_NAME: "llama-3.3-70b-versatile"
+        OPENAI_API_BASE: "https://api.groq.com/openai/v1/"
+        OPENAI_API_BASE_URL: "https://api.groq.com/openai/v1/"
+        PRAISONAI_NON_INTERACTIVE: "true"
+
+    - name: Test Basic Functionality
+      run: |
+        set -e  # Exit on any error
+        
+        # Random sleep between 60-120 seconds to avoid API rate limits
+        SLEEP_TIME=$((RANDOM % 61 + 60))
+        echo "Sleeping for $SLEEP_TIME seconds to avoid API rate limits..."
+        sleep $SLEEP_TIME
+        
+        lsof -ti:8084 | xargs -r kill -9 || true
+        source .venv/bin/activate || { echo "Failed to activate virtual environment"; exit 1; }
+        mkdir -p test_output || { echo "Failed to create test_output directory"; exit 1; }
+        
+        echo "Testing basic CLI functionality..."
+        
+        # Test auto generation with explicit framework
+        praisonai --framework ${{ matrix.framework }}  --auto "create a short test script" 2>&1 | tee test_output/auto_test.log
+        
+        # Verify the output file exists and has content
+        if [[ ! -s test_output/auto_test.log ]]; then
+          echo "Error: No output generated from auto test"
+          exit 1
+        fi
+        
+        # Test auto generation without framework
+        echo "Basic functionality tests passed!"
+      env:
+        OPENAI_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        OPENAI_MODEL_NAME: "llama-3.3-70b-versatile"
+        OPENAI_API_BASE: "https://api.groq.com/openai/v1/"
+        OPENAI_API_BASE_URL: "https://api.groq.com/openai/v1/"
+        LOGLEVEL: "debug"
+        PRAISONAI_NON_INTERACTIVE: "true"
+
+    - name: Test Framework-specific Features
+      continue-on-error: false
+      run: |
+        source .venv/bin/activate
+        
+        # Random sleep between 60-120 seconds to avoid API rate limits
+        SLEEP_TIME=$((RANDOM % 61 + 60))
+        echo "Sleeping for $SLEEP_TIME seconds to avoid API rate limits..."
+        sleep $SLEEP_TIME
+        
+        lsof -ti:8084 | xargs -r kill -9 || true
+        praisonai --framework ${{ matrix.framework }} --auto "create a movie script about Robots in Mars" 2>&1 | tee test_output/framework_output.txt || echo "Framework-specific test failed" >> test_output/errors.log
+      env:
+        OPENAI_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        OPENAI_MODEL_NAME: "llama-3.3-70b-versatile"
+        OPENAI_API_BASE: "https://api.groq.com/openai/v1/"
+        OPENAI_API_BASE_URL: "https://api.groq.com/openai/v1/"
+        PRAISONAI_NON_INTERACTIVE: "true"
+
+    - name: Test Core Functionality
+      continue-on-error: false
+      run: |
+        source .venv/bin/activate
+        
+        # Random sleep between 60-120 seconds to avoid API rate limits
+        SLEEP_TIME=$((RANDOM % 61 + 60))
+        echo "Sleeping for $SLEEP_TIME seconds to avoid API rate limits..."
+        sleep $SLEEP_TIME
+        
+        echo "Testing core functionality..."
+        
+        # Test package imports
+        python3 -c "from praisonai.cli import PraisonAI; from praisonai.auto import AutoGenerator; from praisonai.agents_generator import AgentsGenerator" || exit 1
+        
+        # Test configuration loading
+        python3 -c "from praisonai.inc.config import generate_config; print(generate_config())" || exit 1
+        
+        # Test tools loading
+        python3 -c "from praisonai.inbuilt_tools import *" || exit 1
+        
+        echo "Core functionality tests passed!"
+      env:
+        OPENAI_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        OPENAI_MODEL_NAME: "llama-3.3-70b-versatile"
+        OPENAI_API_BASE: "https://api.groq.com/openai/v1/"
+        OPENAI_API_BASE_URL: "https://api.groq.com/openai/v1/"
+        LOGLEVEL: "debug"
+        PRAISONAI_NON_INTERACTIVE: "true"
+
+    - name: Test Agent Generation
+      continue-on-error: false
+      run: |
+        source .venv/bin/activate
+        
+        # Random sleep between 60-120 seconds to avoid API rate limits
+        SLEEP_TIME=$((RANDOM % 61 + 60))
+        echo "Sleeping for $SLEEP_TIME seconds to avoid API rate limits..."
+        sleep $SLEEP_TIME
+        
+        echo "Testing agent generation..."
+        
+        # Create a test YAML file
+        cat > test_agents.yaml <<EOF
+        topic: "Test automation task"
+        framework: "${{ matrix.framework }} "
+        roles:
+          - name: "Tester"
+            goal: "Test the system"
+            backstory: "Expert system tester"
+            tasks:
+              - description: "Verify system functionality"
+                expected_output: "Test results"
+        EOF
+        
+        # Test YAML loading and agent generation
+        python3 -c '
+        from praisonai.agents_generator import AgentsGenerator
+        config = [{"model": "llama-3.3-70b-versatile", "base_url": "https://api.groq.com/openai/v1/"}]
+        generator = AgentsGenerator("test_agents.yaml", "${{ matrix.framework }} ", config)
+        print("Agent generation test passed!")
+        ' || exit 1
+        
+        echo "Agent generation tests passed!"
+      env:
+        OPENAI_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        OPENAI_MODEL_NAME: "llama-3.3-70b-versatile"
+        OPENAI_API_BASE: "https://api.groq.com/openai/v1/"
+        OPENAI_API_BASE_URL: "https://api.groq.com/openai/v1/"
+        LOGLEVEL: "debug"
+        PRAISONAI_NON_INTERACTIVE: "true"
+
+    - name: Test Custom Tools Integration
+      continue-on-error: false
+      run: |
+        source .venv/bin/activate
+        
+        # Random sleep between 60-120 seconds to avoid API rate limits
+        SLEEP_TIME=$((RANDOM % 61 + 60))
+        echo "Sleeping for $SLEEP_TIME seconds to avoid API rate limits..."
+        sleep $SLEEP_TIME
+        
+        echo "Testing custom tools integration..."
+        
+        # Create a test tool
+        cat > test_tool.py <<EOF
+        from duckduckgo_search import DDGS
+        from praisonai_tools import BaseTool
+
+        class InternetSearchTool(BaseTool):
+            name: str = "Internet Search Tool"
+            description: str = "Search Internet for relevant information"
+
+            def _run(self, query: str):
+                return {"status": "success", "query": query}
+                
+            def test(self):
+                """Test method to verify tool setup"""
+                test_query = "test query"
+                result = self._run(test_query)
+                assert result["status"] == "success"
+                assert result["query"] == test_query
+                return True
+        EOF
+        
+        # Test tool loading and initialization
+        python3 -c '
+        import importlib.util
+        import sys
+        
+        # Load the test tool
+        spec = importlib.util.spec_from_file_location("test_tool", "test_tool.py")
+        module = importlib.util.module_from_spec(spec)
+        sys.modules["test_tool"] = module
+        spec.loader.exec_module(module)
+        
+        # Initialize and test the tool
+        tool = module.InternetSearchTool()
+        assert tool.test(), "Tool test failed"
+        print("Custom tool test passed!")
+        ' || exit 1
+        
+        echo "Custom tools integration test passed!"
+      env:
+        OPENAI_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        OPENAI_MODEL_NAME: "llama-3.3-70b-versatile"
+        OPENAI_API_BASE: "https://api.groq.com/openai/v1/"
+        OPENAI_API_BASE_URL: "https://api.groq.com/openai/v1/"
+        LOGLEVEL: "debug"
+        PRAISONAI_NON_INTERACTIVE: "true"
+
+    - name: Test PraisonAI Agents Configuration
+      continue-on-error: false
+      run: |
+        source .venv/bin/activate
+        
+        # Random sleep between 60-120 seconds to avoid API rate limits
+        SLEEP_TIME=$((RANDOM % 61 + 60))
+        echo "Sleeping for $SLEEP_TIME seconds to avoid API rate limits..."
+        sleep $SLEEP_TIME
+        
+        echo "Testing agents configuration..."
+        mkdir -p test_output || { echo "Failed to create test_output directory"; exit 1; }
+        
+        # Create test script
+        cat > test_agents.py <<EOF
+        from langchain_openai import ChatOpenAI
+        from crewai import Agent, Task, Crew
+        import os
+        import logging
+        import time
+        import random
+
+        logging.basicConfig(level="DEBUG")
+        logger = logging.getLogger(__name__)
+
+        def random_sleep(min_seconds=15, max_seconds=30):
+            """Sleep for a random duration to prevent API rate limiting"""
+            duration = random.uniform(min_seconds, max_seconds)
+            logger.info(f"Rate limit protection: Sleeping for {duration:.2f} seconds...")
+            time.sleep(duration)
+
+        class RateLimitedChatOpenAI(ChatOpenAI):
+            """ChatOpenAI with built-in rate limiting"""
+            def __call__(self, *args, **kwargs):
+                random_sleep()
+                return super().__call__(*args, **kwargs)
+
+        def run_test():
+            logger.info("Initializing test components...")
+            
+            # Initialize the LLM with rate limiting
+            llm = RateLimitedChatOpenAI(
+                model=os.getenv('OPENAI_MODEL_NAME', 'llama-3.3-70b-versatile'),
+                base_url=os.getenv('OPENAI_API_BASE', 'https://api.groq.com/openai/v1/'),
+                api_key=os.getenv('OPENAI_API_KEY'),
+                temperature=0.7
+            )
+
+            random_sleep()
+            logger.info("Creating researcher agent...")
+            researcher = Agent(
+                role="Test Automation Expert",
+                goal="Verify system functionality and performance",
+                backstory="""You are an expert in test automation and system verification,
+                skilled in identifying potential issues and validating functionality.""",
+                verbose=True,
+                allow_delegation=False,
+                llm=llm
+            )
+
+            random_sleep()
+            logger.info("Creating validator agent...")
+            validator = Agent(
+                role="Quality Assurance Specialist",
+                goal="Validate test results and ensure system reliability",
+                backstory="""You are a QA specialist focused on ensuring
+                system reliability and proper functionality.""",
+                verbose=True,
+                allow_delegation=False,
+                llm=llm
+            )
+
+            random_sleep()
+            logger.info("Creating test tasks...")
+            test_task = Task(
+                description="Run a basic system verification test",
+                expected_output="A report on system functionality verification",
+                agent=researcher
+            )
+
+            random_sleep()
+            validation_task = Task(
+                description="Validate the test results and compile findings",
+                expected_output="A validation report of test findings",
+                agent=validator
+            )
+
+            random_sleep()
+            logger.info("Initializing crew...")
+            crew = Crew(
+                agents=[researcher, validator],
+                tasks=[test_task, validation_task],
+                verbose=2
+            )
+
+            logger.info("Starting crew execution...")
+            result = crew.kickoff()
+            logger.info("Test execution completed.")
+            logger.info(f"Result: {result}")
+            return result
+
+        if __name__ == "__main__":
+            try:
+                run_test()
+            except Exception as e:
+                logger.error(f"Test failed with error: {str(e)}", exc_info=True)
+                raise
+        EOF
+        
+        # Run the test script with increased timeout
+        echo "Testing with Python API..."
+        timeout 1800 python3 test_agents.py 2>&1 | tee test_output/agents_test.log
+        
+        # Verify the output
+        if [[ ! -s test_output/agents_test.log ]]; then
+          echo "Error: No output generated from agents test"
+          exit 1
+        fi
+        
+        echo "Agents configuration tests passed!"
+      env:
+        OPENAI_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        OPENAI_MODEL_NAME: "llama-3.3-70b-versatile"
+        OPENAI_API_BASE: "https://api.groq.com/openai/v1/"
+        OPENAI_API_BASE_URL: "https://api.groq.com/openai/v1/"
+        LOGLEVEL: "debug"
+        PRAISONAI_NON_INTERACTIVE: "true"
+
+    - name: Upload test artifacts
+      if: always()
+      uses: actions/upload-artifact@v4
+      with:
+        name: praisonai-output-${{ matrix.os }}-${{ matrix.framework }}
+        path: test_output/
+        retention-days: 14
+
+  create-release:
+    needs: [test-ubuntu]
+    runs-on: ubuntu-latest
+    if: success()
+    steps:
+    # First checkout the fork's main branch
+    - name: Checkout fork repo
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        token: ${{ secrets.PAT_TOKEN }}
+        repository: ${{ github.event.inputs.fork_owner }}/PraisonAI
+        ref: main
+
+    # Add upstream and get commit from tag
+    - name: Get upstream tag commit
+      id: get_upstream_commit
+      run: |
+        # Add upstream remote
+        git remote add upstream https://github.com/MervinPraison/PraisonAI.git
+        
+        # Delete local tag if it exists
+        git tag -d ${{ github.event.inputs.tag }} || true
+        
+        # Fetch from upstream including tags with force
+        git fetch upstream --tags --force
+        
+        # Verify tag exists in upstream
+        if ! git ls-remote --tags upstream | grep -q "refs/tags/${{ github.event.inputs.tag }}$"; then
+          echo "::error::Tag ${{ github.event.inputs.tag }} not found in upstream repository"
+          exit 1
+        fi
+        
+        # Get the commit hash from the upstream tag
+        UPSTREAM_COMMIT=$(git rev-list -n 1 refs/tags/${{ github.event.inputs.tag }})
+        if [ -z "$UPSTREAM_COMMIT" ]; then
+          echo "::error::Could not find commit for tag ${{ github.event.inputs.tag }}"
+          exit 1
+        fi
+        echo "upstream_commit=$UPSTREAM_COMMIT" >> $GITHUB_OUTPUT
+        echo "Found commit: $UPSTREAM_COMMIT for tag ${{ github.event.inputs.tag }}"
+
+    # Create tag at the same commit
+    - name: Create tag at commit
+      run: |
+        git config --global user.name "GitHub Actions"
+        git config --global user.email "[email protected]"
+        
+        # Remove tag if it exists locally
+        git tag -d ${{ github.event.inputs.tag }} || true
+        
+        # Remove tag if it exists remotely
+        git push origin :refs/tags/${{ github.event.inputs.tag }} || true
+        
+        # Fetch the specific commit from upstream
+        git fetch upstream ${{ steps.get_upstream_commit.outputs.upstream_commit }} --force
+        
+        # Reset to upstream commit
+        git reset --hard ${{ steps.get_upstream_commit.outputs.upstream_commit }}
+        
+        # Create and push tag
+        git tag -a ${{ github.event.inputs.tag }} -m "Release ${{ github.event.inputs.tag }} (synced from upstream MervinPraison/PraisonAI@${{ github.event.inputs.tag }})"
+        git push origin ${{ github.event.inputs.tag }}
+      env:
+        GIT_ASKPASS: /bin/echo
+        PAT_TOKEN: ${{ secrets.PAT_TOKEN }}
+
+    # Create the release
+    - name: Create Release
+      uses: actions/create-release@v1
+      env:
+        GITHUB_TOKEN: ${{ secrets.PAT_TOKEN }}
+      with:
+        tag_name: ${{ github.event.inputs.tag }}
+        release_name: Release ${{ github.event.inputs.tag }}
+        draft: false
+        prerelease: false
+        body: |
+          Release ${{ github.event.inputs.tag }} (synced from upstream)
+          
+          This release is synchronized with MervinPraison/PraisonAI@${{ github.event.inputs.tag }}
+          Commit: ${{ steps.get_upstream_commit.outputs.upstream_commit }}
+          
+          For installation:
+          ```bash
+          pip install praisonai
+          ```
+          
+          Changes from upstream v2.0.10:
+          - Updated agent configuration tests
+          - Added rate limiting protection
+          - Improved test reliability
+          
+          Forked from: MervinPraison/PraisonAI

.github/workflows/test-comprehensive.yml

@@ -0,0 +1,177 @@
+name: Comprehensive Test Suite
+
+on:
+  workflow_dispatch:  # Allow manual triggering
+    inputs:
+      test_type:
+        description: 'Type of tests to run'
+        required: true
+        default: 'all'
+        type: choice
+        options:
+        - all
+        - unit
+        - integration
+        - fast
+        - performance
+        - frameworks
+        - autogen
+        - crewai
+  release:
+    types: [published, prereleased]
+  schedule:
+    # Run comprehensive tests weekly on Sundays at 3 AM UTC
+    - cron: '0 3 * * 0'
+
+jobs:
+  comprehensive-test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11"]
+    
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install UV
+      run: |
+        curl -LsSf https://astral.sh/uv/install.sh | sh
+        echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+    - name: Install dependencies
+      run: |
+        uv pip install --system ."[ui,gradio,api,agentops,google,openai,anthropic,cohere,chat,code,realtime,call,crewai,autogen]"
+        uv pip install --system duckduckgo_search
+        uv pip install --system pytest pytest-asyncio pytest-cov pytest-benchmark
+
+    - name: Set environment variables
+      run: |
+        echo "OPENAI_API_KEY=${{ secrets.OPENAI_API_KEY }}" >> $GITHUB_ENV
+        echo "OPENAI_API_BASE=${{ secrets.OPENAI_API_BASE }}" >> $GITHUB_ENV
+        echo "OPENAI_MODEL_NAME=${{ secrets.OPENAI_MODEL_NAME }}" >> $GITHUB_ENV
+        echo "PYTHONPATH=${{ github.workspace }}/src/praisonai-agents:$PYTHONPATH" >> $GITHUB_ENV
+
+    - name: Run Comprehensive Test Suite
+      run: |
+        # Determine test type from input or default to 'all'
+        TEST_TYPE="${{ github.event.inputs.test_type || 'all' }}"
+        
+        echo "🧪 Running comprehensive test suite (type: $TEST_TYPE)"
+        
+        case $TEST_TYPE in
+          "unit")
+            python tests/test_runner.py --unit
+            ;;
+          "integration")
+            python tests/test_runner.py --integration
+            ;;
+          "fast")
+            python tests/test_runner.py --fast
+            ;;
+          "performance")
+            python tests/test_runner.py --pattern "performance"
+            ;;
+          "frameworks")
+            python tests/test_runner.py --pattern frameworks
+            ;;
+          "autogen")
+            python tests/test_runner.py --pattern autogen
+            ;;
+          "crewai")
+            python tests/test_runner.py --pattern crewai
+            ;;
+          "all"|*)
+            python tests/test_runner.py --all
+            ;;
+        esac
+
+    - name: Generate Comprehensive Test Report
+      if: always()
+      run: |
+        echo "# 📋 Comprehensive Test Report" > comprehensive_report.md
+        echo "" >> comprehensive_report.md
+        echo "**Python Version:** ${{ matrix.python-version }}" >> comprehensive_report.md
+        echo "**Test Type:** ${{ github.event.inputs.test_type || 'all' }}" >> comprehensive_report.md
+        echo "**Trigger:** ${{ github.event_name }}" >> comprehensive_report.md
+        echo "**Date:** $(date -u)" >> comprehensive_report.md
+        echo "" >> comprehensive_report.md
+        
+        echo "## 🧪 Test Categories Covered:" >> comprehensive_report.md
+        echo "" >> comprehensive_report.md
+        echo "### Unit Tests:" >> comprehensive_report.md
+        echo "- ✅ Core agent functionality" >> comprehensive_report.md
+        echo "- ✅ Async operations" >> comprehensive_report.md
+        echo "- ✅ Tool integrations" >> comprehensive_report.md
+        echo "- ✅ UI components" >> comprehensive_report.md
+        echo "" >> comprehensive_report.md
+        
+        echo "### Integration Tests:" >> comprehensive_report.md
+        echo "- ✅ MCP (Model Context Protocol)" >> comprehensive_report.md
+        echo "- ✅ RAG (Retrieval Augmented Generation)" >> comprehensive_report.md
+        echo "- ✅ Base URL API mapping" >> comprehensive_report.md
+        echo "- ✅ Multi-agent workflows" >> comprehensive_report.md
+        echo "- ✅ AutoGen framework integration" >> comprehensive_report.md
+        echo "- ✅ CrewAI framework integration" >> comprehensive_report.md
+        echo "- 💬 LLM integrations (OpenAI, Anthropic, etc.)" >> comprehensive_report.md
+        echo "- 🖥️ UI frameworks (Gradio, Streamlit)" >> comprehensive_report.md
+        echo "- 📊 Memory and persistence" >> comprehensive_report.md
+        echo "- 🌐 Multi-modal capabilities" >> comprehensive_report.md
+
+        echo "- ✅ AutoGen framework integration" >> comprehensive_report.md
+        echo "- ✅ CrewAI framework integration" >> comprehensive_report.md
+        echo "" >> comprehensive_report.md
+        
+        echo "### Key Features Tested:" >> comprehensive_report.md
+        echo "- 🤖 Agent creation and configuration" >> comprehensive_report.md
+        echo "- 📋 Task management and execution" >> comprehensive_report.md
+        echo "- 🔄 Sync/async workflows" >> comprehensive_report.md
+        echo "- 🛠️ Custom tools and error handling" >> comprehensive_report.md
+        echo "- 🧠 Knowledge bases and RAG" >> comprehensive_report.md
+        echo "- 🔌 MCP server connections" >> comprehensive_report.md
+        echo "- 💬 LLM integrations (OpenAI, Anthropic, etc.)" >> comprehensive_report.md
+
+    - name: Upload Comprehensive Test Results
+      uses: actions/upload-artifact@v4
+      if: always()
+      with:
+        name: comprehensive-test-results-python-${{ matrix.python-version }}
+        path: |
+          comprehensive_report.md
+          htmlcov/
+          coverage.xml
+          .coverage
+        retention-days: 30
+
+  test-matrix-summary:
+    runs-on: ubuntu-latest
+    needs: comprehensive-test
+    if: always()
+    
+    steps:
+    - name: Generate Matrix Summary
+      run: |
+        echo "# 🎯 Test Matrix Summary" > matrix_summary.md
+        echo "" >> matrix_summary.md
+        echo "## Python Version Results:" >> matrix_summary.md
+        echo "- Python 3.10: ${{ needs.comprehensive-test.result }}" >> matrix_summary.md  
+        echo "- Python 3.11: ${{ needs.comprehensive-test.result }}" >> matrix_summary.md
+        echo "" >> matrix_summary.md
+        echo "## Overall Status:" >> matrix_summary.md
+        if [ "${{ needs.comprehensive-test.result }}" == "success" ]; then
+          echo "✅ **All tests passed across all Python versions!**" >> matrix_summary.md
+        else
+          echo "❌ **Some tests failed. Check individual job logs for details.**" >> matrix_summary.md
+        fi
+        
+    - name: Upload Matrix Summary
+      uses: actions/upload-artifact@v4
+      with:
+        name: test-matrix-summary
+        path: matrix_summary.md
+        retention-days: 30 

.github/workflows/test-core.yml

@@ -0,0 +1,75 @@
+name: Core Tests
+
+on: 
+  push:
+    branches: [ main, develop ]
+  pull_request:
+    branches: [ main, develop ]
+
+jobs:
+  test-core:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.11]
+    
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install UV
+      run: |
+        curl -LsSf https://astral.sh/uv/install.sh | sh
+        echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+    - name: Install dependencies
+      run: |
+        uv pip install --system ."[ui,gradio,api,agentops,google,openai,anthropic,cohere,chat,code,realtime,call,crewai,autogen]"
+        uv pip install --system duckduckgo_search
+        uv pip install --system pytest pytest-asyncio pytest-cov
+
+    - name: Set environment variables
+      run: |
+        echo "OPENAI_API_KEY=${{ secrets.OPENAI_API_KEY }}" >> $GITHUB_ENV
+        echo "OPENAI_API_BASE=${{ secrets.OPENAI_API_BASE }}" >> $GITHUB_ENV
+        echo "OPENAI_MODEL_NAME=${{ secrets.OPENAI_MODEL_NAME }}" >> $GITHUB_ENV
+        echo "PYTHONPATH=${{ github.workspace }}/src/praisonai-agents:$PYTHONPATH" >> $GITHUB_ENV
+
+    - name: Run Unit Tests
+      run: |
+        python -m pytest tests/unit/ -v --tb=short --disable-warnings --cov=praisonaiagents --cov-report=term-missing
+
+    - name: Run Integration Tests  
+      run: |
+        python -m pytest tests/integration/ -v --tb=short --disable-warnings
+
+    - name: Run AutoGen Framework Tests
+      run: |
+        echo "🤖 Testing AutoGen Framework Integration..."
+        python tests/test_runner.py --pattern autogen --verbose || echo "⚠️ AutoGen tests completed with issues"
+      continue-on-error: true
+
+    - name: Run CrewAI Framework Tests  
+      run: |
+        echo "⛵ Testing CrewAI Framework Integration..."
+        python tests/test_runner.py --pattern crewai --verbose || echo "⚠️ CrewAI tests completed with issues"
+      continue-on-error: true
+
+    - name: Run Legacy Tests
+      run: |
+        python -m pytest tests/test.py -v --tb=short --disable-warnings
+
+    - name: Upload Coverage Reports
+      if: matrix.python-version == '3.11'
+      uses: actions/upload-artifact@v4
+      with:
+        name: coverage-reports
+        path: |
+          .coverage
+          htmlcov/
+        retention-days: 7

.github/workflows/test-extended.yml

@@ -0,0 +1,156 @@
+name: Extended Tests
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+  schedule:
+    # Run nightly at 2 AM UTC
+    - cron: '0 2 * * *'
+  workflow_dispatch:  # Allow manual triggering
+
+jobs:
+  test-examples:
+    runs-on: ubuntu-latest
+    
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: 3.11
+
+    - name: Install UV
+      run: |
+        curl -LsSf https://astral.sh/uv/install.sh | sh
+        echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+    - name: Install dependencies
+      run: |
+        uv pip install --system ."[ui,gradio,api,agentops,google,openai,anthropic,cohere,chat,code,realtime,call,crewai,autogen]"
+        uv pip install --system duckduckgo_search
+
+    - name: Set environment variables
+      run: |
+        echo "OPENAI_API_KEY=${{ secrets.OPENAI_API_KEY }}" >> $GITHUB_ENV
+        echo "OPENAI_API_BASE=${{ secrets.OPENAI_API_BASE }}" >> $GITHUB_ENV
+        echo "OPENAI_MODEL_NAME=${{ secrets.OPENAI_MODEL_NAME }}" >> $GITHUB_ENV
+        echo "PYTHONPATH=${{ github.workspace }}/src/praisonai-agents:$PYTHONPATH" >> $GITHUB_ENV
+
+    - name: Test Key Example Scripts
+      run: |
+        echo "🧪 Testing key example scripts from praisonai-agents..."
+        
+        # Create a timeout function for consistent handling
+        timeout_run() {
+          timeout 30s "$@" || echo "⏱️  $1 test completed/timed out"
+        }
+        
+        # Test basic agent functionality
+        timeout_run python src/praisonai-agents/basic-agents.py
+        
+        # Test async functionality  
+        timeout_run python src/praisonai-agents/async_example.py
+        
+        # Test knowledge/RAG functionality
+        timeout_run python src/praisonai-agents/knowledge-agents.py
+        
+        # Test MCP functionality
+        timeout_run python src/praisonai-agents/mcp-basic.py
+        
+        # Test UI functionality
+        timeout_run python src/praisonai-agents/ui.py
+        
+        echo "✅ Example script testing completed"
+      continue-on-error: true
+
+  performance-test:
+    runs-on: ubuntu-latest
+    
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: 3.11
+
+    - name: Install UV
+      run: |
+        curl -LsSf https://astral.sh/uv/install.sh | sh
+        echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+    - name: Install dependencies
+      run: |
+        uv pip install --system ."[ui,gradio,api,agentops,google,openai,anthropic,cohere,chat,code,realtime,call,crewai,autogen]"
+        uv pip install --system pytest pytest-benchmark
+
+    - name: Run Performance Benchmarks
+      run: |
+        echo "🏃 Running performance benchmarks..."
+        python -c "
+        import time
+        import sys
+        import statistics
+        sys.path.insert(0, 'src/praisonai-agents')
+        
+        print('🏃 Testing agent creation performance...')
+        times = []
+        try:
+            from praisonaiagents import Agent
+            for i in range(5):
+                start_time = time.time()
+                agent = Agent(name=f'PerfAgent{i}')
+                times.append(time.time() - start_time)
+            
+            avg_time = statistics.mean(times)
+            print(f'✅ Average agent creation time: {avg_time:.3f}s')
+            print(f'📊 Min: {min(times):.3f}s, Max: {max(times):.3f}s')
+        except Exception as e:
+            print(f'❌ Agent creation benchmark failed: {e}')
+        
+        print('🏃 Testing import performance...')
+        start_time = time.time()
+        try:
+            import praisonaiagents
+            import_time = time.time() - start_time
+            print(f'✅ Import completed in {import_time:.3f}s')
+        except Exception as e:
+            print(f'❌ Import benchmark failed: {e}')
+        
+        print('🏃 Testing memory usage...')
+        try:
+            import psutil
+            import os
+            process = psutil.Process(os.getpid())
+            memory_mb = process.memory_info().rss / 1024 / 1024
+            print(f'📊 Memory usage: {memory_mb:.1f} MB')
+        except ImportError:
+            print('⚠️  psutil not available for memory testing')
+        except Exception as e:
+            print(f'❌ Memory benchmark failed: {e}')
+        "
+      continue-on-error: true
+
+    - name: Generate Performance Report
+      run: |
+        echo "## 📊 Performance Test Results" > performance_report.md
+        echo "" >> performance_report.md
+        echo "### Benchmarks Run:" >> performance_report.md
+        echo "- ⚡ Agent creation speed" >> performance_report.md
+        echo "- 📦 Import performance" >> performance_report.md
+        echo "- 💾 Memory usage" >> performance_report.md
+        echo "- 🧪 Example script execution" >> performance_report.md
+        echo "" >> performance_report.md
+        echo "_Performance results are logged in the CI output above._" >> performance_report.md
+
+    - name: Upload Performance Report
+      uses: actions/upload-artifact@v4
+      with:
+        name: performance-report
+        path: performance_report.md
+        retention-days: 30 

.github/workflows/test-frameworks.yml

@@ -0,0 +1,152 @@
+name: Framework Integration Tests
+
+on:
+  workflow_dispatch:  # Allow manual triggering
+    inputs:
+      framework:
+        description: 'Framework to test'
+        required: true
+        default: 'all'
+        type: choice
+        options:
+        - all
+        - autogen
+        - crewai
+  schedule:
+    # Run framework tests daily at 6 AM UTC
+    - cron: '0 6 * * *'
+  push:
+    paths:
+      - 'tests/integration/autogen/**'
+      - 'tests/integration/crewai/**'
+      - '.github/workflows/test-frameworks.yml'
+
+jobs:
+  framework-tests:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.11]
+        framework: [autogen, crewai]
+    
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install UV
+      run: |
+        curl -LsSf https://astral.sh/uv/install.sh | sh
+        echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+    - name: Install dependencies
+      run: |
+        uv pip install --system ."[ui,gradio,api,agentops,google,openai,anthropic,cohere,chat,code,realtime,call,crewai,autogen]"
+        uv pip install --system duckduckgo_search
+        uv pip install --system pytest pytest-asyncio pytest-cov
+
+    - name: Set environment variables
+      run: |
+        echo "OPENAI_API_KEY=${{ secrets.OPENAI_API_KEY }}" >> $GITHUB_ENV
+        echo "OPENAI_API_BASE=${{ secrets.OPENAI_API_BASE }}" >> $GITHUB_ENV
+        echo "OPENAI_MODEL_NAME=${{ secrets.OPENAI_MODEL_NAME }}" >> $GITHUB_ENV
+        echo "PYTHONPATH=${{ github.workspace }}/src/praisonai-agents:$PYTHONPATH" >> $GITHUB_ENV
+
+    - name: Test ${{ matrix.framework }} Framework
+      run: |
+        echo "🧪 Testing ${{ matrix.framework }} framework integration with Python ${{ matrix.python-version }}"
+        python tests/test_runner.py --pattern ${{ matrix.framework }} --verbose --coverage
+      continue-on-error: false
+
+    - name: Generate Framework Test Report
+      if: always()
+      run: |
+        echo "# 🤖 ${{ matrix.framework }} Framework Test Report" > ${{ matrix.framework }}_report.md
+        echo "" >> ${{ matrix.framework }}_report.md
+        echo "**Framework:** ${{ matrix.framework }}" >> ${{ matrix.framework }}_report.md
+        echo "**Python Version:** ${{ matrix.python-version }}" >> ${{ matrix.framework }}_report.md
+        echo "**Date:** $(date -u)" >> ${{ matrix.framework }}_report.md
+        echo "**Trigger:** ${{ github.event_name }}" >> ${{ matrix.framework }}_report.md
+        echo "" >> ${{ matrix.framework }}_report.md
+        
+        if [ "${{ matrix.framework }}" == "autogen" ]; then
+          echo "## AutoGen Integration Tests" >> ${{ matrix.framework }}_report.md
+          echo "- ✅ AutoGen import verification" >> ${{ matrix.framework }}_report.md
+          echo "- ✅ Basic agent creation through PraisonAI" >> ${{ matrix.framework }}_report.md
+          echo "- ✅ Conversation flow testing" >> ${{ matrix.framework }}_report.md
+          echo "- ✅ Configuration validation" >> ${{ matrix.framework }}_report.md
+        elif [ "${{ matrix.framework }}" == "crewai" ]; then
+          echo "## CrewAI Integration Tests" >> ${{ matrix.framework }}_report.md
+          echo "- ✅ CrewAI import verification" >> ${{ matrix.framework }}_report.md
+          echo "- ✅ Basic crew creation through PraisonAI" >> ${{ matrix.framework }}_report.md
+          echo "- ✅ Multi-agent workflow testing" >> ${{ matrix.framework }}_report.md
+          echo "- ✅ Agent collaboration verification" >> ${{ matrix.framework }}_report.md
+          echo "- ✅ Configuration validation" >> ${{ matrix.framework }}_report.md
+        fi
+        
+        echo "" >> ${{ matrix.framework }}_report.md
+        echo "## Test Commands" >> ${{ matrix.framework }}_report.md
+        echo '```bash' >> ${{ matrix.framework }}_report.md
+        echo "# Run ${{ matrix.framework }} tests locally:" >> ${{ matrix.framework }}_report.md
+        echo "python tests/test_runner.py --pattern ${{ matrix.framework }} --verbose" >> ${{ matrix.framework }}_report.md
+        echo '```' >> ${{ matrix.framework }}_report.md
+
+    - name: Upload Framework Test Results
+      uses: actions/upload-artifact@v4
+      if: always()
+      with:
+        name: ${{ matrix.framework }}-test-results-python-${{ matrix.python-version }}
+        path: |
+          ${{ matrix.framework }}_report.md
+          htmlcov/
+          coverage.xml
+          .coverage
+        retention-days: 14
+
+  framework-summary:
+    runs-on: ubuntu-latest
+    needs: framework-tests
+    if: always()
+    
+    steps:
+    - name: Generate Framework Summary
+      run: |
+        echo "# 🚀 Framework Integration Test Summary" > framework_summary.md
+        echo "" >> framework_summary.md
+        echo "## Test Results by Framework and Python Version:" >> framework_summary.md
+        echo "" >> framework_summary.md
+        echo "### AutoGen Framework:" >> framework_summary.md
+        echo "- Python 3.11: ${{ needs.framework-tests.result }}" >> framework_summary.md
+        echo "" >> framework_summary.md
+        echo "### CrewAI Framework:" >> framework_summary.md
+        echo "- Python 3.11: ${{ needs.framework-tests.result }}" >> framework_summary.md
+        echo "" >> framework_summary.md
+        echo "## Overall Status:" >> framework_summary.md
+        if [ "${{ needs.framework-tests.result }}" == "success" ]; then
+          echo "✅ **All framework integration tests passed!**" >> framework_summary.md
+        else
+          echo "❌ **Some framework tests failed. Check individual job logs for details.**" >> framework_summary.md
+        fi
+        
+        echo "" >> framework_summary.md
+        echo "## Frameworks Tested:" >> framework_summary.md
+        echo "- **AutoGen**: Microsoft's conversational AI framework" >> framework_summary.md
+        echo "- **CrewAI**: Multi-agent collaboration framework" >> framework_summary.md
+        echo "" >> framework_summary.md
+        echo "## Test Coverage:" >> framework_summary.md
+        echo "- Import verification" >> framework_summary.md
+        echo "- Agent/crew creation" >> framework_summary.md
+        echo "- Workflow execution" >> framework_summary.md
+        echo "- Configuration validation" >> framework_summary.md
+        echo "- Integration with PraisonAI" >> framework_summary.md
+        
+    - name: Upload Framework Summary
+      uses: actions/upload-artifact@v4
+      with:
+        name: framework-test-summary
+        path: framework_summary.md
+        retention-days: 30 

.github/workflows/test-real.yml

@@ -0,0 +1,164 @@
+name: Real End-to-End Tests
+
+# ⚠️ WARNING: This workflow makes real API calls and incurs costs!
+# Only runs when manually triggered to prevent accidental charges
+
+on:
+  workflow_dispatch:  # Manual trigger only
+    inputs:
+      framework:
+        description: 'Framework to test (⚠️ Will incur API costs!)'
+        required: true
+        default: 'none'
+        type: choice
+        options:
+        - none
+        - autogen
+        - crewai
+        - all
+      confirm_costs:
+        description: 'I understand this will make real API calls and may incur costs'
+        required: true
+        type: boolean
+        default: false
+
+jobs:
+  real-tests:
+    runs-on: ubuntu-latest
+    if: ${{ github.event.inputs.confirm_costs == 'true' && github.event.inputs.framework != 'none' }}
+    
+    strategy:
+      matrix:
+        python-version: [3.11]  # Single version to minimize costs
+    
+    steps:
+    - name: 🚨 Cost Warning
+      run: |
+        echo "⚠️  WARNING: This workflow will make real API calls!"
+        echo "💰 This may incur charges on your API accounts"
+        echo "🎯 Framework: ${{ github.event.inputs.framework }}"
+        echo "✅ Cost confirmation: ${{ github.event.inputs.confirm_costs }}"
+        
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install UV
+      run: |
+        curl -LsSf https://astral.sh/uv/install.sh | sh
+        echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+    - name: Install dependencies
+      run: |
+        uv pip install --system ."[ui,gradio,api,agentops,google,openai,anthropic,cohere,chat,code,realtime,call,crewai,autogen]"
+        uv pip install --system pytest pytest-asyncio pytest-cov
+
+    - name: Set environment variables
+      run: |
+        echo "OPENAI_API_KEY=${{ secrets.OPENAI_API_KEY }}" >> $GITHUB_ENV
+        echo "ANTHROPIC_API_KEY=${{ secrets.ANTHROPIC_API_KEY }}" >> $GITHUB_ENV
+        echo "GOOGLE_API_KEY=${{ secrets.GOOGLE_API_KEY }}" >> $GITHUB_ENV
+        echo "PYTHONPATH=${{ github.workspace }}/src/praisonai-agents:$PYTHONPATH" >> $GITHUB_ENV
+
+    - name: Verify API Keys
+      run: |
+        if [ -z "${{ secrets.OPENAI_API_KEY }}" ]; then
+          echo "❌ OPENAI_API_KEY not set in secrets"
+          echo "🔧 Add your API key to repository secrets"
+          exit 1
+        fi
+        echo "✅ API keys configured"
+
+    - name: Run Real AutoGen Tests
+      if: ${{ github.event.inputs.framework == 'autogen' || github.event.inputs.framework == 'all' }}
+      run: |
+        echo "🤖 Running REAL AutoGen tests (⚠️  API costs may apply)"
+        python -m pytest tests/e2e/autogen/ -v -m real --tb=short
+      continue-on-error: false
+
+    - name: Run Real CrewAI Tests
+      if: ${{ github.event.inputs.framework == 'crewai' || github.event.inputs.framework == 'all' }}
+      run: |
+        echo "⛵ Running REAL CrewAI tests (⚠️  API costs may apply)"
+        python -m pytest tests/e2e/crewai/ -v -m real --tb=short
+      continue-on-error: false
+
+    - name: Generate Real Test Report
+      if: always()
+      run: |
+        echo "# 🔥 Real End-to-End Test Report" > real_test_report.md
+        echo "" >> real_test_report.md
+        echo "⚠️  **WARNING: This report represents tests that made real API calls**" >> real_test_report.md
+        echo "" >> real_test_report.md
+        echo "**Framework Tested:** ${{ github.event.inputs.framework }}" >> real_test_report.md
+        echo "**Python Version:** ${{ matrix.python-version }}" >> real_test_report.md
+        echo "**Date:** $(date -u)" >> real_test_report.md
+        echo "**Triggered by:** ${{ github.actor }}" >> real_test_report.md
+        echo "" >> real_test_report.md
+        
+        echo "## 🧪 Test Results" >> real_test_report.md
+        echo "" >> real_test_report.md
+        
+        if [ "${{ github.event.inputs.framework }}" == "autogen" ] || [ "${{ github.event.inputs.framework }}" == "all" ]; then
+          echo "### AutoGen Real Tests:" >> real_test_report.md
+          echo "- Environment verification" >> real_test_report.md
+          echo "- Agent creation with real API calls" >> real_test_report.md
+          echo "- Configuration validation" >> real_test_report.md
+          echo "" >> real_test_report.md
+        fi
+        
+        if [ "${{ github.event.inputs.framework }}" == "crewai" ] || [ "${{ github.event.inputs.framework }}" == "all" ]; then
+          echo "### CrewAI Real Tests:" >> real_test_report.md
+          echo "- Environment verification" >> real_test_report.md
+          echo "- Crew creation with real API calls" >> real_test_report.md
+          echo "- Multi-agent setup validation" >> real_test_report.md
+          echo "" >> real_test_report.md
+        fi
+        
+        echo "## 💰 Cost Considerations" >> real_test_report.md
+        echo "- These tests made actual API calls to LLM providers" >> real_test_report.md
+        echo "- Costs depend on your API pricing tier" >> real_test_report.md
+        echo "- Tests are designed to be minimal to reduce costs" >> real_test_report.md
+        echo "- Check your API provider dashboard for actual usage" >> real_test_report.md
+        
+        echo "## 📋 Next Steps" >> real_test_report.md
+        echo "- Review test results for any failures" >> real_test_report.md
+        echo "- Check API usage in your provider dashboard" >> real_test_report.md
+        echo "- Use mock tests (tests/integration/) for routine testing" >> real_test_report.md
+
+    - name: Upload Real Test Results
+      uses: actions/upload-artifact@v4
+      if: always()
+      with:
+        name: real-test-results-${{ github.event.inputs.framework }}-python-${{ matrix.python-version }}
+        path: |
+          real_test_report.md
+        retention-days: 30
+
+  # Safety job that runs when costs not confirmed
+  safety-check:
+    runs-on: ubuntu-latest
+    if: ${{ github.event.inputs.confirm_costs != 'true' || github.event.inputs.framework == 'none' }}
+    
+    steps:
+    - name: 🛡️ Safety Check Failed
+      run: |
+        echo "🚨 Real tests not executed due to safety checks:"
+        echo ""
+        echo "✅ Costs confirmed: ${{ github.event.inputs.confirm_costs }}"
+        echo "✅ Framework selected: ${{ github.event.inputs.framework }}"
+        echo ""
+        echo "To run real tests:"
+        echo "1. Select a framework (autogen, crewai, or all)"
+        echo "2. Check 'I understand this will make real API calls and may incur costs'"
+        echo "3. Ensure API keys are set in repository secrets"
+        echo ""
+        echo "💡 For cost-free testing, use mock tests instead:"
+        echo "   - Run 'python -m pytest tests/integration/' locally"
+        echo "   - Or trigger other workflows that use mock tests"
+        
+        exit 1 

.github/workflows/unittest.yml

@@ -1,36 +1,44 @@
-name: Run specific unittest
+name: Quick Validation Tests
 
 on: [push, pull_request]
 
 jobs:
-  test:
+  quick-test:
     runs-on: ubuntu-latest
-
+    
     steps:
     - name: Checkout code
-      uses: actions/checkout@v2
+      uses: actions/checkout@v4
 
     - name: Set up Python
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v5
       with:
         python-version: 3.11
 
-    - name: Install Poetry
+    - name: Install UV
       run: |
-        curl -sSL https://install.python-poetry.org | python3 -
-        export PATH="$HOME/.local/bin:$PATH"
+        curl -LsSf https://astral.sh/uv/install.sh | sh
+        echo "$HOME/.local/bin" >> $GITHUB_PATH
 
     - name: Install dependencies
       run: |
-        poetry install
-        poetry run python -m pip install duckduckgo_search
+        uv pip install --system ."[ui,gradio,api,agentops,google,openai,anthropic,cohere,chat,code,realtime,call,crewai,autogen]"
+        uv pip install --system duckduckgo_search
+        uv pip install --system pytest pytest-asyncio pytest-cov
 
     - name: Set environment variables
       run: |
         echo "OPENAI_API_KEY=${{ secrets.OPENAI_API_KEY }}" >> $GITHUB_ENV
         echo "OPENAI_API_BASE=${{ secrets.OPENAI_API_BASE }}" >> $GITHUB_ENV
         echo "OPENAI_MODEL_NAME=${{ secrets.OPENAI_MODEL_NAME }}" >> $GITHUB_ENV
+        echo "PYTHONPATH=${{ github.workspace }}/src/praisonai-agents:$PYTHONPATH" >> $GITHUB_ENV
 
-    - name: Run specific unittest
+    - name: Run Fast Tests
       run: |
-        poetry run python -m unittest tests.test.TestExamples
+        # Run the fastest, most essential tests
+        python tests/test_runner.py --pattern fast
+
+    - name: Run Legacy Example Tests
+      run: |
+        python -m pytest tests/test.py -v --tb=short --disable-warnings
+      continue-on-error: true

.gitignore

@@ -1,3 +1,4 @@
+workspace.code-workspace
 .vscode
 crewai
 .cache
@@ -51,6 +52,8 @@ agentops.log
 
 # crewAI
 crewAI
+!tests/integration/crewai
+!tests/e2e/crewai
 
 # virtualenv
 .venv
@@ -60,3 +63,12 @@ credentials.json
 
 # node_modules
 node_modules
+
+outputs
+agents/praisonaiagents/build
+agents/praisonaiagents/dist
+agents/praisonaiagents/praisonaiagents.egg-info
+.codegpt
+.praison
+# Local Netlify folder
+.netlify

.praisoncontext

@@ -1,2 +1,4 @@
 # praisonai/ui/context.py
-# /Users/praison/miniconda3/envs/praisonai-package/lib/python3.11/site-packages/llama_index/packs/code_hierarchy/code_hierarchy.py
+# /Users/praison/miniconda3/envs/praisonai-package/lib/python3.11/site-packages/llama_index/packs/code_hierarchy/code_hierarchy.py
+praisonai/ui/components/aicoder.py
+praisonai/ui/code.py

.praisonignore

@@ -1,5 +1,4 @@
 cookbooks
 tests
 docs
-praisonai/ui/*
 praisonai/inbuilt_tools/*

README.md

@@ -20,270 +20,477 @@
 
 </div>
 
-Praison AI, leveraging both AutoGen and CrewAI or any other agent framework, represents a low-code, centralised framework designed to simplify the creation and orchestration of multi-agent systems for various LLM applications, emphasizing ease of use, customization, and human-agent interaction.
+PraisonAI is a production-ready Multi-AI Agents framework with self-reflection, designed to create AI Agents to automate and solve problems ranging from simple tasks to complex challenges. By integrating PraisonAI Agents, AG2 (Formerly AutoGen), and CrewAI into a low-code solution, it streamlines the building and management of multi-agent LLM systems, emphasising simplicity, customisation, and effective human-agent collaboration.
 
 <div align="center">
-  <picture>
-    <source media="(prefers-color-scheme: dark)" srcset="docs/images/architecture-dark.png" />
-    <source media="(prefers-color-scheme: light)" srcset="docs/images/architecture-light.png" />
-    <img alt="PraisonAI Architecture" src="docs/images/architecture-light.png" />
-  </picture>
+  <a href="https://docs.praison.ai">
+    <p align="center">
+      <img src="https://img.shields.io/badge/📚_Documentation-Visit_docs.praison.ai-blue?style=for-the-badge&logo=bookstack&logoColor=white" alt="Documentation" />
+    </p>
+  </a>
 </div>
 
-## Different User Interfaces:
-
-| Interface | Description | URL |
-|---|---|---|
-| **UI** | Multi Agents such as CrewAI or AutoGen | [https://docs.praison.ai/ui/ui](https://docs.praison.ai/ui/ui) |
-| **Chat** | Chat with 100+ LLMs, single AI Agent | [https://docs.praison.ai/ui/chat](https://docs.praison.ai/ui/chat) |
-| **Code** | Chat with entire Codebase, single AI Agent | [https://docs.praison.ai/ui/code](https://docs.praison.ai/ui/code) |
-| **Realtime** | Real-time voice interaction with AI | [https://docs.praison.ai/ui/realtime](https://docs.praison.ai/ui/realtime) |
-
-| Other Features | Description | Docs |
-|---|---|---|
-| **Train** | Fine-tune LLMs using your custom data | [https://docs.praison.ai/train](https://docs.praison.ai/train) |
-
-
-## Google Colab Multi Agents
-
-|               | Cookbook        | Open in Colab                                                                                                                                                                                                                                  |
-| ------------- | --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Basic         | PraisonAI       | <a target="_blank" href="https://colab.research.google.com/github/MervinPraison/PraisonAI/blob/main/cookbooks/praisonai-googlecolab.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" /></a>       |
-| Include Tools | PraisonAI Tools | <a target="_blank" href="https://colab.research.google.com/github/MervinPraison/PraisonAI/blob/main/cookbooks/praisonai-tools-googlecolab.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" /></a> |
-
-## Installation Options
-
-### Using pip
-```bash
-pip install praisonai
-```
-
-### Framework-specific Installation
-```bash
-# Install with CrewAI support
-pip install "praisonai[crewai]"
-
-# Install with AutoGen support
-pip install "praisonai[autogen]"
-
-# Install with both frameworks
-pip install "praisonai[crewai,autogen]"
-```
-
-### UI and Additional Features
-```bash
-# Install UI support
-pip install "praisonai[ui]"
-
-# Install Chat interface
-pip install "praisonai[chat]"
-
-# Install Code interface
-pip install "praisonai[code]"
-
-# Install Realtime voice interaction
-pip install "praisonai[realtime]"
-
-# Install Call feature
-pip install "praisonai[call]"
-```
-
-## Quick Start
-
-```bash
-# Set your OpenAI API key
-export OPENAI_API_KEY="Enter your API key"
-
-# Initialize with CrewAI (default)
-praisonai --init "create a movie script about dog in moon"
-
-# Or initialize with AutoGen
-praisonai --framework autogen --init "create a movie script about dog in moon"
-
-# Run the agents
-praisonai
-```
-
-## Full Automatic Mode
-
-```bash
-# With CrewAI (default)
-praisonai --auto "create a movie script about Dog in Moon"
-
-# With AutoGen
-praisonai --framework autogen --auto "create a movie script about Dog in Moon"
-```
-
-## Framework-specific Features
-
-### CrewAI
-When installing with `pip install "praisonai[crewai]"`, you get:
-- CrewAI framework support
-- PraisonAI tools integration
-- Task delegation capabilities
-- Sequential and parallel task execution
-
-### AutoGen
-When installing with `pip install "praisonai[autogen]"`, you get:
-- AutoGen framework support
-- PraisonAI tools integration
-- Multi-agent conversation capabilities
-- Code execution environment
-
 ## Key Features
 
 - 🤖 Automated AI Agents Creation
-- 🔄 Use CrewAI or AutoGen Framework
+- 🔄 Self Reflection AI Agents
+- 🧠 Reasoning AI Agents
+- 👁️ Multi Modal AI Agents
+- 🤝 Multi Agent Collaboration
+- 🎭 AI Agent Workflow
+- 📚 Add Custom Knowledge
+- 🧠 Agents with Short and Long Term Memory
+- 📄 Chat with PDF Agents
+- 💻 Code Interpreter Agents
+- 📚 RAG Agents
+- 🤔 Async & Parallel Processing
+- 🔄 Auto Agents
+- 🔢 Math Agents
+- 🎯 Structured Output Agents
+- 🔗 LangChain Integrated Agents
+- 📞 Callback Agents
+- 🤏 Mini AI Agents
+- 🛠️ 100+ Custom Tools
+- 📄 YAML Configuration
 - 💯 100+ LLM Support
-- 💻 Chat with ENTIRE Codebase
-- 🖥️ Interactive UIs
-- 📄 YAML-based Configuration
-- 🛠️ Custom Tool Integration
-- 🔍 Internet Search Capability (using Crawl4AI and Tavily)
-- 👁️ Vision Language Model (VLM) Support
-- 🎙️ Real-time Voice Interaction
 
-## TL;DR Multi Agents
+## Using Python Code
 
+Light weight package dedicated for coding:
+```bash
+pip install praisonaiagents
+```
+
+```bash
+export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+```
+
+### 1. Single Agent
+
+Create app.py file and add the code below:
+```python
+from praisonaiagents import Agent
+agent = Agent(instructions="Your are a helpful AI assistant")
+agent.start("Write a movie script about a robot in Mars")
+```
+
+Run:
+```bash
+python app.py
+```
+
+### 2. Multi Agents
+
+Create app.py file and add the code below:
+```python
+from praisonaiagents import Agent, PraisonAIAgents
+
+research_agent = Agent(instructions="Research about AI")
+summarise_agent = Agent(instructions="Summarise research agent's findings")
+agents = PraisonAIAgents(agents=[research_agent, summarise_agent])
+agents.start()
+```
+
+Run:
+```bash
+python app.py
+```
+
+## Using No Code
+
+### Auto Mode:
 ```bash
 pip install praisonai
-export OPENAI_API_KEY="Enter your API key"
-praisonai --init create a movie script about dog in moon
-praisonai
+export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+praisonai --auto create a movie script about Robots in Mars
 ```
 
-## Table of Contents
-
-- [Installation](#installation)
-- [Initialise](#initialise)
-- [Run](#run)
-- [Full Automatic Mode](#full-automatic-mode)
-- [User Interface](#user-interface)
-- [Praison AI Chat](#praison-ai-chat)
-- [Create Custom Tools](#create-custom-tools)
-- [Agents Playbook](#agents-playbook)
-- [Include praisonai package in your project](#include-praisonai-package-in-your-project)
-- [Commands to Install Dev Dependencies](#commands-to-install-dependencies)
-- [Other Models](#other-models)
-- [Contributing](#contributing)
-- [Star History](#star-history)
-
-## Installation Multi Agents
+## Using JavaScript Code
 
 ```bash
-pip install praisonai
+npm install praisonai
+export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
 ```
 
-## Initialise
+```javascript
+const { Agent } = require('praisonai');
+const agent = new Agent({ instructions: 'You are a helpful AI assistant' });
+agent.start('Write a movie script about a robot in Mars');
+```
 
+![PraisonAI CLI Demo](docs/demo/praisonai-cli-demo.gif)
+
+## AI Agents Flow
+
+```mermaid
+graph LR
+    %% Define the main flow
+    Start([▶ Start]) --> Agent1
+    Agent1 --> Process[⚙ Process]
+    Process --> Agent2
+    Agent2 --> Output([✓ Output])
+    Process -.-> Agent1
+    
+    %% Define subgraphs for agents and their tasks
+    subgraph Agent1[ ]
+        Task1[📋 Task]
+        AgentIcon1[🤖 AI Agent]
+        Tools1[🔧 Tools]
+        
+        Task1 --- AgentIcon1
+        AgentIcon1 --- Tools1
+    end
+    
+    subgraph Agent2[ ]
+        Task2[📋 Task]
+        AgentIcon2[🤖 AI Agent]
+        Tools2[🔧 Tools]
+        
+        Task2 --- AgentIcon2
+        AgentIcon2 --- Tools2
+    end
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef tools fill:#2E8B57,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Start,Output,Task1,Task2 input
+    class Process,AgentIcon1,AgentIcon2 process
+    class Tools1,Tools2 tools
+    class Agent1,Agent2 transparent
+```
+
+## AI Agents with Tools
+
+Create AI agents that can use tools to interact with external systems and perform actions.
+
+```mermaid
+flowchart TB
+    subgraph Tools
+        direction TB
+        T3[Internet Search]
+        T1[Code Execution]
+        T2[Formatting]
+    end
+
+    Input[Input] ---> Agents
+    subgraph Agents
+        direction LR
+        A1[Agent 1]
+        A2[Agent 2]
+        A3[Agent 3]
+    end
+    Agents ---> Output[Output]
+
+    T3 --> A1
+    T1 --> A2
+    T2 --> A3
+
+    style Tools fill:#189AB4,color:#fff
+    style Agents fill:#8B0000,color:#fff
+    style Input fill:#8B0000,color:#fff
+    style Output fill:#8B0000,color:#fff
+```
+
+## AI Agents with Memory
+
+Create AI agents with memory capabilities for maintaining context and information across tasks.
+
+```mermaid
+flowchart TB
+    subgraph Memory
+        direction TB
+        STM[Short Term]
+        LTM[Long Term]
+    end
+
+    subgraph Store
+        direction TB
+        DB[(Vector DB)]
+    end
+
+    Input[Input] ---> Agents
+    subgraph Agents
+        direction LR
+        A1[Agent 1]
+        A2[Agent 2]
+        A3[Agent 3]
+    end
+    Agents ---> Output[Output]
+
+    Memory <--> Store
+    Store <--> A1
+    Store <--> A2
+    Store <--> A3
+
+    style Memory fill:#189AB4,color:#fff
+    style Store fill:#2E8B57,color:#fff
+    style Agents fill:#8B0000,color:#fff
+    style Input fill:#8B0000,color:#fff
+    style Output fill:#8B0000,color:#fff
+```
+
+## AI Agents with Different Processes
+
+### Sequential Process
+
+The simplest form of task execution where tasks are performed one after another.
+
+```mermaid
+graph LR
+    Input[Input] --> A1
+    subgraph Agents
+        direction LR
+        A1[Agent 1] --> A2[Agent 2] --> A3[Agent 3]
+    end
+    A3 --> Output[Output]
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Input,Output input
+    class A1,A2,A3 process
+    class Agents transparent
+```
+
+### Hierarchical Process
+
+Uses a manager agent to coordinate task execution and agent assignments.
+
+```mermaid
+graph TB
+    Input[Input] --> Manager
+    
+    subgraph Agents
+        Manager[Manager Agent]
+        
+        subgraph Workers
+            direction LR
+            W1[Worker 1]
+            W2[Worker 2]
+            W3[Worker 3]
+        end
+        
+        Manager --> W1
+        Manager --> W2
+        Manager --> W3
+    end
+    
+    W1 --> Manager
+    W2 --> Manager
+    W3 --> Manager
+    Manager --> Output[Output]
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Input,Output input
+    class Manager,W1,W2,W3 process
+    class Agents,Workers transparent
+```
+
+### Workflow Process
+
+Advanced process type supporting complex task relationships and conditional execution.
+
+```mermaid
+graph LR
+    Input[Input] --> Start
+    
+    subgraph Workflow
+        direction LR
+        Start[Start] --> C1{Condition}
+        C1 --> |Yes| A1[Agent 1]
+        C1 --> |No| A2[Agent 2]
+        A1 --> Join
+        A2 --> Join
+        Join --> A3[Agent 3]
+    end
+    
+    A3 --> Output[Output]
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef decision fill:#2E8B57,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Input,Output input
+    class Start,A1,A2,A3,Join process
+    class C1 decision
+    class Workflow transparent
+```
+
+#### Agentic Routing Workflow
+
+Create AI agents that can dynamically route tasks to specialized LLM instances.
+
+```mermaid
+flowchart LR
+    In[In] --> Router[LLM Call Router]
+    Router --> LLM1[LLM Call 1]
+    Router --> LLM2[LLM Call 2]
+    Router --> LLM3[LLM Call 3]
+    LLM1 --> Out[Out]
+    LLM2 --> Out
+    LLM3 --> Out
+    
+    style In fill:#8B0000,color:#fff
+    style Router fill:#2E8B57,color:#fff
+    style LLM1 fill:#2E8B57,color:#fff
+    style LLM2 fill:#2E8B57,color:#fff
+    style LLM3 fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+#### Agentic Orchestrator Worker
+
+Create AI agents that orchestrate and distribute tasks among specialized workers.
+
+```mermaid
+flowchart LR
+    In[In] --> Router[LLM Call Router]
+    Router --> LLM1[LLM Call 1]
+    Router --> LLM2[LLM Call 2]
+    Router --> LLM3[LLM Call 3]
+    LLM1 --> Synthesizer[Synthesizer]
+    LLM2 --> Synthesizer
+    LLM3 --> Synthesizer
+    Synthesizer --> Out[Out]
+    
+    style In fill:#8B0000,color:#fff
+    style Router fill:#2E8B57,color:#fff
+    style LLM1 fill:#2E8B57,color:#fff
+    style LLM2 fill:#2E8B57,color:#fff
+    style LLM3 fill:#2E8B57,color:#fff
+    style Synthesizer fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+#### Agentic Autonomous Workflow
+
+Create AI agents that can autonomously monitor, act, and adapt based on environment feedback.
+
+```mermaid
+flowchart LR
+    Human[Human] <--> LLM[LLM Call]
+    LLM -->|ACTION| Environment[Environment]
+    Environment -->|FEEDBACK| LLM
+    LLM --> Stop[Stop]
+    
+    style Human fill:#8B0000,color:#fff
+    style LLM fill:#2E8B57,color:#fff
+    style Environment fill:#8B0000,color:#fff
+    style Stop fill:#333,color:#fff
+```
+
+#### Agentic Parallelization
+
+Create AI agents that can execute tasks in parallel for improved performance.
+
+```mermaid
+flowchart LR
+    In[In] --> LLM2[LLM Call 2]
+    In --> LLM1[LLM Call 1]
+    In --> LLM3[LLM Call 3]
+    LLM1 --> Aggregator[Aggregator]
+    LLM2 --> Aggregator
+    LLM3 --> Aggregator
+    Aggregator --> Out[Out]
+    
+    style In fill:#8B0000,color:#fff
+    style LLM1 fill:#2E8B57,color:#fff
+    style LLM2 fill:#2E8B57,color:#fff
+    style LLM3 fill:#2E8B57,color:#fff
+    style Aggregator fill:#fff,color:#000
+    style Out fill:#8B0000,color:#fff
+```
+
+#### Agentic Prompt Chaining
+
+Create AI agents with sequential prompt chaining for complex workflows.
+
+```mermaid
+flowchart LR
+    In[In] --> LLM1[LLM Call 1] --> Gate{Gate}
+    Gate -->|Pass| LLM2[LLM Call 2] -->|Output 2| LLM3[LLM Call 3] --> Out[Out]
+    Gate -->|Fail| Exit[Exit]
+    
+    style In fill:#8B0000,color:#fff
+    style LLM1 fill:#2E8B57,color:#fff
+    style LLM2 fill:#2E8B57,color:#fff
+    style LLM3 fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+    style Exit fill:#8B0000,color:#fff
+```
+
+#### Agentic Evaluator Optimizer
+
+Create AI agents that can generate and optimize solutions through iterative feedback.
+
+```mermaid
+flowchart LR
+    In[In] --> Generator[LLM Call Generator] 
+    Generator -->|SOLUTION| Evaluator[LLM Call Evaluator] -->|ACCEPTED| Out[Out]
+    Evaluator -->|REJECTED + FEEDBACK| Generator
+    
+    style In fill:#8B0000,color:#fff
+    style Generator fill:#2E8B57,color:#fff
+    style Evaluator fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+#### Repetitive Agents
+
+Create AI agents that can efficiently handle repetitive tasks through automated loops.
+
+```mermaid
+flowchart LR
+    In[Input] --> LoopAgent[("Looping Agent")]
+    LoopAgent --> Task[Task]
+    Task --> |Next iteration| LoopAgent
+    Task --> |Done| Out[Output]
+    
+    style In fill:#8B0000,color:#fff
+    style LoopAgent fill:#2E8B57,color:#fff,shape:circle
+    style Task fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+## Adding Models
+
+<div align="center">
+  <a href="https://docs.praison.ai/models">
+    <p align="center">
+      <img src="https://img.shields.io/badge/%F0%9F%93%9A_Models-Visit_docs.praison.ai-blue?style=for-the-badge&logo=bookstack&logoColor=white" alt="Models" />
+    </p>
+  </a>
+</div>
+
+## Ollama Integration
 ```bash
-export OPENAI_API_KEY="Enter your API key"
+export OPENAI_BASE_URL=http://localhost:11434/v1
 ```
 
-Generate your OPENAI API KEY from here: https://platform.openai.com/api-keys
-
-Note: You can use other providers such as Ollama, Mistral ... etc. Details are provided at the bottom.
-
+## Groq Integration
+Replace xxxx with Groq API KEY:
 ```bash
-praisonai --init create a movie script about dog in moon
+export OPENAI_API_KEY=xxxxxxxxxxx
+export OPENAI_BASE_URL=https://api.groq.com/openai/v1
 ```
 
-This will automatically create agents.yaml file in the current directory.
-
-### To initialise with a specific agent framework (Optional):
-
-```bash
-praisonai --framework autogen --init create movie script about cat in mars
-```
-
-## Run
-
-```bash
-praisonai
-```
-
-or
-
-```bash
-python -m praisonai
-```
-
-### Specify the agent framework (Optional):
-
-```bash
-praisonai --framework autogen
-```
-
-### Full Automatic Mode
-
-```bash
-praisonai --auto create a movie script about Dog in Moon
-```
-
-## User Interface
-
-## PraisonAI User Interfaces:
-
-| Interface | Description                                | URL                                                                   |
-| --------- | ------------------------------------------ | --------------------------------------------------------------------- |
-| **UI**    | Multi Agents such as CrewAI or AutoGen     | [https://docs.praisonai.com/ui/ui](https://docs.praison.ai/ui/ui)     |
-| **Chat**  | Chat with 100+ LLMs, single AI Agent       | [https://docs.praisonai.com/ui/chat](https://docs.praison.ai/ui/chat) |
-| **Code**  | Chat with entire Codebase, single AI Agent | [https://docs.praisonai.com/ui/code](https://docs.praison.ai/ui/code) |
-
-```bash
-pip install -U "praisonai[ui]"
-export OPENAI_API_KEY="Enter your API key"
-chainlit create-secret
-export CHAINLIT_AUTH_SECRET=xxxxxxxx
-praisonai ui
-```
-
-or
-
-```
-python -m praisonai ui
-```
-
-## Praison AI Chat
-
-- https://docs.praison.ai/chat/
-
-```bash
-pip install "praisonai[chat]"
-export OPENAI_API_KEY="Enter your API key"
-praisonai chat
-```
-
-### Internet Search
-
-Praison AI Chat and Praison AI Code now includes internet search capabilities using Crawl4AI and Tavily, allowing you to retrieve up-to-date information during your conversations.
-
-### Vision Language Model Support
-
-You can now upload images and ask questions based on them using Vision Language Models. This feature enables visual understanding and analysis within your chat sessions.
-
-## Praison AI Code
-
-```bash
-pip install "praisonai[code]"
-export OPENAI_API_KEY="Enter your API key"
-praisonai code
-```
-
-### Internet Search
-
-Praison AI Code also includes internet search functionality, enabling you to find relevant code snippets and programming information online.
-
-## Create Custom Tools
-
-- https://docs.praison.ai/tools/custom/
+## No Code Options
 
 ## Agents Playbook
 
 ### Simple Playbook Example
 
+Create `agents.yaml` file and add the code below:
+
 ```yaml
-framework: crewai
+framework: praisonai
 topic: Artificial Intelligence
 roles:
   screenwriter:
@@ -296,90 +503,27 @@ roles:
         expected_output: "Complete script ready for production."
 ```
 
+*To run the playbook:*
+```bash
+praisonai agents.yaml
+```
+
 ## Use 100+ Models
 
 - https://docs.praison.ai/models/
+<div align="center">
+  <a href="https://docs.praison.ai">
+    <p align="center">
+      <img src="https://img.shields.io/badge/📚_Documentation-Visit_docs.praison.ai-blue?style=for-the-badge&logo=bookstack&logoColor=white" alt="Documentation" />
+    </p>
+  </a>
+</div>
 
-## Include praisonai package in your project
+## Development:
 
-- https://docs.praison.ai/developers/wrapper
-- https://docs.praison.ai/developers/wrapper-tools/
+Below is used for development only.
 
-## Option 1: Using RAW YAML
-
-```python
-from praisonai import PraisonAI
-
-# Example agent_yaml content
-agent_yaml = """
-framework: "crewai"
-topic: "Space Exploration"
-
-roles:
-  astronomer:
-    role: "Space Researcher"
-    goal: "Discover new insights about {topic}"
-    backstory: "You are a curious and dedicated astronomer with a passion for unraveling the mysteries of the cosmos."
-    tasks:
-      investigate_exoplanets:
-        description: "Research and compile information about exoplanets discovered in the last decade."
-        expected_output: "A summarized report on exoplanet discoveries, including their size, potential habitability, and distance from Earth."
-"""
-
-# Create a PraisonAI instance with the agent_yaml content
-praisonai = PraisonAI(agent_yaml=agent_yaml)
-
-# Run PraisonAI
-result = praisonai.run()
-
-# Print the result
-print(result)
-```
-
-## Option 2: Using separate agents.yaml file
-
-Note: Please create agents.yaml file before hand.
-
-```python
-from praisonai import PraisonAI
-
-def basic(): # Basic Mode
-    praisonai = PraisonAI(agent_file="agents.yaml")
-    praisonai.run()
-
-if __name__ == "__main__":
-    basic()
-```
-
-## Commands to Install Dependencies:
-
-1. **Install all dependencies, including dev dependencies:**
-
-   ```sh
-   poetry install
-   ```
-
-2. **Install only documentation dependencies:**
-
-   ```sh
-   poetry install --with docs
-   ```
-
-3. **Install only test dependencies:**
-
-   ```sh
-   poetry install --with test
-   ```
-
-4. **Install only dev dependencies:**
-
-   ```sh
-   poetry install --with dev
-   ```
-
-This configuration ensures that your development dependencies are correctly categorized and installed as needed.
-
-### Using uv (Fast Python Package Installer)
+### Using uv
 ```bash
 # Install uv if you haven't already
 pip install uv
@@ -402,18 +546,34 @@ uv pip install -r pyproject.toml --extra "crewai,autogen"
 - Submit a pull request via GitHub's web interface.
 - Await feedback from project maintainers.
 
+## Other Features
+
+- 🔄 Use CrewAI or AG2 (Formerly AutoGen) Framework
+- 💻 Chat with ENTIRE Codebase
+- 🎨 Interactive UIs
+- 📄 YAML-based Configuration
+- 🛠️ Custom Tool Integration
+- 🔍 Internet Search Capability (using Crawl4AI and Tavily)
+- 🖼️ 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)
 
-## License
-
-Praison AI is an open-sourced software licensed under the **[MIT license](https://opensource.org/licenses/MIT)**.
-
 ## Video Tutorials
 
 | Topic | Video |
 |-------|--------|
+| AI Agents with Self Reflection | [![Self Reflection](https://img.youtube.com/vi/vLXobEN2Vc8/0.jpg)](https://www.youtube.com/watch?v=vLXobEN2Vc8) |
+| Reasoning Data Generating Agent | [![Reasoning Data](https://img.youtube.com/vi/fUT332Y2zA8/0.jpg)](https://www.youtube.com/watch?v=fUT332Y2zA8) |
+| AI Agents with Reasoning | [![Reasoning](https://img.youtube.com/vi/KNDVWGN3TpM/0.jpg)](https://www.youtube.com/watch?v=KNDVWGN3TpM) |
+| Multimodal AI Agents | [![Multimodal](https://img.youtube.com/vi/hjAWmUT1qqY/0.jpg)](https://www.youtube.com/watch?v=hjAWmUT1qqY) |
+| AI Agents Workflow | [![Workflow](https://img.youtube.com/vi/yWTH44QPl2A/0.jpg)](https://www.youtube.com/watch?v=yWTH44QPl2A) |
+| Async AI Agents | [![Async](https://img.youtube.com/vi/VhVQfgo00LE/0.jpg)](https://www.youtube.com/watch?v=VhVQfgo00LE) |
+| Mini AI Agents | [![Mini](https://img.youtube.com/vi/OkvYp5aAGSg/0.jpg)](https://www.youtube.com/watch?v=OkvYp5aAGSg) |
+| AI Agents with Memory | [![Memory](https://img.youtube.com/vi/1hVfVxvPnnQ/0.jpg)](https://www.youtube.com/watch?v=1hVfVxvPnnQ) |
+| Repetitive Agents | [![Repetitive](https://img.youtube.com/vi/dAYGxsjDOPg/0.jpg)](https://www.youtube.com/watch?v=dAYGxsjDOPg) |
 | Introduction | [![Introduction](https://img.youtube.com/vi/Fn1lQjC0GO0/0.jpg)](https://www.youtube.com/watch?v=Fn1lQjC0GO0) |
 | Tools Overview | [![Tools Overview](https://img.youtube.com/vi/XaQRgRpV7jo/0.jpg)](https://www.youtube.com/watch?v=XaQRgRpV7jo) |
 | Custom Tools | [![Custom Tools](https://img.youtube.com/vi/JSU2Rndh06c/0.jpg)](https://www.youtube.com/watch?v=JSU2Rndh06c) |
@@ -426,7 +586,5 @@ Praison AI is an open-sourced software licensed under the **[MIT license](https:
 | Training | [![Training](https://img.youtube.com/vi/aLawE8kwCrI/0.jpg)](https://www.youtube.com/watch?v=aLawE8kwCrI) |
 | Realtime Voice Interface | [![Realtime](https://img.youtube.com/vi/frRHfevTCSw/0.jpg)](https://www.youtube.com/watch?v=frRHfevTCSw) |
 | Call Interface | [![Call](https://img.youtube.com/vi/m1cwrUG2iAk/0.jpg)](https://www.youtube.com/watch?v=m1cwrUG2iAk) |
+| Reasoning Extract Agents | [![Reasoning Extract](https://img.youtube.com/vi/2PPamsADjJA/0.jpg)](https://www.youtube.com/watch?v=2PPamsADjJA) |
 
-## License
-
-Praison AI is an open-sourced software licensed under the **[MIT license](https://opensource.org/licenses/MIT)**.

agents.yaml

@@ -1,18 +1,22 @@
-framework: autogen
+framework: praisonai
+process: sequential
 topic: create movie script about cat in mars
+memory: false
 roles:
   researcher:
     backstory: Skilled in research, with a focus on gathering accurate and relevant
       information.
     goal: Gather information about Mars and cats
     role: Researcher
+    min_reflect: 1
+    max_reflect: 2
     tasks:
       research_task:
         description: Research about Mars, its environment, and the feasibility of
           a cat being on Mars. Also, research about cat behavior and characteristics.
         expected_output: Document with research findings on Mars and cats.
     tools:
-    - ''
+    - search_tool
   narrative_designer:
     backstory: Skilled in narrative development, with a focus on creating engaging
       stories.
@@ -37,4 +41,4 @@ roles:
         expected_output: Final movie script with dialogue and scene details.
     tools:
     - ''
-dependencies: []
+dependencies: []

chainlit.md

@@ -1 +0,0 @@
-# Welcome to Praison AI! 🚀🤖

cookbooks/agents_playbook/agents-scrapewebitetool.yaml

@@ -1,42 +0,0 @@
-framework: crewai
-topic: create a movie about cat in mars based on https://blog.celtx.com/how-to-write-a-good-story/
-roles:
-  story_developer:
-    backstory: Experienced in crafting compelling narratives for a diverse audience.
-    goal: Develop an engaging storyline for a movie about cats in Mars
-    role: Story Developer
-    tasks:
-      storyline_creation:
-        description: Create a captivating storyline for a movie about cats in Mars
-          inspired by the blog post at https://blog.celtx.com/how-to-write-a-good-story/
-        expected_output: Detailed storyline with key plot points, character motivations,
-          and setting descriptions.
-    tools:
-    - 'ScrapeWebsiteTool'
-  screenwriter:
-    backstory: Proficient in translating complex narratives into engaging screenplay
-      format.
-    goal: Transform the storyline into a script
-    role: Screenwriter
-    tasks:
-      script_creation:
-        description: Transform the developed storyline into a script for the movie
-          about cats in Mars.
-        expected_output: Complete script with dialogues, scenes, and stage directions
-          ready for production.
-    tools:
-    - ''
-  director:
-    backstory: Experienced in visual storytelling and bringing scripts to life on
-      screen.
-    goal: Oversee the production of the movie
-    role: Director
-    tasks:
-      movie_production:
-        description: Take the script and lead the team to produce the movie 'Cats
-          in Mars' based on the provided content and script.
-        expected_output: Completed movie ready for distribution with compelling visuals
-          and engaging storytelling.
-    tools:
-    - ''
-dependencies: []

cookbooks/agents_playbook/create-movie-agents.yaml

@@ -1,42 +0,0 @@
-framework: crewai
-topic: create a movie about cat in mars based on https://www.grammarly.com/blog/how-to-write-a-story/
-roles:
-  story_developer:
-    backstory: Experienced in crafting compelling narratives for a diverse audience.
-    goal: Develop an engaging storyline for a movie about cats in Mars
-    role: Story Developer
-    tasks:
-      storyline_creation:
-        description: Create a captivating storyline for a movie about cats in Mars
-          inspired by the blog post at https://www.grammarly.com/blog/how-to-write-a-story/
-        expected_output: Detailed storyline with key plot points, character motivations,
-          and setting descriptions.
-    tools:
-    - 'ScrapeWebsiteTool'
-  screenwriter:
-    backstory: Proficient in translating complex narratives into engaging screenplay
-      format.
-    goal: Transform the storyline into a script
-    role: Screenwriter
-    tasks:
-      script_creation:
-        description: Transform the developed storyline into a script for the movie
-          about cats in Mars.
-        expected_output: Complete script with dialogues, scenes, and stage directions
-          ready for production.
-    tools:
-    - ''
-  director:
-    backstory: Experienced in visual storytelling and bringing scripts to life on
-      screen.
-    goal: Oversee the production of the movie
-    role: Director
-    tasks:
-      movie_production:
-        description: Take the script and lead the team to produce the movie 'Cats
-          in Mars' based on the provided content and script.
-        expected_output: Completed movie ready for distribution with compelling visuals
-          and engaging storytelling.
-    tools:
-    - ''
-dependencies: []

cookbooks/agents_playbook/examples/researchers.yml

@@ -1,41 +0,0 @@
-framework: "crewai"
-topic: "Artificial Intelligence"
-
-roles:
-  researcher:
-    role: "Senior Data Researcher"
-    goal: "Uncover cutting-edge developments in {topic}"
-    backstory: > 
-      You're a seasoned researcher with a knack for uncovering the latest
-      developments in {topic}. Known for your ability to find the most relevant
-      information and present it in a clear and concise manner.
-    tools:
-      - search_tool: 
-          engine: google
-    tasks:
-      research_task:
-        description: >
-          Conduct thorough research about {topic}, focusing on the latest 
-          trends and technologies.
-        expected_output: > 
-          A list of 10 bullet points summarizing key findings with links to 
-          relevant sources. 
-
-  reporting_analyst:
-    role: "Reporting Analyst"
-    goal: "Create detailed reports based on {topic} data analysis and research findings."
-    backstory: >
-      You're a meticulous analyst with a keen eye for detail. You're known for 
-      your ability to turn complex data into clear and concise reports, making 
-      it easy for others to understand and act on the information you provide.
-    tasks:
-      reporting_task:
-        description: >
-          Review the research findings and create a comprehensive report on 
-          {topic}. Include insights, potential opportunities, and recommendations.
-        expected_output: >
-          A well-structured report in Markdown format, ready for distribution.
-
-dependencies:
- - task: reporting_task
-   depends_on: research_task  

cookbooks/agents_playbook/examples/scriptwriters.yml

@@ -1,41 +0,0 @@
-framework: "autogen"
-topic: "Artificial Intelligence"
-
-roles:
-  narrative_designer:
-    role: "Narrative Designer"
-    goal: "Craft engaging storylines and narratives for {topic}"
-    backstory: >
-      You're a creative visionary skilled in weaving complex narratives and 
-      developing engaging story worlds within {topic}. Your expertise lies in 
-      conceptualizing the overarching story and ensuring it resonates with the audience.
-    tasks:
-      story_concept_development:
-        description: >
-          Develop a compelling story concept for {topic}, focusing on originality, 
-          thematic depth, and audience engagement. Outline the main narrative arcs,
-          characters, and settings.
-        expected_output: >
-          A comprehensive document outlining the story concept, including key narrative 
-          arcs, character bios, and settings descriptions.
-
-  scriptwriter:
-    role: "Scriptwriter"
-    goal: "Transform story concepts into detailed scripts for {topic}"
-    backstory: >
-      With a flair for dialogue and a deep understanding of pacing and structure,
-      you excel at bringing narratives to life through scriptwriting. Your work 
-      turns story concepts into blueprints for compelling {topic} experiences.
-    tasks:
-      scriptwriting_task:
-        description: >
-          Based on the narrative concept, write a detailed script for {topic}. 
-          Include dialogue, stage directions, and scene descriptions that bring 
-          the story to life.
-        expected_output: >
-          A detailed script ready for production, including dialogue, stage 
-          directions, and scene descriptions.
-
-dependencies:
- - task: scriptwriting_task
-   depends_on: story_concept_development  

cookbooks/agents_playbook/finance-research.yaml

@@ -1,43 +0,0 @@
-framework: crewai
-topic: research about nvidia growth
-roles:
-  data_collector:
-    backstory: An experienced researcher with the ability to efficiently collect and
-      organize vast amounts of data.
-    goal: Gather information on Nvidia's growth
-    role: Data Collector
-    tasks:
-      data_collection_task:
-        description: Collect data on Nvidia's growth from various sources such as
-          financial reports, news articles, and company announcements.
-        expected_output: A comprehensive document detailing data points on Nvidia's
-          growth over the years.
-    tools:
-    - 'YouSearchTool'
-  data_analyst:
-    backstory: Specializes in extracting insights from large datasets, proficient
-      in quantitative and qualitative analysis.
-    goal: Analyze the collected data to identify trends and patterns
-    role: Data Analyst
-    tasks:
-      data_analysis_task:
-        description: Analyze the collected data to identify key trends and patterns
-          in Nvidia's growth.
-        expected_output: An analytical report summarizing trends, patterns, and key
-          growth metrics of Nvidia.
-    tools:
-    - ''
-  report_preparer:
-    backstory: Experienced in creating detailed reports and presentations, turning
-      analytical data into actionable insights.
-    goal: Generate a final report on Nvidia's growth
-    role: Report Preparer
-    tasks:
-      report_preparation_task:
-        description: Create a detailed report based on the analysis, highlighting
-          Nvidia's growth trajectory.
-        expected_output: A polished, comprehensive report summarizing Nvidia's growth
-          with visual aids and key insights.
-    tools:
-    - ''
-dependencies: []

cookbooks/agents_playbook/internet-research-agents.yaml

@@ -1,26 +0,0 @@
-framework: crewai
-topic: research about the latest AI News and prepare a detailed report
-roles:
-  research_analyst:
-    backstory: Experienced in gathering and analyzing data related to AI news trends.
-    goal: Analyze AI News trends
-    role: Research Analyst
-    tasks:
-      gather_data:
-        description: Conduct in-depth research on the latest AI News trends from reputable
-          sources.
-        expected_output: Comprehensive report on current AI News trends.
-    tools:
-    - 'InternetSearchTool'
-  content_creator:
-    backstory: Skilled in writing informative and engaging content about AI News.
-    goal: Create detailed reports on AI News
-    role: Content Creator
-    tasks:
-      compile_report:
-        description: Compile all gathered data into a detailed report with analysis
-          and insights.
-        expected_output: Well-structured report on the latest AI News with key insights.
-    tools:
-    - ''
-dependencies: []

cookbooks/agents_playbook/medical-research-pubmed-agents.yaml

@@ -1,39 +0,0 @@
-framework: crewai
-topic: research about the causes of lung disease
-roles:
-  research_analyst:
-    backstory: Experienced in analyzing scientific data related to respiratory health.
-    goal: Analyze data on lung diseases
-    role: Research Analyst
-    tasks:
-      data_analysis:
-        description: Gather and analyze data on the causes and risk factors of lung
-          diseases.
-        expected_output: Report detailing key findings on lung disease causes.
-    tools:
-    - 'PubmedQueryRun'
-  medical_writer:
-    backstory: Skilled in translating complex medical information into accessible
-      content.
-    goal: Compile comprehensive content on lung disease causes
-    role: Medical Writer
-    tasks:
-      content_creation:
-        description: Create detailed content summarizing the research findings on
-          lung disease causes.
-        expected_output: Document outlining various causes and risk factors of lung
-          diseases.
-    tools:
-    - ''
-  editor:
-    backstory: Proficient in editing medical content for accuracy and clarity.
-    goal: Review and refine content on lung disease causes
-    role: Editor
-    tasks:
-      content_review:
-        description: Edit and refine the compiled content on lung disease causes for
-          accuracy and coherence.
-        expected_output: Finalized document on lung disease causes ready for dissemination.
-    tools:
-    - ''
-dependencies: []

cookbooks/praisonai-googlecolab.ipynb

@@ -1,311 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": 1,
-      "metadata": {
-        "id": "cW47IVIvdyii",
-        "outputId": "dad73c8c-7506-440b-da37-8d8b21f7813f",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        }
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "\u001b[?25l     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/173.7 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m173.7/173.7 kB\u001b[0m \u001b[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
-            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
-            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.9/40.9 kB\u001b[0m \u001b[31m3.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.3/67.3 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
-            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
-            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
-            "\u001b[33mWARNING: embedchain 0.1.124 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.124 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.123 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.123 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.122 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.122 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.121 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.121 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.120 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.120 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.119 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.119 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.118 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.118 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.117 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.117 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m160.7/160.7 kB\u001b[0m \u001b[31m11.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.2/76.2 kB\u001b[0m \u001b[31m7.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.2/50.2 kB\u001b[0m \u001b[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m54.3/54.3 kB\u001b[0m \u001b[31m4.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m47.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m525.5/525.5 kB\u001b[0m \u001b[31m40.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.4/2.4 MB\u001b[0m \u001b[31m72.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m55.3/55.3 kB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m202.6/202.6 kB\u001b[0m \u001b[31m19.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m327.6/327.6 kB\u001b[0m \u001b[31m30.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m115.1/115.1 kB\u001b[0m \u001b[31m11.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.6/21.6 MB\u001b[0m \u001b[31m73.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m64.0/64.0 kB\u001b[0m \u001b[31m4.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m52.5/52.5 kB\u001b[0m \u001b[31m4.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m110.5/110.5 kB\u001b[0m \u001b[31m10.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m149.7/149.7 kB\u001b[0m \u001b[31m13.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m342.3/342.3 kB\u001b[0m \u001b[31m29.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.6/57.6 kB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m774.0/774.0 kB\u001b[0m \u001b[31m42.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.7/9.7 MB\u001b[0m \u001b[31m38.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m233.2/233.2 kB\u001b[0m \u001b[31m19.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m273.8/273.8 kB\u001b[0m \u001b[31m19.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m172.8/172.8 kB\u001b[0m \u001b[31m13.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.7/67.7 kB\u001b[0m \u001b[31m5.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m94.7/94.7 kB\u001b[0m \u001b[31m7.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m131.6/131.6 kB\u001b[0m \u001b[31m10.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.9/1.9 MB\u001b[0m \u001b[31m67.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m71.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m302.9/302.9 kB\u001b[0m \u001b[31m23.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m93.2/93.2 kB\u001b[0m \u001b[31m8.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.2/13.2 MB\u001b[0m \u001b[31m88.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m53.0/53.0 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m54.4/54.4 kB\u001b[0m \u001b[31m4.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.4/5.4 MB\u001b[0m \u001b[31m85.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m342.2/342.2 kB\u001b[0m \u001b[31m28.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m295.8/295.8 kB\u001b[0m \u001b[31m22.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.1/71.1 kB\u001b[0m \u001b[31m6.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.1 MB\u001b[0m \u001b[31m58.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m481.7/481.7 kB\u001b[0m \u001b[31m34.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m63.7/63.7 kB\u001b[0m \u001b[31m6.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.0/3.0 MB\u001b[0m \u001b[31m81.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m254.9/254.9 kB\u001b[0m \u001b[31m23.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m248.1/248.1 kB\u001b[0m \u001b[31m23.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m442.1/442.1 kB\u001b[0m \u001b[31m36.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.5/49.5 kB\u001b[0m \u001b[31m4.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m98.7/98.7 kB\u001b[0m \u001b[31m9.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m856.7/856.7 kB\u001b[0m \u001b[31m48.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m73.3/73.3 kB\u001b[0m \u001b[31m7.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m14.0/14.0 MB\u001b[0m \u001b[31m75.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.8/3.8 MB\u001b[0m \u001b[31m91.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m425.7/425.7 kB\u001b[0m \u001b[31m32.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m164.1/164.1 kB\u001b[0m \u001b[31m14.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.0/3.0 MB\u001b[0m \u001b[31m78.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m3.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m78.6/78.6 kB\u001b[0m \u001b[31m7.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.4/194.4 kB\u001b[0m \u001b[31m18.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.3/2.3 MB\u001b[0m \u001b[31m72.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m80.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m8.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.7/1.7 MB\u001b[0m \u001b[31m67.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Building wheel for praisonai (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Building wheel for docx2txt (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Building wheel for pypika (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n"
-          ]
-        }
-      ],
-      "source": [
-        "!pip install -Uq \"praisonai[crewai]\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 3,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 1000
-        },
-        "id": "myh-_QCuHfOs",
-        "outputId": "5384b8e0-e56c-4833-a829-2593ba6c6393"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "\u001b[1m\u001b[95m [2024-10-31 21:43:52][DEBUG]: == Working Agent: Space Researcher\u001b[00m\n",
-            "\u001b[1m\u001b[95m [2024-10-31 21:43:52][INFO]: == Starting Task: Research and compile information about exoplanets discovered in the last decade.\u001b[00m\n",
-            "\n",
-            "\n",
-            "\u001b[1m> Entering new CrewAgentExecutor chain...\u001b[0m\n",
-            "\u001b[32;1m\u001b[1;3mThought: I now can give a great answer  \n",
-            "Final Answer: my best complete final answer to the task.  \n",
-            "Over the last decade, the field of exoplanet research has experienced remarkable advancements, leading to the discovery of thousands of new planets beyond our solar system. Here is a summarized report on some of the most significant exoplanet discoveries in terms of their size, potential habitability, and distance from Earth:\n",
-            "\n",
-            "1. **Kepler-452b**: Discovered in 2015 by NASA's Kepler mission, Kepler-452b is often referred to as Earth's \"cousin.\" It is about 1.6 times the size of Earth and orbits within the habitable zone of a G-type star similar to our Sun, located approximately 1,400 light-years away from Earth. Its potential for hosting life lies in its Earth-like characteristics, though its actual habitability remains uncertain due to its distance and lack of detailed atmospheric data.\n",
-            "\n",
-            "2. **Proxima Centauri b**: Found in 2016, this exoplanet orbits the closest star to our solar system, Proxima Centauri, at a distance of just 4.24 light-years. Proxima Centauri b is roughly 1.27 times the size of Earth and resides within the star's habitable zone, where liquid water could potentially exist. Its proximity makes it a prime candidate for future studies on habitability and atmospheric composition.\n",
-            "\n",
-            "3. **TRAPPIST-1 System**: Discovered in 2017, the TRAPPIST-1 system contains seven Earth-sized exoplanets, three of which lie in the star's habitable zone. Located about 39 light-years away, these planets are of significant interest due to their potential for liquid water. The compact nature of the system and the small, cool star around which they orbit make them excellent targets for atmospheric studies using telescopes like the James Webb Space Telescope.\n",
-            "\n",
-            "4. **LHS 1140 b**: This exoplanet was discovered in 2017 and is located approximately 41 light-years away. It is about 1.4 times the size of Earth and orbits within the habitable zone of a red dwarf star. Its dense, rocky composition and the presence of a substantial atmosphere make it a compelling candidate for habitability studies.\n",
-            "\n",
-            "5. **K2-18b**: Announced in 2019, K2-18b is situated 124 light-years from Earth and is a super-Earth with a mass about 8 times that of our planet. It orbits within the habitable zone of its star, and water vapor has been detected in its atmosphere, making it one of the most intriguing exoplanets in terms of potential habitability.\n",
-            "\n",
-            "These discoveries highlight the diversity of exoplanets in terms of size, composition, and orbit, as well as the progress made in identifying worlds that could potentially host life. Advances in technology and observational techniques continue to enhance our understanding of these distant worlds, bringing us closer to answering the age-old question of whether we are alone in the universe.\u001b[0m\n",
-            "\n",
-            "\u001b[1m> Finished chain.\u001b[0m\n",
-            "\u001b[1m\u001b[92m [2024-10-31 21:44:05][DEBUG]: == [Space Researcher] Task output: my best complete final answer to the task.  \n",
-            "Over the last decade, the field of exoplanet research has experienced remarkable advancements, leading to the discovery of thousands of new planets beyond our solar system. Here is a summarized report on some of the most significant exoplanet discoveries in terms of their size, potential habitability, and distance from Earth:\n",
-            "\n",
-            "1. **Kepler-452b**: Discovered in 2015 by NASA's Kepler mission, Kepler-452b is often referred to as Earth's \"cousin.\" It is about 1.6 times the size of Earth and orbits within the habitable zone of a G-type star similar to our Sun, located approximately 1,400 light-years away from Earth. Its potential for hosting life lies in its Earth-like characteristics, though its actual habitability remains uncertain due to its distance and lack of detailed atmospheric data.\n",
-            "\n",
-            "2. **Proxima Centauri b**: Found in 2016, this exoplanet orbits the closest star to our solar system, Proxima Centauri, at a distance of just 4.24 light-years. Proxima Centauri b is roughly 1.27 times the size of Earth and resides within the star's habitable zone, where liquid water could potentially exist. Its proximity makes it a prime candidate for future studies on habitability and atmospheric composition.\n",
-            "\n",
-            "3. **TRAPPIST-1 System**: Discovered in 2017, the TRAPPIST-1 system contains seven Earth-sized exoplanets, three of which lie in the star's habitable zone. Located about 39 light-years away, these planets are of significant interest due to their potential for liquid water. The compact nature of the system and the small, cool star around which they orbit make them excellent targets for atmospheric studies using telescopes like the James Webb Space Telescope.\n",
-            "\n",
-            "4. **LHS 1140 b**: This exoplanet was discovered in 2017 and is located approximately 41 light-years away. It is about 1.4 times the size of Earth and orbits within the habitable zone of a red dwarf star. Its dense, rocky composition and the presence of a substantial atmosphere make it a compelling candidate for habitability studies.\n",
-            "\n",
-            "5. **K2-18b**: Announced in 2019, K2-18b is situated 124 light-years from Earth and is a super-Earth with a mass about 8 times that of our planet. It orbits within the habitable zone of its star, and water vapor has been detected in its atmosphere, making it one of the most intriguing exoplanets in terms of potential habitability.\n",
-            "\n",
-            "These discoveries highlight the diversity of exoplanets in terms of size, composition, and orbit, as well as the progress made in identifying worlds that could potentially host life. Advances in technology and observational techniques continue to enhance our understanding of these distant worlds, bringing us closer to answering the age-old question of whether we are alone in the universe.\n",
-            "\n",
-            "\u001b[00m\n"
-          ]
-        },
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "### Task Output ###\n",
-              "my best complete final answer to the task.  \n",
-              "Over the last decade, the field of exoplanet research has experienced remarkable advancements, leading to the \n",
-              "discovery of thousands of new planets beyond our solar system. Here is a summarized report on some of the most \n",
-              "significant exoplanet discoveries in terms of their size, potential habitability, and distance from Earth:\n",
-              "\n",
-              "\u001b[1;36m1\u001b[0m. **Kepler-452b**: Discovered in \u001b[1;36m2015\u001b[0m by NASA's Kepler mission, Kepler-452b is often referred to as Earth's \n",
-              "\u001b[32m\"cousin.\"\u001b[0m It is about \u001b[1;36m1.6\u001b[0m times the size of Earth and orbits within the habitable zone of a G-type star similar to \n",
-              "our Sun, located approximately \u001b[1;36m1\u001b[0m,\u001b[1;36m400\u001b[0m light-years away from Earth. Its potential for hosting life lies in its \n",
-              "Earth-like characteristics, though its actual habitability remains uncertain due to its distance and lack of \n",
-              "detailed atmospheric data.\n",
-              "\n",
-              "\u001b[1;36m2\u001b[0m. **Proxima Centauri b**: Found in \u001b[1;36m2016\u001b[0m, this exoplanet orbits the closest star to our solar system, Proxima \n",
-              "Centauri, at a distance of just \u001b[1;36m4.24\u001b[0m light-years. Proxima Centauri b is roughly \u001b[1;36m1.27\u001b[0m times the size of Earth and \n",
-              "resides within the star's habitable zone, where liquid water could potentially exist. Its proximity makes it a \n",
-              "prime candidate for future studies on habitability and atmospheric composition.\n",
-              "\n",
-              "\u001b[1;36m3\u001b[0m. **TRAPPIST-\u001b[1;36m1\u001b[0m System**: Discovered in \u001b[1;36m2017\u001b[0m, the TRAPPIST-\u001b[1;36m1\u001b[0m system contains seven Earth-sized exoplanets, three of\n",
-              "which lie in the star's habitable zone. Located about \u001b[1;36m39\u001b[0m light-years away, these planets are of significant \n",
-              "interest due to their potential for liquid water. The compact nature of the system and the small, cool star around \n",
-              "which they orbit make them excellent targets for atmospheric studies using telescopes like the James Webb Space \n",
-              "Telescope.\n",
-              "\n",
-              "\u001b[1;36m4\u001b[0m. **LHS \u001b[1;36m1140\u001b[0m b**: This exoplanet was discovered in \u001b[1;36m2017\u001b[0m and is located approximately \u001b[1;36m41\u001b[0m light-years away. It is \n",
-              "about \u001b[1;36m1.4\u001b[0m times the size of Earth and orbits within the habitable zone of a red dwarf star. Its dense, rocky \n",
-              "composition and the presence of a substantial atmosphere make it a compelling candidate for habitability studies.\n",
-              "\n",
-              "\u001b[1;36m5\u001b[0m. **K2-18b**: Announced in \u001b[1;36m2019\u001b[0m, K2-18b is situated \u001b[1;36m124\u001b[0m light-years from Earth and is a super-Earth with a mass \n",
-              "about \u001b[1;36m8\u001b[0m times that of our planet. It orbits within the habitable zone of its star, and water vapor has been \n",
-              "detected in its atmosphere, making it one of the most intriguing exoplanets in terms of potential habitability.\n",
-              "\n",
-              "These discoveries highlight the diversity of exoplanets in terms of size, composition, and orbit, as well as the \n",
-              "progress made in identifying worlds that could potentially host life. Advances in technology and observational \n",
-              "techniques continue to enhance our understanding of these distant worlds, bringing us closer to answering the \n",
-              "age-old question of whether we are alone in the universe.\n"
-            ],
-            "text/html": [
-              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">### Task Output ###\n",
-              "my best complete final answer to the task.  \n",
-              "Over the last decade, the field of exoplanet research has experienced remarkable advancements, leading to the \n",
-              "discovery of thousands of new planets beyond our solar system. Here is a summarized report on some of the most \n",
-              "significant exoplanet discoveries in terms of their size, potential habitability, and distance from Earth:\n",
-              "\n",
-              "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1</span>. **Kepler-452b**: Discovered in <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2015</span> by NASA's Kepler mission, Kepler-452b is often referred to as Earth's \n",
-              "<span style=\"color: #008000; text-decoration-color: #008000\">\"cousin.\"</span> It is about <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.6</span> times the size of Earth and orbits within the habitable zone of a G-type star similar to \n",
-              "our Sun, located approximately <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1</span>,<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">400</span> light-years away from Earth. Its potential for hosting life lies in its \n",
-              "Earth-like characteristics, though its actual habitability remains uncertain due to its distance and lack of \n",
-              "detailed atmospheric data.\n",
-              "\n",
-              "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2</span>. **Proxima Centauri b**: Found in <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2016</span>, this exoplanet orbits the closest star to our solar system, Proxima \n",
-              "Centauri, at a distance of just <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">4.24</span> light-years. Proxima Centauri b is roughly <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.27</span> times the size of Earth and \n",
-              "resides within the star's habitable zone, where liquid water could potentially exist. Its proximity makes it a \n",
-              "prime candidate for future studies on habitability and atmospheric composition.\n",
-              "\n",
-              "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>. **TRAPPIST-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1</span> System**: Discovered in <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2017</span>, the TRAPPIST-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1</span> system contains seven Earth-sized exoplanets, three of\n",
-              "which lie in the star's habitable zone. Located about <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">39</span> light-years away, these planets are of significant \n",
-              "interest due to their potential for liquid water. The compact nature of the system and the small, cool star around \n",
-              "which they orbit make them excellent targets for atmospheric studies using telescopes like the James Webb Space \n",
-              "Telescope.\n",
-              "\n",
-              "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">4</span>. **LHS <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1140</span> b**: This exoplanet was discovered in <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2017</span> and is located approximately <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">41</span> light-years away. It is \n",
-              "about <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.4</span> times the size of Earth and orbits within the habitable zone of a red dwarf star. Its dense, rocky \n",
-              "composition and the presence of a substantial atmosphere make it a compelling candidate for habitability studies.\n",
-              "\n",
-              "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">5</span>. **K2-18b**: Announced in <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2019</span>, K2-18b is situated <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">124</span> light-years from Earth and is a super-Earth with a mass \n",
-              "about <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">8</span> times that of our planet. It orbits within the habitable zone of its star, and water vapor has been \n",
-              "detected in its atmosphere, making it one of the most intriguing exoplanets in terms of potential habitability.\n",
-              "\n",
-              "These discoveries highlight the diversity of exoplanets in terms of size, composition, and orbit, as well as the \n",
-              "progress made in identifying worlds that could potentially host life. Advances in technology and observational \n",
-              "techniques continue to enhance our understanding of these distant worlds, bringing us closer to answering the \n",
-              "age-old question of whether we are alone in the universe.\n",
-              "</pre>\n"
-            ]
-          },
-          "metadata": {}
-        },
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "None\n"
-          ]
-        }
-      ],
-      "source": [
-        "import os\n",
-        "import yaml\n",
-        "from praisonai import PraisonAI\n",
-        "from google.colab import userdata\n",
-        "\n",
-        "# Example agent_yaml content\n",
-        "agent_yaml = \"\"\"\n",
-        "framework: \"crewai\"\n",
-        "topic: \"Space Exploration\"\n",
-        "\n",
-        "roles:\n",
-        "  astronomer:\n",
-        "    role: \"Space Researcher\"\n",
-        "    goal: \"Discover new insights about {topic}\"\n",
-        "    backstory: \"You are a curious and dedicated astronomer with a passion for unraveling the mysteries of the cosmos.\"\n",
-        "    tasks:\n",
-        "      investigate_exoplanets:\n",
-        "        description: \"Research and compile information about exoplanets discovered in the last decade.\"\n",
-        "        expected_output: \"A summarized report on exoplanet discoveries, including their size, potential habitability, and distance from Earth.\"\n",
-        "\"\"\"\n",
-        "\n",
-        "# Create a PraisonAI instance with the agent_yaml content\n",
-        "praisonai = PraisonAI(agent_yaml=agent_yaml)\n",
-        "\n",
-        "# Add OPENAI_API_KEY Secrets to Google Colab on the Left Hand Side 🔑 or Enter Manually Below\n",
-        "os.environ[\"OPENAI_API_KEY\"] = userdata.get('OPENAI_API_KEY') or \"ENTER OPENAI_API_KEY HERE\"\n",
-        "\n",
-        "# Run PraisonAI\n",
-        "result = praisonai.run()\n",
-        "\n",
-        "# Print the result\n",
-        "print(result)"
-      ]
-    }
-  ],
-  "metadata": {
-    "accelerator": "GPU",
-    "colab": {
-      "gpuType": "T4",
-      "provenance": []
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

cookbooks/praisonai-tools-googlecolab.ipynb

@@ -1,358 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "source": [
-        "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/MervinPraison/PraisonAI/blob/main/cookbooks/praisonai-tools-googlecolab.ipynb)"
-      ],
-      "metadata": {
-        "id": "MHwYRTSdlNUS"
-      }
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 1,
-      "metadata": {
-        "id": "cW47IVIvdyii",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "outputId": "ad31a979-acb4-4200-9ce8-439ab4193594"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "\u001b[?25l     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/173.7 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m173.7/173.7 kB\u001b[0m \u001b[31m8.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
-            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
-            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.9/40.9 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.3/67.3 kB\u001b[0m \u001b[31m6.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
-            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
-            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
-            "\u001b[33mWARNING: embedchain 0.1.124 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.124 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.123 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.123 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.122 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.122 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.121 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.121 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.120 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.120 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.119 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.119 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.118 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.118 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.117 does not provide the extra 'github'\u001b[0m\u001b[33m\n",
-            "\u001b[0m\u001b[33mWARNING: embedchain 0.1.117 does not provide the extra 'youtube'\u001b[0m\u001b[33m\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m160.7/160.7 kB\u001b[0m \u001b[31m13.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.2/76.2 kB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.2/50.2 kB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m54.3/54.3 kB\u001b[0m \u001b[31m4.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m46.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.0/3.0 MB\u001b[0m \u001b[31m13.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m525.5/525.5 kB\u001b[0m \u001b[31m32.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.4/2.4 MB\u001b[0m \u001b[31m18.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m55.3/55.3 kB\u001b[0m \u001b[31m4.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m202.6/202.6 kB\u001b[0m \u001b[31m16.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m327.6/327.6 kB\u001b[0m \u001b[31m25.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m115.1/115.1 kB\u001b[0m \u001b[31m7.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.6/21.6 MB\u001b[0m \u001b[31m39.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m64.0/64.0 kB\u001b[0m \u001b[31m6.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m52.5/52.5 kB\u001b[0m \u001b[31m4.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m110.5/110.5 kB\u001b[0m \u001b[31m10.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m149.7/149.7 kB\u001b[0m \u001b[31m14.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m342.3/342.3 kB\u001b[0m \u001b[31m22.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.6/57.6 kB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m774.0/774.0 kB\u001b[0m \u001b[31m9.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.7/9.7 MB\u001b[0m \u001b[31m116.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m233.2/233.2 kB\u001b[0m \u001b[31m19.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m273.8/273.8 kB\u001b[0m \u001b[31m24.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m172.8/172.8 kB\u001b[0m \u001b[31m16.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.7/67.7 kB\u001b[0m \u001b[31m6.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m94.7/94.7 kB\u001b[0m \u001b[31m9.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m131.6/131.6 kB\u001b[0m \u001b[31m13.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.9/1.9 MB\u001b[0m \u001b[31m76.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m84.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m302.9/302.9 kB\u001b[0m \u001b[31m25.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m93.2/93.2 kB\u001b[0m \u001b[31m8.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.2/13.2 MB\u001b[0m \u001b[31m48.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m53.0/53.0 kB\u001b[0m \u001b[31m4.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m54.4/54.4 kB\u001b[0m \u001b[31m5.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.4/5.4 MB\u001b[0m \u001b[31m15.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m342.2/342.2 kB\u001b[0m \u001b[31m25.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m295.8/295.8 kB\u001b[0m \u001b[31m22.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.1/71.1 kB\u001b[0m \u001b[31m2.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.1 MB\u001b[0m \u001b[31m58.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m481.7/481.7 kB\u001b[0m \u001b[31m38.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m63.7/63.7 kB\u001b[0m \u001b[31m6.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.0/3.0 MB\u001b[0m \u001b[31m93.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m254.9/254.9 kB\u001b[0m \u001b[31m21.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m248.1/248.1 kB\u001b[0m \u001b[31m20.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m442.1/442.1 kB\u001b[0m \u001b[31m32.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.5/49.5 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m98.7/98.7 kB\u001b[0m \u001b[31m10.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m856.7/856.7 kB\u001b[0m \u001b[31m53.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m73.3/73.3 kB\u001b[0m \u001b[31m7.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m14.0/14.0 MB\u001b[0m \u001b[31m37.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.8/3.8 MB\u001b[0m \u001b[31m72.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m425.7/425.7 kB\u001b[0m \u001b[31m32.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m164.1/164.1 kB\u001b[0m \u001b[31m14.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.0/3.0 MB\u001b[0m \u001b[31m98.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m78.6/78.6 kB\u001b[0m \u001b[31m7.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.4/194.4 kB\u001b[0m \u001b[31m17.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.3/2.3 MB\u001b[0m \u001b[31m71.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m94.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m7.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.7/1.7 MB\u001b[0m \u001b[31m5.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Building wheel for praisonai (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Building wheel for docx2txt (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Building wheel for pypika (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n"
-          ]
-        }
-      ],
-      "source": [
-        "!pip install -Uq \"praisonai[crewai]\" duckduckgo_search"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 2,
-      "metadata": {
-        "id": "Qwds0ad96Pco"
-      },
-      "outputs": [],
-      "source": [
-        "# tools.py\n",
-        "from duckduckgo_search import DDGS\n",
-        "from praisonai_tools import BaseTool\n",
-        "\n",
-        "class InternetSearchTool(BaseTool):\n",
-        "    name: str = \"InternetSearchTool\"\n",
-        "    description: str = \"Search Internet for relevant information based on a query or latest news\"\n",
-        "\n",
-        "    def _run(self, query: str):\n",
-        "        ddgs = DDGS()\n",
-        "        results = ddgs.text(keywords=query, region='wt-wt', safesearch='moderate', max_results=5)\n",
-        "        return results"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 3,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 1000
-        },
-        "id": "myh-_QCuHfOs",
-        "outputId": "8024c5db-cdf3-4099-cf15-86c33c35f795"
-      },
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "\u001b[1m\u001b[95m [2024-10-31 17:13:31][DEBUG]: == Working Agent: Space Researcher\u001b[00m\n",
-            "\u001b[1m\u001b[95m [2024-10-31 17:13:31][INFO]: == Starting Task: Research and compile information about exoplanets discovered in the last decade.\u001b[00m\n",
-            "\n",
-            "\n",
-            "\u001b[1m> Entering new CrewAgentExecutor chain...\u001b[0m\n",
-            "\u001b[32;1m\u001b[1;3mTo compile a comprehensive report on exoplanets discovered in the last decade, I should start by searching for relevant information on recent exoplanet discoveries, focusing on their size, potential habitability, and distance from Earth. \n",
-            "\n",
-            "Action: InternetSearchTool\n",
-            "Action Input: {\"query\": \"exoplanets discovered in the last decade size habitability distance from Earth\"}\u001b[0m"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "/usr/local/lib/python3.10/dist-packages/pydantic/main.py:214: UserWarning: A custom validator is returning a value other than `self`.\n",
-            "Returning anything other than `self` from a top level model validator isn't supported when validating via `__init__`.\n",
-            "See the `model_validator` docs (https://docs.pydantic.dev/latest/concepts/validators/#model-validators) for more details.\n",
-            "  warnings.warn(\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "\u001b[95m \n",
-            "\n",
-            "[{'title': 'Earth-Size, Habitable Zone Planet Found Hidden in Early NASA Kepler ...', 'href': 'https://www.nasa.gov/news-release/earth-size-habitable-zone-planet-found-hidden-in-early-nasa-kepler-data/', 'body': \"A team of transatlantic scientists, using reanalyzed data from NASA's Kepler space telescope, has discovered an Earth-size exoplanet orbiting in its star's habitable zone, the area around a star where a rocky planet could support liquid water. Scientists discovered this planet, called Kepler-1649c, when looking through old observations from ...\"}, {'title': 'Largest Batch of Earth-size Habitable Zone Planets Found ...', 'href': 'https://science.nasa.gov/exoplanets/trappist1/', 'body': \"TRAPPIST-1: Largest Batch of Earth-sized Exoplanets The most studied planetary system, aside from our own solar system, lies about 40 light-years away. We've looked at the seven rocky exoplanets orbiting the TRAPPIST-1 star with ground and space telescopes like Spitzer, Kepler, Hubble, and, now, the James Webb Space Telescope. In March 2023, the first science […]\"}, {'title': 'NASA Telescope Reveals Largest Batch of Earth-Size ...', 'href': 'https://www.nasa.gov/news-release/nasa-telescope-reveals-largest-batch-of-earth-size-habitable-zone-planets-around-single-star/', 'body': '\"The seven wonders of TRAPPIST-1 are the first Earth-size planets that have been found orbiting this kind of star,\" said Michael Gillon, lead author of the paper and the principal investigator of the TRAPPIST exoplanet survey at the University of Liege, Belgium. \"It is also the best target yet for studying the atmospheres of potentially ...'}, {'title': 'NASA finds potentially habitable Earth-sized exoplanet ...', 'href': 'https://www.usatoday.com/story/news/nation/2024/05/28/nasa-exoplanet-discovery/73882055007/', 'body': '0:00. 0:59. NASA announced the discovery of a planet 40 light years from Earth that orbits every 12.8 days and is possibly even habitable. Gliese 12 b is a \"super Earth exoplanet\" that is nearly ...'}, {'title': \"NASA space telescope finds Earth-size exoplanet that's\", 'href': 'https://www.space.com/gliese-12-b-tess-exoplanet-hunt-for-life', 'body': \"The exoplanet — which the team found with NASA's Transiting Exoplanet Survey Satellite (TESS) — is estimated to have a width around 1.1 times that of Earth, making it similar to our planet as ...\"}]\n",
-            "\u001b[00m\n",
-            "\u001b[32;1m\u001b[1;3mThought: I have gathered multiple sources discussing exoplanet discoveries, including details about their size, potential habitability, and distance from Earth. I will now compile this information into a comprehensive report.\n",
-            "\n",
-            "Final Answer:\n",
-            "\n",
-            "### Exoplanet Discoveries in the Last Decade\n",
-            "\n",
-            "1. **Kepler-1649c**\n",
-            "   - **Size:** Earth-sized\n",
-            "   - **Habitability:** This exoplanet orbits in its star's habitable zone, where a rocky planet could support liquid water.\n",
-            "   - **Distance from Earth:** Discovered using reanalyzed data from NASA's Kepler space telescope, the exact distance wasn't specified in the initial search result.\n",
-            "\n",
-            "2. **TRAPPIST-1 System**\n",
-            "   - **Size:** The system consists of seven Earth-sized exoplanets.\n",
-            "   - **Habitability:** The TRAPPIST-1 system is one of the most studied, and it provides the best targets for studying the atmospheres of potentially habitable planets.\n",
-            "   - **Distance from Earth:** About 40 light-years away.\n",
-            "\n",
-            "3. **Gliese 12 b**\n",
-            "   - **Size:** Classified as a \"super Earth\" exoplanet, with a width approximately 1.1 times that of Earth.\n",
-            "   - **Habitability:** Potentially habitable and orbits every 12.8 days, suggesting it could support liquid water.\n",
-            "   - **Distance from Earth:** 40 light-years away.\n",
-            "\n",
-            "These discoveries highlight significant strides in identifying exoplanets that resemble Earth in size and orbit within habitable zones. The proximity of these planets, particularly the TRAPPIST-1 system and Gliese 12 b, offers promising opportunities for future exploration and study of potentially habitable worlds beyond our solar system.\u001b[0m\n",
-            "\n",
-            "\u001b[1m> Finished chain.\u001b[0m\n",
-            "\u001b[1m\u001b[92m [2024-10-31 17:13:47][DEBUG]: == [Space Researcher] Task output: ### Exoplanet Discoveries in the Last Decade\n",
-            "\n",
-            "1. **Kepler-1649c**\n",
-            "   - **Size:** Earth-sized\n",
-            "   - **Habitability:** This exoplanet orbits in its star's habitable zone, where a rocky planet could support liquid water.\n",
-            "   - **Distance from Earth:** Discovered using reanalyzed data from NASA's Kepler space telescope, the exact distance wasn't specified in the initial search result.\n",
-            "\n",
-            "2. **TRAPPIST-1 System**\n",
-            "   - **Size:** The system consists of seven Earth-sized exoplanets.\n",
-            "   - **Habitability:** The TRAPPIST-1 system is one of the most studied, and it provides the best targets for studying the atmospheres of potentially habitable planets.\n",
-            "   - **Distance from Earth:** About 40 light-years away.\n",
-            "\n",
-            "3. **Gliese 12 b**\n",
-            "   - **Size:** Classified as a \"super Earth\" exoplanet, with a width approximately 1.1 times that of Earth.\n",
-            "   - **Habitability:** Potentially habitable and orbits every 12.8 days, suggesting it could support liquid water.\n",
-            "   - **Distance from Earth:** 40 light-years away.\n",
-            "\n",
-            "These discoveries highlight significant strides in identifying exoplanets that resemble Earth in size and orbit within habitable zones. The proximity of these planets, particularly the TRAPPIST-1 system and Gliese 12 b, offers promising opportunities for future exploration and study of potentially habitable worlds beyond our solar system.\n",
-            "\n",
-            "\u001b[00m\n"
-          ]
-        },
-        {
-          "output_type": "display_data",
-          "data": {
-            "text/plain": [
-              "### Task Output ###\n",
-              "### Exoplanet Discoveries in the Last Decade\n",
-              "\n",
-              "\u001b[1;36m1\u001b[0m. **Kepler-1649c**\n",
-              "   - **Size:** Earth-sized\n",
-              "   - **Habitability:** This exoplanet orbits in its star's habitable zone, where a rocky planet could support \n",
-              "liquid water.\n",
-              "   - **Distance from Earth:** Discovered using reanalyzed data from NASA's Kepler space telescope, the exact \n",
-              "distance wasn't specified in the initial search result.\n",
-              "\n",
-              "\u001b[1;36m2\u001b[0m. **TRAPPIST-\u001b[1;36m1\u001b[0m System**\n",
-              "   - **Size:** The system consists of seven Earth-sized exoplanets.\n",
-              "   - **Habitability:** The TRAPPIST-\u001b[1;36m1\u001b[0m system is one of the most studied, and it provides the best targets for \n",
-              "studying the atmospheres of potentially habitable planets.\n",
-              "   - **Distance from Earth:** About \u001b[1;36m40\u001b[0m light-years away.\n",
-              "\n",
-              "\u001b[1;36m3\u001b[0m. **Gliese \u001b[1;36m12\u001b[0m b**\n",
-              "   - **Size:** Classified as a \u001b[32m\"super Earth\"\u001b[0m exoplanet, with a width approximately \u001b[1;36m1.1\u001b[0m times that of Earth.\n",
-              "   - **Habitability:** Potentially habitable and orbits every \u001b[1;36m12.8\u001b[0m days, suggesting it could support liquid water.\n",
-              "   - **Distance from Earth:** \u001b[1;36m40\u001b[0m light-years away.\n",
-              "\n",
-              "These discoveries highlight significant strides in identifying exoplanets that resemble Earth in size and orbit \n",
-              "within habitable zones. The proximity of these planets, particularly the TRAPPIST-\u001b[1;36m1\u001b[0m system and Gliese \u001b[1;36m12\u001b[0m b, offers \n",
-              "promising opportunities for future exploration and study of potentially habitable worlds beyond our solar system.\n"
-            ],
-            "text/html": [
-              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">### Task Output ###\n",
-              "### Exoplanet Discoveries in the Last Decade\n",
-              "\n",
-              "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1</span>. **Kepler-1649c**\n",
-              "   - **Size:** Earth-sized\n",
-              "   - **Habitability:** This exoplanet orbits in its star's habitable zone, where a rocky planet could support \n",
-              "liquid water.\n",
-              "   - **Distance from Earth:** Discovered using reanalyzed data from NASA's Kepler space telescope, the exact \n",
-              "distance wasn't specified in the initial search result.\n",
-              "\n",
-              "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">2</span>. **TRAPPIST-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1</span> System**\n",
-              "   - **Size:** The system consists of seven Earth-sized exoplanets.\n",
-              "   - **Habitability:** The TRAPPIST-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1</span> system is one of the most studied, and it provides the best targets for \n",
-              "studying the atmospheres of potentially habitable planets.\n",
-              "   - **Distance from Earth:** About <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">40</span> light-years away.\n",
-              "\n",
-              "<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>. **Gliese <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">12</span> b**\n",
-              "   - **Size:** Classified as a <span style=\"color: #008000; text-decoration-color: #008000\">\"super Earth\"</span> exoplanet, with a width approximately <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1.1</span> times that of Earth.\n",
-              "   - **Habitability:** Potentially habitable and orbits every <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">12.8</span> days, suggesting it could support liquid water.\n",
-              "   - **Distance from Earth:** <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">40</span> light-years away.\n",
-              "\n",
-              "These discoveries highlight significant strides in identifying exoplanets that resemble Earth in size and orbit \n",
-              "within habitable zones. The proximity of these planets, particularly the TRAPPIST-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">1</span> system and Gliese <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">12</span> b, offers \n",
-              "promising opportunities for future exploration and study of potentially habitable worlds beyond our solar system.\n",
-              "</pre>\n"
-            ]
-          },
-          "metadata": {}
-        },
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "None\n"
-          ]
-        }
-      ],
-      "source": [
-        "import os\n",
-        "import yaml\n",
-        "from praisonai import PraisonAI\n",
-        "from google.colab import userdata\n",
-        "\n",
-        "# Example agent_yaml content\n",
-        "agent_yaml = \"\"\"\n",
-        "framework: \"crewai\"\n",
-        "topic: \"Space Exploration\"\n",
-        "\n",
-        "roles:\n",
-        "  astronomer:\n",
-        "    role: \"Space Researcher\"\n",
-        "    goal: \"Discover new insights about {topic}\"\n",
-        "    backstory: \"You are a curious and dedicated astronomer with a passion for unraveling the mysteries of the cosmos.\"\n",
-        "    tasks:\n",
-        "      investigate_exoplanets:\n",
-        "        description: \"Research and compile information about exoplanets discovered in the last decade.\"\n",
-        "        expected_output: \"A summarized report on exoplanet discoveries, including their size, potential habitability, and distance from Earth.\"\n",
-        "    tools:\n",
-        "      - \"InternetSearchTool\"\n",
-        "\"\"\"\n",
-        "\n",
-        "# Create a PraisonAI instance with the agent_yaml content\n",
-        "praisonai = PraisonAI(agent_yaml=agent_yaml, tools=[InternetSearchTool])\n",
-        "\n",
-        "# Add OPENAI_API_KEY Secrets to Google Colab on the Left Hand Side 🔑 or Enter Manually Below\n",
-        "os.environ[\"OPENAI_API_KEY\"] = userdata.get('OPENAI_API_KEY') or \"ENTER OPENAI_API_KEY HERE\"\n",
-        "\n",
-        "# Run PraisonAI\n",
-        "result = praisonai.run()\n",
-        "\n",
-        "# Print the result\n",
-        "print(result)"
-      ]
-    }
-  ],
-  "metadata": {
-    "accelerator": "GPU",
-    "colab": {
-      "gpuType": "T4",
-      "provenance": []
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

cookbooks/python/10_wikipedia_praison_ai_integration.py

@@ -1,67 +0,0 @@
-# tools.py
-from langchain_community.utilities import WikipediaAPIWrapper
-from praisonai_tools import BaseTool
-
-class WikipediaSearchTool(BaseTool):
-    name: str = "WikipediaSearchTool"
-    description: str = "Search Wikipedia for relevant information based on a query."
-
-    def _run(self, query: str):
-        api_wrapper = WikipediaAPIWrapper(top_k_results=4, doc_content_chars_max=100)
-        results = api_wrapper.load(query=query)
-        return results
-
-# Example agent_yaml content
-
-import os
-import yaml
-from praisonai import PraisonAI
-
-agent_yaml = """
-framework: "crewai"
-topic: "research about Nvidia growth"
-roles:
-  data_collector:
-    role: "Data Collector"
-    backstory: "An experienced researcher with the ability to efficiently collect and organize vast amounts of data."
-    goal: "Gather information on Nvidia's growth by providing the Ticket Symbol to YahooFinanceNewsTool"
-    tasks:
-      data_collection_task:
-        description: "Collect data on Nvidia's growth from various sources such as financial reports, news articles, and company announcements."
-        expected_output: "A comprehensive document detailing data points on Nvidia's growth over the years."
-    tools:
-      - "WikipediaSearchTool"
-  data_analyst:
-    role: "Data Analyst"
-    backstory: "Specializes in extracting insights from large datasets, proficient in quantitative and qualitative analysis."
-    goal: "Analyze the collected data to identify trends and patterns"
-    tasks:
-      data_analysis_task:
-        description: "Analyze the collected data to identify key trends and patterns in Nvidia's growth."
-        expected_output: "An analytical report summarizing trends, patterns, and key growth metrics of Nvidia."
-    tools: []
-  report_preparer:
-    role: "Report Preparer"
-    backstory: "Experienced in creating detailed reports and presentations, turning analytical data into actionable insights."
-    goal: "Generate a final report on Nvidia's growth"
-    tasks:
-      report_preparation_task:
-        description: "Create a detailed report based on the analysis, highlighting Nvidia's growth trajectory."
-        expected_output: "A polished, comprehensive report summarizing Nvidia's growth with visual aids and key insights."
-    tools: []
-dependencies: []
-
-"""
-
-# Create a PraisonAI instance with the agent_yaml content
-praisonai = PraisonAI(agent_yaml=agent_yaml)
-
-# Add OPENAI_API_KEY Secrets to Google Colab on the Left Hand Side 🔑 or Enter Manually Below
-# os.environ["OPENAI_API_KEY"] = userdata.get('OPENAI_API_KEY') or "ENTER OPENAI_API_KEY HERE"
-openai_api_key = os.getenv("OPENAI_API_KEY")
-
-# Run PraisonAI
-result = praisonai.run()
-
-# Print the result
-print(result)

cookbooks/python/11_crawl4ai_and_praison_ai_integration.py

@@ -1,97 +0,0 @@
-# tools.py
-import os
-from crawl4ai import WebCrawler
-from crawl4ai.extraction_strategy import LLMExtractionStrategy
-from pydantic import BaseModel, Field
-from praisonai_tools import BaseTool
-
-class ModelFee(BaseModel):
-    llm_model_name: str = Field(..., description="Name of the model.")
-    input_fee: str = Field(..., description="Fee for input token for the model.")
-    output_fee: str = Field(..., description="Fee for output token for the model.")
-
-class ModelFeeTool(BaseTool):
-    name: str = "ModelFeeTool"
-    description: str = "Extracts model fees for input and output tokens from the given pricing page."
-
-    def _run(self, url: str):
-        crawler = WebCrawler()
-        crawler.warmup()
-
-        result = crawler.run(
-            url=url,
-            word_count_threshold=1,
-            extraction_strategy= LLMExtractionStrategy(
-                provider="openai/gpt-4o",
-                api_token=os.getenv('OPENAI_API_KEY'), 
-                schema=ModelFee.schema(),
-                extraction_type="schema",
-                instruction="""From the crawled content, extract all mentioned model names along with their fees for input and output tokens. 
-                Do not miss any models in the entire content. One extracted model JSON format should look like this: 
-                {"model_name": "GPT-4", "input_fee": "US$10.00 / 1M tokens", "output_fee": "US$30.00 / 1M tokens"}."""
-            ),            
-            bypass_cache=True,
-        )
-        return result.extracted_content
-    
-
-
-# Example agent_yaml content
-
-import os
-import yaml
-from praisonai import PraisonAI
-
-agent_yaml = """
-framework: "crewai"
-topic: "extract model pricing from websites"
-roles:
-  web_scraper:
-    role: "Web Scraper"
-    backstory: |
-      An expert in web scraping with a deep understanding of extracting structured
-      data from online sources.
-
-      https://openai.com/api/pricing/
-      https://www.anthropic.com/pricing
-      https://cohere.com/pricing
-    goal: "Gather model pricing data from various websites"
-    tasks:
-      scrape_model_pricing:
-        description: "Scrape model pricing information from the provided list of websites."
-        expected_output: "Raw HTML or JSON containing model pricing data."
-    tools:
-      - "ModelFeeTool"
-  data_cleaner:
-    role: "Data Cleaner"
-    backstory: "Specialist in data cleaning, ensuring that all collected data is accurate and properly formatted."
-    goal: "Clean and organize the scraped pricing data"
-    tasks:
-      clean_pricing_data:
-        description: "Process the raw scraped data to remove any duplicates and inconsistencies, and convert it into a structured format."
-        expected_output: "Cleaned and organized JSON or CSV file with model pricing data."
-    tools: []
-  data_analyzer:
-    role: "Data Analyzer"
-    backstory: "Data analysis expert focused on deriving actionable insights from structured data."
-    goal: "Analyze the cleaned pricing data to extract insights"
-    tasks:
-      analyze_pricing_data:
-        description: "Analyze the cleaned data to extract trends, patterns, and insights on model pricing."
-        expected_output: "Detailed report summarizing model pricing trends and insights."
-    tools: []
-dependencies: []
-"""
-
-# Create a PraisonAI instance with the agent_yaml content
-praisonai = PraisonAI(agent_yaml=agent_yaml)
-
-# Add OPENAI_API_KEY Secrets to Google Colab on the Left Hand Side 🔑 or Enter Manually Below
-# os.environ["OPENAI_API_KEY"] = userdata.get('OPENAI_API_KEY') or "ENTER OPENAI_API_KEY HERE"
-openai_api_key = os.getenv("OPENAI_API_KEY")
-
-# Run PraisonAI
-result = praisonai.run()
-
-# Print the result
-print(result)

cookbooks/python/1_business_product_launch_agents.py

@@ -1,66 +0,0 @@
-# tools.py
-from duckduckgo_search import DDGS
-from praisonai_tools import BaseTool
-
-class InternetSearchTool(BaseTool):
-    name: str = "InternetSearchTool"
-    description: str = "Search Internet for relevant information based on a query or latest news"
-
-    def _run(self, query: str):
-        ddgs = DDGS()
-        results = ddgs.text(keywords=query, region='wt-wt', safesearch='moderate', max_results=5)
-        return results
-
-# Example agents_yaml content
-
-import os
-import yaml
-from praisonai import PraisonAI
-
-agents_yaml = """framework: "crewai"
-topic: "Product Development"
-roles:
-  market_research_analyst:
-    role: "Market Research Analyst"
-    backstory: "Expert at understanding market demand, target audience, and competition for products like the product. Skilled in developing marketing strategies to reach a wide audience."
-    goal: "Analyze the market demand for the product and suggest marketing strategies using InternetSearchTool."
-    tasks:
-      market_analysis_task:
-        description: "Analyze the market demand for the product. Current month is Jan 2024. Write a report on the ideal customer profile and marketing strategies to reach the widest possible audience. Include at least 10 bullet points addressing key marketing areas. Search the internet using InternetSearchTool."
-        expected_output: "Report on the ideal customer profile and marketing strategies, with at least 10 bullet points addressing key marketing areas."
-    tools:
-      - InternetSearchTool
-  technology_expert:
-    role: "Technology Expert"
-    backstory: "Visionary in current and emerging technological trends, especially in products like the product. Identifies which technologies are best suited for different business models."
-    goal: "Assess technological feasibilities and requirements for producing high-quality the product"
-    tasks:
-      technology_assessment_task:
-        description: "Assess the technological aspects of manufacturing high-quality the product. Write a report detailing necessary technologies and manufacturing approaches. Include at least 10 bullet points on key technological areas."
-        expected_output: "Report detailing necessary technologies and manufacturing approaches, including at least 10 bullet points on key technological areas."
-  business_consultant:
-    role: "Business Development Consultant"
-    backstory: "Seasoned in shaping business strategies for products like the product. Understands scalability and potential revenue streams to ensure long-term sustainability."
-    goal: "Evaluate the business model for the product, focusing on scalability and revenue streams"
-    tasks:
-      business_model_evaluation_task:
-        description: "Summarize the market and technological reports and evaluate the business model for the product. Write a report on the scalability and revenue streams for the product. Include at least 10 bullet points on key business areas. Give Business Plan, Goals, and Timeline for the product launch. Current month is Jan 2024."
-        expected_output: "Comprehensive business model evaluation report including scalability, revenue streams, at least 10 key business areas, Business Plan, Goals, and Timeline for the product launch."
-      """
-
-
-# Create a PraisonAI instance with the agent_yaml content and tools
-praisonai = PraisonAI(
-    agent_yaml=agents_yaml,
-    tools=[InternetSearchTool]  # Just pass the class directly in a list
-)
-
-# Add OPENAI_API_KEY Secrets to Google Colab on the Left Hand Side 🔑 or Enter Manually Below
-# os.environ["OPENAI_API_KEY"] = userdata.get('OPENAI_API_KEY') or "ENTER OPENAI_API_KEY HERE"
-openai_api_key = os.getenv("OPENAI_API_KEY")
-
-# Run PraisonAI
-result = praisonai.run()
-
-# Print the result
-print(result)

cookbooks/python/2_create_story_book_agent.py

@@ -1,80 +0,0 @@
-# tools.py
-from duckduckgo_search import DDGS
-from praisonai_tools import BaseTool
-
-class InternetSearchTool(BaseTool):
-    name: str = "InternetSearchTool"
-    description: str = "Search Internet for relevant information based on a query or latest news"
-
-    def _run(self, query: str):
-        ddgs = DDGS()
-        results = ddgs.text(keywords=query, region='wt-wt', safesearch='moderate', max_results=5)
-        return results
-    
-# Example agent_yaml content
-
-import os
-from praisonai import PraisonAI
-
-agent_yaml = """
-framework: "crewai"
-topic: "Children's Storybook Creation"
-roles:
-  story_outliner:
-    role: "Story Outliner"
-    backstory: "An imaginative creator who lays the foundation of captivating stories for children."
-    goal: "Develop an outline for a children's storybook about Animals, including chapter titles and characters for 5 chapters."
-    tasks:
-      task_outline:
-        description: "Create an outline for the children's storybook about Animals, detailing chapter titles and character descriptions for 5 chapters."
-        expected_output: "A structured outline document containing 5 chapter titles, with detailed character descriptions and the main plot points for each chapter."
-    tools:
-      - InternetSearchTool
-  story_writer:
-    role: "Story Writer"
-    backstory: "A talented storyteller who brings to life the world and characters outlined, crafting engaging and imaginative tales for children."
-    goal: "Write the full content of the story for all 5 chapters, each chapter 100 words, weaving together the narratives and characters outlined."
-    tasks:
-      task_write:
-        description: "Using the outline provided, write the full story content for all chapters, ensuring a cohesive and engaging narrative for children. Each chapter should contain approximately 100 words. Include the title of the story at the top."
-        expected_output: "A complete manuscript of the children's storybook about Animals with 5 chapters, each approximately 100 words, following the provided outline and integrating the characters and plot points into a cohesive narrative."
-  image_generator:
-    role: "Image Generator"
-    backstory: "A creative AI specialized in visual storytelling, bringing each chapter to life through imaginative imagery."
-    goal: "Generate one image per chapter based on the content provided by the story writer. Start with chapter number, chapter content, character details, detailed location information, and detailed items in the location where the activity happens. Generate a total of 5 images one by one. Final output should contain all 5 images in JSON format."
-    tasks:
-      task_image_generate:
-        description: "Generate 5 images that capture the essence of the children's storybook about Animals, aligning with the themes, characters, and narratives outlined in the chapters. Do it one by one."
-        expected_output: "A set of digital images that visually represent each chapter of the children's storybook, incorporating elements from the characters and plot as described in the chapters. The images should be suitable for inclusion in the storybook as illustrations."
-  content_formatter:
-    role: "Content Formatter"
-    backstory: "A meticulous formatter who enhances the readability and presentation of the storybook."
-    goal: "Format the written story content in markdown, including images at the beginning of each chapter."
-    tasks:
-      task_format_content:
-        description: "Format the story content in markdown, including an image at the beginning of each chapter."
-        expected_output: "The entire storybook content formatted in markdown, with each chapter title followed by the corresponding image and the chapter content."
-        output_file: "story.md"
-  markdown_to_pdf_creator:
-    role: "PDF Converter"
-    backstory: "An efficient converter that transforms Markdown files into professionally formatted PDF documents."
-    goal: "Convert the Markdown file to a PDF document. 'story.md' is the markdown file name."
-    tasks:
-      task_markdown_to_pdf:
-        description: "Convert a Markdown file to a PDF document, ensuring the preservation of formatting, structure, and embedded images using the mdpdf library."
-        expected_output: "A PDF file generated from the Markdown input, accurately reflecting the content with proper formatting. The PDF should be ready for sharing or printing."
-
-"""
-
-# Create a PraisonAI instance with the agent_yaml content
-praisonai = PraisonAI(agent_yaml=agent_yaml)
-
-# Add OPENAI_API_KEY Secrets to Google Colab on the Left Hand Side 🔑 or Enter Manually Below
-# os.environ["OPENAI_API_KEY"] = userdata.get('OPENAI_API_KEY') or "ENTER OPENAI_API_KEY HERE"
-openai_api_key = os.getenv("OPENAI_API_KEY")
-
-# Run PraisonAI
-result = praisonai.run()
-
-# Print the result
-print(result)

cookbooks/python/3_crewai_open_interpreter.py

@@ -1,51 +0,0 @@
-# tools.py
-from duckduckgo_search import DDGS
-from praisonai_tools import BaseTool
-
-class InternetSearchTool(BaseTool):
-    name: str = "InternetSearchTool"
-    description: str = "Search Internet for relevant information based on a query or latest news"
-
-    def _run(self, query: str):
-        ddgs = DDGS()
-        results = ddgs.text(keywords=query, region='wt-wt', safesearch='moderate', max_results=5)
-        return results
-    
-
-
-# Example agent_yaml content
-
-import os
-import yaml
-from praisonai import PraisonAI
-
-agent_yaml = """
-framework: "crewai"
-topic: "Command Line Operations"
-
-roles:
-  cli_agent:
-    role: "Software Engineer"
-    backstory: "Expert in command line operations, creating and executing code."
-    goal: "Always use Executor Tool. Ability to perform CLI operations, write programs, and execute using Executor Tool."
-    tools:
-      - "CLITool.execute_cli_command"
-    tasks:
-      cli_task:
-        description: "Identify the operating system."
-        expected_output: "Successfully identifies the OS."
-
-"""
-
-# Create a PraisonAI instance with the agent_yaml content
-praisonai = PraisonAI(agent_yaml=agent_yaml)
-
-# Add OPENAI_API_KEY Secrets to Google Colab on the Left Hand Side 🔑 or Enter Manually Below
-# os.environ["OPENAI_API_KEY"] = userdata.get('OPENAI_API_KEY') or "ENTER OPENAI_API_KEY HERE"
-openai_api_key = os.getenv("OPENAI_API_KEY")
-
-# Run PraisonAI
-result = praisonai.run()
-
-# Print the result
-print(result)

cookbooks/python/4_rag_using_tools.py

@@ -1,75 +0,0 @@
-# tools.py
-from duckduckgo_search import DDGS
-from praisonai_tools import BaseTool
-
-class InternetSearchTool(BaseTool):
-    name: str = "InternetSearchTool"
-    description: str = "Search Internet for relevant information based on a query or latest news"
-
-    def _run(self, query: str):
-        ddgs = DDGS()
-        results = ddgs.text(keywords=query, region='wt-wt', safesearch='moderate', max_results=5)
-        return results
-    
-
-
-# Example agent_yaml content
-
-import os
-import yaml
-from praisonai import PraisonAI
-
-agent_yaml = """
-              framework: "crewai"
-              topic: "News Analysis"
-
-              roles:
-                news_search_agent:
-                  role: "News Searcher"
-                  backstory: "Expert in analyzing and generating key points from news content for quick updates."
-                  goal: "Generate key points for each news article from the latest news."
-                  tools:
-                    - "SearchNewsDB.news"
-                  allow_delegation: true
-                  tasks:
-                    news_search_task:
-                      description: "Search for 'AI 2024' and create key points for each news."
-                      expected_output: "Key points for each news article related to 'AI 2024'."
-                writer_agent:
-                  role: "Writer"
-                  backstory: "Expert in crafting engaging narratives from complex information."
-                  goal: "Identify all the topics received. Use the Get News Tool to verify each topic to search. Use the Search tool for detailed exploration of each topic. Summarize the retrieved information in depth for every topic."
-                  tools:
-                    - "GetNews.news"
-                    - "DuckDuckGoSearchRun"
-                  allow_delegation: true
-                  tasks:
-                    writer_task:
-                      description: |
-                        Go step by step.
-                        Step 1: Identify all the topics received.
-                        Step 2: Use the Get News Tool to verify each topic by going through one by one.
-                        Step 3: Use the Search tool to search for information on each topic one by one.
-                        Step 4: Go through every topic and write an in-depth summary of the information retrieved.
-                        Don't skip any topic.
-                      expected_output: "An in-depth summary of the information retrieved for each topic."
-
-              dependencies:
-                - task: "writer_task"
-                  depends_on:
-                    - "news_search_task"
-
-"""
-
-# Create a PraisonAI instance with the agent_yaml content
-praisonai = PraisonAI(agent_yaml=agent_yaml)
-
-# Add OPENAI_API_KEY Secrets to Google Colab on the Left Hand Side 🔑 or Enter Manually Below
-# os.environ["OPENAI_API_KEY"] = userdata.get('OPENAI_API_KEY') or "ENTER OPENAI_API_KEY HERE"
-openai_api_key = os.getenv("OPENAI_API_KEY")
-
-# Run PraisonAI
-result = praisonai.run()
-
-# Print the result
-print(result)

cookbooks/python/5_job_search.py

@@ -1,94 +0,0 @@
-# tools.py
-from duckduckgo_search import DDGS
-from praisonai_tools import BaseTool
-
-class InternetSearchTool(BaseTool):
-    name: str = "InternetSearchTool"
-    description: str = "Search Internet for relevant information based on a query or latest news"
-
-    def _run(self, query: str):
-        ddgs = DDGS()
-        results = ddgs.text(keywords=query, region='wt-wt', safesearch='moderate', max_results=5)
-        return results
-    
-# Example agent_yaml content
-
-import os
-import yaml
-from praisonai import PraisonAI
-
-agent_yaml = """
-framework: "crewai"
-topic: "Job Search Assistance"
-
-roles:
-  job_searcher_agent:
-    role: "Job Searcher"
-    backstory: "You are actively searching for job opportunities in your field, ready to utilize and expand your skill set in a new role."
-    goal: "Search for jobs in the field of interest, focusing on enhancing relevant skills."
-    tools:
-      - "JobSearchTools.search_jobs"
-    allow_delegation: true
-    tasks:
-      job_search_task:
-        description: |
-          Search for current job openings for the Senior Data Scientist role in New York using the Job Search tool. Find 5 vacant positions in total. Emphasize the key skills required. The tool accepts input in JSON format with the following schema: 'role': '<role>', 'location': '<location>', 'num_results': <number>. Ensure to format the input accordingly.
-        expected_output: "A list of 5 Senior Data Scientist job openings in New York, including key skills required for each position."
-
-  skills_development_agent:
-    role: "Skills Development Advisor"
-    backstory: "As a skills development advisor, you assist job searchers in identifying crucial skills for their target roles and recommend ways to develop these skills."
-    goal: "Identify key skills required for jobs of interest and advise on improving them."
-    allow_delegation: true
-    tasks:
-      skills_highlighting_task:
-        description: |
-          Based on the identified job openings, list the key skills required for each position separately. Provide recommendations on how candidates can acquire or improve these skills through courses, self-study, or practical experience.
-        expected_output: "A detailed list of key skills for each position with recommendations on how to develop them."
-
-  interview_preparation_coach:
-    role: "Interview Preparation Coach"
-    backstory: "Expert in coaching job searchers on successful interview techniques, including mock interviews and feedback."
-    goal: "Enhance interview skills, focusing on common questions, presentation, and communication."
-    allow_delegation: true
-    tasks:
-      interview_preparation_task:
-        description: |
-          Prepare job searchers for interviews by conducting mock interviews and offering feedback on their responses, presentation, and communication skills, for each role separately.
-        expected_output: "Feedback and guidance on interview skills for each role, including common questions and tips on presentation and communication."
-
-  career_advisor:
-    role: "Career Advisor"
-    backstory: "Experienced in guiding candidates through their job search journey, offering personalized advice on career development and application processes."
-    goal: "Assist in resume building, LinkedIn profile optimization, and networking strategies."
-    allow_delegation: true
-    tasks:
-      career_advisory_task:
-        description: |
-          Offer guidance on resume building, optimizing LinkedIn profiles, and effective networking strategies to enhance job application success, for each role separately.
-        expected_output: "Personalized advice on resume enhancement, LinkedIn optimization, and networking strategies for each position."
-
-dependencies:
-  - task: "skills_highlighting_task"
-    depends_on:
-      - "job_search_task"
-  - task: "interview_preparation_task"
-    depends_on:
-      - "job_search_task"
-  - task: "career_advisory_task"
-    depends_on:
-      - "job_search_task"
-"""
-
-# Create a PraisonAI instance with the agent_yaml content
-praisonai = PraisonAI(agent_yaml=agent_yaml)
-
-# Add OPENAI_API_KEY Secrets to Google Colab on the Left Hand Side 🔑 or Enter Manually Below
-# os.environ["OPENAI_API_KEY"] = userdata.get('OPENAI_API_KEY') or "ENTER OPENAI_API_KEY HERE"
-openai_api_key = os.getenv("OPENAI_API_KEY")
-
-# Run PraisonAI
-result = praisonai.run()
-
-# Print the result
-print(result)

cookbooks/python/6_rag_2-0.py

@@ -1,103 +0,0 @@
-# tools.py
-from duckduckgo_search import DDGS
-from praisonai_tools import BaseTool
-
-class InternetSearchTool(BaseTool):
-    name: str = "InternetSearchTool"
-    description: str = "Search Internet for relevant information based on a query or latest news"
-
-    def _run(self, query: str):
-        ddgs = DDGS()
-        results = ddgs.text(keywords=query, region='wt-wt', safesearch='moderate', max_results=5)
-        return results
-    
-
-
-# Example agent_yaml content
-
-import os
-import yaml
-from praisonai import PraisonAI
-
-agent_yaml = """
-framework: "crewai"
-topic: "AI in healthcare"
-
-roles:
-  manager:
-    role: "Project Manager"
-    backstory: |
-      With a strategic mindset and a knack for leadership, you excel at guiding teams towards
-      their goals, ensuring projects not only meet but exceed expectations.
-    goal: "Coordinate the project to ensure a seamless integration of research findings into compelling narratives"
-    verbose: true
-    allow_delegation: true
-    max_iter: 10
-    max_rpm: 20
-    tasks:
-      manager_task:
-        description: |
-          Oversee the integration of research findings and narrative development to produce a final comprehensive
-          report on AI in healthcare. Ensure the research is accurately represented and the narrative is engaging and informative.
-        expected_output: "A final comprehensive report that combines the research findings and narrative on AI in healthcare."
-
-  researcher:
-    role: "Senior Researcher"
-    backstory: |
-      Driven by curiosity, you're at the forefront of innovation, eager to explore and share
-      knowledge that could change the world.
-    goal: "Uncover groundbreaking technologies around AI in healthcare"
-    verbose: true
-    tools:
-      - "search_tool"
-      - "ContentTools.read_content"
-    tasks:
-      list_ideas:
-        description: "List of 5 interesting ideas to explore for an article about AI in healthcare."
-        expected_output: "Bullet point list of 5 ideas for an article."
-        async_execution: true
-      list_important_history:
-        description: "Research the history of AI in healthcare and identify the 5 most important events."
-        expected_output: "Bullet point list of 5 important events."
-        async_execution: true
-
-  writer:
-    role: "Writer"
-    backstory: |
-      With a flair for simplifying complex topics, you craft engaging narratives that captivate
-      and educate, bringing new discoveries to light in an accessible manner.
-    goal: "Narrate compelling tech stories around AI in healthcare"
-    verbose: true
-    tools:
-      - "search_tool"
-      - "ContentTools.read_content"
-    tasks:
-      write_article:
-        description: |
-          Compose an insightful article on AI in healthcare, including its history and the latest interesting ideas.
-        expected_output: "A 4-paragraph article about AI in healthcare."
-        context:
-          - "list_ideas"
-          - "list_important_history"
-        callback: "callback_function"
-
-dependencies:
-  - task: "write_article"
-    depends_on:
-      - "list_ideas"
-      - "list_important_history"
-
-"""
-
-# Create a PraisonAI instance with the agent_yaml content
-praisonai = PraisonAI(agent_yaml=agent_yaml)
-
-# Add OPENAI_API_KEY Secrets to Google Colab on the Left Hand Side 🔑 or Enter Manually Below
-# os.environ["OPENAI_API_KEY"] = userdata.get('OPENAI_API_KEY') or "ENTER OPENAI_API_KEY HERE"
-openai_api_key = os.getenv("OPENAI_API_KEY")
-
-# Run PraisonAI
-result = praisonai.run()
-
-# Print the result
-print(result)

cookbooks/python/7_crew_ai_example_code.py

@@ -1,69 +0,0 @@
-# tools.py
-from duckduckgo_search import DDGS
-from praisonai_tools import BaseTool
-
-class InternetSearchTool(BaseTool):
-    name: str = "InternetSearchTool"
-    description: str = "Search Internet for relevant information based on a query or latest news"
-
-    def _run(self, query: str):
-        ddgs = DDGS()
-        results = ddgs.text(keywords=query, region='wt-wt', safesearch='moderate', max_results=5)
-        return results
-    
-
-
-# Example agent_yaml content
-
-import os
-import yaml
-from praisonai import PraisonAI
-
-agent_yaml = """framework: "crewai"
-topic: "AI Advancements in 2024"
-roles:
-  researcher:
-    role: "Senior Research Analyst"
-    backstory: |
-      You are an expert at a technology research group, skilled in identifying trends and analyzing complex data.
-    goal: "Uncover cutting-edge developments in AI and data science"
-    verbose: true
-    allow_delegation: false
-    tools:
-      - "search_tool"
-    tasks:
-      task1:
-        description: |
-          Analyze 2024's AI advancements. Find major trends, new technologies, and their effects. Provide a detailed report.
-        expected_output: "A detailed report on major AI trends, new technologies, and their effects in 2024."
-  writer:
-    role: "Tech Content Strategist"
-    backstory: |
-      You are a content strategist known for making complex tech topics interesting and easy to understand.
-    goal: "Craft compelling content on tech advancements"
-    verbose: true
-    allow_delegation: true
-    tasks:
-      task2:
-        description: |
-          Create a blog post about major AI advancements using your insights. Make it interesting, clear, and suited for tech enthusiasts. It should be at least 4 paragraphs long.
-        expected_output: "An engaging blog post of at least 4 paragraphs about major AI advancements, suitable for tech enthusiasts."
-dependencies:
-  - task: "task2"
-    depends_on:
-      - "task1"
-"""
-
-
-# Create a PraisonAI instance with the agent_yaml content
-praisonai = PraisonAI(agent_yaml=agent_yaml)
-
-# Add OPENAI_API_KEY Secrets to Google Colab on the Left Hand Side 🔑 or Enter Manually Below
-# os.environ["OPENAI_API_KEY"] = userdata.get('OPENAI_API_KEY') or "ENTER OPENAI_API_KEY HERE"
-openai_api_key = os.getenv("OPENAI_API_KEY")
-
-# Run PraisonAI
-result = praisonai.run()
-
-# Print the result
-print(result)

cookbooks/python/8_libre_translate.py

@@ -1,83 +0,0 @@
-# tools.py
-import requests
-from praisonai_tools import BaseTool
-
-class TranslatorTool(BaseTool):
-    name: str = "Translator Tool"
-    description: str = "Translate text from one language to another."
-
-    def _run(self, q: str, target: str):
-        url = "http://127.0.0.1:5000/translate"
-        payload = {
-            "q": q,
-            "source": "auto",  # Automatically detect the source language
-            "target": target
-        }
-        headers = {
-            "Content-Type": "application/json"
-        }
-
-        response = requests.post(url, json=payload, headers=headers)
-
-        if response.status_code == 200:
-            try:
-                data = response.json()
-                return data
-            except requests.exceptions.JSONDecodeError:
-                return "Failed to decode JSON from the response."
-        else:
-            return f"Request failed with status code: {response.status_code}"
-        
-
-# Example agent_yaml content
-
-import os
-import yaml
-from praisonai import PraisonAI
-
-agent_yaml = """
-framework: "crewai"
-topic: "Writing an article about AI"
-roles:
-  article_writer:
-    role: "Article Writer"
-    backstory: "Experienced writer with a deep understanding of artificial intelligence and technology trends."
-    goal: "Write an informative and engaging article about AI."
-    tasks:
-      write_article:
-        description: "Write a comprehensive article about the latest developments and implications of AI."
-        expected_output: "A well-written article on AI in English."
-  french_translator:
-    role: "Translator"
-    backstory: "Fluent in French with expertise in translating technical and non-technical content accurately."
-    goal: "Translate the AI article into French."
-    tasks:
-      translate_to_french:
-        description: "Translate the English article on AI into French."
-        expected_output: "The AI article translated into French."
-    tools:
-      - "TranslatorTool"
-  german_translator:
-    role: "Translator"
-    backstory: "Proficient in German with a strong background in technical translation."
-    goal: "Translate the AI article into German."
-    tasks:
-      translate_to_german:
-        description: "Translate the English article on AI into German."
-        expected_output: "The AI article translated into German."
-    tools:
-      - "TranslatorTool"
-"""
-
-# Create a PraisonAI instance with the agent_yaml content
-praisonai = PraisonAI(agent_yaml=agent_yaml)
-
-# Add OPENAI_API_KEY Secrets to Google Colab on the Left Hand Side 🔑 or Enter Manually Below
-# os.environ["OPENAI_API_KEY"] = userdata.get('OPENAI_API_KEY') or "ENTER OPENAI_API_KEY HERE"
-openai_api_key = os.getenv("OPENAI_API_KEY")
-
-# Run PraisonAI
-result = praisonai.run()
-
-# Print the result
-print(result)

cookbooks/python/9_mem0_praison_ai_integration.py

@@ -1,126 +0,0 @@
-# tools.py
-from mem0 import Memory
-from praisonai_tools import BaseTool
-
-class AddMemoryTool(BaseTool):
-    name: str = "Add Memory Tool"
-    description: str = ("This tool allows storing a new memory with user ID and optional metadata.\n"
-                        "Example:\n"
-                        "   - Input: text='I am working on improving my tennis skills. Suggest some online courses.', user_id='alice', metadata={'category': 'hobbies'}\n"
-                        "   - Output: Memory added with summary 'Improving her tennis skills. Looking for online suggestions.'")
-
-    def _run(self, text: str, user_id: str, metadata: dict = None):
-        m = Memory()
-        result = m.add(text, user_id=user_id, metadata=metadata)
-        return result
-
-class GetAllMemoriesTool(BaseTool):
-    name: str = "Get All Memories Tool"
-    description: str = ("This tool retrieves all stored memories.\n"
-                        "Example:\n"
-                        "   - Input: action='get_all'\n"
-                        "   - Output: List of all stored memories.")
-
-    def _run(self):
-        m = Memory()
-        result = m.get_all()
-        return result
-
-class SearchMemoryTool(BaseTool):
-    name: str = "Search Memory Tool"
-    description: str = ("This tool searches for specific memories based on a query and user ID.\n"
-                        "Example:\n"
-                        "   - Input: query='What are Alice's hobbies?', user_id='alice'\n"
-                        "   - Output: Search results related to Alice's hobbies.")
-
-    def _run(self, query: str, user_id: str):
-        m = Memory()
-        result = m.search(query=query, user_id=user_id)
-        return result
-
-class UpdateMemoryTool(BaseTool):
-    name: str = "Update Memory Tool"
-    description: str = ("This tool updates an existing memory by memory ID and new data.\n"
-                        "Example:\n"
-                        "   - Input: memory_id='cb032b42-0703-4b9c-954d-77c36abdd660', data='Likes to play tennis on weekends'\n"
-                        "   - Output: Memory updated to 'Likes to play tennis on weekends.'")
-
-    def _run(self, memory_id: str, data: str):
-        m = Memory()
-        result = m.update(memory_id=memory_id, data=data)
-        return result
-
-class MemoryHistoryTool(BaseTool):
-    name: str = "Memory History Tool"
-    description: str = ("This tool gets the history of changes made to a specific memory by memory ID.\n"
-                        "Example:\n"
-                        "   - Input: memory_id='cb032b42-0703-4b9c-954d-77c36abdd660'\n"
-                        "   - Output: History of the specified memory.")
-
-    def _run(self, memory_id: str):
-        m = Memory()
-        result = m.history(memory_id=memory_id)
-        return result
-
-
-from duckduckgo_search import DDGS
-from praisonai_tools import BaseTool
-
-class InternetSearchTool(BaseTool):
-    name: str = "InternetSearchTool"
-    description: str = "Search Internet for relevant information based on a query or latest news"
-
-    def _run(self, query: str):
-        ddgs = DDGS()
-        results = ddgs.text(keywords=query, region='wt-wt', safesearch='moderate', max_results=5)
-        return results
-    
-
-
-# Example agent_yaml content
-
-import os
-import yaml
-from praisonai import PraisonAI
-
-agent_yaml = """
-framework: "crewai"
-topic: "personal memory management"
-roles:
-  data_analyst:
-    role: "Data Analyst"
-    backstory: "Skilled in analyzing data to find trends and insights."
-    goal: "Analyze the data to provide useful insights and recommendations."
-    tasks:
-      research_ai_news:
-        description: "Analyze the latest AI news from July 2024 and trends to provide insights and recommendations."
-        expected_output: "Report with insights on the latest AI trends and personalized recommendations."
-    tools:
-      - "InternetSearchTool"
-  user_support:
-    role: "User Support"
-    backstory: "Expert in assisting users with queries and issues related to memory management."
-    goal: "Provide support to users for adding information to memories."
-    tasks:
-      support_users:
-        description: "Assist users in adding information to memories."
-        expected_output: "User queries resolved and memories managed effectively."
-    tools:
-      - "AddMemoryTool"
-      - "GetAllMemoriesTool"
-      - "SearchMemoryTool"
-
-"""
-
-# Create a PraisonAI instance with the agent_yaml content
-praisonai = PraisonAI(agent_yaml=agent_yaml)
-
-# Add OPENAI_API_KEY Secrets to Google Colab on the Left Hand Side 🔑 or Enter Manually Below
-# os.environ["OPENAI_API_KEY"] = userdata.get('OPENAI_API_KEY') or "ENTER OPENAI_API_KEY HERE"
-openai_api_key = os.getenv("OPENAI_API_KEY")
-
-# Run PraisonAI
-result = praisonai.run()
-
-# Print the result
-print(result)

cookbooks/python/story.md

@@ -1,49 +0,0 @@
-```markdown
-# The Secret Meeting Spot
-
-![The Secret Meeting Spot](A serene and vibrant illustration of the Enchanted Forest, with Luna the Wise Owl perched on a branch of the ancient oak tree. Max the Brave Squirrel stands excitedly next to the tree, and Ella the Curious Fawn gazes at a mysterious map held by Luna. The forest is lush with magical flora and a soft, mystical glow, capturing the sense of wonder and the beginning of their adventure.)
-
-## Chapter 1: The Secret Meeting Spot
-
-Luna the Wise Owl had called for a secret meeting in the heart of the Enchanted Forest. Perched on the branch of the ancient oak tree, she awaited her friends with a mysterious map clutched in her talons. Max the Brave Squirrel scampered up to the tree, his eyes gleaming with excitement. Ella the Curious Fawn approached, her gaze fixed on the map that promised an adventure like no other. The forest around them was alive with magical flora, casting a soft, mystical glow that hinted at the wonders to come.
-
----
-
-# The Mysterious Riverbank
-
-![The Mysterious Riverbank](A lively scene at the bustling riverbank, featuring Benny the Playful Beaver busy constructing a sturdy wooden bridge. Luna, Max, Ella, and Benny are depicted crossing the bridge, while the river sparkles beneath them. Strange markings on the trees along the riverbank hint at the presence of others, creating an atmosphere of mystery and excitement.)
-
-## Chapter 2: The Mysterious Riverbank
-
-The group made their way to the bustling riverbank, where Benny the Playful Beaver was hard at work constructing a sturdy wooden bridge. Luna, Max, Ella, and Benny crossed the bridge together, the river sparkling beneath them. As they journeyed along the riverbank, they noticed strange markings on the trees, hinting at the presence of others. The air was filled with an atmosphere of mystery and excitement, urging them forward on their quest.
-
----
-
-# The Hidden Glade of Whispers
-
-![The Hidden Glade of Whispers](A magical hidden glade where the wind whispers secrets. Mia the Shy Rabbit stands with Luna, Max, Ella, and Benny, all gathered around as they decipher the whispers. Sunlight filters through the trees, and the glade is filled with ethereal light and soft colors, reflecting the growing bond and shared purpose of the friends as they solve the riddle together.)
-
-## Chapter 3: The Hidden Glade of Whispers
-
-In the heart of the forest lay the Hidden Glade of Whispers, a place where the wind itself shared secrets. Mia the Shy Rabbit joined Luna, Max, Ella, and Benny as they gathered to decipher the whispers. Sunlight filtered through the trees, casting an ethereal light that enveloped the glade in soft colors. It was here that the bond between the friends grew stronger, their shared purpose guiding them as they unraveled the riddle together.
-
----
-
-# The Cavern of Echoes
-
-![The Cavern of Echoes](Inside the dark and mysterious cavern, illuminated by Oliver the Inventive Raccoon's gadgets. The friends, including Luna, Max, Ella, Benny, and Mia, navigate the maze-like tunnels, facing challenges together. The echoes play tricks on their minds, portrayed with swirling shadows and light, highlighting their teamwork and trust as they discover a crucial clue.)
-
-## Chapter 4: The Cavern of Echoes
-
-The journey led them to the Cavern of Echoes, a dark and mysterious place where Oliver the Inventive Raccoon's gadgets illuminated their path. Together, Luna, Max, Ella, Benny, and Mia navigated the maze-like tunnels, each echo playing tricks on their minds. Swirling shadows and light portrayed the challenges they faced, their teamwork and trust shining through as they discovered a crucial clue that would lead them to their goal.
-
----
-
-# The Treasure of Friendship
-
-![The Treasure of Friendship](A serene meadow bathed in the warm glow of the setting sun, where the friends uncover a chest filled with seeds and a heartfelt message. The group, united and joyful, plants the seeds together, symbolizing growth and new adventures. The scene captures the essence of friendship and the realization of their true treasure, with a backdrop of nature's beauty and promise of more to come.)
-
-## Chapter 5: The Treasure of Friendship
-
-Finally, the friends emerged into a serene meadow bathed in the warm glow of the setting sun. There, they uncovered a chest filled with seeds and a heartfelt message. United and joyful, they planted the seeds together, a symbol of growth and new adventures on the horizon. The scene captured the essence of friendship, the realization of their true treasure, and the promise of nature's beauty and more adventures to come.
-```

cookbooks/tools/tools.py

@@ -1,72 +0,0 @@
-# tools.py
-from duckduckgo_search import DDGS
-from praisonai_tools import BaseTool
-
-class InternetSearchTool(BaseTool):
-    name: str = "InternetSearchTool"
-    description: str = "Search Internet for relevant information based on a query or latest news"
-
-    def _run(self, query: str):
-        ddgs = DDGS()
-        results = ddgs.text(keywords=query, region='wt-wt', safesearch='moderate', max_results=5)
-        return results
-    
-from langchain_community.tools.pubmed.tool import PubmedQueryRun
-from langchain_community.tools.reddit_search.tool import RedditSearchRun
-# pip install tavily-python
-from langchain_community.utilities.tavily_search import TavilySearchAPIWrapper
-from langchain_community.utilities.you import YouSearchAPIWrapper
-# pip install youtube_search
-from langchain_community.tools import YouTubeSearchTool
-# pip install wikipedia
-from langchain_community.utilities import WikipediaAPIWrapper
-
-class TavilyTool(BaseTool):
-    name: str = "TavilyTool"
-    description: str = "Search Tavily for relevant information based on a query."
-
-    def _run(self, query: str):
-        api_wrapper = TavilySearchAPIWrapper()
-        results = api_wrapper.results(query=query, max_results=5)
-        return results
-
-class YouSearchTool(BaseTool):
-    name: str = "You Search Tool"
-    description: str = "Search You.com for relevant information based on a query."
-
-    def _run(self, query: str):
-        api_wrapper = YouSearchAPIWrapper()
-        results = api_wrapper.results(query=query, max_results=5)
-        return results
-
-class WikipediaSearchTool(BaseTool):
-    name: str = "WikipediaSearchTool"
-    description: str = "Search Wikipedia for relevant information based on a query."
-
-    def _run(self, query: str):
-        api_wrapper = WikipediaAPIWrapper(top_k_results=4, doc_content_chars_max=100)
-        results = api_wrapper.load(query=query)
-        return results
-
-# pip install open-interpreter
-from interpreter import interpreter
-from praisonai_tools import BaseTool
-
-class OpenInterpreterTool(BaseTool):
-    name: str = "Open Interpreter Tool"
-    description: str = "Use Open Interpreter configured to create and execute code based on natural language commands."
-
-    def __init__(self):
-        super().__init__()
-        interpreter.auto_run = True
-
-    def _run(self, code: str):
-        result = interpreter.chat(code)
-        return result
-
-# Example usage
-if __name__ == "__main__":
-    tool = OpenInterpreterTool()
-    code = "Plot AAPL and META's normalized stock prices"
-    output = tool._run(code)
-    print(output)

docker/Dockerfile

@@ -1,6 +1,6 @@
 FROM python:3.11-slim
 WORKDIR /app
 COPY . .
-RUN pip install flask praisonai==1.0.10 gunicorn markdown
+RUN pip install flask praisonai==2.2.5 gunicorn markdown
 EXPOSE 8080
 CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]

docker/Dockerfile.chat

@@ -0,0 +1,24 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    gcc \
+    python3-dev \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Python packages
+RUN pip install --no-cache-dir \
+    praisonaiagents>=0.0.4 \
+    praisonai_tools \
+    "praisonai==2.2.5" \
+    "praisonai[chat]" \
+    "embedchain[github,youtube]"
+
+# Copy application code
+COPY . .
+
+# Default command (will be overridden by docker-compose)
+CMD ["praisonai", "chat"]

docker/Dockerfile.dev

@@ -0,0 +1,28 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    gcc \
+    python3-dev \
+    portaudio19-dev \
+    python3-pyaudio \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Python packages
+RUN pip install --no-cache-dir \
+    praisonaiagents>=0.0.4 \
+    praisonai_tools \
+    "praisonai==2.2.5" \
+    "praisonai[ui]" \
+    "praisonai[chat]" \
+    "praisonai[realtime]" \
+    "embedchain[github,youtube]"
+
+# Copy application code
+COPY . .
+
+# Default command (will be overridden by docker-compose)
+CMD ["praisonai", "ui"]

docker/Dockerfile.ui

@@ -0,0 +1,24 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    gcc \
+    python3-dev \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Python packages
+RUN pip install --no-cache-dir \
+    praisonaiagents>=0.0.4 \
+    praisonai_tools \
+    "praisonai==2.2.5" \
+    "praisonai[ui]" \
+    "praisonai[crewai]"
+
+# Copy application code
+COPY . .
+
+# Default command (will be overridden by docker-compose)
+CMD ["praisonai", "ui"]

docker/docker-compose.yml

@@ -0,0 +1,21 @@
+services:
+  ui:
+    build:
+      context: .
+      dockerfile: Dockerfile.ui
+    volumes:
+      - .:/app
+    ports:
+      - "8082:8082"
+    environment:
+      FLASK_ENV: development
+      CHAINLIT_PORT: "8082"
+      CHAINLIT_HOST: "0.0.0.0"
+      OPENAI_API_KEY: ${OPENAI_API_KEY}
+      CHAINLIT_AUTH_SECRET: ${CHAINLIT_AUTH_SECRET}
+    command: praisonai ui --host 0.0.0.0
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8082"]
+      interval: 10s
+      timeout: 5s
+      retries: 3

docker/services.yaml

@@ -0,0 +1,5 @@
+framework: praisonaiagents
+services:
+  - ui
+  - chat
+  - realtime

docs/agents/agents.mdx

@@ -0,0 +1,124 @@
+---
+title: "AI Agents"
+description: "Overview of all available PraisonAI agents and their capabilities"
+icon: "robot"
+---
+
+PraisonAI provides a diverse set of specialized agents for various tasks. Each agent is designed with specific capabilities and tools to handle different types of tasks effectively.
+
+```mermaid
+graph LR
+    %% Define the main flow
+    Start([▶ Start]) --> Agent1
+    Agent1 --> Process[⚙ Process]
+    Process --> Agent2
+    Agent2 --> Output([✓ Output])
+    Process -.-> Agent1
+    
+    %% Define subgraphs for agents and their tasks
+    subgraph Agent1[ ]
+        Task1[📋 Task]
+        AgentIcon1[🤖 AI Agent]
+        Tools1[🔧 Tools]
+        
+        Task1 --- AgentIcon1
+        AgentIcon1 --- Tools1
+    end
+    
+    subgraph Agent2[ ]
+        Task2[📋 Task]
+        AgentIcon2[🤖 AI Agent]
+        Tools2[🔧 Tools]
+        
+        Task2 --- AgentIcon2
+        AgentIcon2 --- Tools2
+    end
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef tools fill:#2E8B57,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Start,Output,Task1,Task2 input
+    class Process,AgentIcon1,AgentIcon2 process
+    class Tools1,Tools2 tools
+    class Agent1,Agent2 transparent
+```
+
+## Data & Analysis
+
+<CardGroup cols={2}>
+  <Card title="Data Analyst" icon="chart-line" href="/agents/data-analyst">
+    Analyze data from various sources, create visualizations, and generate insights.
+  </Card>
+  <Card title="Finance" icon="money-bill-trend-up" href="/agents/finance">
+    Track stocks, analyze financial data, and provide investment recommendations.
+  </Card>
+  <Card title="Research" icon="magnifying-glass-chart" href="/agents/research">
+    Conduct comprehensive research and analysis across various topics.
+  </Card>
+  <Card title="Wikipedia" icon="book" href="/agents/wikipedia">
+    Search and extract information from Wikipedia articles.
+  </Card>
+</CardGroup>
+
+## Media & Content
+
+<CardGroup cols={2}>
+  <Card title="Image Analysis" icon="image" href="/agents/image">
+    Analyze and understand visual content from images.
+  </Card>
+  <Card title="Image to Text" icon="text" href="/agents/image-to-text">
+    Convert images to textual descriptions and extract text content.
+  </Card>
+  <Card title="Video" icon="video" href="/agents/video">
+    Analyze video content and extract meaningful information.
+  </Card>
+  <Card title="Markdown" icon="markdown" href="/agents/markdown">
+    Generate and format content in Markdown syntax.
+  </Card>
+</CardGroup>
+
+## Search & Recommendations
+
+<CardGroup cols={2}>
+  <Card title="Web Search" icon="globe" href="/agents/websearch">
+    Perform intelligent web searches and gather information.
+  </Card>
+  <Card title="Recommendation" icon="thumbs-up" href="/agents/recommendation">
+    Generate personalized recommendations based on preferences.
+  </Card>
+  <Card title="Shopping" icon="shop" href="/agents/shopping">
+    Compare prices and find the best deals across stores.
+  </Card>
+  <Card title="Planning" icon="calendar" href="/agents/planning">
+    Create travel plans and detailed itineraries.
+  </Card>
+</CardGroup>
+
+## Development
+
+<CardGroup cols={2}>
+  <Card title="Programming" icon="code" href="/agents/programming">
+    Write, analyze, and debug code across multiple languages.
+  </Card>
+  <Card title="Single Agent" icon="circle-1" href="/agents/single">
+    Simple, focused agent for basic tasks without external tools.
+  </Card>
+</CardGroup>
+
+## Getting Started
+
+Each agent can be easily initialized and customized for your specific needs. Here's a basic example:
+
+```python
+from praisonaiagents import Agent
+
+# Create an agent with specific instructions
+agent = Agent(instructions="Your task-specific instructions")
+
+# Start the agent with a task
+response = agent.start("Your task description")
+```
+
+For more detailed information about each agent, click on the respective cards above.

docs/agents/data-analyst.mdx

@@ -0,0 +1,120 @@
+---
+title: "Data Analyst Agent"
+sidebarTitle: "Data Analyst"
+description: "Learn how to create AI agents for data analysis and insights generation."
+icon: "chart-line"
+---
+
+```mermaid
+flowchart LR
+    In[Data Source] --> Reader[Data Reader]
+    Reader --> Analyzer[Data Analyzer]
+    Analyzer --> Generator[Insights Generator]
+    Generator --> Out[Output]
+    
+    style In fill:#8B0000,color:#fff
+    style Reader fill:#2E8B57,color:#fff
+    style Analyzer fill:#2E8B57,color:#fff
+    style Generator fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+A workflow demonstrating how the Data Analyst Agent can read data from various sources, analyze it, and generate insights.
+
+## Quick Start
+
+<Steps>
+    <Step title="Install Package">
+        First, install the PraisonAI Agents package:
+        ```bash
+        pip install praisonaiagents
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+    </Step>
+
+    <Step title="Create Script">
+        Create a new file `data_analysis.py`:
+        ```python
+        from praisonaiagents import Agent, Tools
+        from praisonaiagents.tools import (
+            read_csv, read_excel, write_csv, write_excel,
+            filter_data, get_summary, group_by, pivot_table
+        )
+
+        agent = Agent(
+            instructions="You are a Data Analyst Agent",
+            tools=[
+                read_csv, read_excel, write_csv, write_excel,
+                filter_data, get_summary, group_by, pivot_table
+            ]
+        )
+
+        # Start analysis with a specific task
+        agent.start(f"""
+            Read the data from the csv file {os.path.join(os.path.dirname(__file__), "tesla-stock-price.csv")}
+            Analyse the data and give me the insights
+            read_csv to read the file
+        """)
+        ```
+    </Step>
+</Steps>
+
+## Understanding Data Analysis Workflow
+
+The Data Analyst Agent is designed to perform comprehensive data analysis tasks using a suite of specialized tools. Here's how it works:
+
+1. **Data Reading**: The agent can read data from various sources:
+   - CSV files using `read_csv`
+   - Excel files using `read_excel`
+
+2. **Data Analysis**: Multiple analysis tools are available:
+   - `filter_data`: Filter datasets based on conditions
+   - `get_summary`: Generate statistical summaries
+   - `group_by`: Group data by specific columns
+   - `pivot_table`: Create pivot tables for analysis
+
+3. **Data Export**: Results can be exported to:
+   - CSV format using `write_csv`
+   - Excel format using `write_excel`
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Multiple Data Sources" icon="table">
+    Support for both CSV and Excel file formats.
+  </Card>
+  <Card title="Analysis Tools" icon="calculator">
+    Comprehensive suite of analysis tools including filtering, summarization, and pivoting.
+  </Card>
+  <Card title="Data Export" icon="file-export">
+    Export capabilities to various formats.
+  </Card>
+  <Card title="Automated Insights" icon="lightbulb">
+    Automatic generation of data insights and patterns.
+  </Card>
+</CardGroup>
+
+## Example Usage
+
+```python
+# Example: Analyzing stock data
+agent.start("""
+    1. Read 'stock_data.csv'
+    2. Filter data for the last 30 days
+    3. Calculate daily returns
+    4. Generate summary statistics
+    5. Export results to 'analysis_results.xlsx'
+""")
+```
+
+## Next Steps
+
+- Learn about [Prompt Chaining](/features/promptchaining) for complex analysis workflows
+- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving analysis accuracy
+- Check out other specialized agents like the [Finance Agent](/agents/finance) for specific use cases

docs/agents/finance.mdx

@@ -0,0 +1,97 @@
+---
+title: "Finance Agent"
+sidebarTitle: "Finance"
+description: "Learn how to create AI agents for financial analysis and investment recommendations."
+icon: "money-bill-trend-up"
+---
+
+```mermaid
+flowchart LR
+    In[Request] --> Price[Stock Price]
+    Price --> Info[Stock Info]
+    Info --> History[Historical Data]
+    History --> Out[Investment Advice]
+    
+    style In fill:#8B0000,color:#fff
+    style Price fill:#2E8B57,color:#fff
+    style Info fill:#2E8B57,color:#fff
+    style History fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+A workflow demonstrating how the Finance Agent can analyze stock market data and provide investment recommendations.
+
+## Quick Start
+
+<Steps>
+    <Step title="Install Package">
+        First, install the PraisonAI Agents package:
+        ```bash
+        pip install praisonaiagents
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+    </Step>
+
+    <Step title="Create Script">
+        Create a new file `finance_analysis.py`:
+        ```python
+        from praisonaiagents import Agent, Tools
+        from praisonaiagents.tools import get_stock_price, get_stock_info, get_historical_data
+
+        agent = Agent(
+            instructions="You are a Research Agent",
+            tools=[get_stock_price, get_stock_info, get_historical_data]
+        )
+        agent.start("Understand current stock price and historical data of Apple and Google. Tell me if I can invest in them")
+        ```
+    </Step>
+</Steps>
+
+## Understanding Financial Analysis
+
+The Finance Agent specializes in stock market analysis and investment recommendations using three key components:
+
+1. **Real-time Price Data**: Uses `get_stock_price` to fetch current market prices
+2. **Company Information**: Retrieves company details using `get_stock_info`
+3. **Historical Analysis**: Analyzes trends with `get_historical_data`
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Real-time Data" icon="clock">
+    Access to current stock market prices and information.
+  </Card>
+  <Card title="Company Analysis" icon="building">
+    Detailed company information and fundamentals.
+  </Card>
+  <Card title="Historical Trends" icon="chart-line">
+    Analysis of historical price movements and patterns.
+  </Card>
+  <Card title="Investment Advice" icon="money-bill">
+    AI-powered investment recommendations.
+  </Card>
+</CardGroup>
+
+## Example Usage
+
+```python
+# Example: Analyzing specific stocks
+agent.start("""
+    1. Get current prices for AAPL and GOOGL
+    2. Retrieve company information
+    3. Analyze 6-month historical data
+    4. Provide investment recommendations
+""")
+```
+
+## Next Steps
+
+- Learn about [Prompt Chaining](/features/promptchaining) for complex financial analysis
+- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving recommendation accuracy
+- Check out the [Data Analyst Agent](/agents/data-analyst) for detailed data analysis capabilities

docs/agents/image-to-text.mdx

@@ -0,0 +1,140 @@
+---
+title: "Image to Text Agent"
+sidebarTitle: "Image to Text"
+description: "Learn how to create AI agents for converting images to textual descriptions and extracting text from images."
+icon: "text"
+---
+
+```mermaid
+flowchart LR
+    In[Image Input] --> OCR[Text Extractor]
+    OCR --> Analyzer[Content Analyzer]
+    Analyzer --> Generator[Description Generator]
+    Generator --> Out[Text Output]
+    
+    style In fill:#8B0000,color:#fff
+    style OCR fill:#2E8B57,color:#fff
+    style Analyzer fill:#2E8B57,color:#fff
+    style Generator fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+A workflow demonstrating how the Image-to-Text Agent can extract text from images and generate comprehensive descriptions.
+
+## Quick Start
+
+<Steps>
+    <Step title="Install Package">
+        First, install the PraisonAI Agents package:
+        ```bash
+        pip install praisonaiagents
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+    </Step>
+
+    <Step title="Create Script">
+        Create a new file `image_to_text.py`:
+        ```python
+        from praisonaiagents import Agent, Task, PraisonAIAgents
+
+        # Create Image-to-Text Agent
+        image_text_agent = Agent(
+            name="ImageTextConverter",
+            role="Image Text Extraction Specialist",
+            goal="Convert image content to textual descriptions and extract text",
+            backstory="""You are an expert in OCR and image understanding.
+            You excel at extracting text from images and generating detailed descriptions.""",
+            llm="gpt-4o-mini",
+            self_reflect=False
+        )
+
+        # Create text extraction task
+        extraction_task = Task(
+            name="extract_text",
+            description="Extract all text from this image and describe its layout.",
+            expected_output="Extracted text and layout description",
+            agent=image_text_agent,
+            images=["document.jpg"]
+        )
+
+        # Create description task
+        description_task = Task(
+            name="generate_description",
+            description="Generate a detailed description of the image content.",
+            expected_output="Comprehensive description of visual elements",
+            agent=image_text_agent,
+            images=["scene.jpg"]
+        )
+
+        # Create PraisonAIAgents instance
+        agents = PraisonAIAgents(
+            agents=[image_text_agent],
+            tasks=[extraction_task, description_task],
+            process="sequential",
+            verbose=1
+        )
+
+        # Run analysis
+        agents.start()
+        ```
+    </Step>
+</Steps>
+
+## Understanding Image-to-Text Conversion
+
+The Image-to-Text Agent combines multiple capabilities to convert visual content into textual form:
+
+1. **OCR Processing**: Extracts text from images using optical character recognition
+2. **Layout Analysis**: Understands the spatial arrangement of text and visual elements
+3. **Content Description**: Generates natural language descriptions of image content
+4. **Text Formatting**: Preserves text formatting and structure where possible
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Text Extraction" icon="text">
+    Advanced OCR capabilities for text extraction.
+  </Card>
+  <Card title="Layout Understanding" icon="table-layout">
+    Analysis of text and content layout.
+  </Card>
+  <Card title="Content Description" icon="pen-to-square">
+    Detailed descriptions of visual content.
+  </Card>
+  <Card title="Format Preservation" icon="paragraph">
+    Maintains text formatting and structure.
+  </Card>
+</CardGroup>
+
+## Example Usage
+
+```python
+# Example: Processing a document image
+document_task = Task(
+    name="process_document",
+    description="Extract text and analyze document layout",
+    expected_output="Extracted text with layout information",
+    agent=image_text_agent,
+    images=["business_document.jpg"]
+)
+
+# Run single task
+agents = PraisonAIAgents(
+    agents=[image_text_agent],
+    tasks=[document_task],
+    process="sequential"
+)
+agents.start()
+```
+
+## Next Steps
+
+- Learn about [Prompt Chaining](/features/promptchaining) for complex document processing
+- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving text extraction accuracy
+- Check out the [Image Agent](/agents/image) for pure image analysis capabilities

docs/agents/image.mdx

@@ -0,0 +1,139 @@
+---
+title: "Image Analysis Agent"
+sidebarTitle: "Image Analysis"
+description: "Learn how to create AI agents for image analysis and visual content understanding."
+icon: "image"
+---
+
+```mermaid
+flowchart LR
+    In[Image Input] --> Analyzer[Image Analyzer]
+    Analyzer --> Detector[Object Detector]
+    Detector --> Generator[Description Generator]
+    Generator --> Out[Analysis Output]
+    
+    style In fill:#8B0000,color:#fff
+    style Analyzer fill:#2E8B57,color:#fff
+    style Detector fill:#2E8B57,color:#fff
+    style Generator fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+A workflow demonstrating how the Image Analysis Agent can process and analyze visual content, detect objects, and generate detailed descriptions.
+
+## Quick Start
+
+<Steps>
+    <Step title="Install Package">
+        First, install the PraisonAI Agents package:
+        ```bash
+        pip install praisonaiagents
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+    </Step>
+
+    <Step title="Create Script">
+        Create a new file `image_analysis.py`:
+        ```python
+        from praisonaiagents import Agent, Task, PraisonAIAgents
+
+        # Create Image Analysis Agent
+        image_agent = Agent(
+            name="ImageAnalyst",
+            role="Image Analysis Specialist",
+            goal="Analyze images and videos to extract meaningful information",
+            backstory="""You are an expert in computer vision and image analysis.
+            You excel at describing images, detecting objects, and understanding visual content.""",
+            llm="gpt-4o-mini",
+            self_reflect=False
+        )
+
+        # Create tasks for different types of analysis
+        task1 = Task(
+            name="analyze_landmark",
+            description="Describe this famous landmark and its architectural features.",
+            expected_output="Detailed description of the landmark's architecture and significance",
+            agent=image_agent,
+            images=["https://example.com/landmark.jpg"]
+        )
+
+        task2 = Task(
+            name="analyze_local_image",
+            description="What objects can you see in this image? Describe their arrangement.",
+            expected_output="Detailed description of objects and their spatial relationships",
+            agent=image_agent,
+            images=["local_image.jpg"]
+        )
+
+        # Create PraisonAIAgents instance
+        agents = PraisonAIAgents(
+            agents=[image_agent],
+            tasks=[task1, task2],
+            process="sequential",
+            verbose=1
+        )
+
+        # Run analysis
+        agents.start()
+        ```
+    </Step>
+</Steps>
+
+## Understanding Image Analysis
+
+The Image Analysis Agent is designed to process and understand visual content through several key capabilities:
+
+1. **Image Input**: Supports both URL and local file inputs
+2. **Object Detection**: Identifies and locates objects within images
+3. **Architectural Analysis**: Specialized in analyzing architectural features
+4. **Spatial Understanding**: Describes spatial relationships between objects
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Multiple Input Sources" icon="images">
+    Support for both URL and local image files.
+  </Card>
+  <Card title="Object Detection" icon="magnifying-glass">
+    Advanced object detection and recognition.
+  </Card>
+  <Card title="Architectural Analysis" icon="building">
+    Specialized analysis of architectural features.
+  </Card>
+  <Card title="Detailed Descriptions" icon="pen">
+    Generation of comprehensive visual descriptions.
+  </Card>
+</CardGroup>
+
+## Example Usage
+
+```python
+# Example: Analyzing a landmark image
+landmark_task = Task(
+    name="analyze_famous_landmark",
+    description="Analyze this historical landmark",
+    expected_output="Architectural details and historical significance",
+    agent=image_agent,
+    images=["https://example.com/landmark.jpg"]
+)
+
+# Run single task
+agents = PraisonAIAgents(
+    agents=[image_agent],
+    tasks=[landmark_task],
+    process="sequential"
+)
+agents.start()
+```
+
+## Next Steps
+
+- Learn about [Prompt Chaining](/features/promptchaining) for complex image analysis workflows
+- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving analysis accuracy
+- Check out the [Video Agent](/agents/video) for video content analysis

docs/agents/markdown.mdx

@@ -0,0 +1,120 @@
+---
+title: "Markdown Agent"
+sidebarTitle: "Markdown"
+description: "Learn how to create AI agents for generating and formatting content in Markdown."
+icon: "markdown"
+---
+
+```mermaid
+flowchart LR
+    In[Content Request] --> Generator[Content Generator]
+    Generator --> Formatter[Markdown Formatter]
+    Formatter --> Validator[Format Validator]
+    Validator --> Out[Markdown Output]
+    
+    style In fill:#8B0000,color:#fff
+    style Generator fill:#2E8B57,color:#fff
+    style Formatter fill:#2E8B57,color:#fff
+    style Validator fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+A workflow demonstrating how the Markdown Agent can generate and format content in Markdown syntax.
+
+## Quick Start
+
+<Steps>
+    <Step title="Install Package">
+        First, install the PraisonAI Agents package:
+        ```bash
+        pip install praisonaiagents
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+    </Step>
+
+    <Step title="Create Script">
+        Create a new file `markdown_generator.py`:
+        ```python
+        from praisonaiagents import Agent
+
+        # Create Markdown Agent
+        markdown_agent = Agent(
+            name="MarkdownWriter",
+            role="Markdown Content Specialist",
+            goal="Generate well-formatted content in Markdown syntax",
+            instructions="You are a Markdown Agent, output in markdown format",
+            llm="gpt-4o-mini",
+            self_reflect=False
+        )
+
+        # Generate content
+        response = markdown_agent.start(
+            "Write a blog post about artificial intelligence"
+        )
+        
+        # Save to file
+        with open('blog_post.md', 'w') as f:
+            f.write(response)
+        ```
+    </Step>
+</Steps>
+
+## Understanding Markdown Generation
+
+The Markdown Agent specializes in creating properly formatted Markdown content:
+
+1. **Content Generation**: Creates original content based on prompts
+2. **Markdown Formatting**: Applies proper Markdown syntax
+3. **Structure Validation**: Ensures correct formatting
+4. **Document Organization**: Creates well-structured documents
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Content Creation" icon="pen-to-square">
+    Generates original, well-structured content.
+  </Card>
+  <Card title="Markdown Syntax" icon="code">
+    Proper implementation of Markdown formatting.
+  </Card>
+  <Card title="Document Structure" icon="sitemap">
+    Organized document hierarchy and sections.
+  </Card>
+  <Card title="Format Validation" icon="check">
+    Ensures correct Markdown syntax usage.
+  </Card>
+</CardGroup>
+
+## Example Usage
+
+```python
+# Example: Generate a technical documentation
+agent = Agent(
+    instructions="You are a Markdown Agent, output in markdown format"
+)
+
+# Generate API documentation
+response = agent.start("""
+    Create technical documentation for a REST API with:
+    - Introduction
+    - Authentication
+    - Endpoints
+    - Examples
+""")
+
+# Save documentation
+with open('api_docs.md', 'w') as f:
+    f.write(response)
+```
+
+## Next Steps
+
+- Learn about [Prompt Chaining](/features/promptchaining) for complex document generation
+- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving content quality
+- Check out the [Documentation Agent](/agents/documentation) for specialized documentation generation

docs/agents/planning.mdx

@@ -0,0 +1,109 @@
+---
+title: "Planning Agent"
+sidebarTitle: "Planning"
+description: "Learn how to create AI agents for trip planning and itinerary generation."
+icon: "calendar"
+---
+
+```mermaid
+flowchart LR
+    In[Request] --> Search[Web Search]
+    Search --> Analyzer[Options Analyzer]
+    Analyzer --> Generator[Plan Generator]
+    Generator --> Out[Itinerary]
+    
+    style In fill:#8B0000,color:#fff
+    style Search fill:#2E8B57,color:#fff
+    style Analyzer fill:#2E8B57,color:#fff
+    style Generator fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+A workflow demonstrating how the Planning Agent can search for travel options and create detailed itineraries.
+
+## Quick Start
+
+<Steps>
+    <Step title="Install Package">
+        First, install the PraisonAI Agents package:
+        ```bash
+        pip install praisonaiagents
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+    </Step>
+
+    <Step title="Create Script">
+        Create a new file `travel_planner.py`:
+        ```python
+        from praisonaiagents import Agent, Tools
+        from praisonaiagents.tools import duckduckgo
+
+        # Create Planning Agent
+        planning_agent = Agent(
+            name="TravelPlanner",
+            role="Travel Planning Specialist",
+            goal="Create comprehensive travel plans and itineraries",
+            instructions="You are a Planning Agent",
+            tools=[duckduckgo]
+        )
+
+        # Generate travel plan
+        response = planning_agent.start(
+            "I want to go to London next week, find me a good hotel and flight"
+        )
+        
+        # Save plan
+        with open('travel_plan.txt', 'w') as f:
+            f.write(response)
+        ```
+    </Step>
+</Steps>
+
+## Understanding Travel Planning
+
+The Planning Agent combines multiple capabilities to create comprehensive travel plans:
+
+1. **Web Search**: Uses DuckDuckGo to find current travel options
+2. **Options Analysis**: Evaluates and compares different choices
+3. **Plan Generation**: Creates detailed itineraries
+4. **Recommendations**: Provides personalized suggestions
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Flight Search" icon="plane">
+    Finds and compares flight options.
+  </Card>
+  <Card title="Hotel Booking" icon="hotel">
+    Recommends suitable accommodations.
+  </Card>
+  <Card title="Itinerary Creation" icon="calendar-days">
+    Generates detailed travel schedules.
+  </Card>
+  <Card title="Real-time Data" icon="clock">
+    Uses current pricing and availability.
+  </Card>
+</CardGroup>
+
+## Example Usage
+
+```python
+# Example: Create a weekend trip plan
+from praisonaiagents import Agent, Tools
+from praisonaiagents.tools import duckduckgo
+
+agent = Agent(instructions="You are a Planning Agent", tools=[duckduckgo])
+agent.start("I want to go London next week, find me a good hotel and flight")
+```
+
+## Next Steps
+
+- Learn about [Prompt Chaining](/features/promptchaining) for complex travel planning
+- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving recommendations
+- Check out the [Research Agent](/agents/research) for detailed destination research

docs/agents/programming.mdx

@@ -0,0 +1,125 @@
+---
+title: "Programming Agent"
+sidebarTitle: "Programming"
+description: "Learn how to create AI agents for code development, analysis, and execution."
+icon: "code"
+---
+
+```mermaid
+flowchart LR
+    In[Code Request] --> Analyzer[Code Analyzer]
+    Analyzer --> Generator[Code Generator]
+    Generator --> Executor[Code Executor]
+    Executor --> Debugger[Code Debugger]
+    Debugger --> Out[Output]
+    
+    style In fill:#8B0000,color:#fff
+    style Analyzer fill:#2E8B57,color:#fff
+    style Generator fill:#2E8B57,color:#fff
+    style Executor fill:#2E8B57,color:#fff
+    style Debugger fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+A workflow demonstrating how the Programming Agent can analyze, generate, execute, and debug code.
+
+## Quick Start
+
+<Steps>
+    <Step title="Install Package">
+        First, install the PraisonAI Agents package:
+        ```bash
+        pip install praisonaiagents
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+    </Step>
+
+    <Step title="Create Script">
+        Create a new file `code_assistant.py`:
+        ```python
+        from praisonaiagents import Agent, Tools
+        from praisonaiagents.tools import execute_code, analyze_code, format_code, lint_code, disassemble_code # Code Tools
+        from praisonaiagents.tools import execute_command, list_processes, kill_process, get_system_info # Shell Tools
+        from praisonaiagents.tools import duckduckgo # Web Search Tool
+
+        agent = Agent(
+            instructions="You are a Programming Agent", self_reflect=True, min_reflect=5, max_reflect=10, 
+            tools=[execute_code, analyze_code, format_code, lint_code, disassemble_code, execute_command, list_processes, kill_process, get_system_info, duckduckgo]
+        )
+        agent.start(
+            "Write a python script using yfinance to find the stock price of Tesla"
+            "First check if required packages are installed"
+            "Run it using execute_code"
+            "execute_command if you want to run any terminal command"
+            "search internet using duckduckgo if you want to know update python package information"
+            "Analyse the output using analyze_code and fix error if required"
+            "if no package is installed, install it"
+            "then run the code"
+        )
+        ```
+    </Step>
+</Steps>
+
+## Understanding Code Development
+
+The Programming Agent combines multiple tools for comprehensive code development:
+
+1. **Code Tools**:
+   - `execute_code`: Run Python code
+   - `analyze_code`: Analyze code structure
+   - `format_code`: Format code to standards
+   - `lint_code`: Check code quality
+   - `disassemble_code`: View bytecode
+
+2. **Shell Tools**:
+   - `execute_command`: Run terminal commands
+   - `list_processes`: View running processes
+   - `kill_process`: Terminate processes
+   - `get_system_info`: System information
+
+3. **Web Tools**:
+   - `duckduckgo`: Search for programming resources
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Code Execution" icon="play">
+    Run and test code directly.
+  </Card>
+  <Card title="Code Analysis" icon="magnifying-glass-code">
+    Analyze and improve code quality.
+  </Card>
+  <Card title="System Integration" icon="terminal">
+    Execute system commands and manage processes.
+  </Card>
+  <Card title="Package Management" icon="box">
+    Handle dependencies and installations.
+  </Card>
+</CardGroup>
+
+## Example Usage
+
+```python
+# Example: Create and run a data analysis script
+response = agent.start("""
+    1. Create a script that:
+       - Uses pandas for data analysis
+       - Reads a CSV file
+       - Performs basic statistics
+       - Creates a visualization
+    2. Check and install required packages
+    3. Execute and analyze the results
+""")
+```
+
+## Next Steps
+
+- Learn about [Prompt Chaining](/features/promptchaining) for complex development workflows
+- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving code quality
+- Check out the [Data Analyst Agent](/agents/data-analyst) for specialized data analysis

docs/agents/recommendation.mdx

@@ -0,0 +1,109 @@
+---
+title: "Recommendation Agent"
+sidebarTitle: "Recommendation"
+description: "Learn how to create AI agents for personalized recommendations across various domains."
+icon: "thumbs-up"
+---
+
+```mermaid
+flowchart LR
+    In[User Preferences] --> Search[Content Search]
+    Search --> Analyzer[Preference Analyzer]
+    Analyzer --> Generator[Recommendation Generator]
+    Generator --> Out[Recommendations]
+    
+    style In fill:#8B0000,color:#fff
+    style Search fill:#2E8B57,color:#fff
+    style Analyzer fill:#2E8B57,color:#fff
+    style Generator fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+A workflow demonstrating how the Recommendation Agent can analyze preferences and generate personalized recommendations.
+
+## Quick Start
+
+<Steps>
+    <Step title="Install Package">
+        First, install the PraisonAI Agents package:
+        ```bash
+        pip install praisonaiagents
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+    </Step>
+
+    <Step title="Create Script">
+        Create a new file `recommendation_system.py`:
+        ```python
+        from praisonaiagents import Agent, Tools
+        from praisonaiagents.tools import duckduckgo
+
+        # Create Recommendation Agent
+        recommendation_agent = Agent(
+            name="RecommendationEngine",
+            role="Recommendation Specialist",
+            goal="Generate personalized recommendations based on preferences",
+            instructions="You are a Recommendation Agent",
+            tools=[duckduckgo]
+        )
+
+        # Get recommendations
+        response = recommendation_agent.start(
+            "Recommend me a good movie to watch in 2025"
+        )
+        
+        # Save recommendations
+        with open('recommendations.txt', 'w') as f:
+            f.write(response)
+        ```
+    </Step>
+</Steps>
+
+## Understanding Recommendation System
+
+The Recommendation Agent uses multiple approaches to generate personalized suggestions:
+
+1. **Content Search**: Uses DuckDuckGo to find current options
+2. **Preference Analysis**: Understands user preferences
+3. **Recommendation Generation**: Creates personalized suggestions
+4. **Content Filtering**: Filters based on relevance and quality
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Personalization" icon="user">
+    Tailored recommendations based on preferences.
+  </Card>
+  <Card title="Real-time Data" icon="clock">
+    Up-to-date content and information.
+  </Card>
+  <Card title="Multi-domain" icon="layer-group">
+    Recommendations across various categories.
+  </Card>
+  <Card title="Content Filtering" icon="filter">
+    Quality-based content selection.
+  </Card>
+</CardGroup>
+
+## Example Usage
+
+```python
+# Example: Get personalized recommendations
+from praisonaiagents import Agent, Tools
+from praisonaiagents.tools import duckduckgo
+
+agent = Agent(instructions="You are a Recommendation Agent", tools=[duckduckgo])
+agent.start("Recommend me a good movie to watch in 2025")
+```
+
+## Next Steps
+
+- Learn about [Prompt Chaining](/features/promptchaining) for complex recommendation systems
+- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving recommendation accuracy
+- Check out the [Research Agent](/agents/research) for detailed content research

docs/agents/research.mdx

@@ -0,0 +1,108 @@
+---
+title: "Research Agent"
+sidebarTitle: "Research"
+description: "Learn how to create AI agents for conducting comprehensive research and analysis."
+icon: "magnifying-glass-chart"
+---
+
+```mermaid
+flowchart LR
+    In[Research Query] --> Search[Web Search]
+    Search --> Analyzer[Content Analyzer]
+    Analyzer --> Synthesizer[Information Synthesizer]
+    Synthesizer --> Out[Research Report]
+    
+    style In fill:#8B0000,color:#fff
+    style Search fill:#2E8B57,color:#fff
+    style Analyzer fill:#2E8B57,color:#fff
+    style Synthesizer fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+A workflow demonstrating how the Research Agent can gather, analyze, and synthesize information from various sources.
+
+## Quick Start
+
+<Steps>
+    <Step title="Install Package">
+        First, install the PraisonAI Agents package:
+        ```bash
+        pip install praisonaiagents
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+    </Step>
+
+    <Step title="Create Script">
+        Create a new file `research_assistant.py`:
+        ```python
+        from praisonaiagents import Agent, Tools
+        from praisonaiagents.tools import duckduckgo
+
+        # Create Research Agent
+        research_agent = Agent(
+            name="ResearchAssistant",
+            role="Research Specialist",
+            goal="Conduct comprehensive research and analysis",
+            instructions="You are a Research Agent",
+            tools=[duckduckgo]
+        )
+
+        # Conduct research
+        response = research_agent.start(
+            "Research about AI developments in 2024"
+        )
+        
+        # Save research findings
+        with open('research_report.md', 'w') as f:
+            f.write(response)
+        ```
+    </Step>
+</Steps>
+
+## Understanding Research Process
+
+The Research Agent employs a systematic approach to information gathering and analysis:
+
+1. **Web Search**: Uses DuckDuckGo to find relevant sources
+2. **Content Analysis**: Evaluates source credibility and relevance
+3. **Information Synthesis**: Combines findings into coherent insights
+4. **Report Generation**: Creates structured research reports
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Web Research" icon="globe">
+    Comprehensive online information gathering.
+  </Card>
+  <Card title="Content Analysis" icon="microscope">
+    In-depth evaluation of sources.
+  </Card>
+  <Card title="Information Synthesis" icon="layer-group">
+    Integration of multiple sources.
+  </Card>
+  <Card title="Report Generation" icon="file-lines">
+    Structured research documentation.
+  </Card>
+</CardGroup>
+
+## Example Usage
+
+```python
+from praisonaiagents import Agent, Tools
+from praisonaiagents.tools import duckduckgo
+
+agent = Agent(instructions="You are a Research Agent", tools=[duckduckgo])
+agent.start("Research about AI 2024")
+```
+
+## Next Steps
+
+- Learn about [Prompt Chaining](/features/promptchaining) for complex research projects
+- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving research quality
+- Check out the [Data Analyst Agent](/agents/data-analyst) for data-driven research

docs/agents/shopping.mdx

@@ -0,0 +1,109 @@
+---
+title: "Shopping Agent"
+sidebarTitle: "Shopping"
+description: "Learn how to create AI agents for price comparison and shopping assistance."
+icon: "shop"
+---
+
+```mermaid
+flowchart LR
+    In[Product Query] --> Search[Store Search]
+    Search --> Analyzer[Price Analyzer]
+    Analyzer --> Comparator[Price Comparator]
+    Comparator --> Out[Price Report]
+    
+    style In fill:#8B0000,color:#fff
+    style Search fill:#2E8B57,color:#fff
+    style Analyzer fill:#2E8B57,color:#fff
+    style Comparator fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+A workflow demonstrating how the Shopping Agent can search for products, compare prices, and provide shopping recommendations.
+
+## Quick Start
+
+<Steps>
+    <Step title="Install Package">
+        First, install the PraisonAI Agents package:
+        ```bash
+        pip install praisonaiagents
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+    </Step>
+
+    <Step title="Create Script">
+        Create a new file `shopping_assistant.py`:
+        ```python
+        from praisonaiagents import Agent, Tools
+        from praisonaiagents.tools import duckduckgo
+
+        # Create Shopping Agent
+        shopping_agent = Agent(
+            name="ShoppingAssistant",
+            role="Shopping Specialist",
+            goal="Find the best prices and deals across stores",
+            instructions="You are a Shopping Agent",
+            tools=[duckduckgo]
+        )
+
+        # Search for product prices
+        response = shopping_agent.start(
+            "I want to buy iPhone 16 Pro Max, check 5 stores and give me price in table"
+        )
+        
+        # Save price comparison
+        with open('price_comparison.md', 'w') as f:
+            f.write(response)
+        ```
+    </Step>
+</Steps>
+
+## Understanding Shopping Assistant
+
+The Shopping Agent combines multiple capabilities for effective price comparison:
+
+1. **Store Search**: Uses DuckDuckGo to find retailers
+2. **Price Analysis**: Gathers pricing information
+3. **Price Comparison**: Compares prices across stores
+4. **Deal Finding**: Identifies special offers and discounts
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Price Comparison" icon="scale-balanced">
+    Compare prices across multiple stores.
+  </Card>
+  <Card title="Deal Detection" icon="tag">
+    Find special offers and discounts.
+  </Card>
+  <Card title="Store Analysis" icon="store">
+    Evaluate retailer reliability.
+  </Card>
+  <Card title="Price Tracking" icon="chart-line">
+    Monitor price changes over time.
+  </Card>
+</CardGroup>
+
+## Example Usage
+
+```python
+# Example: Compare product prices
+from praisonaiagents import Agent, Tools
+from praisonaiagents.tools import duckduckgo
+
+agent = Agent(instructions="You are a Shopping Agent", tools=[duckduckgo])
+agent.start("I want to buy iPhone 16 Pro Max, check 5 stores and give me price in table")
+```
+
+## Next Steps
+
+- Learn about [Prompt Chaining](/features/promptchaining) for complex shopping research
+- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving price accuracy
+- Check out the [Research Agent](/agents/research) for detailed product research

docs/agents/single.mdx

@@ -0,0 +1,102 @@
+---
+title: "Single Agent"
+sidebarTitle: "Single"
+description: "Learn how to create a basic single-purpose AI agent for simple tasks."
+icon: "circle-1"
+---
+
+```mermaid
+flowchart LR
+    In[Input] --> Agent[Single Agent]
+    Agent --> Out[Output]
+    
+    style In fill:#8B0000,color:#fff
+    style Agent fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+A workflow demonstrating how to create and use a simple single-purpose agent.
+
+## Quick Start
+
+<Steps>
+    <Step title="Install Package">
+        First, install the PraisonAI Agents package:
+        ```bash
+        pip install praisonaiagents
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+    </Step>
+
+    <Step title="Create Script">
+        Create a new file `simple_agent.py`:
+        ```python
+        from praisonaiagents import Agent
+
+        agent = Agent(instructions="You are a Markdown Agent, output in markdown format")
+        agent.start("Write a blog post about AI")
+        ```
+    </Step>
+</Steps>
+
+## Understanding Single Agent
+
+The Single Agent is the simplest form of PraisonAI agent:
+
+1. **Simple Setup**: Minimal configuration required
+2. **Single Purpose**: Focused on one specific task
+3. **Direct Execution**: Straightforward input-output flow
+4. **No Dependencies**: No external tools required
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Simple Setup" icon="square-1">
+    Minimal configuration needed.
+  </Card>
+  <Card title="Focused Task" icon="bullseye">
+    Single-purpose execution.
+  </Card>
+  <Card title="Quick Start" icon="bolt">
+    Rapid implementation.
+  </Card>
+  <Card title="No Tools" icon="toolbox">
+    No external dependencies.
+  </Card>
+</CardGroup>
+
+## Example Usage
+
+```python
+# Example: Create a content generation agent
+from praisonaiagents import Agent
+
+# Create content agent
+agent = Agent(
+    instructions="You are a Content Generation Agent, create engaging content"
+)
+
+# Generate content
+response = agent.start("""
+    Write a short story about:
+    - A future world
+    - With advanced AI
+    - And human collaboration
+""")
+
+# Save the story
+with open('ai_story.txt', 'w') as f:
+    f.write(response)
+```
+
+## Next Steps
+
+- Learn about [Prompt Chaining](/features/promptchaining) for more complex workflows
+- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving output quality
+- Check out other specialized agents like the [Markdown Agent](/agents/markdown) for specific use cases

docs/agents/video.mdx

@@ -0,0 +1,149 @@
+---
+title: "Video Agent"
+sidebarTitle: "Video"
+description: "Learn how to create AI agents for video analysis and content understanding."
+icon: "video"
+---
+
+```mermaid
+flowchart LR
+    In[Video Input] --> Analyzer[Content Analyzer]
+    Analyzer --> Detector[Object Detector]
+    Detector --> Transcriber[Text Transcriber]
+    Transcriber --> Out[Analysis Report]
+    
+    style In fill:#8B0000,color:#fff
+    style Analyzer fill:#2E8B57,color:#fff
+    style Detector fill:#2E8B57,color:#fff
+    style Transcriber fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+A workflow demonstrating how the Video Agent can analyze video content, detect objects, and extract meaningful information.
+
+## Quick Start
+
+<Steps>
+    <Step title="Install Package">
+        First, install the PraisonAI Agents package:
+        ```bash
+        pip install praisonaiagents
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+    </Step>
+
+    <Step title="Create Script">
+        Create a new file `video_analyzer.py`:
+        ```python
+        from praisonaiagents import Agent, Task, PraisonAIAgents
+
+        # Create Video Analysis Agent
+        video_agent = Agent(
+            name="VideoAnalyst",
+            role="Video Analysis Specialist",
+            goal="Analyze videos to extract meaningful information",
+            backstory="""You are an expert in computer vision and video analysis.
+            You excel at describing content, detecting objects, and understanding context.""",
+            llm="gpt-4o-mini",
+            self_reflect=False
+        )
+
+        # Create video analysis task
+        analysis_task = Task(
+            name="analyze_video",
+            description="""Analyze this video and provide:
+                1. Summary of main events
+                2. Key objects and people
+                3. Text and important information
+                4. Context and setting""",
+            expected_output="Comprehensive video analysis",
+            agent=video_agent,
+            images=["video.mp4"]
+        )
+
+        # Create PraisonAIAgents instance
+        agents = PraisonAIAgents(
+            agents=[video_agent],
+            tasks=[analysis_task],
+            process="sequential",
+            verbose=1
+        )
+
+        # Run analysis
+        agents.start()
+        ```
+    </Step>
+</Steps>
+
+## Understanding Video Analysis
+
+The Video Agent combines multiple capabilities for comprehensive video understanding:
+
+1. **Content Analysis**: Analyzes video scenes and events
+2. **Object Detection**: Identifies objects and people
+3. **Text Extraction**: Captures text shown in videos
+4. **Context Understanding**: Interprets settings and situations
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Scene Analysis" icon="film">
+    Detailed analysis of video scenes.
+  </Card>
+  <Card title="Object Detection" icon="cube">
+    Identification of objects and people.
+  </Card>
+  <Card title="Text Extraction" icon="closed-captioning">
+    Capture of text and captions.
+  </Card>
+  <Card title="Context Analysis" icon="sitemap">
+    Understanding of video context.
+  </Card>
+</CardGroup>
+
+## Example Usage
+
+```python
+# Example: Analyze a presentation video
+from praisonaiagents import Agent, Task, PraisonAIAgents
+
+video_agent = Agent(
+    name="VideoAnalyst",
+    role="Video Analysis Specialist",
+    goal="Extract information from presentation videos",
+    llm="gpt-4o-mini"
+)
+
+# Create presentation analysis task
+presentation_task = Task(
+    name="analyze_presentation",
+    description="""Analyze this presentation video:
+        1. Extract key points
+        2. Capture slide content
+        3. Note speaker's main arguments
+        4. Summarize Q&A session""",
+    expected_output="Detailed presentation summary",
+    agent=video_agent,
+    images=["presentation.mp4"]
+)
+
+# Run analysis
+agents = PraisonAIAgents(
+    agents=[video_agent],
+    tasks=[presentation_task],
+    process="sequential"
+)
+agents.start()
+```
+
+## Next Steps
+
+- Learn about [Prompt Chaining](/features/promptchaining) for complex video analysis
+- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving analysis accuracy
+- Check out the [Image Agent](/agents/image) for still image analysis

docs/agents/websearch.mdx

@@ -0,0 +1,124 @@
+---
+title: "Web Search Agent"
+sidebarTitle: "Web Search"
+description: "Learn how to create AI agents for intelligent web searching and information gathering."
+icon: "globe"
+---
+
+```mermaid
+flowchart LR
+    In[Search Query] --> Search[Web Search]
+    Search --> Filter[Content Filter]
+    Filter --> Summarizer[Content Summarizer]
+    Summarizer --> Out[Search Results]
+    
+    style In fill:#8B0000,color:#fff
+    style Search fill:#2E8B57,color:#fff
+    style Filter fill:#2E8B57,color:#fff
+    style Summarizer fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+A workflow demonstrating how the Web Search Agent can perform intelligent searches and process web content.
+
+## Quick Start
+
+<Steps>
+    <Step title="Install Package">
+        First, install the PraisonAI Agents package:
+        ```bash
+        pip install praisonaiagents
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+    </Step>
+
+    <Step title="Create Script">
+        Create a new file `web_search.py`:
+        ```python
+        from praisonaiagents import Agent, Tools
+        from praisonaiagents.tools import duckduckgo
+
+        # Create Web Search Agent
+        search_agent = Agent(
+            name="WebSearcher",
+            role="Web Search Specialist",
+            goal="Perform intelligent web searches and gather information",
+            instructions="You are a Web Search Agent",
+            tools=[duckduckgo]
+        )
+
+        # Perform search
+        response = search_agent.start(
+            "Search about AI developments in 2024"
+        )
+        
+        # Save search results
+        with open('search_results.md', 'w') as f:
+            f.write(response)
+        ```
+    </Step>
+</Steps>
+
+## Understanding Web Search
+
+The Web Search Agent employs sophisticated search strategies:
+
+1. **Query Processing**: Optimizes search queries
+2. **Content Filtering**: Filters relevant results
+3. **Information Extraction**: Extracts key information
+4. **Result Summarization**: Summarizes findings
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Smart Search" icon="magnifying-glass">
+    Intelligent query processing.
+  </Card>
+  <Card title="Content Filtering" icon="filter">
+    Relevance-based filtering.
+  </Card>
+  <Card title="Information Extraction" icon="scissors">
+    Key information extraction.
+  </Card>
+  <Card title="Result Summary" icon="list">
+    Concise result summaries.
+  </Card>
+</CardGroup>
+
+## Example Usage
+
+```python
+# Example: Perform topic research
+from praisonaiagents import Agent, Tools
+from praisonaiagents.tools import duckduckgo
+
+agent = Agent(
+    instructions="You are a Web Search Agent",
+    tools=[duckduckgo]
+)
+
+# Research specific topic
+response = agent.start("""
+    Search for information about quantum computing:
+    - Recent breakthroughs
+    - Leading companies
+    - Current applications
+    - Future predictions
+""")
+
+# Save research results
+with open('quantum_computing_research.md', 'w') as f:
+    f.write(response)
+```
+
+## Next Steps
+
+- Learn about [Prompt Chaining](/features/promptchaining) for complex search workflows
+- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving search relevance
+- Check out the [Research Agent](/agents/research) for comprehensive research capabilities

docs/agents/wikipedia.mdx

@@ -0,0 +1,139 @@
+---
+title: "Wikipedia Agent"
+sidebarTitle: "Wikipedia"
+description: "Learn how to create AI agents for searching and extracting information from Wikipedia."
+icon: "book"
+---
+
+```mermaid
+flowchart LR
+    In[Query] --> Search[Wiki Search]
+    Search --> Page[Page Retrieval]
+    Page --> Summary[Content Summary]
+    Summary --> Out[Knowledge Output]
+    
+    style In fill:#8B0000,color:#fff
+    style Search fill:#2E8B57,color:#fff
+    style Page fill:#2E8B57,color:#fff
+    style Summary fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+A workflow demonstrating how the Wikipedia Agent can search, retrieve, and summarize Wikipedia content.
+
+## Quick Start
+
+<Steps>
+    <Step title="Install Package">
+        First, install the PraisonAI Agents package:
+        ```bash
+        pip install praisonaiagents
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+    </Step>
+
+    <Step title="Create Script">
+        Create a new file `wikipedia_assistant.py`:
+        ```python
+        from praisonaiagents import Agent, Task, PraisonAIAgents
+        from praisonaiagents.tools import (
+            wiki_search,
+            wiki_summary,
+            wiki_page,
+            wiki_random,
+            wiki_language
+        )
+
+        # Create Wikipedia Agent
+        wiki_agent = Agent(
+            name="WikipediaAssistant",
+            role="Wikipedia Research Specialist",
+            goal="Extract and summarize Wikipedia content",
+            instructions="You are a Wikipedia Agent",
+            tools=[
+                wiki_search,
+                wiki_summary,
+                wiki_page,
+                wiki_random,
+                wiki_language
+            ],
+            self_reflect=True,
+            min_reflect=3,
+            max_reflect=5
+        )
+
+        # Research a topic
+        response = wiki_agent.start("""
+            What is the history of AI?
+            First search the history of AI
+            Read the page of the history of AI
+            Get the summary of the page
+        """)
+        
+        # Save research results
+        with open('ai_history.md', 'w') as f:
+            f.write(response)
+        ```
+    </Step>
+</Steps>
+
+## Understanding Wikipedia Research
+
+The Wikipedia Agent provides comprehensive Wikipedia access through multiple tools:
+
+1. **Wiki Search**: `wiki_search` for finding relevant articles
+2. **Page Access**: `wiki_page` for retrieving full articles
+3. **Summarization**: `wiki_summary` for concise overviews
+4. **Random Articles**: `wiki_random` for discovering content
+5. **Language Support**: `wiki_language` for multilingual access
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Article Search" icon="magnifying-glass">
+    Find relevant Wikipedia articles.
+  </Card>
+  <Card title="Content Retrieval" icon="book-open">
+    Access complete article content.
+  </Card>
+  <Card title="Summarization" icon="compress">
+    Generate concise article summaries.
+  </Card>
+  <Card title="Multilingual" icon="language">
+    Access content in multiple languages.
+  </Card>
+</CardGroup>
+
+## Example Usage
+
+```python
+# Example: Research a scientific topic
+from praisonaiagents import Agent
+from praisonaiagents.tools import wiki_search, wiki_summary, wiki_page, wiki_random, wiki_language
+
+agent = Agent(
+    instructions="You are a Wikipedia Agent", 
+    tools=[wiki_search, wiki_summary, wiki_page, wiki_random, wiki_language],
+    self_reflect=True,
+    min_reflect=3,
+    max_reflect=5,
+)
+agent.start(
+    "What is the history of AI?"
+    "First search the history of AI"
+    "Read the page of the history of AI"
+    "Get the summary of the page"
+)
+```
+
+## Next Steps
+
+- Learn about [Prompt Chaining](/features/promptchaining) for complex Wikipedia research
+- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving research quality
+- Check out the [Research Agent](/agents/research) for broader research capabilities

docs/api-reference/index.mdx

@@ -1,6 +1,7 @@
 ---
 title: 'API Reference'
 description: 'PraisonAI API documentation with framework-specific details'
+icon: "book-open"
 ---
 
 # API Reference
@@ -29,7 +30,7 @@ Features:
 - Built-in tools
 - Structured workflows
 
-### AutoGen Integration
+### AG2 (Formerly AutoGen) Integration
 Requires installation with:
 ```bash
 pip install "praisonai[autogen]"

docs/api.mdx

@@ -1,4 +1,8 @@
-# API Reference
+---
+title: "API Reference"
+description: "Complete API reference for PraisonAI, including core modules, installation options, and framework-specific features"
+icon: "code"
+---
 
 ## Core Modules
 
@@ -19,7 +23,7 @@ from praisonai.auto import AutoGenerator
 ### praisonai.agents_generator
 Framework-specific agent generation and orchestration:
 - CrewAI support (requires `praisonai[crewai]`)
-- AutoGen support (requires `praisonai[autogen]`)
+- AG2 (Formerly AutoGen) support (requires `praisonai[autogen]`)
 
 ```python
 from praisonai.agents_generator import AgentsGenerator
@@ -47,7 +51,7 @@ pip install praisonai
 
 # Framework-specific installations
 pip install "praisonai[crewai]"    # Install with CrewAI support
-pip install "praisonai[autogen]"   # Install with AutoGen support
+pip install "praisonai[autogen]"   # Install with AG2 support
 pip install "praisonai[crewai,autogen]"  # Install both frameworks
 
 # Additional features
@@ -67,9 +71,9 @@ When installing with `pip install "praisonai[crewai]"`, you get:
 - Task delegation capabilities
 - Sequential and parallel task execution
 
-### AutoGen
+### AG2 (Formerly AutoGen)
 When installing with `pip install "praisonai[autogen]"`, you get:
-- AutoGen framework support
+- AG2 framework support
 - PraisonAI tools integration
 - Multi-agent conversation capabilities
 - Code execution environment

docs/api/praisonai/deploy.html

@@ -110,7 +110,7 @@ Loads environment variables from .env file or system and sets them.</p>
             file.write(&#34;FROM python:3.11-slim\n&#34;)
             file.write(&#34;WORKDIR /app\n&#34;)
             file.write(&#34;COPY . .\n&#34;)
-            file.write(&#34;RUN pip install flask praisonai==1.0.10 gunicorn markdown\n&#34;)
+            file.write(&#34;RUN pip install flask praisonai==2.2.5 gunicorn markdown\n&#34;)
             file.write(&#34;EXPOSE 8080\n&#34;)
             file.write(&#39;CMD [&#34;gunicorn&#34;, &#34;-b&#34;, &#34;0.0.0.0:8080&#34;, &#34;api:app&#34;]\n&#39;)