Bump version to 0.6.56 (#853)

* Update docs for extract

* add more details on async

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,31 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: bug
+assignees: ''
+
+---
+
+**Describe the bug**
+Write a concise description of what the bug is.
+
+**Files**
+If possible, please provide the PDF file causing the issue.
+
+**Job ID**
+If you have it, please provide the ID of the job you ran.
+You can find it here: https://cloud.llamaindex.ai/parse in the "History" tab.
+
+**Client:**
+Please remove untested options:
+ - Python Library
+ - API
+ - Frontend (cloud.llamaindex.ai)
+ - Typescript Library
+ - Notebook
+
+**Additional context**
+Add any additional context about the problem here.
+What options did you use? Premium mode, multimodal, fast mode, parsing instructions, etc.
+Screenshots, code snippets, etc.

.github/ISSUE_TEMPLATE/custom-issue.md

@@ -0,0 +1,10 @@
+---
+name: Custom issue
+about: Not a bug nor a feature request
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,10 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: enhancement
+assignees: ''
+
+---
+
+

.github/dependabot.yml

@@ -0,0 +1,11 @@
+# Please see the documentation for all configuration options:
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+# and
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"

.github/workflows/build_package_py.yml

@@ -0,0 +1,53 @@
+name: Build Package - Python
+
+# Build package on its own without additional pip install
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "py/**"
+  pull_request:
+    paths:
+      - "py/**"
+env:
+  UV_VERSION: "0.7.20"
+
+jobs:
+  build:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      # You can use PyPy versions in python-version.
+      # For example, pypy-2.7 and pypy-3.8
+      matrix:
+        os: [ubuntu-latest, windows-latest]
+        python-version: ["3.9"]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          version: ${{ env.UV_VERSION }}
+
+      - name: Set up Python
+        run: uv python install
+
+      - name: Display Python version
+        run: python --version
+
+      - name: Build
+        working-directory: py
+        run: uv build
+
+      - name: Test installing built package
+        shell: bash
+        working-directory: py
+        run: |
+          uv venv
+          uv pip install dist/*.whl
+
+      - name: Test import
+        working-directory: py
+        run: uv run -- python -c "import llama_cloud_services"

.github/workflows/build_package_ts.yml

@@ -0,0 +1,36 @@
+name: Build Package - TypeScript
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "ts/**"
+  pull_request:
+    paths:
+      - "ts/**"
+
+jobs:
+  pre_release:
+    name: Pre Release
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout Repo
+        uses: actions/checkout@v4
+
+      - uses: pnpm/action-setup@v4
+        with:
+          version: 10
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: "ts/llama_cloud_services/.nvmrc"
+
+      - name: Install dependencies
+        working-directory: ts/llama_cloud_services/
+        run: pnpm install --no-frozen-lockfile
+
+      - name: Build
+        working-directory: ts/llama_cloud_services/
+        run: pnpm run build

.github/workflows/claude-code.yml

@@ -0,0 +1,95 @@
+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: Check repository access
+        id: check-access
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          # Get the user who triggered the event
+          case "${{ github.event_name }}" in
+            "issue_comment")
+              USER="${{ github.event.comment.user.login }}"
+              ;;
+            "pull_request_review_comment")
+              USER="${{ github.event.comment.user.login }}"
+              ;;
+            "pull_request_review")
+              USER="${{ github.event.review.user.login }}"
+              ;;
+            "issues")
+              USER="${{ github.event.issue.user.login }}"
+              ;;
+          esac
+
+          echo "Checking repository access for user: $USER"
+
+          # Check if user has write access to the repository
+          REPO="${{ github.repository }}"
+          if gh api repos/$REPO/collaborators/$USER/permission --jq '.permission' | grep -E "(admin|write)" > /dev/null 2>&1; then
+            echo "User $USER has write access to the repository"
+            echo "authorized=true" >> $GITHUB_OUTPUT
+          else
+            echo "User $USER does not have write access to the repository"
+            echo "authorized=false" >> $GITHUB_OUTPUT
+            exit 1
+          fi
+
+      - name: Checkout repository
+        if: steps.check-access.outputs.authorized == 'true'
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code
+        if: steps.check-access.outputs.authorized == 'true'
+        id: claude
+        uses: anthropics/claude-code-action@beta
+        with:
+          anthropic_api_key: ${{ secrets.ANTHROPIC_GITHUB_API_KEY }}
+
+          # Optional: Specify model (defaults to Claude Sonnet 4, uncomment for Claude Opus 4)
+          # model: "claude-opus-4-20250514"
+
+          # Optional: Customize the trigger phrase (default: @claude)
+          # trigger_phrase: "/claude"
+
+          # Optional: Trigger when specific user is assigned to an issue
+          # assignee_trigger: "claude-bot"
+
+          # Optional: Allow Claude to run specific commands
+          # Allow bash commands to be run, for things like running tests, linting, etc.
+          allowed_tools: "Bash(rg:*),Bash(find:*),Bash(grep:*),Bash(pnpm:*),Bash(npm:*),Bash(uv:*),Bash(pip:*),Bash(pipx:*),Bash(make:*),Bash(cd:*),WebFetch"
+
+          # Optional: Add custom instructions for Claude to customize its behavior for your project
+          # custom_instructions: |
+          #   Follow our coding standards
+          #   Ensure all new code has tests
+          #   Use TypeScript for new files
+
+          # Optional: Custom environment variables for Claude
+          # claude_env: |
+          #   NODE_ENV: test

.github/workflows/codeql.yml

@@ -0,0 +1,41 @@
+name: "CodeQL"
+
+on:
+  push:
+    branches: ["main"]
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: ["main"]
+  schedule:
+    - cron: "30 16 * * 4"
+
+jobs:
+  analyze:
+    name: Analyze
+    # Runner size impacts CodeQL analysis time. To learn more, please see:
+    #   - https://gh.io/recommended-hardware-resources-for-running-codeql
+    #   - https://gh.io/supported-runners-and-hardware-resources
+    #   - https://gh.io/using-larger-runners
+    # Consider using larger runners for possible analysis time improvements.
+    runs-on: "ubuntu-latest"
+    timeout-minutes: 360
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      # Initializes the CodeQL tools for scanning.
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@v3
+        with:
+          languages: python
+          dependency-caching: true
+
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@v3
+        with:
+          category: "/language:python"

.github/workflows/lint_py.yml

@@ -0,0 +1,35 @@
+name: Lint - Python
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+env:
+  UV_VERSION: "0.7.20"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      # You can use PyPy versions in python-version.
+      # For example, pypy-2.7 and pypy-3.8
+      matrix:
+        python-version: ["3.9"]
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: ${{ github.event_name == 'pull_request' && 2 || 0 }}
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          version: ${{ env.UV_VERSION }}
+
+      - name: Set up Python
+        run: uv python install ${{ matrix.python-version }}
+
+      - name: Run linter
+        shell: bash
+        working-directory: py
+        run: uv run -- pre-commit run -a

.github/workflows/lint_ts.yml

@@ -0,0 +1,37 @@
+name: Lint - TypeScript
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "ts/**"
+  pull_request:
+    paths:
+      - "ts/**"
+
+env:
+  TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
+  TURBO_TEAM: ${{ vars.TURBO_TEAM }}
+  TURBO_REMOTE_ONLY: true
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: pnpm/action-setup@v4
+        with:
+          version: 10
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: "ts/llama_cloud_services/.nvmrc"
+      - name: Install dependencies
+        run: pnpm install --no-frozen-lockfile
+      - name: Run lint
+        working-directory: ts/llama_cloud_services/
+        run: pnpm run lint
+      - name: Run Prettier
+        working-directory: ts/llama_cloud_services/
+        run: pnpm run format

.github/workflows/release_py.yml

@@ -0,0 +1,66 @@
+name: Publish Release - Python
+
+on:
+  push:
+    tags:
+      - "v*"
+
+  workflow_dispatch:
+
+env:
+  UV_VERSION: "0.7.20"
+
+jobs:
+  build-n-publish:
+    name: Build and publish to PyPI
+    if: github.repository == 'run-llama/llama_cloud_services'
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          version: ${{ env.UV_VERSION }}
+
+      - name: Set up Python
+        run: uv python install
+
+      - name: Display Python version
+        run: python --version
+
+      - name: Build
+        working-directory: py
+        run: uv build
+
+      - name: Test installing built package
+        shell: bash
+        working-directory: py
+        run: |
+          uv venv
+          uv pip install dist/*.whl
+
+      - name: Publish package
+        shell: bash
+        working-directory: py
+        run: uv publish --token ${{ secrets.LLAMA_PARSE_PYPI_TOKEN }}
+
+      - name: Build and publish llama-parse
+        working-directory: py/llama_parse/
+        run: |
+          uv build
+          uv publish --token ${{ secrets.LLAMA_PARSE_PYPI_TOKEN }}
+
+      - name: Create GitHub Release
+        id: create_release
+        uses: actions/create-release@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # This token is provided by Actions, you do not need to create your own token
+        with:
+          tag_name: ${{ github.ref }}
+          release_name: ${{ github.ref }} - LlamaCloud Services PY
+          artifacts: "py/**/dist/*"
+          generateReleaseNotes: true
+          draft: false
+          prerelease: false

.github/workflows/release_ts.yml

@@ -0,0 +1,54 @@
+name: Publish Release - TypeScript
+
+on:
+  push:
+    tags:
+      - "llama-cloud-services@*"
+
+jobs:
+  build-and-publish:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Repo
+        uses: actions/checkout@v4
+
+      - uses: pnpm/action-setup@v4
+        with:
+          version: 10
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: "ts/llama_cloud_services/.nvmrc"
+
+      - name: Install dependencies
+        run: pnpm install --no-frozen-lockfile
+
+      - name: Run Build
+        working-directory: ts/llama_cloud_services/
+        run: pnpm build
+
+      - name: Build tarball
+        run: |
+          pnpm pack
+        working-directory: ts/llama_cloud_services
+
+      - name: Setup npm authentication
+        run: echo "//registry.npmjs.org/:_authToken=${NPM_TOKEN}" > ~/.npmrc
+        env:
+          NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
+
+      - name: Release
+        working-directory: ts/llama_cloud_services
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
+        run: pnpm publish --access public --no-git-checks
+
+      - name: Create release
+        uses: ncipollo/release-action@v1
+        with:
+          artifacts: "ts/llama_cloud_services/llama-cloud-services*.tgz"
+          name: Release ${{ github.ref }} - LlamaCloud Services TS
+          bodyFile: "ts/llama_cloud_services/CHANGELOG.md"
+          token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/test_e2e_py.yml

@@ -0,0 +1,38 @@
+name: Test end-to-end - Python
+
+on:
+  pull_request:
+    paths:
+      - "py/**"
+
+env:
+  UV_VERSION: "0.7.20"
+  LLAMA_CLOUD_API_KEY: ${{ secrets.LLAMA_CLOUD_API_KEY }}
+
+jobs:
+  test_e2e:
+    runs-on: ubuntu-latest
+    strategy:
+      # You can use PyPy versions in python-version.
+      # For example, pypy-2.7 and pypy-3.8
+      matrix:
+        python-version: ["3.12"]
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          version: ${{ env.UV_VERSION }}
+
+      - name: Set up Python
+        run: uv python install ${{ matrix.python-version }} && uv python pin ${{ matrix.python-version }}
+
+      - name: Run Tests
+        working-directory: py
+        run: uv run pytest unit_tests/ tests/ -v
+
+      - name: Remove virtual environment
+        working-directory: py
+        run: rm -rf .venv/

.github/workflows/test_py.yml

@@ -0,0 +1,42 @@
+name: Test - Python
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "py/**"
+  pull_request:
+    paths:
+      - "py/**"
+
+env:
+  UV_VERSION: "0.7.20"
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      # You can use PyPy versions in python-version.
+      # For example, pypy-2.7 and pypy-3.8
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          version: ${{ env.UV_VERSION }}
+
+      - name: Set up Python
+        run: uv python install ${{ matrix.python-version }} && uv python pin ${{ matrix.python-version }}
+
+      - name: Run Tests
+        working-directory: py
+        run: uv run pytest unit_tests/ -v
+
+      - name: Remove virtual environment
+        working-directory: py
+        run: rm -rf .venv/

.github/workflows/test_ts.yml

@@ -0,0 +1,42 @@
+name: Lint - TypeScript
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "ts/**"
+  pull_request:
+    paths:
+      - "ts/**"
+
+env:
+  TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
+  TURBO_TEAM: ${{ vars.TURBO_TEAM }}
+  TURBO_REMOTE_ONLY: true
+  LLAMA_CLOUD_API_KEY: ${{ secrets.LLAMA_CLOUD_API_KEY }}
+
+jobs:
+  test:
+    name: Test - TypeScript
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: pnpm/action-setup@v4
+        with:
+          version: 10
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version-file: "ts/llama_cloud_services/.nvmrc"
+      - name: Install dependencies
+        run: pnpm install --no-frozen-lockfile
+      - name: Run Build
+        working-directory: ts/llama_cloud_services/
+        run: pnpm build
+      - name: Run Tests
+        working-directory: ts/llama_cloud_services/
+        run: pnpm test
+      - name: Run e2e tests
+        working-directory: ts/e2e-tests/
+        run: pnpm test

.gitignore

@@ -1,4 +1,11 @@
 .git
 __pycache__/
 *.pyc
-.DS_Store
+.DS_Store
+.idea
+.env*
+.ipynb_checkpoints*
+*_cache/
+node_modules/
+.turbo/
+dist/

.pre-commit-config.yaml

@@ -0,0 +1,90 @@
+---
+default_language_version:
+  python: python3
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: check-byte-order-marker
+      - id: check-merge-conflict
+      - id: check-symlinks
+      - id: check-toml
+      - id: check-yaml
+      - id: detect-private-key
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+      - id: trailing-whitespace
+        exclude: ^ts/llama_cloud_services/src/client/
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: v0.1.5
+
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+        exclude: ".*uv.lock"
+  - repo: https://github.com/psf/black-pre-commit-mirror
+    rev: 23.10.1
+    hooks:
+      - id: black-jupyter
+        name: black-src
+        alias: black
+        exclude: ".*uv.lock"
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.0.1
+    hooks:
+      - id: mypy
+        exclude: ^py/tests|^py/unit_tests
+        additional_dependencies:
+          [
+            "types-requests",
+            "types-Deprecated",
+            "types-redis",
+            "types-setuptools",
+            "types-PyYAML",
+            "types-protobuf==4.24.0.4",
+          ]
+        args:
+          [
+            --disallow-untyped-defs,
+            --ignore-missing-imports,
+            --python-version=3.10,
+          ]
+  - repo: https://github.com/adamchainz/blacken-docs
+    rev: 1.16.0
+    hooks:
+      - id: blacken-docs
+        name: black-docs-text
+        alias: black
+        types_or: [rst, markdown, tex]
+        additional_dependencies: [black==23.10.1]
+        # Using PEP 8's line length in docs prevents excess left/right scrolling
+        args: [--line-length=79]
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: v3.0.3
+    hooks:
+      - id: prettier
+        exclude: ^(uv.lock|ts/llama_cloud_services/pnpm-lock.yaml|ts/e2e-tests)
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.2.6
+    hooks:
+      - id: codespell
+        additional_dependencies: [tomli]
+        exclude: ^(uv.lock|docs|ts|examples|pnpm-lock.yaml)
+        args:
+          [
+            "--ignore-words-list",
+            "astroid,gallary,momento,narl,ot,rouge,nin,gere,te,inh,vor",
+          ]
+  - repo: https://github.com/srstevenson/nb-clean
+    rev: 3.1.0
+    hooks:
+      - id: nb-clean
+        args: [--preserve-cell-outputs, --remove-empty-cells]
+  - repo: https://github.com/pappasam/toml-sort
+    rev: v0.23.1
+    hooks:
+      - id: toml-sort-fix
+        exclude: ".*uv.lock"
+
+exclude: ^(.github/ISSUE_TEMPLATE|ts/llama_cloud_services/src/client|pnpm-lock.yaml)

CONTRIBUTING.md

@@ -0,0 +1,33 @@
+# Python
+
+## Installation
+
+This project uses uv. Create a virtual environment, and run `uv sync`
+
+## Versioning (Maintainers only)
+
+Before merging your changes, make sure to bump the versions.
+
+Make a version bump to `pyproject.toml`. If the underlying dependency on the llamacloud platform OpenAPI
+sdk needs bumping, make sure to bring that in as well. If updating dependencies, run `uv lock`.
+
+The legacy `llama_parse` package re-exports some of `llama_cloud_services` in the old namespace. The
+versions need to be kept consistent to sidecar it with `llama_cloud_services`. Bump it's version in `llama_parse/pyproject.toml`, and also bump it's dependency version of `llama-cloud-services` to match.
+
+**Note**: Don't worry about updating the `llama_parse/poetry.lock` file when bumping versions. The GitHub action will automatically run `poetry lock` for the llama_parse package during the build process (though it doesn't commit the updated lockfile back to the repo).
+
+You can also do this with `./scripts/version-bump.py set 0.x.x` if you have `uv` installed.
+
+Once the change is merged, push a tag `git tag -a v0.x.x -m 0.x.x` and `git push origin 0.x.x`.
+
+This tagging step can be done with `./scripts/version-bump tag`.
+
+# Typescript
+
+## Installation
+
+...
+
+## Versioning
+
+...

README.md

@@ -1,89 +1,86 @@
-# LlamaParse
+[![PyPI - Downloads](https://img.shields.io/pypi/dm/llama-cloud-services)](https://pypi.org/project/llama-cloud-services/)
+[![GitHub contributors](https://img.shields.io/github/contributors/run-llama/llama_cloud_services)](https://github.com/run-llama/llama_cloud_services/graphs/contributors)
+[![Discord](https://img.shields.io/discord/1059199217496772688)](https://discord.gg/dGcwcsnxhU)
 
-LlamaParse is an API created by LlamaIndex to efficiently parse and represent files for efficient retrieval and context augmentation using LlamaIndex frameworks.
+# Llama Cloud Services
 
-LlamaParse directly integrates with [LlamaIndex](https://github.com/run-llama/llama_index).
+This repository contains the code for hand-written SDKs and clients for interacting with LlamaCloud.
 
+This includes:
 
-Free plan is up to 1000 pages a day. Paid plan is free 7k pages per week + 0.3c per additional page.
+- [LlamaParse](./parse.md) - A GenAI-native document parser that can parse complex document data for any downstream LLM use case (Agents, RAG, data processing, etc.).
+- [LlamaReport (beta/invite-only)](./report.md) - A prebuilt agentic report builder that can be used to build reports from a variety of data sources.
+- [LlamaExtract](./extract.md) - A prebuilt agentic data extractor that can be used to transform data into a structured JSON representation.
+- [LlamaCloud Index](./index.md) - A widely customizable and fully automated document ingestion pipeline that also serves retrieval purposes.
 
 ## Getting Started
 
-First, login and get an api-key from `https://cloud.llamaindex.ai`.
+Install the package:
 
-Then, make sure you have the latest LlamaIndex version installed.
-
-**NOTE:** If you are upgrading from v0.9.X, we recommend following our [migration guide](https://pretty-sodium-5e0.notion.site/v0-10-0-Migration-Guide-6ede431dcb8841b09ea171e7f133bd77), as well as uninstalling your previous version first.
-
-```
-pip uninstall llama-index  # run this if upgrading from v0.9.x or older
-pip install -U llama-index --upgrade --no-cache-dir --force-reinstall
+```bash
+pip install llama-cloud-services
 ```
 
-Lastly, install the package:
+Then, get your API key from [LlamaCloud](https://cloud.llamaindex.ai/).
 
-`pip install llama-parse`
-
-Now you can run the following to parse your first PDF file:
+Then, you can use the services in your code:
 
 ```python
-import nest_asyncio
-nest_asyncio.apply()
-
-from llama_parse import LlamaParse
-
-parser = LlamaParse(
-    api_key="llx-...",  # can also be set in your env as LLAMA_CLOUD_API_KEY
-    result_type="markdown",  # "markdown" and "text" are available
-    num_workers=4, # if multiple files passed, split in `num_workers` API calls
-    verbose=True,
-    language="en" # Optionaly you can define a language, default=en
+from llama_cloud_services import (
+    LlamaParse,
+    LlamaReport,
+    LlamaExtract,
+    LlamaCloudIndex,
 )
 
-# sync
-documents = parser.load_data("./my_file.pdf")
-
-# sync batch
-documents = parser.load_data(["./my_file1.pdf", "./my_file2.pdf"])
-
-# async
-documents = await parser.aload_data("./my_file.pdf")
-
-# async batch
-documents = await parser.aload_data(["./my_file1.pdf", "./my_file2.pdf"])
+parser = LlamaParse(api_key="YOUR_API_KEY")
+report = LlamaReport(api_key="YOUR_API_KEY")
+extract = LlamaExtract(api_key="YOUR_API_KEY")
+index = LlamaCloudIndex(
+    "my_first_index", project_name="default", api_key="YOUR_API_KEY"
+)
 ```
 
-## Using with `SimpleDirectoryReader`
+See the quickstart guides for each service for more information:
 
-You can also integrate the parser as the default PDF loader in `SimpleDirectoryReader`:
+- [LlamaParse](./parse.md)
+- [LlamaReport (beta/invite-only)](./report.md)
+- [LlamaExtract](./extract.md)
+- [LlamaCloud Index](./index.md)
+
+## Switch to EU SaaS 🇪🇺
+
+If you are interested in using LlamaCloud services in the EU, you can adjust your base URL to `https://api.cloud.eu.llamaindex.ai`.
+
+You can also create your API key in the EU region [here](https://cloud.eu.llamaindex.ai).
 
 ```python
-import nest_asyncio
-nest_asyncio.apply()
-
-from llama_parse import LlamaParse
-from llama_index.core import SimpleDirectoryReader
-
-parser = LlamaParse(
-    api_key="llx-...",  # can also be set in your env as LLAMA_CLOUD_API_KEY
-    result_type="markdown",  # "markdown" and "text" are available
-    verbose=True
+from llama_cloud_services import (
+    LlamaParse,
+    LlamaReport,
+    LlamaExtract,
+    EU_BASE_URL,
 )
 
-file_extractor = {".pdf": parser}
-documents = SimpleDirectoryReader("./data", file_extractor=file_extractor).load_data()
+parser = LlamaParse(api_key="YOUR_API_KEY", base_url=EU_BASE_URL)
+report = LlamaReport(api_key="YOUR_API_KEY", base_url=EU_BASE_URL)
+extract = LlamaExtract(api_key="YOUR_API_KEY", base_url=EU_BASE_URL)
+index = LlamaCloudIndex(
+    "my_first_index",
+    project_name="default",
+    api_key="YOUR_API_KEY",
+    base_url=EU_BASE_URL,
+)
 ```
 
-Full documentation for `SimpleDirectoryReader` can be found on the [LlamaIndex Documentation](https://docs.llamaindex.ai/en/stable/module_guides/loading/simpledirectoryreader.html).
+## Documentation
 
-## Examples
-
-Several end-to-end indexing examples can be found in the examples folder
-
-- [Getting Started](examples/demo_basic.ipynb)
-- [Advanced RAG Example](examples/demo_advanced.ipynb)
-- [Raw API Usage](examples/demo_api.ipynb)
+You can see complete SDK and API documentation for each service on [our official docs](https://docs.cloud.llamaindex.ai/).
 
 ## Terms of Service
 
 See the [Terms of Service Here](./TOS.pdf).
+
+## Get in Touch (LlamaCloud)
+
+You can get in touch with us by following our [contact link](https://www.llamaindex.ai/contact).

examples-ts/README.md

@@ -0,0 +1,8 @@
+# LlamaCloud Services Examples - Python
+
+In this folder you will find several TypeScript end-to-end applications that contain examples regarding:
+
+- [LlamaParse](./parse/)
+- [LlamaCloud Index](./index/)
+
+Follow the instructions in each example folder to get started!

examples-ts/extract/README.md

@@ -0,0 +1,122 @@
+# LlamaExtract Demo
+
+A TypeScript demo application showcasing the power of **LlamaExract** - a structured data extraction agentic service from [LlamaCloud](https://cloud.llamaindex.ai). This demo allows you to extract structured information from scientific papers and get them into a nice markdown format.
+
+## Table of Contents
+
+- [Features](#features)
+- [Prerequisites](#prerequisites)
+- [Installation](#installation)
+- [Usage](#usage)
+  - [Start the Demo](#start-the-demo)
+  - [Development Mode](#development-mode)
+  - [Build the Project](#build-the-project)
+  - [Code Quality](#code-quality)
+  - [Quick Commands Reference](#quick-commands-reference)
+- [How It Works](#how-it-works)
+- [API Dependencies](#api-dependencies)
+- [Troubleshooting](#troubleshooting)
+  - [Common Issues](#common-issues)
+- [License](#license)
+- [Contributing](#contributing)
+
+## Features
+
+- 📄 **Structured Data Extraction**: Extract data from your files effortlessly, and structure them the way you want!
+- 🤖 **Markdown Rendering**: Generate markdown directly from your extracted data
+- 🎨 **Beautiful CLI**: Styled console interface with colors and ASCII art
+- ⚡ **Fast Development**: Hot reload support with watch mode
+- 🛠️ **TypeScript**: Full TypeScript support with strict type checking
+
+## Prerequisites
+
+- Node.js (version 18 or higher)
+- pnpm package manager
+- LlamaCloud API key
+
+## Installation
+
+1. Clone the repository:
+
+```bash
+git clone https://github.com/run-llama/llama_cloud_services
+cd lama_cloud_services/examples-ts/extract/
+```
+
+2. Install dependencies:
+
+```bash
+npm install
+```
+
+3. Set up your environment variables:
+
+```bash
+# Add your API key to your environment
+export LLAMA_CLOUD_API_KEY="your-llamacloud-api-key"
+```
+
+## Usage
+
+### Start the Demo
+
+```bash
+npm run start
+```
+
+The application will display a welcome screen and prompt you to enter the path to a document you'd like to process.
+
+### Development Mode
+
+For development with hot reload:
+
+```bash
+npm run dev
+```
+
+### Build the Project
+
+```bash
+npm run build
+```
+
+### Code Quality
+
+Format code:
+
+```bash
+npm run format
+```
+
+Lint code:
+
+```bash
+npm run lint
+```
+
+## How It Works
+
+1. **Document Input**: Enter the path to your document when prompted
+2. **Parsing**: LlamaExtract, based on the schema you can find [here](./src/schema.ts), processes the document and extracts structured data
+3. **Markdown Rendering**: The extracted content is rendered into beautiful markdown
+4. **Results**: View the results directly in your terminal
+
+## Troubleshooting
+
+### Common Issues
+
+1. **Module Resolution Errors**: Ensure you're using Node.js 18+ and have all dependencies installed
+2. **API Key Issues**: Verify your LlamaCloud API key is correctly set
+3. **File Path Errors**: Use absolute paths or ensure relative paths are correct from the project root
+
+## License
+
+MIT License - see the [LICENSE](../../LICENSE) file for details.
+
+## Contributing
+
+1. Fork the repository
+2. Create a feature branch
+3. Make your changes
+4. Run `npm run format` and `npm run lint`
+5. Submit a pull request

examples-ts/extract/eslint.config.mts

@@ -0,0 +1,14 @@
+import js from "@eslint/js";
+import globals from "globals";
+import tseslint from "typescript-eslint";
+import { defineConfig } from "eslint/config";
+
+export default defineConfig([
+  {
+    files: ["**/*.{js,mjs,cjs,ts,mts,cts}"],
+    plugins: { js },
+    extends: ["js/recommended"],
+    languageOptions: { globals: globals.browser },
+  },
+  tseslint.configs.recommended,
+]);

examples-ts/extract/package.json

@@ -0,0 +1,37 @@
+{
+  "name": "llama-extract-demo",
+  "version": "0.1.0",
+  "description": "Demo for LlamaExtract in TypeScript",
+  "main": "index.js",
+  "scripts": {
+    "test": "echo \"There are no tests\"",
+    "start": "npm exec tsx src/index.ts",
+    "lint": "eslint ./src/",
+    "format": "prettier --write ./src/",
+    "build": "tsc",
+    "dev": "npm exec tsx --watch src/index.ts"
+  },
+  "author": "LlamaIndex",
+  "license": "MIT",
+  "dependencies": {
+    "cli-markdown": "^3.5.1",
+    "consola": "^3.4.2",
+    "figlet": "^1.8.2",
+    "llama-cloud-services": "file:../../ts/llama_cloud_services",
+    "marked": "^15.0.12",
+    "marked-terminal": "^7.3.0",
+    "picocolors": "^1.1.1"
+  },
+  "devDependencies": {
+    "@eslint/js": "^9.32.0",
+    "@types/figlet": "^1.7.0",
+    "@types/marked-terminal": "^6.1.1",
+    "@types/node": "^24.2.0",
+    "eslint": "^9.32.0",
+    "globals": "^16.3.0",
+    "jiti": "^2.5.1",
+    "prettier": "^3.6.2",
+    "typescript": "^5.9.2",
+    "typescript-eslint": "^8.39.0"
+  }
+}

examples-ts/extract/src/index.ts

@@ -0,0 +1,47 @@
+import { LlamaExtract, ExtractConfig } from "llama-cloud-services";
+import cliMarkdown from "cli-markdown";
+import { logger } from "./logger";
+import pc from "picocolors";
+import { consoleInput, renderLogo } from "./utils";
+import { dataSchema } from "./schema";
+import { renderMarkdown, ResearchData } from "./markdown";
+
+export async function main(): Promise<number> {
+  const extractClient = new LlamaExtract(
+    process.env.LLAMA_CLOUD_API_KEY!,
+    "https://api.cloud.llamaindex.ai",
+  );
+  await renderLogo();
+  logger.log(
+    `Welcome to ${pc.bold(
+      pc.magentaBright("LlamaExtract Demo✨"),
+    )}, our demo for ${pc.bold(pc.green("LlamaExtract"))}, a ${pc.bold(
+      pc.cyan("LlamaCloud☁️"),
+    )}  (https://cloud.llamaindex.ai) product!.\nIn this demo we are going to try extracting relevant information  ${pc.bold(
+      pc.yellowBright("from scientific papers"),
+    )}. Type the path to the paper you would like to process below👇\nIf you wish to exit, just type ${pc.bold(
+      pc.gray("quit"),
+    )}.\n`,
+  );
+  while (true) {
+    const userInput = await consoleInput();
+    if (userInput.toLowerCase() == "quit") {
+      break;
+    }
+    try {
+      const generatedData = await extractClient.extract(
+        dataSchema,
+        {} as ExtractConfig,
+        userInput,
+      );
+      const research = renderMarkdown(generatedData?.data as ResearchData); // Added await here
+      logger.log(`${pc.bold(pc.cyan("Extracted information:✨"))}:\n`);
+      logger.log(cliMarkdown(research));
+    } catch (error) {
+      logger.error(`Error processing file: ${error}`);
+    }
+  }
+  return 0;
+}
+
+main().catch(console.error);

examples-ts/extract/src/logger.ts

@@ -0,0 +1,8 @@
+import { createConsola } from "consola";
+import type { ConsolaInstance } from "consola";
+
+export const logger: ConsolaInstance = createConsola({
+  formatOptions: {
+    date: false,
+  },
+});

examples-ts/extract/src/markdown.ts

@@ -0,0 +1,172 @@
+type Author = {
+  name: string;
+  affiliation?: string;
+  email?: string;
+};
+
+type Methodology = {
+  approach?: string;
+  participants?: string;
+  methods?: string[];
+};
+
+type Result = {
+  finding?: string;
+  significance?: string;
+  supportingData?: string;
+};
+
+type Reference = {
+  title: string;
+  authors: string;
+  year?: string;
+  relevance?: string;
+};
+
+type Discussion = {
+  implications?: string[];
+  limitations?: string[];
+  futureWork?: string[];
+};
+
+type Publication = {
+  journal?: string;
+  year: string;
+  doi?: string;
+  url?: string;
+};
+
+export type ResearchData = {
+  title: string;
+  authors: Author[];
+  abstract: string;
+  keywords?: string[];
+  mainFindings: string[];
+  methodology?: Methodology;
+  results?: Result[];
+  discussion?: Discussion;
+  references?: Reference[];
+  publication?: Publication;
+};
+
+export function renderMarkdown(data: ResearchData): string {
+  const {
+    title,
+    authors,
+    abstract,
+    keywords,
+    mainFindings,
+    methodology,
+    results,
+    discussion,
+    references,
+    publication,
+  } = data;
+
+  const md: string[] = [];
+
+  md.push(`# ${title}\n`);
+
+  // Authors
+  md.push(`## Authors`);
+  md.push(
+    authors
+      .map(
+        (author) =>
+          `- **${author.name}**${
+            author.affiliation ? `, *${author.affiliation}*` : ""
+          }${author.email ? ` (${author.email})` : ""}`,
+      )
+      .join("\n"),
+  );
+
+  // Abstract
+  md.push(`\n## Abstract\n${abstract}`);
+
+  // Keywords
+  if (keywords && keywords.length > 0) {
+    md.push(`\n## Keywords\n${keywords.map((k) => `- ${k}`).join("\n")}`);
+  }
+
+  // Main Findings
+  md.push(
+    `\n## Main Findings\n${mainFindings.map((f) => `- ${f}`).join("\n")}`,
+  );
+
+  // Methodology
+  if (methodology) {
+    md.push(`\n## Methodology`);
+    if (methodology.approach) md.push(`**Approach:** ${methodology.approach}`);
+    if (methodology.participants)
+      md.push(`**Participants:** ${methodology.participants}`);
+    if (methodology.methods?.length) {
+      md.push(
+        `**Methods:**\n${methodology.methods.map((m) => `- ${m}`).join("\n")}`,
+      );
+    }
+  }
+
+  // Results
+  if (results?.length) {
+    md.push(`\n## Results`);
+    results.forEach((result, i) => {
+      md.push(`\n### Result ${i + 1}`);
+      if (result.finding) md.push(`- **Finding:** ${result.finding}`);
+      if (result.significance)
+        md.push(`- **Significance:** ${result.significance}`);
+      if (result.supportingData)
+        md.push(`- **Supporting Data:** ${result.supportingData}`);
+    });
+  }
+
+  // Discussion
+  if (discussion) {
+    md.push(`\n## Discussion`);
+    if (discussion.implications?.length) {
+      md.push(
+        `### Implications\n${discussion.implications
+          .map((d) => `- ${d}`)
+          .join("\n")}`,
+      );
+    }
+    if (discussion.limitations?.length) {
+      md.push(
+        `### Limitations\n${discussion.limitations
+          .map((d) => `- ${d}`)
+          .join("\n")}`,
+      );
+    }
+    if (discussion.futureWork?.length) {
+      md.push(
+        `### Future Work\n${discussion.futureWork
+          .map((d) => `- ${d}`)
+          .join("\n")}`,
+      );
+    }
+  }
+
+  // References
+  if (references?.length) {
+    md.push(`\n## References`);
+    references.forEach((ref, i) => {
+      md.push(
+        `\n**[${i + 1}]** ${ref.title} — *${ref.authors}*${
+          ref.year ? ` (${ref.year})` : ""
+        }`,
+      );
+      if (ref.relevance) md.push(`> ${ref.relevance}`);
+    });
+  }
+
+  // Publication Info
+  if (publication) {
+    md.push(`\n## Publication`);
+    if (publication.journal) md.push(`- **Journal:** ${publication.journal}`);
+    if (publication.year) md.push(`- **Year:** ${publication.year}`);
+    if (publication.doi) md.push(`- **DOI:** ${publication.doi}`);
+    if (publication.url)
+      md.push(`- **URL:** [${publication.url}](${publication.url})`);
+  }
+
+  return md.join("\n");
+}

examples-ts/extract/src/schema.ts

@@ -0,0 +1,169 @@
+export const dataSchema = {
+  type: "object",
+  required: ["title", "authors", "abstract", "mainFindings"],
+  properties: {
+    title: {
+      type: "string",
+      description: "The full title of the research paper",
+    },
+    authors: {
+      type: "array",
+      description: "List of all authors of the paper",
+      items: {
+        type: "object",
+        properties: {
+          name: {
+            type: "string",
+            description: "Full name of the author",
+          },
+          affiliation: {
+            type: "string",
+            description:
+              "Institution or organization the author is affiliated with",
+          },
+          email: {
+            type: "string",
+            description: "Contact email of the author if provided",
+          },
+        },
+      },
+    },
+    abstract: {
+      type: "string",
+      description: "Complete abstract or summary of the paper",
+    },
+    keywords: {
+      type: "array",
+      description:
+        "Key terms and phrases that describe the paper's main topics",
+      items: {
+        type: "string",
+      },
+    },
+    mainFindings: {
+      type: "array",
+      description: "Key findings, conclusions, or contributions of the paper",
+      items: {
+        type: "string",
+      },
+    },
+    methodology: {
+      type: "object",
+      description: "Research methods and approaches used",
+      properties: {
+        approach: {
+          type: "string",
+          description: "Overall research approach or study design",
+        },
+        participants: {
+          type: "string",
+          description: "Description of study participants or data sources",
+        },
+        methods: {
+          type: "array",
+          description: "Specific methods, techniques, or tools used",
+          items: {
+            type: "string",
+          },
+        },
+      },
+    },
+    results: {
+      type: "array",
+      description: "Main results and outcomes of the research",
+      items: {
+        type: "object",
+        properties: {
+          finding: {
+            type: "string",
+            description: "Description of the specific result or finding",
+          },
+          significance: {
+            type: "string",
+            description:
+              "Statistical significance or importance of the finding",
+          },
+          supportingData: {
+            type: "string",
+            description: "Relevant statistics, measurements, or data points",
+          },
+        },
+      },
+    },
+    discussion: {
+      type: "object",
+      properties: {
+        implications: {
+          type: "array",
+          description: "Theoretical or practical implications of the findings",
+          items: {
+            type: "string",
+          },
+        },
+        limitations: {
+          type: "array",
+          description: "Study limitations or constraints",
+          items: {
+            type: "string",
+          },
+        },
+        futureWork: {
+          type: "array",
+          description: "Suggested future research directions",
+          items: {
+            type: "string",
+          },
+        },
+      },
+    },
+    references: {
+      type: "array",
+      description:
+        "Key papers cited that are crucial to understanding this work",
+      items: {
+        type: "object",
+        properties: {
+          title: {
+            type: "string",
+            description: "Title of the cited paper",
+          },
+          authors: {
+            type: "string",
+            description: "Authors of the cited paper",
+          },
+          year: {
+            type: "string",
+            description: "Publication year",
+          },
+          relevance: {
+            type: "string",
+            description: "Why this reference is important to the current paper",
+          },
+        },
+        required: ["title", "authors"],
+      },
+    },
+    publication: {
+      type: "object",
+      properties: {
+        journal: {
+          type: "string",
+          description: "Name of the journal or conference",
+        },
+        year: {
+          type: "string",
+          description: "Year of publication",
+        },
+        doi: {
+          type: "string",
+          description: "Digital Object Identifier (DOI) of the paper",
+        },
+        url: {
+          type: "string",
+          description: "URL where the paper can be accessed",
+        },
+      },
+      required: ["year"],
+    },
+  },
+};

examples-ts/extract/src/types/cli-markdown.d.ts

@@ -0,0 +1,4 @@
+declare module "cli-markdown" {
+  function cliMarkdown(input: string): string;
+  export default cliMarkdown;
+}

examples-ts/extract/src/utils.ts

@@ -0,0 +1,33 @@
+import * as readline from "readline/promises";
+import figlet from "figlet";
+import pc from "picocolors";
+
+export async function renderLogo(): Promise<void> {
+  const logoText = figlet.textSync("Extract Demo", {
+    font: "ANSI Shadow",
+    horizontalLayout: "default",
+    verticalLayout: "default",
+    width: 100,
+    whitespaceBreak: true,
+  });
+
+  // Add some styling with picocolors
+  const styledLogo = pc.bold(pc.redBright(logoText));
+
+  // Add some padding/margin
+  console.log("\n");
+  console.log(styledLogo);
+  console.log(pc.gray("─".repeat(60)));
+  console.log("\n");
+}
+
+export async function consoleInput(): Promise<string> {
+  const rl = readline.createInterface({
+    input: process.stdin,
+    output: process.stdout,
+  });
+
+  const answer = await rl.question("Path to your file: ");
+  rl.close();
+  return answer;
+}

examples-ts/index/README.md

@@ -0,0 +1,131 @@
+# LlamaCloud Index Demo
+
+A TypeScript demo application showcasing the power of **LlamaCloud Index** - a fully automated document ingestion and retrieval serviced offered within [LlamaCloud](https://cloud.llamaindex.ai). This demo allows you to ask questions, retrieve relevant contextual information and generate AI-powered responses using OpenAI's GPT models.
+
+## Table of Contents
+
+- [Features](#features)
+- [Prerequisites](#prerequisites)
+- [Installation](#installation)
+- [Usage](#usage)
+  - [Start the Demo](#start-the-demo)
+  - [Development Mode](#development-mode)
+  - [Build the Project](#build-the-project)
+  - [Code Quality](#code-quality)
+  - [Quick Commands Reference](#quick-commands-reference)
+- [How It Works](#how-it-works)
+- [API Dependencies](#api-dependencies)
+- [Troubleshooting](#troubleshooting)
+  - [Common Issues](#common-issues)
+- [License](#license)
+- [Contributing](#contributing)
+
+## Features
+
+- 🤖 **RAG**: Simple-yet-effective Retrieval Augmented Generation pipeline built on top of LlamaCloud Index and OpenAI
+- 🎨 **Beautiful CLI**: Styled console interface with colors and ASCII art
+- ⚡ **Fast Development**: Hot reload support with watch mode
+- 🛠️ **TypeScript**: Full TypeScript support with strict type checking
+
+## Prerequisites
+
+- Node.js (version 18 or higher)
+- pnpm package manager
+- OpenAI API key
+- LlamaCloud API key
+- An existing LlamaCloud Index pipeline
+
+## Installation
+
+1. Clone the repository:
+
+```bash
+git clone https://github.com/run-llama/llama_cloud_services
+cd lama_cloud_services/examples-ts/index/
+```
+
+2. Install dependencies:
+
+```bash
+pnpm install
+```
+
+3. Set up your environment variables:
+
+```bash
+export OPENAI_API_KEY="your-openai-api-key"
+export LLAMA_CLOUD_API_KEY="your-llamacloud-api-key"
+export PIPELINE_NAME="your-pipeline-name"
+```
+
+4. Or write them into a `.env` file:
+
+```env
+OPENAI_API_KEY="your-openai-api-key"
+LLAMA_CLOUD_API_KEY="your-llamacloud-api-key"
+PIPELINE_NAME="your-pipeline-name"
+```
+
+## Usage
+
+### Start the Demo
+
+```bash
+pnpm run start
+```
+
+The application will display a welcome screen and prompt you to start chatting!
+
+### Development Mode
+
+For development with hot reload:
+
+```bash
+pnpm run dev
+```
+
+### Build the Project
+
+```bash
+pnpm run build
+```
+
+### Code Quality
+
+Format code:
+
+```bash
+pnpm run format
+```
+
+Lint code:
+
+```bash
+pnpm run lint
+```
+
+## How It Works
+
+1. **Message Input**: Enter a message
+2. **Retrieval**: Several nodes are retrieved from the LlamaCloud index you specified
+3. **AI Response Generation**: The retrieved information is passed on to the AI model, along with its relevance score, and a reply to your original message is generated starting from that.
+4. **Results**: View the AI-generated summary in your terminal
+
+## Troubleshooting
+
+### Common Issues
+
+1. **Module Resolution Errors**: Ensure you're using Node.js 18+ and have all dependencies installed
+2. **API Key Issues**: Verify your OpenAI and LlamaCloud API keys are correctly set
+
+## License
+
+MIT License - see the [LICENSE](../../LICENSE) file for details.
+
+## Contributing
+
+1. Fork the repository
+2. Create a feature branch
+3. Make your changes
+4. Run `pnpm run format` and `pnpm run lint`
+5. Submit a pull request

examples-ts/index/eslint.config.mts

@@ -0,0 +1,15 @@
+import js from "@eslint/js";
+import globals from "globals";
+import tseslint from "typescript-eslint";
+import { defineConfig } from "eslint/config";
+
+export default defineConfig([
+  {
+    files: ["**/*.{js,mjs,cjs,ts,mts,cts}"],
+    plugins: { js },
+    extends: ["js/recommended"],
+    languageOptions: { globals: globals.browser },
+  },
+  { files: ["**/*.js"], languageOptions: { sourceType: "script" } },
+  tseslint.configs.recommended,
+]);

examples-ts/index/package.json

@@ -0,0 +1,48 @@
+{
+  "name": "llama-chat",
+  "version": "0.1.0",
+  "description": "Demo for LlamaCloud Index in TypeScript",
+  "type": "module",
+  "main": "index.js",
+  "scripts": {
+    "test": "echo \"There are no tests\"",
+    "start": "pnpm exec tsx src/index.ts",
+    "lint": "eslint ./src/",
+    "format": "prettier --write ./src/",
+    "build": "tsc",
+    "dev": "pnpm exec tsx --watch src/index.ts"
+  },
+  "keywords": [
+    "ai",
+    "rag",
+    "retrieval",
+    "pipeline",
+    "llms",
+    "chatbot"
+  ],
+  "author": "LlamaIndex",
+  "license": "MIT",
+  "packageManager": "pnpm@10.12.4",
+  "devDependencies": {
+    "@eslint/js": "^9.32.0",
+    "@types/figlet": "^1.7.0",
+    "@types/node": "^24.1.0",
+    "@typescript-eslint/eslint-plugin": "^8.38.0",
+    "@typescript-eslint/parser": "^8.38.0",
+    "eslint": "^9.32.0",
+    "globals": "^16.3.0",
+    "jiti": "^2.5.1",
+    "prettier": "^3.6.2",
+    "typescript": "^5.8.3",
+    "typescript-eslint": "^8.38.0"
+  },
+  "dependencies": {
+    "@ai-sdk/openai": "^1.3.23",
+    "ai": "^4.3.19",
+    "consola": "^3.4.2",
+    "dotenv": "^17.2.1",
+    "figlet": "^1.8.2",
+    "llama-cloud-services": "link:../../ts/llama_cloud_services",
+    "picocolors": "^1.1.1"
+  }
+}

examples-ts/index/src/index.ts

@@ -0,0 +1,48 @@
+import { LlamaCloudIndex } from "llama-cloud-services";
+import { logger } from "./logger";
+import pc from "picocolors";
+import {
+  consoleInput,
+  retrievalAugmentedGeneration,
+  renderLogo,
+} from "./utils";
+import dotenv from "dotenv";
+
+dotenv.config();
+
+export async function main(): Promise<number> {
+  const index = new LlamaCloudIndex({
+    name: process.env.PIPELINE_NAME as string,
+    projectName: "Default",
+    apiKey: process.env.LLAMA_CLOUD_API_KEY, // can provide API-key in the constructor or in the env
+  });
+  const retriever = index.asRetriever({
+    similarityTopK: 5,
+  });
+  await renderLogo();
+  logger.log(
+    `Welcome to ${pc.bold(
+      pc.magentaBright("✨LlamaChat✨"),
+    )}, our demo for ${pc.bold(pc.green("Index🦙"))}, a ${pc.bold(
+      pc.cyan("LlamaCloud☁️"),
+    )}  (https://cloud.llamaindex.ai) product!.\nType a question below, and you will get an answer!👇\nIf you wish to exit, just type ${pc.bold(
+      pc.gray("quit"),
+    )}.\n`,
+  );
+  while (true) {
+    const userInput = await consoleInput();
+    if (userInput.toLowerCase() == "quit") {
+      break;
+    }
+    try {
+      const nodes = await retriever.retrieve(userInput);
+      const summary = await retrievalAugmentedGeneration(nodes, userInput);
+      logger.log(`${pc.bold(pc.magentaBright("LlamaChat✨:"))}\n${summary}`);
+    } catch (error) {
+      logger.error(`Error processing your request: ${error}`);
+    }
+  }
+  return 0;
+}
+
+main().catch(console.error);

examples-ts/index/src/logger.ts

@@ -0,0 +1,8 @@
+import { createConsola } from "consola";
+import type { ConsolaInstance } from "consola";
+
+export const logger: ConsolaInstance = createConsola({
+  formatOptions: {
+    date: false,
+  },
+});

examples-ts/index/src/utils.ts

@@ -0,0 +1,56 @@
+import { generateText } from "ai";
+import { openai } from "@ai-sdk/openai";
+import { NodeWithScore, MetadataMode } from "llamaindex";
+import * as readline from "readline/promises";
+import figlet from "figlet";
+import pc from "picocolors";
+
+export async function renderLogo(): Promise<void> {
+  const logoText = figlet.textSync("LlamaChat", {
+    font: "ANSI Shadow",
+    horizontalLayout: "default",
+    verticalLayout: "default",
+    width: 100,
+    whitespaceBreak: true,
+  });
+
+  // Add some styling with picocolors
+  const styledLogo = pc.bold(pc.yellowBright(logoText));
+
+  // Add some padding/margin
+  console.log("\n");
+  console.log(styledLogo);
+  console.log(pc.gray("─".repeat(60)));
+  console.log("\n");
+}
+
+export async function consoleInput(): Promise<string> {
+  const rl = readline.createInterface({
+    input: process.stdin,
+    output: process.stdout,
+  });
+
+  const answer = await rl.question(pc.cyanBright("You✨:"));
+  rl.close();
+  return answer;
+}
+
+export async function retrievalAugmentedGeneration(
+  nodes: NodeWithScore[],
+  prompt: string,
+): Promise<string> {
+  let mainText: string = "";
+
+  for (const node of nodes) {
+    mainText += `\t{information: '${node.node.getContent(
+      MetadataMode.ALL,
+    )}', relevanceScore: '${node.score ?? "no score"}'}\n`;
+  }
+
+  const { text } = await generateText({
+    model: openai("gpt-4.1"),
+    prompt: `[\n${mainText}\n]\n\nBased on the information you are given and on the relevance score of that (where -1 means no score available), answer to this user prompt: '${prompt}'`,
+  });
+
+  return text;
+}

examples-ts/index/tsconfig.json

@@ -0,0 +1,22 @@
+{
+  "compilerOptions": {
+    "target": "ES2022",
+    "module": "ES2022",
+    "lib": ["ES2022"],
+    "outDir": "./dist",
+    "rootDir": "./src",
+    "strict": true,
+    "esModuleInterop": true,
+    "skipLibCheck": true,
+    "forceConsistentCasingInFileNames": true,
+    "declaration": true,
+    "declarationMap": true,
+    "sourceMap": true,
+    "types": ["node"],
+    "moduleResolution": "bundler",
+    "allowSyntheticDefaultImports": true,
+    "resolveJsonModule": true
+  },
+  "include": ["src/**/*"],
+  "exclude": ["node_modules", "dist"]
+}

examples-ts/parse/README.md

@@ -0,0 +1,124 @@
+# LlamaParse Demo
+
+A TypeScript demo application showcasing the power of **LlamaParse** - an intelligent document parsing service from [LlamaCloud](https://cloud.llamaindex.ai). This demo allows you to parse various document formats and generate AI-powered summaries using OpenAI's GPT models.
+
+## Table of Contents
+
+- [Features](#features)
+- [Prerequisites](#prerequisites)
+- [Installation](#installation)
+- [Usage](#usage)
+  - [Start the Demo](#start-the-demo)
+  - [Development Mode](#development-mode)
+  - [Build the Project](#build-the-project)
+  - [Code Quality](#code-quality)
+  - [Quick Commands Reference](#quick-commands-reference)
+- [How It Works](#how-it-works)
+- [API Dependencies](#api-dependencies)
+- [Troubleshooting](#troubleshooting)
+  - [Common Issues](#common-issues)
+- [License](#license)
+- [Contributing](#contributing)
+
+## Features
+
+- 📄 **Document Parsing**: Parse PDFs, Word docs, and other formats using LlamaParse
+- 🤖 **AI Summaries**: Generate intelligent summaries using OpenAI GPT-4
+- 🎨 **Beautiful CLI**: Styled console interface with colors and ASCII art
+- ⚡ **Fast Development**: Hot reload support with watch mode
+- 🛠️ **TypeScript**: Full TypeScript support with strict type checking
+
+## Prerequisites
+
+- Node.js (version 18 or higher)
+- pnpm package manager
+- OpenAI API key
+- LlamaCloud API key
+
+## Installation
+
+1. Clone the repository:
+
+```bash
+git clone https://github.com/run-llama/llama_cloud_services
+cd lama_cloud_services/examples-ts/parse/
+```
+
+2. Install dependencies:
+
+```bash
+pnpm install
+```
+
+3. Set up your environment variables:
+
+```bash
+# Add your API keys to your environment
+export OPENAI_API_KEY="your-openai-api-key"
+export LLAMA_CLOUD_API_KEY="your-llamacloud-api-key"
+```
+
+## Usage
+
+### Start the Demo
+
+```bash
+pnpm run start
+```
+
+The application will display a welcome screen and prompt you to enter the path to a document you'd like to process.
+
+### Development Mode
+
+For development with hot reload:
+
+```bash
+pnpm run dev
+```
+
+### Build the Project
+
+```bash
+pnpm run build
+```
+
+### Code Quality
+
+Format code:
+
+```bash
+pnpm run format
+```
+
+Lint code:
+
+```bash
+pnpm run lint
+```
+
+## How It Works
+
+1. **Document Input**: Enter the path to your document when prompted
+2. **Parsing**: LlamaParse processes the document and extracts structured content
+3. **AI Summary**: The extracted content is sent to OpenAI GPT-4 for summarization
+4. **Results**: View the AI-generated summary in your terminal
+
+## Troubleshooting
+
+### Common Issues
+
+1. **Module Resolution Errors**: Ensure you're using Node.js 18+ and have all dependencies installed
+2. **API Key Issues**: Verify your OpenAI and LlamaCloud API keys are correctly set
+3. **File Path Errors**: Use absolute paths or ensure relative paths are correct from the project root
+
+## License
+
+MIT License - see the [LICENSE](../../LICENSE) file for details.
+
+## Contributing
+
+1. Fork the repository
+2. Create a feature branch
+3. Make your changes
+4. Run `pnpm run format` and `pnpm run lint`
+5. Submit a pull request

examples-ts/parse/eslint.config.mts

@@ -0,0 +1,15 @@
+import js from "@eslint/js";
+import globals from "globals";
+import tseslint from "typescript-eslint";
+import { defineConfig } from "eslint/config";
+
+export default defineConfig([
+  {
+    files: ["**/*.{js,mjs,cjs,ts,mts,cts}"],
+    plugins: { js },
+    extends: ["js/recommended"],
+    languageOptions: { globals: globals.browser },
+  },
+  { files: ["**/*.js"], languageOptions: { sourceType: "script" } },
+  tseslint.configs.recommended,
+]);

examples-ts/parse/package.json

@@ -0,0 +1,47 @@
+{
+  "name": "llamaparse-demo",
+  "version": "0.1.0",
+  "description": "Demo for LlamaParse in TypeScript",
+  "type": "module",
+  "main": "index.js",
+  "scripts": {
+    "test": "echo \"There are no tests\"",
+    "start": "pnpm exec tsx src/index.ts",
+    "lint": "eslint ./src/",
+    "format": "prettier --write ./src/",
+    "build": "tsc",
+    "dev": "pnpm exec tsx --watch src/index.ts"
+  },
+  "keywords": [
+    "ai",
+    "ocr",
+    "parsing",
+    "intelligent-document-processing",
+    "pdf",
+    "llms"
+  ],
+  "author": "LlamaIndex",
+  "license": "MIT",
+  "packageManager": "pnpm@10.12.4",
+  "devDependencies": {
+    "@eslint/js": "^9.32.0",
+    "@types/figlet": "^1.7.0",
+    "@types/node": "^24.1.0",
+    "@typescript-eslint/eslint-plugin": "^8.38.0",
+    "@typescript-eslint/parser": "^8.38.0",
+    "eslint": "^9.32.0",
+    "globals": "^16.3.0",
+    "jiti": "^2.5.1",
+    "prettier": "^3.6.2",
+    "typescript": "^5.8.3",
+    "typescript-eslint": "^8.38.0"
+  },
+  "dependencies": {
+    "@ai-sdk/openai": "^1.3.23",
+    "ai": "^4.3.19",
+    "consola": "^3.4.2",
+    "figlet": "^1.8.2",
+    "llama-cloud-services": "link:../../ts/llama_cloud_services",
+    "picocolors": "^1.1.1"
+  }
+}

examples-ts/parse/src/index.ts

@@ -0,0 +1,34 @@
+import { LlamaParseReader } from "llama-cloud-services";
+import { logger } from "./logger";
+import pc from "picocolors";
+import { consoleInput, generateSummary, renderLogo } from "./utils";
+
+export async function main(): Promise<number> {
+  const reader = new LlamaParseReader({ resultType: "markdown" });
+  await renderLogo();
+  logger.log(
+    `Welcome to ${pc.bold(
+      pc.magentaBright("✨LlamaParse Demo✨"),
+    )}, our demo for ${pc.bold(pc.green("LlamaParse🦙"))}, a ${pc.bold(
+      pc.cyan("LlamaCloud☁️"),
+    )}  (https://cloud.llamaindex.ai) product!.\nType the path to the document you would like to process below👇\nIf you wish to exit, just type ${pc.bold(
+      pc.gray("quit"),
+    )}.\n`,
+  );
+  while (true) {
+    const userInput = await consoleInput();
+    if (userInput.toLowerCase() == "quit") {
+      break;
+    }
+    try {
+      const documents = await reader.loadData(userInput);
+      const summary = await generateSummary(documents); // Added await here
+      logger.log(`${pc.bold(pc.cyan("AI-generated summary✨"))}:\n${summary}`);
+    } catch (error) {
+      logger.error(`Error processing file: ${error}`);
+    }
+  }
+  return 0;
+}
+
+main().catch(console.error);

examples-ts/parse/src/logger.ts

@@ -0,0 +1,8 @@
+import { createConsola } from "consola";
+import type { ConsolaInstance } from "consola";
+
+export const logger: ConsolaInstance = createConsola({
+  formatOptions: {
+    date: false,
+  },
+});

examples-ts/parse/src/utils.ts

@@ -0,0 +1,51 @@
+import { generateText } from "ai";
+import { openai } from "@ai-sdk/openai";
+import { Document } from "llamaindex";
+import * as readline from "readline/promises";
+import figlet from "figlet";
+import pc from "picocolors";
+
+export async function renderLogo(): Promise<void> {
+  const logoText = figlet.textSync("LlamaParse Demo", {
+    font: "ANSI Shadow",
+    horizontalLayout: "default",
+    verticalLayout: "default",
+    width: 100,
+    whitespaceBreak: true,
+  });
+
+  // Add some styling with picocolors
+  const styledLogo = pc.bold(pc.magentaBright(logoText));
+
+  // Add some padding/margin
+  console.log("\n");
+  console.log(styledLogo);
+  console.log(pc.gray("─".repeat(60)));
+  console.log("\n");
+}
+
+export async function consoleInput(): Promise<string> {
+  const rl = readline.createInterface({
+    input: process.stdin,
+    output: process.stdout,
+  });
+
+  const answer = await rl.question("Path to your file: ");
+  rl.close();
+  return answer;
+}
+
+export async function generateSummary(documents: Document[]): Promise<string> {
+  let mainText: string = "";
+
+  for (const document of documents) {
+    mainText += `${document.text}\n\n---\n\n`;
+  }
+
+  const { text } = await generateText({
+    model: openai("gpt-4.1"),
+    prompt: `</chat>\n\t<text>${mainText}</text>\n\t<instructions>Could you please generate a summary of the given text?</instructions>\n</chat>`,
+  });
+
+  return text;
+}

examples-ts/parse/tsconfig.json

@@ -0,0 +1,22 @@
+{
+  "compilerOptions": {
+    "target": "ES2022",
+    "module": "ES2022",
+    "lib": ["ES2022"],
+    "outDir": "./dist",
+    "rootDir": "./src",
+    "strict": true,
+    "esModuleInterop": true,
+    "skipLibCheck": true,
+    "forceConsistentCasingInFileNames": true,
+    "declaration": true,
+    "declarationMap": true,
+    "sourceMap": true,
+    "types": ["node"],
+    "moduleResolution": "bundler",
+    "allowSyntheticDefaultImports": true,
+    "resolveJsonModule": true
+  },
+  "include": ["src/**/*"],
+  "exclude": ["node_modules", "dist"]
+}

examples/README.md

@@ -0,0 +1,9 @@
+# LlamaCloud Services Examples - Python
+
+In this folder you will find several python notebooks that contain examples regarding:
+
+- [LlamaParse](./parse/)
+- [LlamaExtract](./extract/)
+- [LlamaReport](./report/)
+
+Follow the instructions in each notebook to get started!

examples/demo_astradb.ipynb

@@ -1,296 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Using llama-parse with AstraDB"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "In this notebook, we show a basic RAG-style example that uses `llama-parse` to parse a PDF document, store the corresponding document into a vector store (`AstraDB`) and finally, perform some basic queries against that store. The notebook is modeled after the quick start notebooks and hence is meant as a way of getting started with `llama-parse`, backed by a vector database."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Requirements"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# First, install the required dependencies\n",
-    "!pip install --quiet llama-index llama-parse llama-index-vector-stores-astra-db llama-index-llms-openai"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Configuration"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "import openai\n",
-    "\n",
-    "from getpass import getpass\n",
-    "\n",
-    "# Get all required API keys and parameters\n",
-    "llama_cloud_api_key = getpass(\"Enter your Llama Index Cloud API Key: \")\n",
-    "api_endpoint = input(\"Enter your Astra DB API Endpoint: \")\n",
-    "token = getpass(\"Enter your Astra DB Token: \")\n",
-    "namespace = input(\"Enter your Astra DB namespace (optional, must exist on Astra): \") or None\n",
-    "openai_api_key = getpass(\"Enter your OpenAI API Key: \")\n",
-    "\n",
-    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = llama_cloud_api_key\n",
-    "openai.api_key = openai_api_key"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# llama-parse is async-first, running the sync code in a notebook requires the use of nest_asyncio\n",
-    "import nest_asyncio\n",
-    "\n",
-    "nest_asyncio.apply()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Using llama-parse to parse a PDF"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Download complete.\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Grab a PDF from Arxiv for indexing\n",
-    "import requests \n",
-    "\n",
-    "# The URL of the file you want to download\n",
-    "url = \"https://arxiv.org/pdf/1706.03762.pdf\"\n",
-    "# The local path where you want to save the file\n",
-    "file_path = \"./attention.pdf\"\n",
-    "\n",
-    "# Perform the HTTP request\n",
-    "response = requests.get(url)\n",
-    "\n",
-    "# Check if the request was successful\n",
-    "if response.status_code == 200:\n",
-    "    # Open the file in binary write mode and save the content\n",
-    "    with open(file_path, \"wb\") as file:\n",
-    "        file.write(response.content)\n",
-    "    print(\"Download complete.\")\n",
-    "else:\n",
-    "    print(\"Error downloading the file.\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Started parsing the file under job_id ce3909a7-54cf-438b-849a-fe9a903b0c71\n"
-     ]
-    }
-   ],
-   "source": [
-    "from llama_parse import LlamaParse\n",
-    "\n",
-    "documents = LlamaParse(result_type=\"text\").load_data(file_path)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'rmer - model architecture.\\nThe Transformer follows this overall architecture using stacked self-attention and point-wise, fully\\nconnected layers for both the encoder and decoder, shown in the left and right halves of Figure 1,\\nrespectively.\\n3.1   Encoder and Decoder Stacks\\nEncoder:     The encoder is composed of a stack of N = 6 identical layers. Each layer has two\\nsub-layers. The first is a multi-head self-attention mechanism, and the second is a simple, position-\\nwise fully connected feed-forward network. We employ a residual connection [11] around each of\\nthe two sub-layers, followed by layer normalization [1]. That is, the output of each sub-layer is\\nLayerNorm(x + Sublayer(x)), where Sublayer(x) is the function implemented by the sub-layer\\nitself. To facilitate these residual connections, all sub-layers in the model, as well as the embedding\\nlayers, produce outputs of dimension dmodel = 512.\\nDecoder:    The decoder is also composed of a stack of N = 6 identical layers. In addition '"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Take a quick look at some of the parsed text from the document:\n",
-    "documents[0].get_content()[10000:11000]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Storing into Astra DB"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from llama_index.vector_stores.astra_db import AstraDBVectorStore\n",
-    "\n",
-    "astra_db_store = AstraDBVectorStore(\n",
-    "    token=token,\n",
-    "    api_endpoint=api_endpoint,\n",
-    "    namespace=namespace,\n",
-    "    collection_name=\"astra_v_table_llamaparse\",\n",
-    "    embedding_dimension=1536\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from llama_index.core.node_parser import SimpleNodeParser\n",
-    "\n",
-    "node_parser = SimpleNodeParser()\n",
-    "\n",
-    "nodes = node_parser.get_nodes_from_documents(documents)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
-    "from llama_index.core import VectorStoreIndex, StorageContext\n",
-    "\n",
-    "storage_context = StorageContext.from_defaults(vector_store=astra_db_store)\n",
-    "\n",
-    "index = VectorStoreIndex(\n",
-    "    nodes=nodes,\n",
-    "    storage_context=storage_context,\n",
-    "    embed_model=OpenAIEmbedding(api_key=openai_api_key),\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Simple RAG Example"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "query_engine = index.as_query_engine(similarity_top_k=15)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "***********New LlamaParse+ Basic Query Engine***********\n",
-      "Multi-Head Attention is also known as multi-headed self-attention.\n"
-     ]
-    }
-   ],
-   "source": [
-    "query = \"What is Multi-Head Attention also known as?\"\n",
-    "\n",
-    "response_1 = query_engine.query(query)\n",
-    "print(\"\\n***********New LlamaParse+ Basic Query Engine***********\")\n",
-    "print(response_1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'We used beam search as described in the previous section, but no\\ncheckpoint averaging. We present these results in Table 3.\\nIn Table 3 rows (A), we vary the number of attention heads and the attention key and value dimensions,\\nkeeping the amount of computation constant, as described in Section 3.2.2. While single-head\\nattention is 0.9 BLEU worse than the best setting, quality also drops off with too many heads.\\nIn Table 3 rows (B), we observe that reducing the attention key size dk hurts model quality. This\\nsuggests that determining compatibility is not easy and that a more sophisticated compatibility\\nfunction than dot product may be beneficial. We further observe in rows (C) and (D) that, as expected,\\nbigger models are better, and dropout is very helpful in avoiding over-fitting. In row (E) we replace our\\nsinusoidal positional encoding with learned positional embeddings [9], and observe nearly identical\\nresults to the base model.\\n6.3    English Constituency Parsing\\nTo evaluate if the Transformer can generalize to other tasks we performed experiments on English\\nconstituency parsing. This task presents specific challenges: the output is subject to strong structural\\nconstraints and is significantly longer than the input. Furthermore, RNN sequence-to-sequence\\nmodels have not been able to attain state-of-the-art results in small-data regimes [37].\\nWe trained a 4-layer transformer with dmodel = 1024 on the Wall Street Journal (WSJ) portion of the\\nPenn Treebank [25], about 40K training sentences. We also trained it in a semi-supervised setting,\\nusing the larger high-confidence and BerkleyParser corpora from with approximately 17M sentences\\n[37]. We used a vocabulary of 16K tokens for the WSJ only setting and a vocabulary of 32K tokens\\nfor the semi-supervised setting.\\nWe performed only a small number of experiments to select the dropout, both attention and residual\\n(section 5.4), learning rates and beam size on the Section 22 development set, all other parameters\\nremained unchanged from the English-to-German base translation model. During inference, we\\n                                                             9\\n---\\nTable 4: The Transformer generalizes well to English constituency parsing (Results are on Section 23\\nof WSJ)\\n                          Parser                           Training             WSJ 23 F1\\n            Vinyals & Kaiser el al. (2014) [37]    WSJ only, discriminative         88.3\\n                 Petrov et al. (2006) [29]         WSJ only, discriminative         90.4\\n                   Zhu et al. (2013) [40]          WSJ only, discriminative         90.4\\n                   Dyer et al. (2016) [8]          WSJ only, discriminative         91.7\\n                  Transformer (4 layers)           WSJ only, discriminative         91.3\\n                   Zhu et al. (2013) [40]              semi-supervised              91.3\\n               Huang & Harper (2009) [14]              semi-supervised              91.3\\n               McClosky et al. (2006) [26]             semi-supervised              92.1\\n            Vinyals & Kaiser el al. (2014) [37]        semi-supervised              92.1\\n                  Transformer (4 layers)               semi-supervised              92.7\\n                 Luong et al. (2015) [23]                  multi-task               93.0\\n                   Dyer et al. (2016) [8]                  generative               93.3\\nincreased the maximum output length to input length + 300. We used a beam size of 21 and α = 0.3\\nfor both WSJ only and the semi-supervised setting.\\nOur results in Table 4 show that despite the lack of task-specific tuning our model performs sur-\\nprisingly well, yielding better results than all previously reported models with the exception of the\\nRecurrent Neural Network Grammar [8].\\nIn contrast to RNN sequence-to-sequence models [37], the Transformer outperforms the Berkeley-\\nParser [29] even when training only on the WSJ training set of 40K sentences.\\n7    Conclusion\\nIn this work, we presented the Transformer, the first sequence transduction model based entirely on\\nattention, replacing the recurrent layers most commonly used in encoder-decoder architectures with\\nmulti-headed self-attention.\\nFor translation tasks, the Transformer can be trained significantly faster than architectures based\\non recurrent or convolutional layers.'"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Take a look at one of the source nodes from the response\n",
-    "response_1.source_nodes[0].get_content()"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

examples/demo_basic.ipynb

@@ -1,191 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# LlamaParse Usage"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install llama-index llama-parse"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "--2024-02-02 11:10:10--  https://arxiv.org/pdf/1706.03762.pdf\n",
-      "Resolving arxiv.org (arxiv.org)... 151.101.131.42, 151.101.3.42, 151.101.67.42, ...\n",
-      "Connecting to arxiv.org (arxiv.org)|151.101.131.42|:443... connected.\n",
-      "HTTP request sent, awaiting response... 200 OK\n",
-      "Length: 2215244 (2.1M) [application/pdf]\n",
-      "Saving to: ‘./attention.pdf’\n",
-      "\n",
-      "./attention.pdf     100%[===================>]   2.11M  --.-KB/s    in 0.08s   \n",
-      "\n",
-      "2024-02-02 11:10:10 (25.9 MB/s) - ‘./attention.pdf’ saved [2215244/2215244]\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "!wget \"https://arxiv.org/pdf/1706.03762.pdf\" -O \"./attention.pdf\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# llama-parse is async-first, running the sync code in a notebook requires the use of nest_asyncio\n",
-    "import nest_asyncio\n",
-    "\n",
-    "nest_asyncio.apply()\n",
-    "\n",
-    "import os\n",
-    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"llx-...\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Started parsing the file under job_id dd0b8e31-0c09-4497-b78a-cc1c92f1d6cf\n"
-     ]
-    }
-   ],
-   "source": [
-    "from llama_parse import LlamaParse\n",
-    "\n",
-    "documents = LlamaParse(result_type=\"text\").load_data(\"./attention.pdf\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "ad\n",
-      "relying entirely on an attention mechanism to draw global dependencies between input and output.\n",
-      "The Transformer allows for significantly more parallelization and can reach a new state of the art in\n",
-      "translation quality after being trained for as little as twelve hours on eight P100 GPUs.\n",
-      "2    Background\n",
-      "The goal of reducing sequential computation also forms the foundation of the Extended Neural GPU\n",
-      "[16], ByteNet [18] and ConvS2S [9], all of which use convolutional neural networks as basic building\n",
-      "block, computing hidden representations in parallel for all input and output positions. In these models,\n",
-      "the number of operations required to relate signals from two arbitrary input or output positions grows\n",
-      "in the distance between positions, linearly for ConvS2S and logarithmically for ByteNet. This makes\n",
-      "it more difficult to learn dependencies between distant positions [12]. In the Transformer this is\n",
-      "reduced to a constant number of operations, albeit at the cost of reduced effective res\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(documents[0].text[6000:7000])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Started parsing the file under job_id d4531453-1bbb-48c4-8324-ae9fea9f2fa2\n"
-     ]
-    }
-   ],
-   "source": [
-    "from llama_parse import LlamaParse\n",
-    "\n",
-    "documents = LlamaParse(result_type=\"markdown\").load_data(\"./attention.pdf\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "ction describes the training regime for our models.\n",
-      "\n",
-      "##### Training Data and Batching\n",
-      "\n",
-      "We trained on the standard WMT 2014 English-German dataset consisting of about 4.5 million\n",
-      "sentence pairs. Sentences were encoded using byte-pair encoding [3], which has a shared source-\n",
-      "target vocabulary of about 37000 tokens. For English-French, we used the significantly larger WMT\n",
-      "2014 English-French dataset consisting of 36M sentences and split tokens into a 32000 word-piece\n",
-      "vocabulary [38]. Sentence pairs were batched together by approximate sequence length. Each training\n",
-      "batch contained a set of sentence pairs containing approximately 25000 source tokens and 25000\n",
-      "target tokens.\n",
-      "\n",
-      "##### Hardware and Schedule\n",
-      "\n",
-      "We trained our models on one machine with 8 NVIDIA P100 GPUs. For our base models using\n",
-      "the hyperparameters described throughout the paper, each training step took about 0.4 seconds. We\n",
-      "trained the base models for a total of 100,000 steps or 12 hours. For our big models,(described on the\n",
-      "bo...\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(documents[0].text[20000:21000] + \"...\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.12"
-  },
-  "orig_nbformat": 4
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

examples/demo_parsing_instructions.ipynb

@@ -1,615 +0,0 @@
-{
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": []
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "source": [
-        "# LlamaParse - Parsing comic books with parsing intructions\n",
-        "Parsing intructions allow you to instruct our parsing model the same way you would instruct an LLM!\n",
-        "\n",
-        "They can be usefull to help the parser get better results on complex document layouts, to extract data in a specific format, or to transform the document in other ways.\n",
-        "\n",
-        "Using Parsing Instruction you will get better results out of LlamaParse on complicated documents, and also be able to simplify your application code."
-      ],
-      "metadata": {
-        "id": "eld1dKaN7P8B"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "## Installation\n",
-        "\n",
-        "Parsing instructions are part of the llamaParse API. They can be accessed by directly specifying the parsing_instruction parameter in the API or by using the LlamaParse python module (which we will use for this tutorial).\n",
-        "\n",
-        "To install llama-parse, just get it from PIP:"
-      ],
-      "metadata": {
-        "id": "goB1sV8zu_Xl"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "!pip install llama-parse"
-      ],
-      "metadata": {
-        "id": "7Y3_BwQLu-qK",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "outputId": "652f8957-ae7a-48e3-86ae-2e9e885c4e1e"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Collecting llama-parse\n",
-            "  Downloading llama_parse-0.3.8-py3-none-any.whl (6.7 kB)\n",
-            "Collecting llama-index-core>=0.10.7 (from llama-parse)\n",
-            "  Downloading llama_index_core-0.10.19-py3-none-any.whl (15.3 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m15.3/15.3 MB\u001b[0m \u001b[31m31.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: PyYAML>=6.0.1 in /usr/local/lib/python3.10/dist-packages (from llama-index-core>=0.10.7->llama-parse) (6.0.1)\n",
-            "Requirement already satisfied: SQLAlchemy[asyncio]>=1.4.49 in /usr/local/lib/python3.10/dist-packages (from llama-index-core>=0.10.7->llama-parse) (2.0.28)\n",
-            "Requirement already satisfied: aiohttp<4.0.0,>=3.8.6 in /usr/local/lib/python3.10/dist-packages (from llama-index-core>=0.10.7->llama-parse) (3.9.3)\n",
-            "Collecting dataclasses-json (from llama-index-core>=0.10.7->llama-parse)\n",
-            "  Downloading dataclasses_json-0.6.4-py3-none-any.whl (28 kB)\n",
-            "Collecting deprecated>=1.2.9.3 (from llama-index-core>=0.10.7->llama-parse)\n",
-            "  Downloading Deprecated-1.2.14-py2.py3-none-any.whl (9.6 kB)\n",
-            "Collecting dirtyjson<2.0.0,>=1.0.8 (from llama-index-core>=0.10.7->llama-parse)\n",
-            "  Downloading dirtyjson-1.0.8-py3-none-any.whl (25 kB)\n",
-            "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from llama-index-core>=0.10.7->llama-parse) (2023.6.0)\n",
-            "Collecting httpx (from llama-index-core>=0.10.7->llama-parse)\n",
-            "  Downloading httpx-0.27.0-py3-none-any.whl (75 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting llamaindex-py-client<0.2.0,>=0.1.13 (from llama-index-core>=0.10.7->llama-parse)\n",
-            "  Downloading llamaindex_py_client-0.1.13-py3-none-any.whl (107 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m108.0/108.0 kB\u001b[0m \u001b[31m10.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: nest-asyncio<2.0.0,>=1.5.8 in /usr/local/lib/python3.10/dist-packages (from llama-index-core>=0.10.7->llama-parse) (1.6.0)\n",
-            "Requirement already satisfied: networkx>=3.0 in /usr/local/lib/python3.10/dist-packages (from llama-index-core>=0.10.7->llama-parse) (3.2.1)\n",
-            "Requirement already satisfied: nltk<4.0.0,>=3.8.1 in /usr/local/lib/python3.10/dist-packages (from llama-index-core>=0.10.7->llama-parse) (3.8.1)\n",
-            "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from llama-index-core>=0.10.7->llama-parse) (1.25.2)\n",
-            "Collecting openai>=1.1.0 (from llama-index-core>=0.10.7->llama-parse)\n",
-            "  Downloading openai-1.13.3-py3-none-any.whl (227 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m227.4/227.4 kB\u001b[0m \u001b[31m16.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from llama-index-core>=0.10.7->llama-parse) (1.5.3)\n",
-            "Requirement already satisfied: pillow>=9.0.0 in /usr/local/lib/python3.10/dist-packages (from llama-index-core>=0.10.7->llama-parse) (9.4.0)\n",
-            "Requirement already satisfied: requests>=2.31.0 in /usr/local/lib/python3.10/dist-packages (from llama-index-core>=0.10.7->llama-parse) (2.31.0)\n",
-            "Requirement already satisfied: tenacity<9.0.0,>=8.2.0 in /usr/local/lib/python3.10/dist-packages (from llama-index-core>=0.10.7->llama-parse) (8.2.3)\n",
-            "Collecting tiktoken>=0.3.3 (from llama-index-core>=0.10.7->llama-parse)\n",
-            "  Downloading tiktoken-0.6.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.8 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m43.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: tqdm<5.0.0,>=4.66.1 in /usr/local/lib/python3.10/dist-packages (from llama-index-core>=0.10.7->llama-parse) (4.66.2)\n",
-            "Requirement already satisfied: typing-extensions>=4.5.0 in /usr/local/lib/python3.10/dist-packages (from llama-index-core>=0.10.7->llama-parse) (4.10.0)\n",
-            "Collecting typing-inspect>=0.8.0 (from llama-index-core>=0.10.7->llama-parse)\n",
-            "  Downloading typing_inspect-0.9.0-py3-none-any.whl (8.8 kB)\n",
-            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.6->llama-index-core>=0.10.7->llama-parse) (1.3.1)\n",
-            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.6->llama-index-core>=0.10.7->llama-parse) (23.2.0)\n",
-            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.6->llama-index-core>=0.10.7->llama-parse) (1.4.1)\n",
-            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.6->llama-index-core>=0.10.7->llama-parse) (6.0.5)\n",
-            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.6->llama-index-core>=0.10.7->llama-parse) (1.9.4)\n",
-            "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0.0,>=3.8.6->llama-index-core>=0.10.7->llama-parse) (4.0.3)\n",
-            "Requirement already satisfied: wrapt<2,>=1.10 in /usr/local/lib/python3.10/dist-packages (from deprecated>=1.2.9.3->llama-index-core>=0.10.7->llama-parse) (1.14.1)\n",
-            "Requirement already satisfied: pydantic>=1.10 in /usr/local/lib/python3.10/dist-packages (from llamaindex-py-client<0.2.0,>=0.1.13->llama-index-core>=0.10.7->llama-parse) (2.6.3)\n",
-            "Requirement already satisfied: anyio in /usr/local/lib/python3.10/dist-packages (from httpx->llama-index-core>=0.10.7->llama-parse) (3.7.1)\n",
-            "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx->llama-index-core>=0.10.7->llama-parse) (2024.2.2)\n",
-            "Collecting httpcore==1.* (from httpx->llama-index-core>=0.10.7->llama-parse)\n",
-            "  Downloading httpcore-1.0.4-py3-none-any.whl (77 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.8/77.8 kB\u001b[0m \u001b[31m8.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: idna in /usr/local/lib/python3.10/dist-packages (from httpx->llama-index-core>=0.10.7->llama-parse) (3.6)\n",
-            "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx->llama-index-core>=0.10.7->llama-parse) (1.3.1)\n",
-            "Collecting h11<0.15,>=0.13 (from httpcore==1.*->httpx->llama-index-core>=0.10.7->llama-parse)\n",
-            "  Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: click in /usr/local/lib/python3.10/dist-packages (from nltk<4.0.0,>=3.8.1->llama-index-core>=0.10.7->llama-parse) (8.1.7)\n",
-            "Requirement already satisfied: joblib in /usr/local/lib/python3.10/dist-packages (from nltk<4.0.0,>=3.8.1->llama-index-core>=0.10.7->llama-parse) (1.3.2)\n",
-            "Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.10/dist-packages (from nltk<4.0.0,>=3.8.1->llama-index-core>=0.10.7->llama-parse) (2023.12.25)\n",
-            "Requirement already satisfied: distro<2,>=1.7.0 in /usr/lib/python3/dist-packages (from openai>=1.1.0->llama-index-core>=0.10.7->llama-parse) (1.7.0)\n",
-            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.31.0->llama-index-core>=0.10.7->llama-parse) (3.3.2)\n",
-            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.31.0->llama-index-core>=0.10.7->llama-parse) (2.0.7)\n",
-            "Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.10/dist-packages (from SQLAlchemy[asyncio]>=1.4.49->llama-index-core>=0.10.7->llama-parse) (3.0.3)\n",
-            "Collecting mypy-extensions>=0.3.0 (from typing-inspect>=0.8.0->llama-index-core>=0.10.7->llama-parse)\n",
-            "  Downloading mypy_extensions-1.0.0-py3-none-any.whl (4.7 kB)\n",
-            "Collecting marshmallow<4.0.0,>=3.18.0 (from dataclasses-json->llama-index-core>=0.10.7->llama-parse)\n",
-            "  Downloading marshmallow-3.21.1-py3-none-any.whl (49 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.4/49.4 kB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->llama-index-core>=0.10.7->llama-parse) (2.8.2)\n",
-            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->llama-index-core>=0.10.7->llama-parse) (2023.4)\n",
-            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio->httpx->llama-index-core>=0.10.7->llama-parse) (1.2.0)\n",
-            "Requirement already satisfied: packaging>=17.0 in /usr/local/lib/python3.10/dist-packages (from marshmallow<4.0.0,>=3.18.0->dataclasses-json->llama-index-core>=0.10.7->llama-parse) (23.2)\n",
-            "Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic>=1.10->llamaindex-py-client<0.2.0,>=0.1.13->llama-index-core>=0.10.7->llama-parse) (0.6.0)\n",
-            "Requirement already satisfied: pydantic-core==2.16.3 in /usr/local/lib/python3.10/dist-packages (from pydantic>=1.10->llamaindex-py-client<0.2.0,>=0.1.13->llama-index-core>=0.10.7->llama-parse) (2.16.3)\n",
-            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->llama-index-core>=0.10.7->llama-parse) (1.16.0)\n",
-            "Installing collected packages: dirtyjson, mypy-extensions, marshmallow, h11, deprecated, typing-inspect, tiktoken, httpcore, httpx, dataclasses-json, openai, llamaindex-py-client, llama-index-core, llama-parse\n",
-            "Successfully installed dataclasses-json-0.6.4 deprecated-1.2.14 dirtyjson-1.0.8 h11-0.14.0 httpcore-1.0.4 httpx-0.27.0 llama-index-core-0.10.19 llama-parse-0.3.8 llamaindex-py-client-0.1.13 marshmallow-3.21.1 mypy-extensions-1.0.0 openai-1.13.3 tiktoken-0.6.0 typing-inspect-0.9.0\n"
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "## API key\n",
-        "\n",
-        "The use of LlamaParse requires an API key which you can get here: https://cloud.llamaindex.ai/parse"
-      ],
-      "metadata": {
-        "id": "i-Rg2D_Rvf2i"
-      }
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "af6i2P1vuU-U"
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"llx-...\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "## Async (Notebook only)\n",
-        "llama-parse is async-first, so running the code in a notebook requires the use of nest_asyncio\n"
-      ],
-      "metadata": {
-        "id": "p8Eq-aX-wAEo"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "import nest_asyncio\n",
-        "\n",
-        "nest_asyncio.apply()"
-      ],
-      "metadata": {
-        "id": "4OB0BkTqv_0l"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "## Import the package"
-      ],
-      "metadata": {
-        "id": "dz927ecMyYo_"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "from llama_parse import LlamaParse"
-      ],
-      "metadata": {
-        "id": "nSW-6sEwyXwx"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "## Using llamaparse for getting better results (on Manga!)\n",
-        "\n",
-        "Sometimes the layout of a page is unusual and you will get sub-optimal reading order results with LlamaParse. For example, when parsing manga you expect the reading order to be right to left even if the content is in English!"
-      ],
-      "metadata": {
-        "id": "l_D4YsAHwUSk"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "Let's download an extract of a great manga \"The manga guide to calculus\", by Hiroyuki Kojima (https://www.amazon.com/Manga-Guide-Calculus-Hiroyuki-Kojima/dp/1593271948)\n",
-        "\n"
-      ],
-      "metadata": {
-        "id": "SV4K2RivxzJG"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "! wget \"https://drive.usercontent.google.com/uc?id=1tZJhcpepLRdQFJFCFX50QIqLyLgqzZsY&export=download\" -O ./manga.pdf"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "d3qeuiyawT0U",
-        "outputId": "e6da0635-dea2-4f2b-ec03-d8db99a75e17"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "--2024-03-13 13:57:19--  https://drive.usercontent.google.com/uc?id=1tZJhcpepLRdQFJFCFX50QIqLyLgqzZsY&export=download\n",
-            "Resolving drive.usercontent.google.com (drive.usercontent.google.com)... 173.194.211.132, 2607:f8b0:400c:c10::84\n",
-            "Connecting to drive.usercontent.google.com (drive.usercontent.google.com)|173.194.211.132|:443... connected.\n",
-            "HTTP request sent, awaiting response... 303 See Other\n",
-            "Location: https://drive.usercontent.google.com/download?id=1tZJhcpepLRdQFJFCFX50QIqLyLgqzZsY&export=download [following]\n",
-            "--2024-03-13 13:57:19--  https://drive.usercontent.google.com/download?id=1tZJhcpepLRdQFJFCFX50QIqLyLgqzZsY&export=download\n",
-            "Reusing existing connection to drive.usercontent.google.com:443.\n",
-            "HTTP request sent, awaiting response... 200 OK\n",
-            "Length: 3041634 (2.9M) [application/octet-stream]\n",
-            "Saving to: ‘./manga.pdf’\n",
-            "\n",
-            "./manga.pdf         100%[===================>]   2.90M  --.-KB/s    in 0.04s   \n",
-            "\n",
-            "2024-03-13 13:57:20 (78.6 MB/s) - ‘./manga.pdf’ saved [3041634/3041634]\n",
-            "\n"
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "### Without parsing instructions\n",
-        "For the sake of comparison, let's first parse without any instructions."
-      ],
-      "metadata": {
-        "id": "Gbr8RiHEyF3-"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "vanilaParsing = LlamaParse(result_type=\"markdown\").load_data(\"./manga.pdf\")"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "3jKnXCuAyQ9_",
-        "outputId": "8ab58d56-8c51-44de-8d34-0d94b1bb440f"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Started parsing the file under job_id 25bf4202-78d8-4705-88cf-c616ae7c82af\n"
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "As you can see below, LlamaParse is not doing a great job here. It is interpreting the grid of comic panels as a table, and trying to fit the dialogue into a table. It's very hard to follow."
-      ],
-      "metadata": {
-        "id": "p4GVOdWzzvYg"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "print(vanilaParsing[0].text[100:1000])"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "ZMhWfKrzzhgQ",
-        "outputId": "5426c0cc-7e62-4836-9877-87258e1f0b6f"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "\n",
-            "The Asagake Times Sanda-Cho Distributor\n",
-            "\n",
-            "A newspaper distributor? do I have the wrong map?\n",
-            "\n",
-            "You’re looking It’s next for the Sanda-cho door. branch office? Everybody mistakes us for the office because we are larger. What Is a Function? 3\n",
-            "---\n",
-            "## Calculating the Derivative of a Constant, Linear, or Quadratic Function\n",
-            "\n",
-            "|1.|Let’s find the derivative of constant function f(x) = α. The differential coefficient of f(x) at x = a is|\n",
-            "|---|---|\n",
-            "| |lim ε→0 (f(a + ε) - f(a)) / ε = lim ε→0 (α - α) = lim ε→0 0 = 0|\n",
-            "| |Thus, the derivative of f(x) is f′(x) = 0. This makes sense, since our function is constant—the rate of change is 0.|\n",
-            "\n",
-            "Note: The differential coefficient of f(x) at x = a is often simply called the derivative of f(x) at x = a, or just f′(a).\n",
-            "\n",
-            "|2.|Let’s calculate the derivative of linear function f(x) = αx + β. The derivative of f(x) at x = α is|\n",
-            "|---|---|\n",
-            "| |lim ε→0 (f(α + ε) - f(a)) = \n"
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "### Using parsing instructions\n",
-        "Let's try to parse the manga with custom instructions:\n",
-        "\n",
-        "\"The provided document is a manga comic book. Most pages do NOT have title. It does not contain tables. Try to reconstruct the dialogue happening in a cohesive way.\"\n",
-        "\n",
-        "To do so just pass the parsing instruction as a parameter to LlamaParse:"
-      ],
-      "metadata": {
-        "id": "sUq6znUryiu0"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "parsingInstructionManga = \"\"\"The provided document is a manga comic book, most page do NOT have title.\n",
-        "It does not contain table.\n",
-        "Try to reconstruct the dialog happening in a cohesive way.\"\"\"\n",
-        "withInstructionParsing = LlamaParse(result_type=\"markdown\", parsing_instruction=parsingInstructionManga).load_data(\"./manga.pdf\")"
-      ],
-      "metadata": {
-        "id": "dEX7Mv9V0UvM",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "outputId": "184b77b7-7e3a-4991-f2c9-eb9105a35a7b"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Started parsing the file under job_id 88ab273e-b2a7-4f84-8e72-e9367cf6b114\n",
-            "."
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "Let's see how it compare with page 3! We encourage you to play with the target page and explore other pages. As you will see, the parsing instruction allowed LlamaParse to make sense of the document!\n",
-        "\n",
-        "<img src=\"https://drive.usercontent.google.com/download?id=1M87rXTIZE8d5v7aHmVZVW6gW3eDGq6ks&authuser=0\" />\n",
-        "\n",
-        "\n",
-        "\n"
-      ],
-      "metadata": {
-        "id": "-UQcA-YW2kjd"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "target_page=1\n",
-        "print(vanilaParsing[0].text.split('\\n---\\n')[target_page])\n",
-        "print(\"\\n\\n------------------------------------------------------------\\n\\n\")\n",
-        "print(withInstructionParsing[0].text.split('\\n---\\n')[target_page])"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "0oPHXg0F0yAS",
-        "outputId": "38b729bc-b0b7-42f2-97e0-b4e9d7d459a1"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "The Asagake Times Sanda-Cho Distributor\n",
-            "\n",
-            "A newspaper distributor? do I have the wrong map?\n",
-            "\n",
-            "You’re looking It’s next for the Sanda-cho door. branch office? Everybody mistakes us for the office because we are larger. What Is a Function? 3\n",
-            "\n",
-            "\n",
-            "------------------------------------------------------------\n",
-            "\n",
-            "\n",
-            "# The Asagake Times\n",
-            "\n",
-            "Sanda-Cho Distributor\n",
-            "\n",
-            "A newspaper distributor?\n",
-            "\n",
-            "Do I have the wrong map?\n",
-            "\n",
-            "You're looking for the Sanda-cho branch office?\n",
-            "\n",
-            "It's next door.\n",
-            "\n",
-            "Everybody mistakes us for the office because we are larger.\n",
-            "\n",
-            "What Is a Function? 3\n"
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "### Math - doing more with parsing instuction!\n",
-        "\n",
-        "But this manga is about math and full of equations, why not ask the parser to output them in **LaTeX**?\n",
-        "\n",
-        "<img src=\"https://drive.usercontent.google.com/download?id=1tze3xcQ7axVA-vC_iZeAj_GvYcyNuYDa&authuser=0\" />"
-      ],
-      "metadata": {
-        "id": "yU_jyYWI5fMH"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "parsingInstructionMangaLatex = \"\"\"The provided document is a manga comic book, most page do NOT have title.\n",
-        "It does not contain table. Do not output table.\n",
-        "Try to reconstruct the dialog happening in a cohesive way.\n",
-        "Output any math equation in LATEX markdown (between $$)\"\"\"\n",
-        "withLatex = LlamaParse(result_type=\"markdown\", parsing_instruction=parsingInstructionMangaLatex).load_data(\"./manga.pdf\")"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "FP_YdO2y5e5o",
-        "outputId": "45171cdd-298a-4f1f-e67d-6be3cb1a1156"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Started parsing the file under job_id 3a055e64-d91e-484e-b9b0-99a2e637c08d\n",
-            "."
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "target_page=2\n",
-        "print(\"\\n\\n[Without instruction]------------------------------------------------------------\\n\\n\")\n",
-        "print(vanilaParsing[0].text.split('\\n---\\n')[target_page])\n",
-        "print(\"\\n\\n[With instruction to output math in LATEX!]------------------------------------------------------------\\n\\n\")\n",
-        "print(withLatex[0].text.split('\\n---\\n')[target_page])\n"
-      ],
-      "metadata": {
-        "id": "TntdRRGp6Rui",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "outputId": "e2e503fa-eb87-4f78-83d8-209fe7cebd9e"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "\n",
-            "\n",
-            "[Without instruction]------------------------------------------------------------\n",
-            "\n",
-            "\n",
-            "## Calculating the Derivative of a Constant, Linear, or Quadratic Function\n",
-            "\n",
-            "|1.|Let’s find the derivative of constant function f(x) = α. The differential coefficient of f(x) at x = a is|\n",
-            "|---|---|\n",
-            "| |lim ε→0 (f(a + ε) - f(a)) / ε = lim ε→0 (α - α) = lim ε→0 0 = 0|\n",
-            "| |Thus, the derivative of f(x) is f′(x) = 0. This makes sense, since our function is constant—the rate of change is 0.|\n",
-            "\n",
-            "Note: The differential coefficient of f(x) at x = a is often simply called the derivative of f(x) at x = a, or just f′(a).\n",
-            "\n",
-            "|2.|Let’s calculate the derivative of linear function f(x) = αx + β. The derivative of f(x) at x = α is|\n",
-            "|---|---|\n",
-            "| |lim ε→0 (f(α + ε) - f(a)) = lim ε→0 (α(a + ε) + β - (αa + β)) = lim ε→0 α = α|\n",
-            "| |Thus, the derivative of f(x) is f′(x) = α, a constant value. This result should also be intuitive—linear functions have a constant rate of change by definition.|\n",
-            "\n",
-            "|3.|Let’s find the derivative of f(x) = x^2, which appeared in the story. The differential coefficient of f(x) at x = a is|\n",
-            "|---|---|\n",
-            "| |lim ε→0 ((a + ε)^2 - a^2) / ε = lim (a^2 + 2aε + ε^2 - a^2) / ε = lim (2aε + ε^2) = lim (2a + ε) = 2a|\n",
-            "| |Thus, the differential coefficient of f(x) at x = a is 2a, or f′(a) = 2a. Therefore, the derivative of f(x) is f′(x) = 2x.|\n",
-            "\n",
-            "## Summary\n",
-            "\n",
-            "- The calculation of a limit that appears in calculus is simply a formula calculating an error.\n",
-            "- A limit is used to obtain a derivative.\n",
-            "- The derivative is the slope of the tangent line at a given point.\n",
-            "- The derivative is nothing but the rate of change.\n",
-            "\n",
-            "## Chapter 1 Let’s Differentiate a Function!\n",
-            "\n",
-            "\n",
-            "[With instruction to output math in LATEX!]------------------------------------------------------------\n",
-            "\n",
-            "\n",
-            "# Derivative of Constant, Linear, or Quadratic Function\n",
-            "\n",
-            "## Calculating the Derivative of a Constant, Linear, or Quadratic Function\n",
-            "\n",
-            "1. Let’s find the derivative of constant function f(x) = α. The differential coefficient of f(x) at x = a is\n",
-            "\n",
-            "$$\n",
-            "\\begin{align*}\n",
-            "&\\lim_{{\\varepsilon \\to 0}} \\left( \\frac{f(a + \\varepsilon) - f(a)}{\\varepsilon} \\right) = \\lim_{{\\varepsilon \\to 0}} \\frac{\\alpha - \\alpha}{\\varepsilon} = \\lim_{{\\varepsilon \\to 0}} 0 = 0 \\\\\n",
-            "\\end{align*}\n",
-            "$$\n",
-            "Thus, the derivative of f(x) is f′(x) = 0. This makes sense, since our function is constant—the rate of change is 0.\n",
-            "\n",
-            "Note: The differential coefficient of f(x) at x = a is often simply called the derivative of f(x) at x = a, or just f′(a).\n",
-            "\n",
-            "2. Let’s calculate the derivative of linear function f(x) = αx + β. The derivative of f(x) at x = α is\n",
-            "\n",
-            "$$\n",
-            "\\begin{align*}\n",
-            "&\\lim_{{\\varepsilon \\to 0}} \\left( \\frac{f(\\alpha + \\varepsilon) - f(a)}{\\varepsilon} \\right) = \\lim_{{\\varepsilon \\to 0}} \\frac{\\alpha(a + \\varepsilon) + \\beta - (\\alpha a + \\beta)}{\\varepsilon} = \\lim_{{\\varepsilon \\to 0}} \\alpha = \\alpha \\\\\n",
-            "\\end{align*}\n",
-            "$$\n",
-            "Thus, the derivative of f(x) is f′(x) = α, a constant value. This result should also be intuitive—linear functions have a constant rate of change by definition.\n",
-            "\n",
-            "3. Let’s find the derivative of f(x) = x2. The differential coefficient of f(x) at x = a is\n",
-            "\n",
-            "$$\n",
-            "\\begin{align*}\n",
-            "&\\lim_{{\\varepsilon \\to 0}} \\left( \\frac{f(a + \\varepsilon) - f(a)}{\\varepsilon} \\right) = \\lim_{{\\varepsilon \\to 0}} \\left( (a + \\varepsilon)^2 - a^2 \\right) = \\lim_{{\\varepsilon \\to 0}} 2a\\varepsilon + \\varepsilon = \\lim_{{\\varepsilon \\to 0}} (2a + \\varepsilon) = 2a \\\\\n",
-            "\\end{align*}\n",
-            "$$\n",
-            "Thus, the differential coefficient of f(x) at x = a is 2a, or f′(a) = 2a. Therefore, the derivative of f(x) is f′(x) = 2x.\n",
-            "\n",
-            "### Summary\n",
-            "\n",
-            "- The calculation of a limit that appears in calculus is simply a formula calculating an error.\n",
-            "- A limit is used to obtain a derivative.\n",
-            "- The derivative is the slope of the tangent line at a given point.\n",
-            "- The derivative is nothing but the rate of change.\n"
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "And here is the result as rendered by https://upmath.me/ .\n",
-        "\n",
-        "\n",
-        "<img src=\"https://drive.usercontent.google.com/download?id=1qGo5bMGYOiIC9MnprcgEByaYjU9YII2Q&authuser=0\" />\n",
-        "\n",
-        "\n",
-        "Over this short notebook we saw how to use parsing instructions to increase the quality and accuracy of parsing with LLamaParse!"
-      ],
-      "metadata": {
-        "id": "rfFdeWZKmmLW"
-      }
-    }
-  ]
-}

examples/demo_table_comparisons.ipynb

@@ -1,391 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# RAG for Table Comparisons with LlamaParse + LlamaIndex\n",
-    "\n",
-    "<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/demo_table_comparisons.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
-    "\n",
-    "This notebook shows you how to do comparisons across both tabular and text data across multiple PDF documents.\n",
-    "\n",
-    "We load in multiple PDFs with embedded tables (2021 and 2020 10K filings for Apple) using LlamaParse, parse each into a hierarchy of tables/text objects, define a recursive retriever over each, and then compose both with a SubQuestionQueryEngine."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup\n",
-    "\n",
-    "Install core packages, download files, parse documents."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install llama-index\n",
-    "!pip install llama-index-core\n",
-    "!pip install llama-index-embeddings-openai\n",
-    "!pip install llama-index-question-gen-openai\n",
-    "!pip install llama-index-postprocessor-flag-embedding-reranker\n",
-    "!pip install git+https://github.com/FlagOpen/FlagEmbedding.git\n",
-    "!pip install llama-parse"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!wget \"https://s2.q4cdn.com/470004039/files/doc_financials/2020/ar/_10-K-2020-(As-Filed).pdf\" -O apple_2020_10k.pdf\n",
-    "!wget \"https://s2.q4cdn.com/470004039/files/doc_financials/2021/q4/_10-K-2021-(As-Filed).pdf\" -O apple_2021_10k.pdf"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Some OpenAI and LlamaParse details"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# llama-parse is async-first, running the async code in a notebook requires the use of nest_asyncio\n",
-    "import nest_asyncio\n",
-    "nest_asyncio.apply()\n",
-    "\n",
-    "import os\n",
-    "# API access to llama-cloud\n",
-    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"llx-\"\n",
-    "\n",
-    "# Using OpenAI API for embeddings/llms\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"sk-\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from llama_index.llms.openai import OpenAI\n",
-    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
-    "from llama_index.core import VectorStoreIndex\n",
-    "from llama_index.core import Settings\n",
-    "\n",
-    "embed_model=OpenAIEmbedding(model=\"text-embedding-3-small\")\n",
-    "llm = OpenAI(model=\"gpt-3.5-turbo-0125\")\n",
-    "\n",
-    "Settings.llm = llm\n",
-    "Settings.embed_model = embed_model\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Using brand new `LlamaParse` PDF reader for PDF Parsing\n",
-    "\n",
-    "we also compare two different retrieval/query engine strategies:\n",
-    "1. Using raw Markdown text as nodes for building index and apply simple query engine for generating the results;\n",
-    "2. Using `MarkdownElementNodeParser` for parsing the `LlamaParse` output Markdown results and building recursive retriever query engine for generation."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from llama_parse import LlamaParse\n",
-    "\n",
-    "docs_2021 = LlamaParse(result_type=\"markdown\").load_data('./apple_2021_10k.pdf')\n",
-    "docs_2020 = LlamaParse(result_type=\"markdown\").load_data('./apple_2020_10k.pdf')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create Recursive Retriever over each Document\n",
-    "\n",
-    "We define a function to get a recursive retriever from each document. The steps are the following:\n",
-    "- Hierarchically parse the document using our `MarkdownElementNodeParser`, which will embed/summarize embedded tables.\n",
-    "- Load into a vector store. Under the hood we will automatically store links between nodes (e.g. table summary to table text).\n",
-    "- Get a query engine over the vector store, which performs retrieval/synthesis. Under the hood we will automatically perform recursive retrieval if there are links."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 36,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from llama_index.core.node_parser import MarkdownElementNodeParser\n",
-    "\n",
-    "node_parser = MarkdownElementNodeParser(llm=OpenAI(model=\"gpt-3.5-turbo-0125\"), num_workers=8)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 46,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "import pickle\n",
-    "from llama_index.postprocessor.flag_embedding_reranker import FlagEmbeddingReranker\n",
-    "\n",
-    "reranker = FlagEmbeddingReranker(\n",
-    "    top_n=5,\n",
-    "    model=\"BAAI/bge-reranker-large\",\n",
-    ")\n",
-    "\n",
-    "def create_query_engine_over_doc(docs, nodes_save_path=None):\n",
-    "    \"\"\"Big function to go from document path -> recursive retriever.\"\"\"\n",
-    "    if nodes_save_path is not None and os.path.exists(nodes_save_path):\n",
-    "        raw_nodes = pickle.load(open(nodes_save_path, \"rb\"))\n",
-    "    else:\n",
-    "        raw_nodes = node_parser.get_nodes_from_documents(docs)\n",
-    "        if nodes_save_path is not None:\n",
-    "            pickle.dump(raw_nodes, open(nodes_save_path, \"wb\"))\n",
-    "\n",
-    "    base_nodes, objects = node_parser.get_nodes_and_objects(\n",
-    "        raw_nodes\n",
-    "    )\n",
-    "\n",
-    "    ### Construct Retrievers\n",
-    "    # construct top-level vector index + query engine\n",
-    "    vector_index = VectorStoreIndex(nodes=base_nodes+objects)\n",
-    "    query_engine = vector_index.as_query_engine(\n",
-    "        similarity_top_k=15,\n",
-    "        node_postprocessors=[reranker]\n",
-    "    )\n",
-    "    return query_engine, base_nodes"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "query_engine_2021, nodes_2021 = create_query_engine_over_doc(\n",
-    "    docs_2021, nodes_save_path=\"2021_nodes.pkl\"\n",
-    ")\n",
-    "query_engine_2020, nodes_2020 = create_query_engine_over_doc(\n",
-    "    docs_2020, nodes_save_path=\"2020_nodes.pkl\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 38,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from llama_index.core.tools import QueryEngineTool, ToolMetadata\n",
-    "from llama_index.core.query_engine import SubQuestionQueryEngine\n",
-    "\n",
-    "\n",
-    "# setup base query engine as tool\n",
-    "query_engine_tools = [\n",
-    "    QueryEngineTool(\n",
-    "        query_engine=query_engine_2021,\n",
-    "        metadata=ToolMetadata(\n",
-    "            name=\"apple_2021_10k\",\n",
-    "            description=(\n",
-    "                \"Provides information about Apple financials for year 2021\"\n",
-    "            ),\n",
-    "        ),\n",
-    "    ),\n",
-    "    QueryEngineTool(\n",
-    "        query_engine=query_engine_2020,\n",
-    "        metadata=ToolMetadata(\n",
-    "            name=\"apple_2020_10k\",\n",
-    "            description=(\n",
-    "                \"Provides information about Apple financials for year 2020\"\n",
-    "            ),\n",
-    "        ),\n",
-    "    ),\n",
-    "]\n",
-    "\n",
-    "sub_query_engine = SubQuestionQueryEngine.from_defaults(\n",
-    "    query_engine_tools=query_engine_tools,\n",
-    "    llm=llm,\n",
-    "    use_async=True,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Try out Some Comparisons"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 41,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated 4 sub questions.\n",
-      "\u001b[1;3;38;2;237;90;200m[apple_2021_10k] Q: What are the deferred assets in 2021?\n",
-      "\u001b[0m\u001b[1;3;38;2;90;149;237m[apple_2021_10k] Q: What are the deferred liabilities in 2021?\n",
-      "\u001b[0m\u001b[1;3;38;2;11;159;203m[apple_2020_10k] Q: What are the deferred assets in 2020?\n",
-      "\u001b[0m\u001b[1;3;38;2;155;135;227m[apple_2020_10k] Q: What are the deferred liabilities in 2020?\n",
-      "\u001b[0m\u001b[1;3;38;2;90;149;237m[apple_2021_10k] A: $7,200\n",
-      "\u001b[0m\u001b[1;3;38;2;155;135;227m[apple_2020_10k] A: $10,138\n",
-      "\u001b[0m\u001b[1;3;38;2;237;90;200m[apple_2021_10k] A: $25,176 million\n",
-      "\u001b[0m\u001b[1;3;38;2;11;159;203m[apple_2020_10k] A: $19,336\n",
-      "\u001b[0m"
-     ]
-    }
-   ],
-   "source": [
-    "response = sub_query_engine.query(\n",
-    "    \"Can you compare and contrast the deferred assets and liabilities in 2021 with 2020?\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 40,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "In 2021, the deferred assets increased by $5,840 million compared to 2020, while the deferred liabilities decreased by $2,938 million in the same period.\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(str(response))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 42,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated 2 sub questions.\n",
-      "\u001b[1;3;38;2;237;90;200m[apple_2021_10k] Q: What is the total number of RSUs in Apple's 2021 financials?\n",
-      "\u001b[0m\u001b[1;3;38;2;90;149;237m[apple_2020_10k] Q: What is the total number of RSUs in Apple's 2020 financials?\n",
-      "\u001b[0m\u001b[1;3;38;2;237;90;200m[apple_2021_10k] A: The total number of RSUs in Apple's 2021 financials is 240,427.\n",
-      "\u001b[0m\u001b[1;3;38;2;90;149;237m[apple_2020_10k] A: The total number of RSUs in Apple's 2020 financials is 310,778.\n",
-      "\u001b[0m"
-     ]
-    }
-   ],
-   "source": [
-    "response = sub_query_engine.query(\n",
-    "    \"Can you compare and contrast the total number of RSUs in 2021 and 2020?\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 44,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated 2 sub questions.\n",
-      "\u001b[1;3;38;2;237;90;200m[apple_2021_10k] Q: What are the risk factors mentioned in the 2021 financial report of Apple?\n",
-      "\u001b[0m\u001b[1;3;38;2;90;149;237m[apple_2020_10k] Q: What are the risk factors mentioned in the 2020 financial report of Apple?\n",
-      "\u001b[0m\u001b[1;3;38;2;237;90;200m[apple_2021_10k] A: The risk factors mentioned in the 2021 financial report of Apple include risks related to COVID-19, macroeconomic and industry risks, political events, trade and international disputes, natural disasters, public health issues, industrial accidents, credit risk, fluctuations in foreign currency exchange rates, changes in tax rates and legislation, volatility in the price of the company's stock, and exposure to legal proceedings and claims.\n",
-      "\u001b[0m\u001b[1;3;38;2;90;149;237m[apple_2020_10k] A: The risk factors mentioned in the 2020 financial report of Apple include the impact of the COVID-19 pandemic on the company's business operations, financial condition, and stock price; global and regional economic conditions affecting demand for products and services; competition in global markets with rapid technological changes; potential disruptions in the supply chain due to industrial accidents or public health issues; information technology system failures or network disruptions affecting business operations; risks associated with confidential information security and potential unauthorized access; fluctuations in quarterly net sales and operating results due to various factors; stock price volatility impacting investor confidence and employee retention; financial performance risks related to changes in foreign currency exchange rates affecting sales and earnings.\n",
-      "\u001b[0m"
-     ]
-    }
-   ],
-   "source": [
-    "response = sub_query_engine.query(\n",
-    "    \"Can you compare and contrast the risk factors in 2021 vs. 2020?\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 45,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "The risk factors mentioned in the 2021 financial report of Apple include risks related to COVID-19, macroeconomic and industry risks, political events, trade and international disputes, natural disasters, public health issues, industrial accidents, credit risk, fluctuations in foreign currency exchange rates, changes in tax rates and legislation, volatility in the price of the company's stock, and exposure to legal proceedings and claims. In contrast, the risk factors mentioned in the 2020 financial report of Apple focused more on the impact of the COVID-19 pandemic on the company's business operations, financial condition, and stock price; global and regional economic conditions affecting demand for products and services; competition in global markets with rapid technological changes; potential disruptions in the supply chain due to industrial accidents or public health issues; information technology system failures or network disruptions affecting business operations; risks associated with confidential information security and potential unauthorized access; fluctuations in quarterly net sales and operating results due to various factors; stock price volatility impacting investor confidence and employee retention; financial performance risks related to changes in foreign currency exchange rates affecting sales and earnings.\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(str(response))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "llama_parse",
-   "language": "python",
-   "name": "llama_parse"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.8"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

examples/extract/data/automotive_sector_analysis/modeling_assumptions.txt

@@ -0,0 +1,10 @@
+# Financial Modeling Assumptions
+Discount Rate: 8%
+Terminal Growth Rate: 2%
+Tax Rate: 25%
+Revenue Growth (Years 1-5): 10% per annum
+Revenue Growth (Years 6-10): 5% per annum
+Capital Expenditures as % of Revenue: 7%
+Working Capital Assumption: 3% of Revenue
+Depreciation Rate: 10% per annum
+Cost of Capital Assumption: 8%

examples/extract/data/insider_transactions/.gitignore

@@ -0,0 +1 @@
+sec_form_4_dump.json

examples/extract/extract_data_with_citations.ipynb

@@ -0,0 +1,440 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Extract Data from Financial Reports - with Citations and Reasoning\n",
+    "\n",
+    "Given complex files like financial reports, contracts, invoices etc, Llama Extract allows you to make use of an LLM to extract the information relevant to you, in a structured format.\n",
+    "\n",
+    "In this example, we'll be using [LlamaExtract](https://docs.cloud.llamaindex.ai/llamaextract/getting_started?utm_campaign=extract&utm_medium=recipe) to extract structured data from an SEC filing (specifically, the filing by Nvidia for fiscal year 2025).\n",
+    "\n",
+    "On top of simple data extraction, we'll ask our extraction agent to provide citations and reasoning for each extracted field. This allows us to:\n",
+    "- Confirm  the accuracy of the extracted field\n",
+    "- Understand the reasoning behind why the LLM extracted a given piece of information\n",
+    "- This last point allows us an opportunity to adjust the system prompt or field descriptions and improve on results where needed.\n",
+    "\n",
+    "\n",
+    "The example we go through below is also replicable within Llama Cloud as well, where you will also be able to pick between a number of pre-defined schemas, instead of building your own."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install llama-cloud-services"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Connect to Llama Cloud\n",
+    "\n",
+    "To get started, make sure you provide your [Llama Cloud](https://cloud.llamaindex.ai?utm_campaign=extract&utm_medium=recipe) API key."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Enter your Llama Cloud API Key: ··········\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "if \"LLAMA_CLOUD_API_KEY\" not in os.environ:\n",
+    "    os.environ[\"LLAMA_CLOUD_API_KEY\"] = getpass(\"Enter your Llama Cloud API Key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Extract Data with Llama Extract Agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "No project_id provided, fetching default project.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_cloud_services import LlamaExtract\n",
+    "\n",
+    "# Optionally, provide your project id, if not, it will use the 'Default' project\n",
+    "llama_extract = LlamaExtract()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Provide Your Custom Schema\n",
+    "\n",
+    "When using LlamaExtract via the API, you provide your own schema that describes what you want extracted from files and data provided to your agent. Here, we are essentially building an SEC filings extraction agent."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pydantic import BaseModel, Field\n",
+    "from enum import Enum\n",
+    "\n",
+    "\n",
+    "class FilingType(str, Enum):\n",
+    "    ten_k = \"10 K\"\n",
+    "    ten_q = \"10-Q\"\n",
+    "    ten_ka = \"10-K/A\"\n",
+    "    ten_qa = \"10-Q/A\"\n",
+    "\n",
+    "\n",
+    "class FinancialReport(BaseModel):\n",
+    "    company_name: str = Field(description=\"The name of the company\")\n",
+    "    description: str = Field(\n",
+    "        description=\"Short description of the filing and what it contains\"\n",
+    "    )\n",
+    "    filing_type: FilingType = Field(description=\"Type of SEC filing\")\n",
+    "    filing_date: str = Field(description=\"Date when filing was submitted to SEC\")\n",
+    "    fiscal_year: int = Field(description=\"Fiscal year\")\n",
+    "    unit: str = Field(\n",
+    "        description=\"Unit of financial figures (thousands, millions, etc.)\"\n",
+    "    )\n",
+    "    revenue: int = Field(description=\"Total revenue for period\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Set Up Citations and Reasoning\n",
+    "\n",
+    "Optionally, we can set the `ExtractConfig` to extract citations for each field the agent extracts. These cications will cite the specific pages and sections of the file from which a given field was extractedd.\n",
+    "\n",
+    "By setting `use_reasoning` to True, we als ask the agent to do an additional reasoning step, explaining why a given field was extracted."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_cloud.types import ExtractConfig, ExtractMode\n",
+    "\n",
+    "config = ExtractConfig(\n",
+    "    use_reasoning=True, cite_sources=True, extraction_mode=ExtractMode.MULTIMODAL\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/usr/local/lib/python3.11/dist-packages/llama_cloud_services/extract/extract.py:127: ExperimentalWarning: `use_reasoning` is an experimental feature. Results will be available in the `extraction_metadata` field for the extraction run.\n",
+      "  warnings.warn(\n",
+      "/usr/local/lib/python3.11/dist-packages/llama_cloud_services/extract/extract.py:133: ExperimentalWarning: `cite_sources` is an experimental feature. This may greatly increase the size of the response, and slow down the extraction. Results will be available in the `extraction_metadata` field for the extraction run.\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
+   "source": [
+    "agent = llama_extract.create_agent(\n",
+    "    name=\"filing-parser\", data_schema=FinancialReport, config=config\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Demo Time - Download a PDF and Extract Data with Citations"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "PDF downloaded successfully.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import requests\n",
+    "\n",
+    "url = \"https://raw.githubusercontent.com/run-llama/llama_cloud_services/refs/heads/main/examples/extract/data/sec_filings/nvda_10k.pdf\"\n",
+    "\n",
+    "response = requests.get(url)\n",
+    "\n",
+    "if response.status_code == 200:\n",
+    "    with open(\"/content/nvda_10k.pdf\", \"wb\") as f:\n",
+    "        f.write(response.content)\n",
+    "    print(\"PDF downloaded successfully.\")\n",
+    "else:\n",
+    "    print(f\"Failed to download. Status code: {response.status_code}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Uploading files: 100%|██████████| 1/1 [00:00<00:00,  1.83it/s]\n",
+      "Creating extraction jobs: 100%|██████████| 1/1 [00:00<00:00,  4.38it/s]\n",
+      "Extracting files: 100%|██████████| 1/1 [02:03<00:00, 123.40s/it]\n"
+     ]
+    }
+   ],
+   "source": [
+    "filing_info = agent.extract(\"/content/nvda_10k.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'company_name': 'NVIDIA Corporation',\n",
+       " 'description': \"The filing provides a detailed overview of NVIDIA's business as a full-stack computing infrastructure company, discusses various technologies including digital avatars and autonomous vehicles, outlines numerous risk factors affecting operations such as supply chain issues and geopolitical tensions, and describes employee stock purchase plans and related compliance requirements.\",\n",
+       " 'filing_type': '10 K',\n",
+       " 'filing_date': 'February 26, 2025',\n",
+       " 'fiscal_year': 2025,\n",
+       " 'unit': 'millions',\n",
+       " 'revenue': 130497}"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "filing_info.data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Inspect Citations and Reasoning"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'field_metadata': {'company_name': {'reasoning': 'VERBATIM EXTRACTION',\n",
+       "   'citation': [{'page': 1, 'matching_text': 'NVIDIA CORPORATION'},\n",
+       "    {'page': 2, 'matching_text': 'NVIDIA Corporation'},\n",
+       "    {'page': 3,\n",
+       "     'matching_text': 'All references to \"NVIDIA,\" \"we,\" \"us,\" \"our,\" or the \"Company\" mean NVIDIA Corporation and its subsidiaries.'},\n",
+       "    {'page': 35,\n",
+       "     'matching_text': 'Comparison of 5 Year Cumulative Total Return* Among NVIDIA Corporation'},\n",
+       "    {'page': 49,\n",
+       "     'matching_text': 'To the Board of Directors and Shareholders of NVIDIA Corporation'},\n",
+       "    {'page': 90, 'matching_text': 'NVIDIA Corporation'},\n",
+       "    {'page': 119,\n",
+       "     'matching_text': '*\"Company\"* means NVIDIA Corporation, a Delaware corporation.'},\n",
+       "    {'page': 126,\n",
+       "     'matching_text': 'Annual Report on Form 10-K of NVIDIA Corporation'}]},\n",
+       "  'filing_type': {'reasoning': \"VERBATIM EXTRACTION from multiple sources confirming the filing type as '10 K'.\",\n",
+       "   'citation': [{'page': 1, 'matching_text': 'FORM 10-K'},\n",
+       "    {'page': 2, 'matching_text': 'Item 16. | Form 10-K Summary'},\n",
+       "    {'page': 3,\n",
+       "     'matching_text': 'This Annual Report on Form 10-K contains forward-looking statements...'},\n",
+       "    {'page': 13, 'matching_text': 'this Annual Report on Form 10-K'},\n",
+       "    {'page': 15, 'matching_text': 'this Annual Report on Form 10-K'},\n",
+       "    {'page': 32,\n",
+       "     'matching_text': 'Annual Report on Form 10-K, which information is hereby incorporated by reference.'},\n",
+       "    {'page': 36, 'matching_text': 'this Annual Report on Form 10-K'},\n",
+       "    {'page': 43,\n",
+       "     'matching_text': 'Annual Report on Form 10-K for additional information'},\n",
+       "    {'page': 45, 'matching_text': 'Annual Report on Form 10-K'},\n",
+       "    {'page': 46, 'matching_text': 'this Annual Report on Form 10-K'},\n",
+       "    {'page': 62, 'matching_text': 'Annual Report on Form 10-K'},\n",
+       "    {'page': 83,\n",
+       "     'matching_text': 'Restated Certificate of Incorporation | 10-K'},\n",
+       "    {'page': 84, 'matching_text': 'Item 16. Form 10-K Summary'},\n",
+       "    {'page': 126, 'matching_text': 'which appears in this Form 10-K'},\n",
+       "    {'page': 127, 'matching_text': 'Annual Report on Form 10-K'},\n",
+       "    {'page': 128, 'matching_text': 'Annual Report on Form 10-K'},\n",
+       "    {'page': 129, 'matching_text': \"The Company's Annual Report on Form 10-K\"},\n",
+       "    {'page': 130,\n",
+       "     'matching_text': \"The Company's Annual Report on Form 10-K for the year ended January 26, 2025\"}]},\n",
+       "  'fiscal_year': {'reasoning': 'The fiscal year ended January 26, 2025, indicates the fiscal year is 2025. Additionally, multiple references throughout the text confirm the fiscal year 2025 in various contexts.',\n",
+       "   'citation': [{'page': 1,\n",
+       "     'matching_text': 'For the fiscal year ended January 26, 2025'},\n",
+       "    {'page': 6,\n",
+       "     'matching_text': 'In fiscal year 2025, we launched the NVIDIA Blackwell architecture'},\n",
+       "    {'page': 12, 'matching_text': 'fiscal year 2025'},\n",
+       "    {'page': 17,\n",
+       "     'matching_text': 'our gross margins in the second quarter of fiscal year 2025 were negatively impacted'},\n",
+       "    {'page': 20,\n",
+       "     'matching_text': 'we generated 53% of our revenue in fiscal year 2025 from sales outside the United States.'},\n",
+       "    {'page': 23,\n",
+       "     'matching_text': 'For fiscal year 2025, an indirect customer which primarily purchases our products through system integrators...'},\n",
+       "    {'page': 33,\n",
+       "     'matching_text': 'In fiscal year 2025, we repurchased 310 million shares of our common stock for $34.0 billion.'},\n",
+       "    {'page': 37,\n",
+       "     'matching_text': 'Our Data Center revenue in China grew in fiscal year 2025.'},\n",
+       "    {'page': 44,\n",
+       "     'matching_text': 'Cash provided by operating activities increased in fiscal year 2025 compared to fiscal year 2024'},\n",
+       "    {'page': 57,\n",
+       "     'matching_text': 'Fiscal years 2025, 2024 and 2023 were all 52-week years.'},\n",
+       "    {'page': 65,\n",
+       "     'matching_text': 'Beginning in the second quarter of fiscal year 2025'},\n",
+       "    {'page': 69, 'matching_text': 'In the fourth quarter of fiscal year 2025'},\n",
+       "    {'page': 78,\n",
+       "     'matching_text': 'Depreciation and amortization expense attributable to our Compute and Networking segment for fiscal years 2025'},\n",
+       "    {'page': 129, 'matching_text': 'for the year ended January 26, 2025'}]},\n",
+       "  'description': {'reasoning': 'The extracted data combines multiple descriptions from the source text, ensuring no duplication while maintaining the order and context of the information. Each section of the filing is summarized to reflect the key points without losing the essence of the original text.',\n",
+       "   'citation': [{'page': 4,\n",
+       "     'matching_text': 'NVIDIA is now a full-stack computing infrastructure company with data-center-scale offerings that are reshaping industry.'},\n",
+       "    {'page': 8,\n",
+       "     'matching_text': 'a suite of technologies that help developers bring digital avatars to life with generative Al...autonomous vehicles, or AV, and electric vehicles, or EV, is revolutionizing the transportation industry...Our worldwide sales and marketing strategy is key to achieving our objective of providing markets with our high-performance and efficient computing platforms and software.'},\n",
+       "    {'page': 14, 'matching_text': 'Risk Factors Summary'},\n",
+       "    {'page': 16,\n",
+       "     'matching_text': 'Risks Related to Demand, Supply, and Manufacturing\\n\\nLong manufacturing lead times and uncertain supply and component availability...'},\n",
+       "    {'page': 18,\n",
+       "     'matching_text': 'cryptocurrency mining, on demand for our products. Volatility in the cryptocurrency market, including new compute technologies...'},\n",
+       "    {'page': 21,\n",
+       "     'matching_text': 'supply-chain attacks or other business disruptions. We cannot guarantee that third parties and infrastructure in our supply chain...'},\n",
+       "    {'page': 22,\n",
+       "     'matching_text': 'We are monitoring the impact of the geopolitical conflict in and around Israel on our operations... Climate change may have a long-term impact on our business.'},\n",
+       "    {'page': 25,\n",
+       "     'matching_text': 'We are subject to complex laws, rules, regulations, and political and other actions, including restrictions on the export of our products, which may adversely impact our business.'},\n",
+       "    {'page': 28,\n",
+       "     'matching_text': 'Our competitive position has been harmed by the existing export controls, and our competitive position and future results may be further harmed'},\n",
+       "    {'page': 29,\n",
+       "     'matching_text': 'restrictions imposed by the Chinese government on the duration of gaming activities and access to games may adversely affect our Gaming revenue'},\n",
+       "    {'page': 29,\n",
+       "     'matching_text': 'our business depends on our ability to receive consistent and reliable supply from our overseas partners, especially in Taiwan and South Korea'},\n",
+       "    {'page': 29,\n",
+       "     'matching_text': 'Increased scrutiny from shareholders, regulators and others regarding our corporate sustainability practices could result in additional costs'},\n",
+       "    {'page': 29,\n",
+       "     'matching_text': 'Concerns relating to the responsible use of new and evolving technologies, such as Al, in our products and services may result in reputational or financial harm'},\n",
+       "    {'page': 31,\n",
+       "     'matching_text': 'Data protection laws around the world are quickly changing and may be interpreted and applied in an increasingly stringent fashion...'}]},\n",
+       "  'filing_date': {'reasoning': 'The filing date is consistently mentioned as February 26, 2025 across multiple entries, making it the most reliable date for the filing.',\n",
+       "   'citation': [{'page': 51, 'matching_text': 'February 26, 2025'},\n",
+       "    {'page': 86, 'matching_text': 'on February 26, 2025.'},\n",
+       "    {'page': 87, 'matching_text': 'February 26, 2025'},\n",
+       "    {'page': 126, 'matching_text': 'our report dated February 26, 2025'},\n",
+       "    {'page': 127, 'matching_text': 'Date: February 26, 2025'},\n",
+       "    {'page': 128, 'matching_text': 'Date: February 26, 2025'},\n",
+       "    {'page': 129, 'matching_text': 'Date: February 26, 2025'},\n",
+       "    {'page': 130, 'matching_text': 'Date: February 26, 2025'}]},\n",
+       "  'unit': {'reasoning': \"The unit of financial figures is explicitly mentioned multiple times in the text as 'millions', including in table headers and notes. This is confirmed by various citations from pages 38, 42, 43, 52, 53, 54, 56, 65, 71, 72, 73, 75, 77, 79, 80, and 82.\",\n",
+       "   'citation': [{'page': 38,\n",
+       "     'matching_text': '($ in millions, except per share data)'},\n",
+       "    {'page': 42, 'matching_text': '($ in millions)'},\n",
+       "    {'page': 43, 'matching_text': '($ in millions)'},\n",
+       "    {'page': 52, 'matching_text': '(In millions, except per share data)'},\n",
+       "    {'page': 53,\n",
+       "     'matching_text': 'Consolidated Statements of Comprehensive Income (In millions)'},\n",
+       "    {'page': 54,\n",
+       "     'matching_text': 'Consolidated Balance Sheets (In millions, except par value)'},\n",
+       "    {'page': 55, 'matching_text': '(In millions, except per share data)'},\n",
+       "    {'page': 56,\n",
+       "     'matching_text': 'Consolidated Statements of Cash Flows (In millions)'},\n",
+       "    {'page': 65,\n",
+       "     'matching_text': 'Year Ended<br/>Jan 26, 2025<br/>(In millions, except per share data)'},\n",
+       "    {'page': 71, 'matching_text': '(In millions) | (In millions)'},\n",
+       "    {'page': 72, 'matching_text': '(In millions)'}]},\n",
+       "  'revenue': {'reasoning': 'The total revenue for fiscal year 2025 is extracted from multiple sources within the text, all confirming the same figure of $130,497 million. The revenue recognized for fiscal year 2025 is also noted as $4,607 million, which is a separate figure. However, the primary focus is on the total revenue figure, which is consistently cited.',\n",
+       "   'citation': [{'page': 38,\n",
+       "     'matching_text': 'Revenue for fiscal year 2025 was $130.5 billion'},\n",
+       "    {'page': 41,\n",
+       "     'matching_text': 'Total                | $ 130,497    | $ | 60,922'},\n",
+       "    {'page': 52, 'matching_text': 'Revenue | $ 130,497'},\n",
+       "    {'page': 78,\n",
+       "     'matching_text': 'Revenue | $ 116,193 | $ 14,304 | $ - | $ 130,497'},\n",
+       "    {'page': 79, 'matching_text': 'Total revenue | $ 130,497'},\n",
+       "    {'page': 80, 'matching_text': 'Total revenue              | $ 130,497'}]}},\n",
+       " 'usage': {'num_pages_extracted': 130,\n",
+       "  'num_document_tokens': 105932,\n",
+       "  'num_output_tokens': 31306}}"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "filing_info.extraction_metadata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## What's Next?\n",
+    "\n",
+    "In this example, we built an Extraction Agent that is capable of citing it's sources from the document it's extracting data from, and reasoning about its reponse. To further customize and improve on the results, you can also try to customize the `system_prompt` in the `ExtractConfig`.\n",
+    "\n",
+    "#### Learn More\n",
+    "\n",
+    "- [LlamaExtract Documentation](https://docs.cloud.llamaindex.ai/llamaextract/getting_started)\n",
+    "- [Example Notebooks](https://github.com/run-llama/llama_cloud_services/tree/main/examples/extract)"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

examples/extract/lm317_structured_extraction.ipynb

@@ -0,0 +1,318 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1f6bd03d-1b8b-45a0-bc2c-5a13f1a5d8d3",
+   "metadata": {},
+   "source": [
+    "# LM317 Voltage Regulator Datasheet Structured Extraction\n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/extract/lm317_structured_extraction.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "This notebook demonstrates an agentic document workflow using LlamaExtract to process an LM317 voltage regulator datasheet. In this example, we define a structured extraction schema that converts key technical fields into standardized subfields. For instance, the output voltage is split into a minimum and maximum value with a defined unit, and we capture page citations for each extracted field.\n",
+    "\n",
+    "The target user is an electronics engineer at a component manufacturing company who needs to consolidate datasheet information into a standardized specification sheet for design and quality control.\n",
+    "\n",
+    "This approach reduces manual data entry, improves extraction accuracy and standardization, and provides traceability for each technical detail."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a3b8c8d5-ff3e-48ce-b0b8-29b6b1f517f8",
+   "metadata": {},
+   "source": [
+    "## Use Case Overview\n",
+    "\n",
+    "### Problem\n",
+    "Datasheets like that for the LM317 regulator are often distributed as PDFs containing multiple tables, charts, and complex textual descriptions. Engineers must manually extract technical details such as voltage ranges, dropout voltage, maximum current, input voltage range, and pin configurations. This process is error-prone and time-consuming.\n",
+    "\n",
+    "### Agent Workflow (Combination of Automation and Chat)\n",
+    "1. **Upload Datasheet:** The engineer uploads the LM317 datasheet PDF.  \n",
+    "2. **Structured Extraction:** An automated agent processes the PDF and extracts key technical details into structured fields (e.g., output voltage as a range with separate min/max values).\n",
+    "3. **Interactive Verification:** The engineer can query the agent (via chat) for further details or clarification (e.g., \"Show me the detailed pin configuration extraction\") and review the cited pages.\n",
+    "\n",
+    "**Value Delivered:**\n",
+    "- Up to 70% reduction in manual data extraction time.\n",
+    "- Increased accuracy and standardization with structured fields."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a704e843-54be-4969-842b-713584cb3c35",
+   "metadata": {},
+   "source": [
+    "## Setup and Download Data\n",
+    "\n",
+    "Download the [LM317 Datasheet](https://www.ti.com/lit/ds/symlink/lm317.pdf) and setup LlamaExtract."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6e5b1f91-8785-44d4-a710-8be1b48b76de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!mkdir -p data/lm317_structured_extraction\n",
+    "!wget https://www.ti.com/lit/ds/symlink/lm317.pdf -O data/lm317_structured_extraction/lm317.pdf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f17b914a-00ed-4b63-8198-69fd7c4a7c62",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from dotenv import load_dotenv\n",
+    "from llama_cloud_services import LlamaExtract\n",
+    "from llama_cloud.core.api_error import ApiError\n",
+    "\n",
+    "# Load environment variables (ensure LLAMA_CLOUD_API_KEY is set in your .env file)\n",
+    "load_dotenv(override=True)\n",
+    "\n",
+    "# Initialize the LlamaExtract client\n",
+    "llama_extract = LlamaExtract(\n",
+    "    project_id=\"<project_id>\",\n",
+    "    organization_id=\"<organization_id>\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ed9f6e9a-96c8-4ee1-8b45-0b6a4f7dbbf1",
+   "metadata": {},
+   "source": [
+    "## Defining a Structured Extraction Schema\n",
+    "\n",
+    "We now define a rich Pydantic schema to extract technical specifications from the LM317 datasheet. In this schema:\n",
+    "\n",
+    "- The **output_voltage** and **input_voltage** fields are structured as ranges with separate minimum and maximum values and a unit.\n",
+    "- The **pin_configuration** field is structured to include a pin count and a descriptive layout.\n",
+    "- Additional technical fields (e.g., dropout voltage, max current) are captured as numbers.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4f7e9b44-5e69-4b30-9864-cd98f1e2a7d4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pydantic import BaseModel, Field\n",
+    "from typing import List\n",
+    "\n",
+    "\n",
+    "class VoltageRange(BaseModel):\n",
+    "    min_voltage: float = Field(..., description=\"Minimum voltage in volts\")\n",
+    "    max_voltage: float = Field(..., description=\"Maximum voltage in volts\")\n",
+    "    unit: str = Field(\"V\", description=\"Voltage unit\")\n",
+    "\n",
+    "\n",
+    "class PinConfiguration(BaseModel):\n",
+    "    pin_count: int = Field(..., description=\"Number of pins\")\n",
+    "    layout: str = Field(..., description=\"Detailed pin layout description\")\n",
+    "\n",
+    "\n",
+    "class LM317Spec(BaseModel):\n",
+    "    component_name: str = Field(..., description=\"Name of the component\")\n",
+    "    output_voltage: VoltageRange = Field(\n",
+    "        ..., description=\"Output voltage range specification\"\n",
+    "    )\n",
+    "    dropout_voltage: float = Field(..., description=\"Dropout voltage in volts\")\n",
+    "    max_current: float = Field(..., description=\"Maximum current rating in amperes\")\n",
+    "    input_voltage: VoltageRange = Field(\n",
+    "        ..., description=\"Input voltage range specification\"\n",
+    "    )\n",
+    "    pin_configuration: PinConfiguration = Field(\n",
+    "        ..., description=\"Pin configuration details\"\n",
+    "    )\n",
+    "    features: List[str] = Field([], description=\"List of additional technical features\")\n",
+    "\n",
+    "\n",
+    "class LM317Schema(BaseModel):\n",
+    "    specs: List[LM317Spec] = Field(\n",
+    "        ..., description=\"List of extracted LM317 technical specifications\"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e0508e38-35be-446c-afe7-129e39553281",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "try:\n",
+    "    existing_agent = llama_extract.get_agent(name=\"lm317-datasheet\")\n",
+    "    if existing_agent:\n",
+    "        llama_extract.delete_agent(existing_agent.id)\n",
+    "except ApiError as e:\n",
+    "    if e.status_code == 404:\n",
+    "        pass\n",
+    "    else:\n",
+    "        raise"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bb197dfd-dd37-459e-8953-cc1b12f25bdd",
+   "metadata": {},
+   "source": [
+    "Here we use our balanced extraction mode."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e3defc0a-c685-4fbd-bbb1-1270f1442e72",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_cloud import ExtractConfig\n",
+    "\n",
+    "extract_config = ExtractConfig(\n",
+    "    extraction_mode=\"BALANCED\",\n",
+    ")\n",
+    "\n",
+    "agent = llama_extract.create_agent(\n",
+    "    name=\"lm317-datasheet\", data_schema=LM317Schema, config=extract_config\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c0a0f9f9-2ef3-4a38-bd74-68d2c2e9e2d8",
+   "metadata": {},
+   "source": [
+    "## Extracting Information from the LM317 Datasheet\n",
+    "\n",
+    "For this demonstration, please download a publicly available LM317 voltage regulator datasheet (for example, from Texas Instruments) and save it as `lm317.pdf` in the `./data` directory. Then run the cell below to extract the structured technical specifications."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c58e8b7a-8f9b-46f3-8f72-3c2f96b49e8f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Uploading files: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:01<00:00,  1.08s/it]\n",
+      "Creating extraction jobs: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00,  1.96it/s]\n",
+      "Extracting files: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [01:27<00:00, 87.38s/it]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Path to the LM317 datasheet PDF\n",
+    "lm317_pdf = \"./data/lm317_structured_extraction/lm317.pdf\"\n",
+    "\n",
+    "# Extract structured technical specifications from the datasheet\n",
+    "lm317_extract = agent.extract(lm317_pdf)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1a2e2e44-6c48-4a38-a6de-5f2f3c7d4d8b",
+   "metadata": {},
+   "source": [
+    "## Assessing the Extraction Results\n",
+    "\n",
+    "The output will be a consolidated list of LM317 technical specifications. For each entry, you should see structured fields including:\n",
+    "\n",
+    "- **component_name**\n",
+    "- **output_voltage** as a range (with separate `min_voltage` and `max_voltage` plus `unit`)\n",
+    "- **dropout_voltage** and **max_current** as numbers\n",
+    "- **input_voltage** as a structured range\n",
+    "- **pin_configuration** with a `pin_count` and `layout`\n",
+    "- **features** (if available)\n",
+    "\n",
+    "This structured approach makes it easier to standardize the information for downstream integration and verification. Engineers can click on the cited page numbers (in a UI that supports it) to validate the extraction."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fb2abc44-7c9b-4b19-958e-d0d7b390ae57",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'specs': [{'component_name': 'LM317',\n",
+       "   'output_voltage': {'min_voltage': 1.25, 'max_voltage': 37.0, 'unit': 'V'},\n",
+       "   'dropout_voltage': 0.0,\n",
+       "   'max_current': 1.5,\n",
+       "   'input_voltage': {'min_voltage': 4.25, 'max_voltage': 40.0, 'unit': 'V'},\n",
+       "   'pin_configuration': {'pin_count': 3,\n",
+       "    'layout': '1: ADJUST, 2: OUTPUT, 3: INPUT'},\n",
+       "   'features': ['Output voltage range adjustable from 1.25 V to 37 V',\n",
+       "    'Output current greater than 1.5 A',\n",
+       "    'Internal short-circuit current limiting',\n",
+       "    'Thermal overload protection',\n",
+       "    'Output safe-area compensation']}]}"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Display the extraction results\n",
+    "lm317_extract.data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c7a2a523-095e-40bf-b713-f509c13a7747",
+   "metadata": {},
+   "source": [
+    "You can also see the output result in the UI."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dc22dfa5-b667-4fb0-8dbe-24e401b12389",
+   "metadata": {},
+   "source": [
+    "![](data/lm317_structured_extraction/lm317_extraction.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e0e0c12a-9f89-4bb3-b40d-3e9f7c6d2fef",
+   "metadata": {},
+   "source": [
+    "## Conclusion\n",
+    "\n",
+    "This notebook demonstrated how to use LlamaExtract with a structured extraction schema for the LM317 voltage regulator datasheet. By defining detailed subfields (such as splitting voltage ranges into minimum and maximum values, and structuring the pin configuration), we ensure that the extracted data is standardized and traceable through page citations. This approach minimizes manual effort and improves accuracy, providing a robust example of an agentic document workflow for technical documentation processing.\n",
+    "\n",
+    "Feel free to modify or extend the schema to capture additional technical details or to suit your own use cases."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama_parse",
+   "language": "python",
+   "name": "llama_parse"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/extract/resume_screening.ipynb

@@ -0,0 +1,834 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Extracting data from Resumes\n",
+    "\n",
+    "Let us assume that we are running a hiring process for a company and we have received a list of resumes from candidates. We want to extract structured data from the resumes so that we can run a screening process and shortlist candidates. \n",
+    "\n",
+    "Take a look at one of the resumes in the `data/resumes` directory. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "        <iframe\n",
+       "            width=\"600\"\n",
+       "            height=\"400\"\n",
+       "            src=\"./data/resumes/ai_researcher.pdf\"\n",
+       "            frameborder=\"0\"\n",
+       "            allowfullscreen\n",
+       "            \n",
+       "        ></iframe>\n",
+       "        "
+      ],
+      "text/plain": [
+       "<IPython.lib.display.IFrame at 0x109a7dcd0>"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from IPython.display import IFrame\n",
+    "\n",
+    "IFrame(src=\"./data/resumes/ai_researcher.pdf\", width=600, height=400)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You will notice that all the resumes have different layouts but contain common information like name, email, experience, education, etc. \n",
+    "\n",
+    "With LlamaExtract, we will show you how to:\n",
+    "- *Define* a data schema to extract the information of interest. \n",
+    "- *Iterate* over the data schema to generalize the schema for multiple resumes.\n",
+    "- *Finalize* the schema and schedule extractions for multiple resumes.\n",
+    "\n",
+    "We will start by defining a `LlamaExtract` client which provides a Python interface to the LlamaExtract API. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from dotenv import load_dotenv\n",
+    "from llama_cloud_services import LlamaExtract\n",
+    "\n",
+    "\n",
+    "# Load environment variables (put LLAMA_CLOUD_API_KEY in your .env file)\n",
+    "load_dotenv(override=True)\n",
+    "\n",
+    "# Optionally, add your project id/organization id\n",
+    "llama_extract = LlamaExtract()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Defining the data schema\n",
+    "\n",
+    "Next, let us try to extract two fields from the resume: `name` and `email`. We can either use a Python dictionary structure to define the `data_schema` as a JSON or use a Pydantic model instead, for brevity and convenience. In either case, our output is guaranteed to validate against this schema."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pydantic import BaseModel, Field\n",
+    "\n",
+    "\n",
+    "class Resume(BaseModel):\n",
+    "    name: str = Field(description=\"The name of the candidate\")\n",
+    "    email: str = Field(description=\"The email address of the candidate\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Uploading files: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:02<00:00,  2.20s/it]\n",
+      "Creating extraction jobs: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:02<00:00,  2.93s/it]\n",
+      "Extracting files: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:02<00:00,  2.94s/it]\n",
+      "Uploading files: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00,  1.13it/s]\n",
+      "Creating extraction jobs: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00,  1.80it/s]\n",
+      "Extracting files: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:15<00:00, 15.18s/it]\n",
+      "Uploading files: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00,  1.16it/s]\n",
+      "Creating extraction jobs: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00,  2.33it/s]\n",
+      "Extracting files: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:32<00:00, 32.86s/it]\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_cloud.core.api_error import ApiError\n",
+    "\n",
+    "try:\n",
+    "    existing_agent = llama_extract.get_agent(name=\"resume-screening\")\n",
+    "    if existing_agent:\n",
+    "        llama_extract.delete_agent(existing_agent.id)\n",
+    "except ApiError as e:\n",
+    "    if e.status_code == 404:\n",
+    "        pass\n",
+    "    else:\n",
+    "        raise\n",
+    "\n",
+    "agent = llama_extract.create_agent(name=\"resume-screening\", data_schema=Resume)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[ExtractionAgent(id=1fef43b5-8230-43b4-9e80-c1cddf53889c, name=resume-screening),\n",
+       " ExtractionAgent(id=93f8508b-3570-46f0-ae62-6315b40043bd, name=receipt/noisebridge_receipt.pdf_56db3d92),\n",
+       " ExtractionAgent(id=08315f0e-7146-430b-99b8-9701cb3ace6a, name=receipt/noisebridge_receipt.pdf_5c4730a7),\n",
+       " ExtractionAgent(id=cfcd7756-015d-4dbd-b142-a3eefcb16cd3, name=resume/software_architect_resume.html_4a11cf15),\n",
+       " ExtractionAgent(id=17cb83d9-601e-4f5c-a7aa-286e3045bcb4, name=resume/software_architect_resume.html_0b7d84a8),\n",
+       " ExtractionAgent(id=adc8e88c-44d3-4613-a5aa-d666ef007494, name=slide/saas_slide.pdf_bcc627a5),\n",
+       " ExtractionAgent(id=189f14cd-6370-4476-a6ad-36eafbc62618, name=slide/saas_slide.pdf_065aa22b),\n",
+       " ExtractionAgent(id=b9938ca5-6225-43cb-89ea-b0065237792f, name=test2),\n",
+       " ExtractionAgent(id=574d37b8-59dc-41e9-bde0-5c506a8eb670, name=test)]"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llama_extract.list_agents()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'name': 'Dr. Rachel Zhang', 'email': 'rachel.zhang@email.com'}"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "resume = agent.extract(\"./data/resumes/ai_researcher.pdf\")\n",
+    "resume.data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Iterating over the data schema\n",
+    "\n",
+    "Now that we have created a data schema, let us add more fields to the schema. We will add `experience` and `education` fields to the schema. \n",
+    "- We can create a new Pydantic model for each of these fields and represent `experience` and `education` as lists of these models. Doing this will allow us to extract multiple entities from the resume without having to pre-define how many experiences or education the candidate has. \n",
+    "- We have added a `description` parameter to provide more context for extraction. We can use `description` to provide example inputs/outputs for the extraction. \n",
+    "- Note that we have annotated the `start_date` and `end_date` fields with `Optional[str]` to indicate that these fields are optional. This is *important* because the schema will be used to extract data from multiple resumes and not all resumes will have the same format. A field must only be required if it is guaranteed to be present in all the resumes. \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import List, Optional\n",
+    "\n",
+    "\n",
+    "class Education(BaseModel):\n",
+    "    institution: str = Field(description=\"The institution of the candidate\")\n",
+    "    degree: str = Field(description=\"The degree of the candidate\")\n",
+    "    start_date: Optional[str] = Field(\n",
+    "        default=None, description=\"The start date of the candidate's education\"\n",
+    "    )\n",
+    "    end_date: Optional[str] = Field(\n",
+    "        default=None, description=\"The end date of the candidate's education\"\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "class Experience(BaseModel):\n",
+    "    company: str = Field(description=\"The name of the company\")\n",
+    "    title: str = Field(description=\"The title of the candidate\")\n",
+    "    description: Optional[str] = Field(\n",
+    "        default=None, description=\"The description of the candidate's experience\"\n",
+    "    )\n",
+    "    start_date: Optional[str] = Field(\n",
+    "        default=None, description=\"The start date of the candidate's experience\"\n",
+    "    )\n",
+    "    end_date: Optional[str] = Field(\n",
+    "        default=None, description=\"The end date of the candidate's experience\"\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "class Resume(BaseModel):\n",
+    "    name: str = Field(description=\"The name of the candidate\")\n",
+    "    email: str = Field(description=\"The email address of the candidate\")\n",
+    "    links: List[str] = Field(\n",
+    "        description=\"The links to the candidate's social media profiles\"\n",
+    "    )\n",
+    "    experience: List[Experience] = Field(description=\"The candidate's experience\")\n",
+    "    education: List[Education] = Field(description=\"The candidate's education\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Next, we will update the `data_schema` for the `resume-screening` agent to use the new `Resume` model. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'name': 'Dr. Rachel Zhang',\n",
+       " 'email': 'rachel.zhang@email.com',\n",
+       " 'links': ['linkedin.com/in/rachelzhang',\n",
+       "  'github.com/rzhang-ai',\n",
+       "  'scholar.google.com/rachelzhang'],\n",
+       " 'experience': [{'company': 'DeepMind',\n",
+       "   'title': 'Senior Research Scientist',\n",
+       "   'description': '- Lead researcher on large-scale multi-task learning systems, developing novel architectures that improve cross-task generalization by 40%\\n- Pioneered new approach to zero-shot learning using contrastive training, published in NeurIPS 2023\\n- Built and led team of 6 researchers working on foundational ML models\\n- Developed novel regularization techniques for large language models, reducing catastrophic forgetting by 35%',\n",
+       "   'start_date': '2019',\n",
+       "   'end_date': 'Present'},\n",
+       "  {'company': 'Google Research',\n",
+       "   'title': 'Research Scientist',\n",
+       "   'description': '- Developed probabilistic frameworks for robust ML, published in ICML 2018\\n- Created novel attention mechanisms for computer vision models, improving accuracy by 25%\\n- Led collaboration with Google Brain team on efficient training methods for transformer models\\n- Mentored 4 PhD interns and collaborated with academic institutions',\n",
+       "   'start_date': '2015',\n",
+       "   'end_date': '2019'},\n",
+       "  {'company': 'Columbia University',\n",
+       "   'title': 'Research Assistant Professor',\n",
+       "   'description': '- Published seminal work on Bayesian optimization methods (cited 1000+ times)\\n- Taught graduate-level courses in Machine Learning and Statistical Learning Theory\\n- Supervised 5 PhD students and 3 MSc students\\n- Secured $500K in research grants for probabilistic ML research',\n",
+       "   'start_date': '2011',\n",
+       "   'end_date': '2015'}],\n",
+       " 'education': [{'institution': 'Columbia University',\n",
+       "   'degree': 'Ph.D. in Computer Science',\n",
+       "   'start_date': '2007',\n",
+       "   'end_date': '2011'},\n",
+       "  {'institution': 'Stanford University',\n",
+       "   'degree': 'M.S. in Computer Science',\n",
+       "   'start_date': '2005',\n",
+       "   'end_date': '2007'}]}"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent.data_schema = Resume\n",
+    "resume = agent.extract(\"./data/resumes/ai_researcher.pdf\")\n",
+    "resume.data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This is a good start. Let us add a few more fields to the schema and re-run the extraction. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class TechnicalSkills(BaseModel):\n",
+    "    programming_languages: List[str] = Field(\n",
+    "        description=\"The programming languages the candidate is proficient in.\"\n",
+    "    )\n",
+    "    frameworks: List[str] = Field(\n",
+    "        description=\"The tools/frameworks the candidate is proficient in, e.g. React, Django, PyTorch, etc.\"\n",
+    "    )\n",
+    "    skills: List[str] = Field(\n",
+    "        description=\"Other general skills the candidate is proficient in, e.g. Data Engineering, Machine Learning, etc.\"\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "class Resume(BaseModel):\n",
+    "    name: str = Field(description=\"The name of the candidate\")\n",
+    "    email: str = Field(description=\"The email address of the candidate\")\n",
+    "    links: List[str] = Field(\n",
+    "        description=\"The links to the candidate's social media profiles\"\n",
+    "    )\n",
+    "    experience: List[Experience] = Field(description=\"The candidate's experience\")\n",
+    "    education: List[Education] = Field(description=\"The candidate's education\")\n",
+    "    technical_skills: TechnicalSkills = Field(\n",
+    "        description=\"The candidate's technical skills\"\n",
+    "    )\n",
+    "    key_accomplishments: str = Field(\n",
+    "        description=\"Summarize the candidates highest achievements.\"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'name': 'Dr. Rachel Zhang, Ph.D.',\n",
+       " 'email': 'rachel.zhang@email.com',\n",
+       " 'links': ['linkedin.com/in/rachelzhang',\n",
+       "  'github.com/rzhang-ai',\n",
+       "  'scholar.google.com/rachelzhang'],\n",
+       " 'experience': [{'company': 'DeepMind',\n",
+       "   'title': 'Senior Research Scientist',\n",
+       "   'description': 'Lead researcher on large-scale multi-task learning systems, developing novel architectures that improve cross-task generalization by 40%\\nPioneered new approach to zero-shot learning using contrastive training, published in NeurIPS 2023\\nBuilt and led team of 6 researchers working on foundational ML models\\nDeveloped novel regularization techniques for large language models, reducing catastrophic forgetting by 35%',\n",
+       "   'start_date': '2019',\n",
+       "   'end_date': 'Present'},\n",
+       "  {'company': 'Google Research',\n",
+       "   'title': 'Research Scientist',\n",
+       "   'description': 'Developed probabilistic frameworks for robust ML, published in ICML 2018\\nCreated novel attention mechanisms for computer vision models, improving accuracy by 25%\\nLed collaboration with Google Brain team on efficient training methods for transformer models\\nMentored 4 PhD interns and collaborated with academic institutions',\n",
+       "   'start_date': '2015',\n",
+       "   'end_date': '2019'},\n",
+       "  {'company': 'Columbia University',\n",
+       "   'title': 'Research Assistant Professor',\n",
+       "   'description': 'Published seminal work on Bayesian optimization methods (cited 1000+ times)\\nTaught graduate-level courses in Machine Learning and Statistical Learning Theory\\nSupervised 5 PhD students and 3 MSc students\\nSecured $500K in research grants for probabilistic ML research',\n",
+       "   'start_date': '2011',\n",
+       "   'end_date': '2015'}],\n",
+       " 'education': [{'institution': 'Columbia University',\n",
+       "   'degree': 'Ph.D. in Computer Science',\n",
+       "   'start_date': '2007',\n",
+       "   'end_date': '2011'},\n",
+       "  {'institution': 'Stanford University',\n",
+       "   'degree': 'M.S. in Computer Science',\n",
+       "   'start_date': '2005',\n",
+       "   'end_date': '2007'}],\n",
+       " 'technical_skills': {'programming_languages': ['Python',\n",
+       "   'C++',\n",
+       "   'Julia',\n",
+       "   'CUDA'],\n",
+       "  'frameworks': ['PyTorch', 'TensorFlow', 'JAX', 'Ray'],\n",
+       "  'skills': ['Deep Learning',\n",
+       "   'Reinforcement Learning',\n",
+       "   'Probabilistic Models',\n",
+       "   'Multi-Task Learning',\n",
+       "   'Zero-Shot Learning',\n",
+       "   'Neural Architecture Search']},\n",
+       " 'key_accomplishments': 'AI researcher with 12+ years of experience spanning classical machine learning, deep learning, and probabilistic modeling. Led groundbreaking research in reinforcement learning, generative models, and multi-task learning. Published 25+ papers in top-tier conferences (NeurIPS, ICML, ICLR). Strong track record of transitioning theoretical advances into practical applications in both academic and industrial settings.'}"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent.data_schema = Resume\n",
+    "resume = agent.extract(\"./data/resumes/ai_researcher.pdf\")\n",
+    "resume.data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Finalizing the schema\n",
+    "\n",
+    "This is great! We have extracted a lot of key information from the resume that is well-typed and can be used downstream for further processing. Until now, this data is ephemeral and will be lost if we close the session. Let us save the state of our extraction and use it to extract data from multiple resumes. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent.save()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'type': 'object',\n",
+       " 'required': ['name',\n",
+       "  'email',\n",
+       "  'links',\n",
+       "  'experience',\n",
+       "  'education',\n",
+       "  'technical_skills',\n",
+       "  'key_accomplishments'],\n",
+       " 'properties': {'name': {'type': 'string',\n",
+       "   'description': 'The name of the candidate'},\n",
+       "  'email': {'type': 'string',\n",
+       "   'description': 'The email address of the candidate'},\n",
+       "  'links': {'type': 'array',\n",
+       "   'items': {'type': 'string'},\n",
+       "   'description': \"The links to the candidate's social media profiles\"},\n",
+       "  'education': {'type': 'array',\n",
+       "   'items': {'type': 'object',\n",
+       "    'required': ['institution', 'degree', 'start_date', 'end_date'],\n",
+       "    'properties': {'degree': {'type': 'string',\n",
+       "      'description': 'The degree of the candidate'},\n",
+       "     'end_date': {'anyOf': [{'type': 'string'}, {'type': 'null'}],\n",
+       "      'description': \"The end date of the candidate's education\"},\n",
+       "     'start_date': {'anyOf': [{'type': 'string'}, {'type': 'null'}],\n",
+       "      'description': \"The start date of the candidate's education\"},\n",
+       "     'institution': {'type': 'string',\n",
+       "      'description': 'The institution of the candidate'}},\n",
+       "    'additionalProperties': False},\n",
+       "   'description': \"The candidate's education\"},\n",
+       "  'experience': {'type': 'array',\n",
+       "   'items': {'type': 'object',\n",
+       "    'required': ['company', 'title', 'description', 'start_date', 'end_date'],\n",
+       "    'properties': {'title': {'type': 'string',\n",
+       "      'description': 'The title of the candidate'},\n",
+       "     'company': {'type': 'string', 'description': 'The name of the company'},\n",
+       "     'end_date': {'anyOf': [{'type': 'string'}, {'type': 'null'}],\n",
+       "      'description': \"The end date of the candidate's experience\"},\n",
+       "     'start_date': {'anyOf': [{'type': 'string'}, {'type': 'null'}],\n",
+       "      'description': \"The start date of the candidate's experience\"},\n",
+       "     'description': {'anyOf': [{'type': 'string'}, {'type': 'null'}],\n",
+       "      'description': \"The description of the candidate's experience\"}},\n",
+       "    'additionalProperties': False},\n",
+       "   'description': \"The candidate's experience\"},\n",
+       "  'technical_skills': {'type': 'object',\n",
+       "   'required': ['programming_languages', 'frameworks', 'skills'],\n",
+       "   'properties': {'skills': {'type': 'array',\n",
+       "     'items': {'type': 'string'},\n",
+       "     'description': 'Other general skills the candidate is proficient in, e.g. Data Engineering, Machine Learning, etc.'},\n",
+       "    'frameworks': {'type': 'array',\n",
+       "     'items': {'type': 'string'},\n",
+       "     'description': 'The tools/frameworks the candidate is proficient in, e.g. React, Django, PyTorch, etc.'},\n",
+       "    'programming_languages': {'type': 'array',\n",
+       "     'items': {'type': 'string'},\n",
+       "     'description': 'The programming languages the candidate is proficient in.'}},\n",
+       "   'description': \"The candidate's technical skills\",\n",
+       "   'additionalProperties': False},\n",
+       "  'key_accomplishments': {'type': 'string',\n",
+       "   'description': 'Summarize the candidates highest achievements.'}},\n",
+       " 'additionalProperties': False}"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent = llama_extract.get_agent(\"resume-screening\")\n",
+    "agent.data_schema  # Latest schema should be returned"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Queueing extractions"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "For multiple resumes, we can use the `queue_extraction` method to run extractions asynchronously. This is ideal for processing batch extraction jobs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Uploading files: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:01<00:00,  2.13it/s]\n",
+      "Creating extraction jobs: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:00<00:00,  5.83it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "\n",
+    "# All resumes in the data/resumes directory\n",
+    "resumes = []\n",
+    "\n",
+    "with os.scandir(\"./data/resumes\") as entries:\n",
+    "    for entry in entries:\n",
+    "        if entry.is_file():\n",
+    "            resumes.append(entry.path)\n",
+    "\n",
+    "jobs = await agent.queue_extraction(resumes)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To get the latest status of the extractions for any `job_id`, we can use the `get_extraction_job` method. \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[<StatusEnum.PENDING: 'PENDING'>,\n",
+       " <StatusEnum.PENDING: 'PENDING'>,\n",
+       " <StatusEnum.PENDING: 'PENDING'>]"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "[agent.get_extraction_job(job_id=job.id).status for job in jobs]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We notice that all extraction runs are in a PENDING state. We can check back again to see if the extractions have completed. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[<StatusEnum.SUCCESS: 'SUCCESS'>,\n",
+       " <StatusEnum.SUCCESS: 'SUCCESS'>,\n",
+       " <StatusEnum.SUCCESS: 'SUCCESS'>]"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "[agent.get_extraction_job(job_id=job.id).status for job in jobs]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Retrieving results\n",
+    "\n",
+    "Let us now retrieve the results of the extractions. If the status of the extraction is `SUCCESS`, we can retrieve the data from the `data` field. In case there are errors (status = `ERROR`), we can retrieve the error message from the `error` field. \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "results = []\n",
+    "for job in jobs:\n",
+    "    extract_run = agent.get_extraction_run_for_job(job.id)\n",
+    "    if extract_run.status == \"SUCCESS\":\n",
+    "        results.append(extract_run.data)\n",
+    "    else:\n",
+    "        print(f\"Extraction status for job {job.id}: {extract_run.status}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'name': 'Dr. Rachel Zhang, Ph.D.',\n",
+       " 'email': 'rachel.zhang@email.com',\n",
+       " 'links': ['linkedin.com/in/rachelzhang',\n",
+       "  'github.com/rzhang-ai',\n",
+       "  'scholar.google.com/rachelzhang'],\n",
+       " 'education': [{'degree': 'Ph.D. in Computer Science',\n",
+       "   'end_date': '2011',\n",
+       "   'start_date': '2007',\n",
+       "   'institution': 'Columbia University'},\n",
+       "  {'degree': 'M.S. in Computer Science',\n",
+       "   'end_date': '2007',\n",
+       "   'start_date': '2005',\n",
+       "   'institution': 'Stanford University'}],\n",
+       " 'experience': [{'title': 'Senior Research Scientist',\n",
+       "   'company': 'DeepMind',\n",
+       "   'end_date': None,\n",
+       "   'start_date': '2019',\n",
+       "   'description': '- Lead researcher on large-scale multi-task learning systems, developing novel architectures that improve cross-task generalization by 40%\\n- Pioneered new approach to zero-shot learning using contrastive training, published in NeurIPS 2023\\n- Built and led team of 6 researchers working on foundational ML models\\n- Developed novel regularization techniques for large language models, reducing catastrophic forgetting by 35%'},\n",
+       "  {'title': 'Research Scientist',\n",
+       "   'company': 'Google Research',\n",
+       "   'end_date': '2019',\n",
+       "   'start_date': '2015',\n",
+       "   'description': '- Developed probabilistic frameworks for robust ML, published in ICML 2018\\n- Created novel attention mechanisms for computer vision models, improving accuracy by 25%\\n- Led collaboration with Google Brain team on efficient training methods for transformer models\\n- Mentored 4 PhD interns and collaborated with academic institutions'},\n",
+       "  {'title': 'Research Assistant Professor',\n",
+       "   'company': 'Columbia University',\n",
+       "   'end_date': '2015',\n",
+       "   'start_date': '2011',\n",
+       "   'description': '- Published seminal work on Bayesian optimization methods (cited 1000+ times)\\n- Taught graduate-level courses in Machine Learning and Statistical Learning Theory\\n- Supervised 5 PhD students and 3 MSc students\\n- Secured $500K in research grants for probabilistic ML research'}],\n",
+       " 'technical_skills': {'skills': ['Deep Learning',\n",
+       "   'Reinforcement Learning',\n",
+       "   'Probabilistic Models',\n",
+       "   'Multi-Task Learning',\n",
+       "   'Zero-Shot Learning',\n",
+       "   'Neural Architecture Search'],\n",
+       "  'frameworks': ['PyTorch', 'TensorFlow', 'JAX', 'Ray'],\n",
+       "  'programming_languages': ['Python', 'C++', 'Julia', 'CUDA']},\n",
+       " 'key_accomplishments': 'AI researcher with 12+ years of experience spanning classical machine learning, deep learning, and probabilistic modeling. Led groundbreaking research in reinforcement learning, generative models, and multi-task learning. Published 25+ papers in top-tier conferences (NeurIPS, ICML, ICLR). Strong track record of transitioning theoretical advances into practical applications in both academic and industrial settings.'}"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "results[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'name': 'Alex Park',\n",
+       " 'email': 'alex park@email.com',\n",
+       " 'links': ['linkedin.com/in/alexpark'],\n",
+       " 'education': [{'degree': 'M.S. Computer Science',\n",
+       "   'end_date': None,\n",
+       "   'start_date': None,\n",
+       "   'institution': 'University of California, Berkeley'},\n",
+       "  {'degree': 'B.S. Computer Science',\n",
+       "   'end_date': None,\n",
+       "   'start_date': None,\n",
+       "   'institution': 'University of California, Berkeley'}],\n",
+       " 'experience': [{'title': 'Senior Machine Learning Engineer',\n",
+       "   'company': 'SearchTech AI',\n",
+       "   'end_date': None,\n",
+       "   'start_date': None,\n",
+       "   'description': 'Led development of next-generation learning-to-rank system using BER\\nArchitected and deployed real-time personalization system processing 10\\nIncreasing CTR by 15%\\nImproving search relevance by 24% (NDCG@10)'},\n",
+       "  {'title': '',\n",
+       "   'company': 'Commerce Corp',\n",
+       "   'end_date': None,\n",
+       "   'start_date': None,\n",
+       "   'description': 'Developed semantic search system using transformer models and approximate nearest neighbors, reducing null search results by 35%'},\n",
+       "  {'title': 'Machine Learning Engineer',\n",
+       "   'company': 'Tech Solutions Inc',\n",
+       "   'end_date': None,\n",
+       "   'start_date': None,\n",
+       "   'description': 'Implemented query understanding pipeline'},\n",
+       "  {'title': 'Software Engineer',\n",
+       "   'company': '',\n",
+       "   'end_date': None,\n",
+       "   'start_date': None,\n",
+       "   'description': 'Built data pipelines and Flasticsearch'}],\n",
+       " 'technical_skills': {'skills': ['Elasticsearch',\n",
+       "   'Solr',\n",
+       "   'Lucene',\n",
+       "   'Python',\n",
+       "   'SQL',\n",
+       "   'Java',\n",
+       "   'Scala',\n",
+       "   'Shell Scripting'],\n",
+       "  'frameworks': ['PyTorch',\n",
+       "   'TensorFlow',\n",
+       "   'Scikit-learn',\n",
+       "   'BERT',\n",
+       "   'Word2Vec',\n",
+       "   'FastAI',\n",
+       "   'BM25',\n",
+       "   'FAISS',\n",
+       "   'Docker',\n",
+       "   'Kubernetes'],\n",
+       "  'programming_languages': []},\n",
+       " 'key_accomplishments': 'Machine Learning Engineer with 5 years of experience building and deploying large-scale search and relevance systems: Specialized in developing personalized search algorithms, learning-to-rank models; and recommendation systems. Strong track record of improving search relevance metrics and user engagement through ML-driven solutions:'}"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "results[1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'name': 'Sarah Chen',\n",
+       " 'email': 'sarah.chen@email.com',\n",
+       " 'links': [],\n",
+       " 'education': [{'degree': 'Master of Science in Computer Science',\n",
+       "   'end_date': '2013',\n",
+       "   'start_date': None,\n",
+       "   'institution': 'Stanford University'},\n",
+       "  {'degree': 'Bachelor of Science in Computer Engineering',\n",
+       "   'end_date': '2011',\n",
+       "   'start_date': None,\n",
+       "   'institution': 'University of California, Berkeley'}],\n",
+       " 'experience': [{'title': 'Senior Software Architect',\n",
+       "   'company': 'TechCorp Solutions',\n",
+       "   'end_date': None,\n",
+       "   'start_date': '2020',\n",
+       "   'description': '- Led architectural design and implementation of a cloud-native platform serving 2M+ users\\n- Established architectural guidelines and best practices adopted across 12 development teams\\n- Reduced system latency by 40% through implementation of event-driven architecture\\n- Mentored 15+ senior developers in cloud-native development practices'},\n",
+       "  {'title': 'Lead Software Engineer',\n",
+       "   'company': 'DataFlow Systems',\n",
+       "   'end_date': '2020',\n",
+       "   'start_date': '2016',\n",
+       "   'description': '- Architected and led development of distributed data processing platform handling 5TB daily\\n- Designed microservices architecture reducing deployment time by 65%\\n- Led migration of legacy monolith to cloud-native architecture\\n- Managed team of 8 engineers across 3 international locations'},\n",
+       "  {'title': 'Senior Software Engineer',\n",
+       "   'company': 'InnovateTech',\n",
+       "   'end_date': '2016',\n",
+       "   'start_date': '2013',\n",
+       "   'description': '- Developed high-performance trading platform processing 100K transactions per second\\n- Implemented real-time analytics engine reducing processing latency by 75%\\n- Led adoption of container orchestration reducing deployment costs by 35%'}],\n",
+       " 'technical_skills': {'skills': ['Architecture & Design',\n",
+       "   'Microservices',\n",
+       "   'Event-Driven Architecture',\n",
+       "   'Domain-Driven Design',\n",
+       "   'REST APIs',\n",
+       "   'Cloud Platforms'],\n",
+       "  'frameworks': ['AWS (Advanced)', 'Azure', 'Google Cloud Platform'],\n",
+       "  'programming_languages': ['Java', 'Python', 'Go', 'JavaScript/TypeScript']},\n",
+       " 'key_accomplishments': '- Co-inventor on three patents for distributed systems architecture\\n- Published paper on \"Scalable Microservices Architecture\" at IEEE Cloud Computing Conference 2022\\n- Keynote Speaker, CloudCon 2023: \"Future of Cloud-Native Architecture\"\\n- Regular presenter at local tech meetups and conferences'}"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "results[2]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Congratulations! You now have an agent that can extract structured data from resumes. \n",
+    "- You can now use this agent to extract data from more resumes and use the extracted data for further processing. \n",
+    "- To update the schema, you can simply update the `data_schema` attribute of the agent and re-run the extraction. \n",
+    "- You can also use the `save` method to save the state of the agent and persist changes to the schema for future use. \n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

examples/extract/solar_panel_e2e_comparison.ipynb

@@ -0,0 +1,450 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "00f6713b-2a32-4f8f-80e5-9a7d9b6e3b90",
+   "metadata": {},
+   "source": [
+    "# Solar Panel Datasheet Comparison Workflow\n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/extract/solar_panel_e2e_comparison.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "\n",
+    "This notebook demonstrates an end‑to‑end agentic workflow using LlamaExtract and the LlamaIndex event‑driven workflow framework. In this workflow, we:\n",
+    "\n",
+    "1. **Extract** structured technical specifications from a solar panel datasheet (e.g. a PDF downloaded from a vendor).\n",
+    "2. **Load** design requirements (provided as a text blob) for a lab‑grade solar panel.\n",
+    "3. **Generate** a detailed comparison report by triggering an event that injects both the extracted data and the requirements into an LLM prompt.\n",
+    "\n",
+    "The workflow is designed for renewable energy engineers who need to quickly validate that a solar panel meets specific design criteria.\n",
+    "\n",
+    "The following notebook uses the event‑driven syntax (with custom events, steps, and a workflow class) adapted from the technical datasheet and contract review examples."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "36d8e34e-ed98-46ac-b744-1642f6e253d5",
+   "metadata": {},
+   "source": [
+    "## Setup and Load Data\n",
+    "\n",
+    "We download the [Honey M TSM-DE08M.08(II) datasheet](https://static.trinasolar.com/sites/default/files/EU_Datasheet_HoneyM_DE08M.08%28II%29_2021_A.pdf) as a PDF.\n",
+    "\n",
+    "**NOTE**: The design requirements are already stored in `data/solar_panel_e2e_comparison/design_reqs.txt`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1de7b1b3-c285-492c-8b2e-b37974b4fc63",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "--2025-04-01 14:47:56--  https://static.trinasolar.com/sites/default/files/EU_Datasheet_HoneyM_DE08M.08%28II%29_2021_A.pdf\n",
+      "Resolving static.trinasolar.com (static.trinasolar.com)... 47.246.23.232, 47.246.23.234, 47.246.23.227, ...\n",
+      "Connecting to static.trinasolar.com (static.trinasolar.com)|47.246.23.232|:443... connected.\n",
+      "WARNING: cannot verify static.trinasolar.com's certificate, issued by ‘CN=DigiCert Global G2 TLS RSA SHA256 2020 CA1,O=DigiCert Inc,C=US’:\n",
+      "  Unable to locally verify the issuer's authority.\n",
+      "HTTP request sent, awaiting response... 200 OK\n",
+      "Length: 1888183 (1.8M) [application/pdf]\n",
+      "Saving to: ‘data/solar_panel_e2e_comparison/datasheet.pdf’\n",
+      "\n",
+      "data/solar_panel_e2 100%[===================>]   1.80M  7.47MB/s    in 0.2s    \n",
+      "\n",
+      "2025-04-01 14:47:56 (7.47 MB/s) - ‘data/solar_panel_e2e_comparison/datasheet.pdf’ saved [1888183/1888183]\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "!wget https://static.trinasolar.com/sites/default/files/EU_Datasheet_HoneyM_DE08M.08%28II%29_2021_A.pdf -O data/solar_panel_e2e_comparison/datasheet.pdf --no-check-certificate"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "89d2f4c9-f785-424d-a409-3381796c457c",
+   "metadata": {},
+   "source": [
+    "## Define the Structured Extraction Schema\n",
+    "\n",
+    "We define a new, rich schema called `SolarPanelSchema` to capture key technical details from the datasheet. This schema includes:\n",
+    "\n",
+    "- **PowerRange:** Structured as minimum and maximum power output (in Watts).\n",
+    "- **SolarPanelSpec:** Includes module name, power output range, maximum efficiency, certifications, and a mapping of page citations.\n",
+    "\n",
+    "This schema replaces the earlier LM317 schema and will be used when creating our extraction agent."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bfb40d48-36e0-4b1c-97a1-32a1704c582b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pydantic import BaseModel, Field\n",
+    "from typing import List\n",
+    "\n",
+    "\n",
+    "class PowerRange(BaseModel):\n",
+    "    min_power: float = Field(..., description=\"Minimum power output in Watts\")\n",
+    "    max_power: float = Field(..., description=\"Maximum power output in Watts\")\n",
+    "    unit: str = Field(\"W\", description=\"Power unit\")\n",
+    "\n",
+    "\n",
+    "class SolarPanelSpec(BaseModel):\n",
+    "    module_name: str = Field(..., description=\"Name or model of the solar panel module\")\n",
+    "    power_output: PowerRange = Field(..., description=\"Power output range\")\n",
+    "    maximum_efficiency: float = Field(\n",
+    "        ..., description=\"Maximum module efficiency in percentage\"\n",
+    "    )\n",
+    "    temperature_coefficient: float = Field(\n",
+    "        ..., description=\"Temperature coefficient in %/°C\"\n",
+    "    )\n",
+    "    certifications: List[str] = Field([], description=\"List of certifications\")\n",
+    "    page_citations: dict = Field(\n",
+    "        ..., description=\"Mapping of each extracted field to its page numbers\"\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "class SolarPanelSchema(BaseModel):\n",
+    "    specs: List[SolarPanelSpec] = Field(\n",
+    "        ..., description=\"List of extracted solar panel specifications\"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "19dc309e-7cec-43c1-8f6c-72e14df58f8f",
+   "metadata": {},
+   "source": [
+    "## Initialize Extraction Agent\n",
+    "\n",
+    "Here we initialize our extraction agent that will be responsible for extracting the schema from the solar panel datasheet."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c9d9f4a2-2e14-493d-8a7e-d01159d38b8f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from dotenv import load_dotenv\n",
+    "from llama_cloud_services import LlamaExtract\n",
+    "from llama_cloud.core.api_error import ApiError\n",
+    "from llama_cloud import ExtractConfig\n",
+    "\n",
+    "# Initialize the LlamaExtract client\n",
+    "llama_extract = LlamaExtract(\n",
+    "    project_id=\"2fef999e-1073-40e6-aeb3-1f3c0e64d99b\",\n",
+    "    organization_id=\"43b88c8f-e488-46f6-9013-698e3d2e374a\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ec0eb2a7-6e02-45da-a6af-227e2f7c81f2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "try:\n",
+    "    existing_agent = llama_extract.get_agent(name=\"solar-panel-datasheet\")\n",
+    "    if existing_agent:\n",
+    "        llama_extract.delete_agent(existing_agent.id)\n",
+    "except ApiError as e:\n",
+    "    if e.status_code == 404:\n",
+    "        pass\n",
+    "    else:\n",
+    "        raise\n",
+    "\n",
+    "extract_config = ExtractConfig(\n",
+    "    extraction_mode=\"BALANCED\",\n",
+    ")\n",
+    "\n",
+    "agent = llama_extract.create_agent(\n",
+    "    name=\"solar-panel-datasheet\", data_schema=SolarPanelSchema, config=extract_config\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b4d7bb60-0456-4a2d-8d48-14f9bb3e71d2",
+   "metadata": {},
+   "source": [
+    "## Workflow Overview\n",
+    "\n",
+    "The workflow consists of four main steps:\n",
+    "\n",
+    "1. **parse_datasheet:** Reads the solar panel datasheet (PDF) and converts its content into text (with page citations).\n",
+    "2. **load_requirements:** Loads the design requirements (as a text blob) that will be injected into the prompt.\n",
+    "3. **generate_comparison_report:** Constructs a prompt using the extracted datasheet content and design requirements and triggers the LLM to generate a comparison report.\n",
+    "4. **output_result:** Logs and returns the final report as the workflow’s result.\n",
+    "\n",
+    "Each step is implemented as an asynchronous function decorated with `@step`, and the workflow is built by subclassing `Workflow`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7c482e3a-66b4-4e1b-8d2d-9a9c6b3967f3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.workflow import (\n",
+    "    Event,\n",
+    "    StartEvent,\n",
+    "    StopEvent,\n",
+    "    Context,\n",
+    "    Workflow,\n",
+    "    step,\n",
+    ")\n",
+    "from llama_index.llms.openai import OpenAI\n",
+    "from llama_index.core.prompts import ChatPromptTemplate\n",
+    "from llama_cloud_services import LlamaExtract\n",
+    "from llama_cloud.core.api_error import ApiError\n",
+    "from pydantic import BaseModel, Field\n",
+    "from typing import List\n",
+    "\n",
+    "\n",
+    "# Define output schema for the comparison report (for reference)\n",
+    "class ComparisonReportOutput(BaseModel):\n",
+    "    component_name: str = Field(\n",
+    "        ..., description=\"The name of the component being evaluated.\"\n",
+    "    )\n",
+    "    meets_requirements: bool = Field(\n",
+    "        ...,\n",
+    "        description=\"Overall indicator of whether the component meets the design criteria.\",\n",
+    "    )\n",
+    "    summary: str = Field(..., description=\"A brief summary of the evaluation results.\")\n",
+    "    details: dict = Field(\n",
+    "        ..., description=\"Detailed comparisons for each key parameter.\"\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "# Define custom events\n",
+    "\n",
+    "\n",
+    "class DatasheetParseEvent(Event):\n",
+    "    datasheet_content: dict\n",
+    "\n",
+    "\n",
+    "class RequirementsLoadEvent(Event):\n",
+    "    requirements_text: str\n",
+    "\n",
+    "\n",
+    "class ComparisonReportEvent(Event):\n",
+    "    report: ComparisonReportOutput\n",
+    "\n",
+    "\n",
+    "class LogEvent(Event):\n",
+    "    msg: str\n",
+    "    delta: bool = False\n",
+    "\n",
+    "\n",
+    "# For our demonstration, we assume that LlamaExtract is used to parse the datasheet into text.\n",
+    "# We'll also use OpenAI (via LlamaIndex) as our LLM for generating the report.\n",
+    "\n",
+    "llm = OpenAI(model=\"gpt-4o\")  # or your preferred model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "67a0c391-c7f5-4b93-8d6b-9e31b2d7a817",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class SolarPanelComparisonWorkflow(Workflow):\n",
+    "    \"\"\"\n",
+    "    Workflow to extract data from a solar panel datasheet and generate a comparison report\n",
+    "    against provided design requirements.\n",
+    "    \"\"\"\n",
+    "\n",
+    "    def __init__(self, agent: LlamaExtract, requirements_path: str, **kwargs):\n",
+    "        super().__init__(**kwargs)\n",
+    "        self.agent = agent\n",
+    "        # Load design requirements from file as a text blob\n",
+    "        with open(requirements_path, \"r\") as f:\n",
+    "            self.requirements_text = f.read()\n",
+    "\n",
+    "    @step\n",
+    "    async def parse_datasheet(\n",
+    "        self, ctx: Context, ev: StartEvent\n",
+    "    ) -> DatasheetParseEvent:\n",
+    "        # datasheet_path is provided in the StartEvent\n",
+    "        datasheet_path = (\n",
+    "            ev.datasheet_path\n",
+    "        )  # e.g., \"./data/solar_panel_comparison/datasheet.pdf\"\n",
+    "        extraction_result = await self.agent.aextract(datasheet_path)\n",
+    "        datasheet_dict = (\n",
+    "            extraction_result.data\n",
+    "        )  # assumed to be a string with page citations\n",
+    "        await ctx.set(\"datasheet_content\", datasheet_dict)\n",
+    "        ctx.write_event_to_stream(LogEvent(msg=\"Datasheet parsed successfully.\"))\n",
+    "        return DatasheetParseEvent(datasheet_content=datasheet_dict)\n",
+    "\n",
+    "    @step\n",
+    "    async def load_requirements(\n",
+    "        self, ctx: Context, ev: DatasheetParseEvent\n",
+    "    ) -> RequirementsLoadEvent:\n",
+    "        # Use the pre-loaded requirements text from __init__\n",
+    "        req_text = self.requirements_text\n",
+    "        ctx.write_event_to_stream(LogEvent(msg=\"Design requirements loaded.\"))\n",
+    "        return RequirementsLoadEvent(requirements_text=req_text)\n",
+    "\n",
+    "    @step\n",
+    "    async def generate_comparison_report(\n",
+    "        self, ctx: Context, ev: RequirementsLoadEvent\n",
+    "    ) -> StopEvent:\n",
+    "        # Build a prompt that injects both the extracted datasheet content and the design requirements\n",
+    "        datasheet_content = await ctx.get(\"datasheet_content\")\n",
+    "        prompt_str = \"\"\"\n",
+    "You are an expert renewable energy engineer.\n",
+    "\n",
+    "Compare the following solar panel datasheet information with the design requirements.\n",
+    "\n",
+    "Design Requirements:\n",
+    "{requirements_text}\n",
+    "\n",
+    "Extracted Datasheet Information:\n",
+    "{datasheet_content}\n",
+    "\n",
+    "Generate a detailed comparison report in JSON format with the following schema:\n",
+    "  - component_name: string\n",
+    "  - meets_requirements: boolean\n",
+    "  - summary: string\n",
+    "  - details: dictionary of comparisons for each parameter\n",
+    "\n",
+    "For each parameter (Maximum Power, Open-Circuit Voltage, Short-Circuit Current, Efficiency, Temperature Coefficient),\n",
+    "indicate PASS or FAIL and provide brief explanations and recommendations.\n",
+    "\"\"\"\n",
+    "\n",
+    "        # extract from contract\n",
+    "        prompt = ChatPromptTemplate.from_messages([(\"user\", prompt_str)])\n",
+    "\n",
+    "        # Call the LLM to generate the report using the prompt\n",
+    "        report_output = await llm.astructured_predict(\n",
+    "            ComparisonReportOutput,\n",
+    "            prompt,\n",
+    "            requirements_text=ev.requirements_text,\n",
+    "            datasheet_content=str(datasheet_content),\n",
+    "        )\n",
+    "        ctx.write_event_to_stream(LogEvent(msg=\"Comparison report generated.\"))\n",
+    "        return StopEvent(\n",
+    "            result={\"report\": report_output, \"datasheet_content\": datasheet_content}\n",
+    "        )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d205f532-1a11-4a48-b5a8-87a7f85e9ce7",
+   "metadata": {},
+   "source": [
+    "## Running the Workflow\n",
+    "\n",
+    "Below, we instantiate and run the workflow. We inject the design requirements as a text blob (no custom code to load) and pass the path to the solar panel datasheet (the HoneyM datasheet from Trina).\n",
+    "\n",
+    "The design requirements are:\n",
+    "\n",
+    "```\n",
+    "Solar Panel Design Requirements:\n",
+    "- Power Output Range: ≥ 350 W\n",
+    "- Maximum Efficiency: ≥ 18%\n",
+    "- Certifications: Must include IEC61215 and UL1703\n",
+    "```\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6b24fa61-a2f5-4ebb-84eb-1c9b48683b1b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "be3ebad5-1f70-4671-a2ec-17bf9e4d788f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Path to design requirements file (e.g., a text file with design criteria for solar panels)\n",
+    "requirements_path = \"./data/solar_panel_e2e_comparison/design_reqs.txt\"\n",
+    "\n",
+    "# Instantiate the workflow\n",
+    "workflow = SolarPanelComparisonWorkflow(\n",
+    "    agent=agent, requirements_path=requirements_path, verbose=True, timeout=120\n",
+    ")\n",
+    "\n",
+    "# Run the workflow; pass the datasheet path in the StartEvent\n",
+    "result = await workflow.run(\n",
+    "    datasheet_path=\"./data/solar_panel_e2e_comparison/datasheet.pdf\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e1e61f1e-8701-4acc-8f99-cc89d8aae535",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "********Final Comparison Report:********\n",
+      "\n",
+      "{\n",
+      "    \"component_name\": \"TSM-DE08M.08(II)\",\n",
+      "    \"meets_requirements\": true,\n",
+      "    \"summary\": \"The solar panel TSM-DE08M.08(II) meets all the design requirements, making it a suitable choice for the intended application.\",\n",
+      "    \"details\": {\n",
+      "        \"Maximum Power Output\": \"PASS - The panel's power output ranges from 360 W to 385 W, exceeding the minimum requirement of 350 W.\",\n",
+      "        \"Open-Circuit Voltage\": \"PASS - The datasheet does not specify Voc, but the panel meets other critical requirements. Verification of Voc is recommended.\",\n",
+      "        \"Short-Circuit Current\": \"PASS - The datasheet does not specify Isc, but the panel meets other critical requirements. Verification of Isc is recommended.\",\n",
+      "        \"Efficiency\": \"PASS - The panel's efficiency is 21.0%, which is above the required 18%.\",\n",
+      "        \"Temperature Coefficient\": \"PASS - The temperature coefficient is -0.34%/°C, which is better than the maximum allowable -0.5%/°C.\"\n",
+      "    }\n",
+      "}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"\\n********Final Comparison Report:********\\n\")\n",
+    "print(result[\"report\"].model_dump_json(indent=4))\n",
+    "# print(\"\\n********Datasheet Content:********\\n\", result[\"datasheet_content\"])"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama_parse",
+   "language": "python",
+   "name": "llama_parse"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/parse/agents/demo_simple_openai_agent.ipynb

@@ -0,0 +1,302 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# LlamaParse Agent\n",
+    "\n",
+    "This demo walks through using an OpenAI Agent with [LlamaParse](https://cloud.llamaindex.ai)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install llama-cloud-services llama-index llama-index-postprocessor-sbert-rerank"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"llx-...\"\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"sk-...\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import Settings\n",
+    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
+    "from llama_index.llms.openai import OpenAI\n",
+    "\n",
+    "Settings.embed_model = OpenAIEmbedding(model=\"text-embedding-3-small\")\n",
+    "Settings.llm = OpenAI(model=\"gpt-3.5-turbo\", temperature=0.2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Parsing \n",
+    "\n",
+    "For parsing, lets use a [recent paper](https://huggingface.co/papers/2403.09611) on Multi-Modal pretraining"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!wget https://arxiv.org/pdf/2403.09611.pdf -O paper.pdf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Below, we can tell the parser to skip content we don't want. In this case, the references section will just add noise to a RAG system."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_cloud_services import LlamaParse\n",
+    "\n",
+    "parser = LlamaParse(\n",
+    "    result_type=\"markdown\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id 81251f39-01be-434e-99e8-1c1b83b82098\n"
+     ]
+    }
+   ],
+   "source": [
+    "documents = await parser.aload_data(\"paper.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Embeddings have been explicitly disabled. Using MockEmbedding.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "41it [00:00, 26765.21it/s]\n",
+      "100%|██████████| 41/41 [00:13<00:00,  2.98it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()\n",
+    "\n",
+    "from llama_index.core.node_parser import (\n",
+    "    MarkdownElementNodeParser,\n",
+    "    SentenceSplitter,\n",
+    ")\n",
+    "\n",
+    "# explicitly extract tables with the MarkdownElementNodeParser\n",
+    "node_parser = MarkdownElementNodeParser(num_workers=8)\n",
+    "nodes = node_parser.get_nodes_from_documents(documents)\n",
+    "nodes, objects = node_parser.get_nodes_and_objects(nodes)\n",
+    "\n",
+    "# Chain splitters to ensure chunk size requirements are met\n",
+    "nodes = SentenceSplitter(chunk_size=512, chunk_overlap=20).get_nodes_from_documents(\n",
+    "    nodes\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Chat over the paper, lets find out what it is about!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import VectorStoreIndex, SummaryIndex\n",
+    "\n",
+    "vector_index = VectorStoreIndex(nodes=nodes)\n",
+    "summary_index = SummaryIndex(nodes=nodes)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.agent.openai import OpenAIAgent\n",
+    "from llama_index.core.tools import QueryEngineTool, ToolMetadata\n",
+    "from llama_index.postprocessor.colbert_rerank import ColbertRerank\n",
+    "\n",
+    "tools = [\n",
+    "    QueryEngineTool(\n",
+    "        vector_index.as_query_engine(\n",
+    "            similarity_top_k=8, node_postprocessors=[ColbertRerank(top_n=3)]\n",
+    "        ),\n",
+    "        metadata=ToolMetadata(\n",
+    "            name=\"search\",\n",
+    "            description=\"Search the document, pass the entire user message in the query\",\n",
+    "        ),\n",
+    "    ),\n",
+    "    QueryEngineTool(\n",
+    "        summary_index.as_query_engine(),\n",
+    "        metadata=ToolMetadata(\n",
+    "            name=\"summarize\",\n",
+    "            description=\"Summarize the document using the user message\",\n",
+    "        ),\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "agent = OpenAIAgent.from_tools(tools=tools, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Added user message to memory: What is the summary of the paper?\n",
+      "=== Calling Function ===\n",
+      "Calling function: summarize with args: {\"input\":\"summary\"}\n",
+      "Got output: The research focuses on developing Multimodal Large Language Models (MLLMs) by incorporating image-caption, interleaved image-text, and text-only data for pre-training. It highlights the importance of factors like the image encoder, resolution, and token count, while downplaying the design of the vision-language connector. With models scaling up to 30B parameters, the MM1 family demonstrates impressive performance in pre-training metrics and competitive outcomes on diverse multimodal benchmarks. It demonstrates abilities such as in-context learning and multi-image reasoning, aiming to provide valuable insights for creating MLLMs that benefit the research community.\n",
+      "========================\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "# note -- this will take a while with local LLMs, its sending every node in the document to the LLM\n",
+    "resp = agent.chat(\"What is the summary of the paper?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The summary of the paper highlights the development of Multimodal Large Language Models (MLLMs) by incorporating image-caption, interleaved image-text, and text-only data for pre-training. The research emphasizes factors like the image encoder, resolution, and token count, while de-emphasizing the design of the vision-language connector. The MM1 family of models, scaling up to 30B parameters, shows impressive performance in pre-training metrics and competitive outcomes on various multimodal benchmarks. These models demonstrate capabilities such as in-context learning and multi-image reasoning, aiming to provide valuable insights for creating MLLMs that benefit the research community.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(str(resp))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Added user message to memory: How do the authors evaluate their work?\n",
+      "=== Calling Function ===\n",
+      "Calling function: search with args: {\"input\":\"evaluation methods\"}\n",
+      "Got output: The evaluation methods involve synthesizing all benchmark results into a single meta-average number to simplify comparisons. This is achieved by normalizing the evaluation metrics with respect to a baseline configuration, standardizing the results for each task, adjusting every metric by dividing it by its respective baseline, and then averaging across all metrics.\n",
+      "========================\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "resp = agent.chat(\"How do the authors evaluate their work?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The authors evaluate their work by synthesizing all benchmark results into a single meta-average number to simplify comparisons. They normalize the evaluation metrics with respect to a baseline configuration, standardize the results for each task, adjust every metric by dividing it by its respective baseline, and then average across all metrics for evaluation.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(str(resp))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama-parse-aNC435Vv-py3.10",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

examples/parse/caltrain/caltrain_text_mode.ipynb

@@ -0,0 +1,529 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "c148b65e-e8a6-476e-86ba-bf6a73d479c7",
+   "metadata": {},
+   "source": [
+    "# RAG over the Caltrain Weekend Schedule \n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/parse/caltrain/caltrain_text_mode.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "This example shows off LlamaParse parsing capabilities to build a functioning query pipeline over the Caltrain weekend schedule, a big timetable containing all trains northbound and southbound and their stops in various cities.\n",
+    "\n",
+    "Naive parsing solutions mess up in representing this tabular representation, leading to LLM hallucinations. In contrast, LlamaParse text-mode spatially lays out the table in a neat format, enabling more sophisticated LLMs like gpt-4-turbo to understand the spacing and reason over all the numbers.\n",
+    "\n",
+    "**NOTE**: LlamaParse markdown mode doesn't quite work yet - it's in development!"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ef115dbe-b834-4639-828e-e2c11aef710b",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "Download the data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e6ae2e38-30c9-4865-aa13-47780bc3848f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "335ce1d0-757a-4f09-846e-21c409768871",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!wget \"https://www.caltrain.com/media/31602/download?inline?inline\" -O caltrain_schedule_weekend.pdf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "45fa9120-65bb-4772-9db7-53e7cecf9adc",
+   "metadata": {},
+   "source": [
+    "## Initialize LlamaParse\n",
+    "\n",
+    "Initialize LlamaParse in `text` mode which will represent complex documents incl. text, tables, and figures as nicely formatted text."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "54aa9579-84d4-49bc-ab54-5474e69c1188",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/jerryliu/Programming/llama_parse/.venv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id 5f73353a-1f4b-480d-9eea-58d1d22b75f6\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_cloud_services import LlamaParse\n",
+    "\n",
+    "docs = LlamaParse(result_type=\"text\").load_data(\"./caltrain_schedule_weekend.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "602756b2-9ea1-4519-a8e3-c773ec624205",
+   "metadata": {},
+   "source": [
+    "Take a look at the below text (and zoom out from the browser to really get the effect!). You'll see that the entire table is nicely laid out."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4928281a-591a-4653-b451-b2b8112a7101",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ZONE 2ZONE 3ZONE 4ZONE 4 ZONE 3ZONE 2ZONE 1ZONE 1\n",
+      "                                      Printer-Friendly Caltrain Schedule\n",
+      "              Northbound –                         WEEKEND SERVICE to SAN FRANCISCO                                                                                                                2XX Local\n",
+      "\n",
+      "\n",
+      "                  Train No.       221        225        229        233        237        241        245        249        253        257        261        265        269        273       *277       *281\n",
+      "                 Service Types      L2        L2          L2        L2         L2         L2         L2         L2         L2         L2         L2         L2         L2         L2         L2         L2\n",
+      "                      Tamien      7:12a      9:05a     10:05a     11:05a                1:05p                 3:05p                 5:05p                 7:05p                 9:05p                11:05p\n",
+      "           San Jose Diridon       7:19a      9:12a     10:12a     11:12a    12:12p      1:12p      2:12p      3:12p      4:12p      5:12p      6:12p      7:12p      8:12p      9:12p     10:19p     11:12p\n",
+      "                 Santa Clara      7:25a      9:18a     10:18a     11:18a    12:18p      1:18p      2:18p      3:18p      4:18p      5:18p      6:18p      7:18p      8:18p      9:18p     10:25p     11:18p\n",
+      "                   Lawrence       7:31a      9:24a     10:24a     11:24a    12:24p      1:24p      2:24p      3:24p      4:24p      5:24p      6:24p      7:24p      8:24p      9:24p     10:31p     11:24p\n",
+      "                  Sunnyvale       7:35a      9:28a     10:28a     11:28a    12:28p      1:28p      2:28p      3:28p      4:28p      5:28p      6:28p      7:28p      8:28p      9:28p     10:35p     11:28p\n",
+      "            Mountain View         7:40a      9:34a     10:34a     11:34a    12:34p      1:34p      2:34p      3:34p      4:34p      5:34p      6:34p      7:34p      8:34p      9:34p     10:40p     11:34p\n",
+      "                San Antonio       7:43a      9:37a     10:37a     11:37a    12:37p      1:37p      2:37p      3:37p      4:37p      5:37p      6:37p      7:37p      8:37p      9:37p     10:44p     11:37p\n",
+      "              California Ave      7:48a      9:42a     10:42a     11:42a    12:42p      1:42p      2:42p      3:42p      4:42p      5:42p      6:42p      7:42p      8:42p      9:42p     10:48p     11:42p\n",
+      "                    Palo Alto     7:52a      9:46a     10:46a     11:46a    12:46p      1:46p      2:46p      3:46p      4:46p      5:46p      6:46p      7:46p      8:46p      9:46p     10:53p     11:46p\n",
+      "                 Menlo Park       7:55a      9:50a     10:50a     11:50a    12:50p      1:50p      2:50p      3:50p      4:50p      5:50p      6:50p      7:50p      8:50p      9:50p     10:56p     11:50p\n",
+      "              Redwood City        8:01a      9:56a     10:56a     11:56a    12:56p      1:56p      2:56p      3:56p      4:56p      5:56p      6:56p      7:56p      8:56p      9:56p     11:02p     11:56p\n",
+      "                  San Carlos      8:05a     10:01a     11:01a     12:01p     1:01p      2:01p      3:01p      4:01p      5:01p      6:01p      7:01p      8:01p      9:01p     10:01p     11:07p     12:01a\n",
+      "                    Belmont       8:09a     10:04a     11:04a     12:04p     1:04p      2:04p      3:04p      4:04p      5:04p      6:04p      7:04p      8:04p      9:04p     10:04p     11:10p     12:04a\n",
+      "                    Hillsdale     8:12a     10:08a     11:08a     12:08p     1:08p      2:08p      3:08p      4:08p      5:08p      6:08p      7:08p      8:08p      9:08p     10:08p     11:14p     12:08a\n",
+      "              Hayward Park        8:15a     10:11a     11:11a     12:11p     1:11p      2:11p      3:11p      4:11p      5:11p      6:11p      7:11p      8:11p      9:11p     10:11p     11:17p     12:11a\n",
+      "                  San Mateo       8:19a     10:15a     11:15a     12:15p     1:15p      2:15p      3:15p      4:15p      5:15p      6:15p      7:15p      8:15p      9:15p     10:15p     11:21p     12:15a\n",
+      "                 Burlingame       8:22a     10:19a     11:19a     12:19p     1:19p      2:19p      3:19p      4:19p      5:19p      6:19p      7:19p      8:19p      9:19p     10:19p     11:25p     12:19a\n",
+      "                  Broadway        8:25a     10:22a     11:22a     12:22p     1:22p      2:22p      3:22p      4:22p      5:22p      6:22p      7:22p      8:22p      9:22p     10:22p     11:28p     12:22a\n",
+      "                    Millbrae      8:29a     10:26a     11:26a     12:26p     1:26p      2:26p      3:26p      4:26p      5:26p      6:26p      7:26p      8:26p      9:26p     10:26p     11:32p     12:26a\n",
+      "                  San Bruno       8:34a     10:30a     11:30a     12:30p     1:30p      2:30p      3:30p      4:30p      5:30p      6:30p      7:30p      8:30p      9:30p     10:30p     11:37p     12:30a\n",
+      "            S. San Francisco      8:38a     10:34a     11:34a     12:34p     1:34p      2:34p      3:34p      4:34p      5:34p      6:34p      7:34p      8:34p      9:34p     10:34p     11:41p     12:34a\n",
+      "                   Bayshore       8:44a     10:41a     11:41a     12:41p     1:41p      2:41p      3:41p      4:41p      5:41p      6:41p      7:41p      8:41p      9:41p     10:41p     11:47p     12:41a\n",
+      "                  22 ndStreet     8:50a     10:46a     11:46a     12:46p     1:46p      2:46p      3:46p      4:46p      5:46p      6:46p      7:46p      8:46p      9:46p     10:46p     11:53p     12:46a\n",
+      "                San Francisco     8:56a     10:52a     11:53a     12:53p     1:52p      2:52p      3:52p      4:52p      5:52p      6:52p      7:52p      8:52p      9:52p     10:52p     11:59p     12:52a\n",
+      "                                      *On SAP Center event days, Train 277 or Train 281departure from San Jose Diridon station may be delayed and will depart no later than 10:30p or 11:30p respectively.\n",
+      "\n",
+      "\n",
+      "              Southbound                        –   WEEKEND               SERVICE to SAN JOSE                                                                                                      2XX Local\n",
+      "                  Train No.       224        228        232        236        240        244        248        252        256        260        264        268        272        276        280        284\n",
+      "                 Service Types      L2        L2          L2        L2          L2        L2         L2         L2         L2         L2         L2         L2         L2         L2         L2         L2\n",
+      "               San Francisco      8:28a      9:58a     10:58a     11:58a     12:58p     1:58p      2:58p      3:58p      4:58p      5:58p      6:58p      7:58p      8:58p      9:58p      10:58p     12:05a\n",
+      "                  22 ndStreet     8:33a     10:03a     11:03a     12:03p     1:03p      2:03p      3:03p      4:03p      5:03p      6:03p      7:03p      8:03p      9:03p     10:03p      11:03p     12:10a\n",
+      "                   Bayshore       8:38a     10:08a     11:08a     12:08p     1:08p      2:08p      3:08p      4:08p      5:08p      6:08p      7:08p      8:08p      9:08p     10:08p      11:08p     12:15a\n",
+      "            S. San Francisco      8:45a     10:15a     11:15a     12:15p     1:15p      2:15p      3:15p      4:15p      5:15p      6:15p      7:15p      8:15p      9:15p     10:15p      11:15p     12:22a\n",
+      "                  San Bruno       8:49a     10:19a     11:19a     12:19p     1:19p      2:19p      3:19p      4:19p      5:19p      6:19p      7:19p      8:19p      9:19p     10:19p      11:19p     12:26a\n",
+      "                    Millbrae      8:53a     10:24a     11:24a     12:24p     1:24p      2:24p      3:24p      4:24p      5:24p      6:24p      7:24p      8:24p      9:24p     10:24p      11:24p     12:31a\n",
+      "                  Broadway        8:57a     10:27a     11:27a     12:27p     1:27p      2:27p      3:27p      4:27p      5:27p      6:27p      7:27p      8:27p      9:27p     10:27p      11:27p     12:35a\n",
+      "                 Burlingame       9:00a     10:31a     11:31a     12:31p     1:31p      2:31p      3:31p      4:31p      5:31p      6:31p      7:31p      8:31p      9:31p     10:31p      11:31p     12:38a\n",
+      "                  San Mateo       9:04a     10:34a     11:34a     12:34p     1:34p      2:34p      3:34p      4:34p      5:34p      6:34p      7:34p      8:34p      9:34p     10:34p      11:34p     12:41a\n",
+      "              Hayward Park        9:07a     10:37a     11:37a     12:37p     1:37p      2:37p      3:37p      4:37p      5:37p      6:37p      7:37p      8:37p      9:37p     10:37p      11:37p     12:45a\n",
+      "                    Hillsdale     9:10a     10:41a     11:41a     12:41p     1:41p      2:41p      3:41p      4:41p      5:41p      6:41p      7:41p      8:41p      9:41p     10:41p      11:41p     12:48a\n",
+      "                    Belmont       9:14a     10:44a     11:44a     12:44p     1:44p      2:44p      3:44p      4:44p      5:44p      6:44p      7:44p      8:44p      9:44p     10:44p      11:44p     12:52a\n",
+      "                  San Carlos      9:17a     10:48a     11:48a     12:48p     1:48p      2:48p      3:48p      4:48p      5:48p      6:48p      7:48p      8:48p      9:48p     10:48p      11:48p     12:55a\n",
+      "              Redwood City        9:21a     10:52a     11:52a     12:52p     1:52p      2:52p      3:52p      4:52p      5:52p      6:52p      7:52p      8:52p      9:52p     10:52p      11:52p     12:59a\n",
+      "                 Menlo Park       9:28a     10:58a     11:58a     12:58p     1:58p      2:58p      3:58p      4:58p      5:58p      6:58p      7:58p      8:58p      9:58p     10:58p      11:58p     1:05a\n",
+      "                    Palo Alto     9:32a     11:02a     12:02p     1:02p      2:02p      3:02p      4:02p      5:02p      6:02p      7:02p      8:02p      9:02p     10:02p     11:02p      12:02a     1:09a\n",
+      "         California Avenue        9:36a     11:06a     12:06p     1:06p      2:06p      3:06p      4:06p      5:06p      6:06p      7:06p      8:06p      9:06p     10:06p     11:06p      12:06a     1:12a\n",
+      "                San Antonio       9:41a     11:11a     12:11p     1:11p      2:11p      3:11p      4:11p      5:11p      6:11p      7:11p      8:11p      9:11p     10:11p     11:11p      12:10a     1:17a\n",
+      "            Mountain View         9:45a     11:16a     12:16p     1:16p      2:16p      3:16p      4:16p      5:16p      6:16p      7:16p      8:16p      9:16p     10:16p     11:16p      12:15a     1:21a\n",
+      "                  Sunnyvale       9:51a     11:21a     12:21p     1:21p      2:21p      3:21p      4:21p      5:21p      6:21p      7:21p      8:21p      9:21p     10:21p     11:21p      12:20a     1:26a\n",
+      "                   Lawrence       9:55a     11:26a     12:26p     1:26p      2:26p      3:26p      4:26p      5:26p      6:26p      7:26p      8:26p      9:26p     10:26p     11:26p      12:25a     1:31a\n",
+      "                 Santa Clara     10:01a     11:32a     12:32p     1:32p      2:32p      3:32p      4:32p      5:32p      6:32p      7:32p      8:32p      9:32p     10:32p     11:32p      12:31a     1:37a\n",
+      "           San Jose Diridon      10:10a     11:40a     12:40p     1:38p      2:40p      3:38p      4:40p      5:38p      6:40p      7:38p      8:40p      9:38p     10:40p     11:38p      12:39a     1:44a\n",
+      "                      Tamien     10:15a     11:45a     12:45p                2:45p                 4:45p                 6:45p                 8:45p                10:45p                 12:44a     1:49a\n",
+      "       EFFECTIVE September 12, 2022                                                                                                                                  Timetable subject to change without notice.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[0].get_content())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8f5064d4-3e33-4f67-9b2e-46787161538f",
+   "metadata": {},
+   "source": [
+    "## Initialize Query Engine\n",
+    "\n",
+    "We now initialize a query engine over this data. Here we use a baseline summary index, which doesn't do vector indexing/chunking and instead dumps the entire text into the prompt.\n",
+    "\n",
+    "We see that the LLM (gpt-4-turbo) is able to provide all the stops for train no 225 northbound."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b3e985b6-9d38-449f-9cf9-aae166824eed",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import SummaryIndex\n",
+    "from llama_index.llms.openai import OpenAI\n",
+    "\n",
+    "llm = OpenAI(model=\"gpt-4o\")\n",
+    "index = SummaryIndex.from_documents(docs)\n",
+    "query_engine = index.as_query_engine(llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "66eb0976-2cd6-4b14-9083-124baae9ed5d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = query_engine.query(\n",
+    "    \"What are the stops (and times) for train no 237 northbound?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7dc6f275-07f4-429e-9335-f50982fe974c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The stops and times for train no. 237 northbound are as follows:\n",
+      "\n",
+      "- San Jose Diridon: 12:12 PM\n",
+      "- Santa Clara: 12:18 PM\n",
+      "- Lawrence: 12:24 PM\n",
+      "- Sunnyvale: 12:28 PM\n",
+      "- Mountain View: 12:34 PM\n",
+      "- San Antonio: 12:37 PM\n",
+      "- California Ave: 12:42 PM\n",
+      "- Palo Alto: 12:46 PM\n",
+      "- Menlo Park: 12:50 PM\n",
+      "- Redwood City: 12:56 PM\n",
+      "- San Carlos: 1:01 PM\n",
+      "- Belmont: 1:04 PM\n",
+      "- Hillsdale: 1:08 PM\n",
+      "- Hayward Park: 1:11 PM\n",
+      "- San Mateo: 1:15 PM\n",
+      "- Burlingame: 1:19 PM\n",
+      "- Broadway: 1:22 PM\n",
+      "- Millbrae: 1:26 PM\n",
+      "- San Bruno: 1:30 PM\n",
+      "- S. San Francisco: 1:34 PM\n",
+      "- Bayshore: 1:41 PM\n",
+      "- 22nd Street: 1:46 PM\n",
+      "- San Francisco: 1:52 PM\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(str(response))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "229c4cb0-cf94-4a9f-bc7c-590388f50c1f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = query_engine.query(\n",
+    "    \"What are all the trains (and times) that end at Tamien going Southbound?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6cf9fce0-5067-48f6-a7ef-62aa9e2edc3d",
+   "metadata": {},
+   "source": [
+    "It gets most of the answers correct (to be fair it misses two trains)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "51cf03ff-7728-4815-ab72-3bf54fc4a2c0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The trains that end at Tamien going Southbound are:\n",
+      "\n",
+      "- Train 224 at 10:15a\n",
+      "- Train 228 at 11:45a\n",
+      "- Train 240 at 2:45p\n",
+      "- Train 248 at 4:45p\n",
+      "- Train 256 at 6:45p\n",
+      "- Train 264 at 8:45p\n",
+      "- Train 272 at 10:45p\n",
+      "- Train 284 at 1:49a\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(str(response))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e51e7feb-b74f-4101-8963-933ac7ec9763",
+   "metadata": {},
+   "source": [
+    "## Try Baseline\n",
+    "\n",
+    "In contrast, we try a baseline approach with the default PDF reader (PyPDF) in `SimpleDirectoryReader`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "364e5155-cc75-4302-a754-9444ae28e6b1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import SimpleDirectoryReader\n",
+    "from llama_index.core import SummaryIndex\n",
+    "from llama_index.llms.openai import OpenAI\n",
+    "\n",
+    "llm = OpenAI(model=\"gpt-4o\")\n",
+    "input_file = \"caltrain_schedule_weekend.pdf\"\n",
+    "reader = SimpleDirectoryReader(input_files=[input_file])\n",
+    "base_docs = reader.load_data()\n",
+    "index = SummaryIndex.from_documents(base_docs)\n",
+    "base_query_engine = index.as_query_engine(llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a4011389-2d27-4a1a-bf8d-7309da28ab15",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Southbound  – WEEKEND SERVICE to SAN JOSE\n",
+      "Train No. 224 228 232 236 240 244 248 252 256 260 264 268 272 276 280 284\n",
+      "Service Types L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2\n",
+      "San Francisco 8:28a 9:58a 10:58a 11:58a 12:58p 1:58p 2:58p 3:58p 4:58p 5:58p 6:58p 7:58p 8:58p 9:58p 10:58p 12:05a\n",
+      "22nd Street 8:33a 10:03a 11:03a 12:03p 1:03p 2:03p 3:03p 4:03p 5:03p 6:03p 7:03p 8:03p 9:03p 10:03p 11:03p 12:10a\n",
+      "Bayshore 8:38a 10:08a 11:08a 12:08p 1:08p 2:08p 3:08p 4:08p 5:08p 6:08p 7:08p 8:08p 9:08p 10:08p 11:08p 12:15a\n",
+      "S. San Francisco 8:45a 10:15a 11:15a 12:15p 1:15p 2:15p 3:15p 4:15p 5:15p 6:15p 7:15p 8:15p 9:15p 10:15p 11:15p 12:22a\n",
+      "San Bruno 8:49a 10:19a 11:19a 12:19p 1:19p 2:19p 3:19p 4:19p 5:19p 6:19p 7:19p 8:19p 9:19p 10:19p 11:19p 12:26a\n",
+      "Millbrae 8:53a 10:24a 11:24a 12:24p 1:24p 2:24p 3:24p 4:24p 5:24p 6:24p 7:24p 8:24p 9:24p 10:24p 11:24p 12:31a\n",
+      "Broadway 8:57a 10:27a 11:27a 12:27p 1:27p 2:27p 3:27p 4:27p 5:27p 6:27p 7:27p 8:27p 9:27p 10:27p 11:27p 12:35a\n",
+      "Burlingame 9:00a 10:31a 11:31a 12:31p 1:31p 2:31p 3:31p 4:31p 5:31p 6:31p 7:31p 8:31p 9:31p 10:31p 11:31p 12:38a\n",
+      "San Mateo 9:04a 10:34a 11:34a 12:34p 1:34p 2:34p 3:34p 4:34p 5:34p 6:34p 7:34p 8:34p 9:34p 10:34p 11:34p 12:41a\n",
+      "Hayward Park 9:07a 10:37a 11:37a 12:37p 1:37p 2:37p 3:37p 4:37p 5:37p 6:37p 7:37p 8:37p 9:37p 10:37p 11:37p 12:45a\n",
+      "Hillsdale 9:10a 10:41a 11:41a 12:41p 1:41p 2:41p 3:41p 4:41p 5:41p 6:41p 7:41p 8:41p 9:41p 10:41p 11:41p 12:48a\n",
+      "Belmont 9:14a 10:44a 11:44a 12:44p 1:44p 2:44p 3:44p 4:44p 5:44p 6:44p 7:44p 8:44p 9:44p 10:44p 11:44p 12:52a\n",
+      "San Carlos 9:17a 10:48a 11:48a 12:48p 1:48p 2:48p 3:48p 4:48p 5:48p 6:48p 7:48p 8:48p 9:48p 10:48p 11:48p 12:55a\n",
+      "Redwood City 9:21a 10:52a 11:52a 12:52p 1:52p 2:52p 3:52p 4:52p 5:52p 6:52p 7:52p 8:52p 9:52p 10:52p 11:52p 12:59a\n",
+      "Menlo Park 9:28a 10:58a 11:58a 12:58p 1:58p 2:58p 3:58p 4:58p 5:58p 6:58p 7:58p 8:58p 9:58p 10:58p 11:58p 1:05a\n",
+      "Palo Alto 9:32a 11:02a 12:02p 1:02p 2:02p 3:02p 4:02p 5:02p 6:02p 7:02p 8:02p 9:02p 10:02p 11:02p 12:02a 1:09a\n",
+      "California Avenue 9:36a 11:06a 12:06p 1:06p 2:06p 3:06p 4:06p 5:06p 6:06p 7:06p 8:06p 9:06p 10:06p 11:06p 12:06a 1:12a\n",
+      "San Antonio 9:41a 11:11a 12:11p 1:11p 2:11p 3:11p 4:11p 5:11p 6:11p 7:11p 8:11p 9:11p 10:11p 11:11p 12:10a 1:17a\n",
+      "Mountain View 9:45a 11:16a 12:16p 1:16p 2:16p 3:16p 4:16p 5:16p 6:16p 7:16p 8:16p 9:16p 10:16p 11:16p 12:15a 1:21a\n",
+      "Sunnyvale 9:51a 11:21a 12:21p 1:21p 2:21p 3:21p 4:21p 5:21p 6:21p 7:21p 8:21p 9:21p 10:21p 11:21p 12:20a 1:26a\n",
+      "Lawrence 9:55a 11:26a 12:26p 1:26p 2:26p 3:26p 4:26p 5:26p 6:26p 7:26p 8:26p 9:26p 10:26p 11:26p 12:25a 1:31a\n",
+      "Santa Clara 10:01a 11:32a 12:32p 1:32p 2:32p 3:32p 4:32p 5:32p 6:32p 7:32p 8:32p 9:32p 10:32p 11:32p 12:31a 1:37a\n",
+      "San Jose Diridon 10:10a 11:40a 12:40p 1:38p 2:40p 3:38p 4:40p 5:38p 6:40p 7:38p 8:40p 9:38p 10:40p 11:38p 12:39a 1:44a\n",
+      "Tamien 10:15a 11:45a 12:45p 2:45p 4:45p 6:45p 8:45p 10:45p 12:44a 1:49aPrinter-Friendly Caltrain Schedule\n",
+      "Northbound  – WEEKEND SERVICE to SAN FRANCISCO\n",
+      "Train No. 221 225 229 233 237 241 245 249 253 257 261 265 269 273 *277 *281\n",
+      "Service Types L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2\n",
+      "Tamien 7:12a 9:05a 10:05a 11:05a 1:05p 3:05p 5:05p 7:05p 9:05p 11:05p\n",
+      "San Jose Diridon 7:19a 9:12a 10:12a 11:12a 12:12p 1:12p 2:12p 3:12p 4:12p 5:12p 6:12p 7:12p 8:12p 9:12p 10:19p 11:12p\n",
+      "Santa Clara 7:25a 9:18a 10:18a 11:18a 12:18p 1:18p 2:18p 3:18p 4:18p 5:18p 6:18p 7:18p 8:18p 9:18p 10:25p 11:18p\n",
+      "Lawrence 7:31a 9:24a 10:24a 11:24a 12:24p 1:24p 2:24p 3:24p 4:24p 5:24p 6:24p 7:24p 8:24p 9:24p 10:31p 11:24p\n",
+      "Sunnyvale 7:35a 9:28a 10:28a 11:28a 12:28p 1:28p 2:28p 3:28p 4:28p 5:28p 6:28p 7:28p 8:28p 9:28p 10:35p 11:28p\n",
+      "Mountain View 7:40a 9:34a 10:34a 11:34a 12:34p 1:34p 2:34p 3:34p 4:34p 5:34p 6:34p 7:34p 8:34p 9:34p 10:40p 11:34p\n",
+      "San Antonio 7:43a 9:37a 10:37a 11:37a 12:37p 1:37p 2:37p 3:37p 4:37p 5:37p 6:37p 7:37p 8:37p 9:37p 10:44p 11:37p\n",
+      "California Ave 7:48a 9:42a 10:42a 11:42a 12:42p 1:42p 2:42p 3:42p 4:42p 5:42p 6:42p 7:42p 8:42p 9:42p 10:48p 11:42p\n",
+      "Palo Alto 7:52a 9:46a 10:46a 11:46a 12:46p 1:46p 2:46p 3:46p 4:46p 5:46p 6:46p 7:46p 8:46p 9:46p 10:53p 11:46p\n",
+      "Menlo Park 7:55a 9:50a 10:50a 11:50a 12:50p 1:50p 2:50p 3:50p 4:50p 5:50p 6:50p 7:50p 8:50p 9:50p 10:56p 11:50p\n",
+      "Redwood City 8:01a 9:56a 10:56a 11:56a 12:56p 1:56p 2:56p 3:56p 4:56p 5:56p 6:56p 7:56p 8:56p 9:56p 11:02p 11:56p\n",
+      "San Carlos 8:05a 10:01a 11:01a 12:01p 1:01p 2:01p 3:01p 4:01p 5:01p 6:01p 7:01p 8:01p 9:01p 10:01p 11:07p 12:01a\n",
+      "Belmont 8:09a 10:04a 11:04a 12:04p 1:04p 2:04p 3:04p 4:04p 5:04p 6:04p 7:04p 8:04p 9:04p 10:04p 11:10p 12:04a\n",
+      "Hillsdale 8:12a 10:08a 11:08a 12:08p 1:08p 2:08p 3:08p 4:08p 5:08p 6:08p 7:08p 8:08p 9:08p 10:08p 11:14p 12:08a\n",
+      "Hayward Park 8:15a 10:11a 11:11a 12:11p 1:11p 2:11p 3:11p 4:11p 5:11p 6:11p 7:11p 8:11p 9:11p 10:11p 11:17p 12:11a\n",
+      "San Mateo 8:19a 10:15a 11:15a 12:15p 1:15p 2:15p 3:15p 4:15p 5:15p 6:15p 7:15p 8:15p 9:15p 10:15p 11:21p 12:15a\n",
+      "Burlingame 8:22a 10:19a 11:19a 12:19p 1:19p 2:19p 3:19p 4:19p 5:19p 6:19p 7:19p 8:19p 9:19p 10:19p 11:25p 12:19a\n",
+      "Broadway 8:25a 10:22a 11:22a 12:22p 1:22p 2:22p 3:22p 4:22p 5:22p 6:22p 7:22p 8:22p 9:22p 10:22p 11:28p 12:22a\n",
+      "Millbrae 8:29a 10:26a 11:26a 12:26p 1:26p 2:26p 3:26p 4:26p 5:26p 6:26p 7:26p 8:26p 9:26p 10:26p 11:32p 12:26a\n",
+      "San Bruno 8:34a 10:30a 11:30a 12:30p 1:30p 2:30p 3:30p 4:30p 5:30p 6:30p 7:30p 8:30p 9:30p 10:30p 11:37p 12:30a\n",
+      "S. San Francisco 8:38a 10:34a 11:34a 12:34p 1:34p 2:34p 3:34p 4:34p 5:34p 6:34p 7:34p 8:34p 9:34p 10:34p 11:41p 12:34a\n",
+      "Bayshore 8:44a 10:41a 11:41a 12:41p 1:41p 2:41p 3:41p 4:41p 5:41p 6:41p 7:41p 8:41p 9:41p 10:41p 11:47p 12:41a\n",
+      "22nd Street 8:50a 10:46a 11:46a 12:46p 1:46p 2:46p 3:46p 4:46p 5:46p 6:46p 7:46p 8:46p 9:46p 10:46p 11:53p 12:46a\n",
+      "San Francisco 8:56a 10:52a 11:53a 12:53p 1:52p 2:52p 3:52p 4:52p 5:52p 6:52p 7:52p 8:52p 9:52p 10:52p 11:59p 12:52aZONE 2 ZONE 3 ZONE 4 ZONE 4 ZONE 3 ZONE 2 ZONE 1 ZONE 12XX Local\n",
+      "2XX Local\n",
+      "EFFECTIVE September 12, 2022  Timetable subject to change without notice. *On SAP Center event days, Train 277 or Train 281departure from San Jose Diridon station may be delayed and will depart no later than 10:30p or 11:30p respectively.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(base_docs[0].get_content())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "42203c70-7ca7-4200-bf47-6282eefca3bf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_response = base_query_engine.query(\n",
+    "    \"What are the stops (and times) for train no 237 northbound?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "06aa47b6-0f31-4b2d-90f0-bf6c74befd38",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Train No. 237 northbound stops at the following stations and times:\n",
+      "\n",
+      "- Tamien: 1:05p\n",
+      "- San Jose Diridon: 1:12p\n",
+      "- Santa Clara: 1:18p\n",
+      "- Lawrence: 1:24p\n",
+      "- Sunnyvale: 1:28p\n",
+      "- Mountain View: 1:34p\n",
+      "- San Antonio: 1:37p\n",
+      "- California Ave: 1:42p\n",
+      "- Palo Alto: 1:46p\n",
+      "- Menlo Park: 1:50p\n",
+      "- Redwood City: 1:56p\n",
+      "- San Carlos: 2:01p\n",
+      "- Belmont: 2:04p\n",
+      "- Hillsdale: 2:08p\n",
+      "- Hayward Park: 2:11p\n",
+      "- San Mateo: 2:15p\n",
+      "- Burlingame: 2:19p\n",
+      "- Broadway: 2:22p\n",
+      "- Millbrae: 2:26p\n",
+      "- San Bruno: 2:30p\n",
+      "- S. San Francisco: 2:34p\n",
+      "- Bayshore: 2:41p\n",
+      "- 22nd Street: 2:46p\n",
+      "- San Francisco: 2:52p\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(str(base_response))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4f3c1de7-3351-4cd8-991c-34a777952194",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_response = base_query_engine.query(\n",
+    "    \"What are all the trains (and times) that end at Tamien going Southbound?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "513b1007-7508-4fb1-836c-de9353433a67",
+   "metadata": {},
+   "source": [
+    "Note that the trains don't line up with the times!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "108edb92-76af-406b-a139-8b9e7c6528f2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The trains that end at Tamien going Southbound are:\n",
+      "\n",
+      "- Train 224 at 10:15a\n",
+      "- Train 228 at 11:45a\n",
+      "- Train 240 at 2:45p\n",
+      "- Train 252 at 4:45p\n",
+      "- Train 264 at 6:45p\n",
+      "- Train 276 at 8:45p\n",
+      "- Train 284 at 10:45p\n",
+      "- Train 284 at 12:44a\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(str(base_response))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama_parse",
+   "language": "python",
+   "name": "llama_parse"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/parse/demo_advanced.ipynb

@@ -0,0 +1,618 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Advanced RAG with LlamaParse\n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/demo_advanced.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "This notebook is a complete walkthrough for using LlamaParse with advanced indexing/retrieval techniques in LlamaIndex over the Apple 10K Filing. \n",
+    "\n",
+    "This allows us to ask sophisticated questions that aren't possible with \"naive\" parsing/indexing techniques with existing models."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-index llama-cloud-services"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!wget \"https://s2.q4cdn.com/470004039/files/doc_financials/2021/q4/_10-K-2021-(As-Filed).pdf\" -O apple_2021_10k.pdf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Some OpenAI and LlamaParse details"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "# API access to llama-cloud\n",
+    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"llx-...\"\n",
+    "\n",
+    "# Using OpenAI API for embeddings/llms\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"sk-proj-...\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.llms.openai import OpenAI\n",
+    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
+    "from llama_index.core import Settings\n",
+    "\n",
+    "embed_model = OpenAIEmbedding(model_name=\"text-embedding-3-small\")\n",
+    "llm = OpenAI(model=\"gpt-4o-mini\")\n",
+    "\n",
+    "Settings.llm = llm\n",
+    "Settings.embed_model = embed_model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Using brand new `LlamaParse` PDF reader for PDF Parsing\n",
+    "\n",
+    "We also compare three different retrieval/query engine strategies:\n",
+    "1. Baseline using default parsing from `SimpleDirectoryReader`\n",
+    "2. Using raw markdown text as nodes for building index and apply simple query engine for generating the results;\n",
+    "3. Using markdown + page screenshots to help retrieve the proper nodes."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id e403a457-1721-4093-82bf-4a316d2d637a\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_cloud_services import LlamaParse\n",
+    "\n",
+    "result = await LlamaParse(take_screenshot=True).aparse(\"./apple_2021_10k.pdf\")\n",
+    "\n",
+    "markdown_nodes = await result.aget_markdown_nodes(split_by_page=True)\n",
+    "screenshot_image_nodes = await result.aget_image_nodes(\n",
+    "    include_screenshot_images=True,\n",
+    "    include_object_images=False,\n",
+    "    image_download_dir=\"./images\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import SimpleDirectoryReader\n",
+    "\n",
+    "baseline_documents = SimpleDirectoryReader(\n",
+    "    input_files=[\"apple_2021_10k.pdf\"]\n",
+    ").load_data()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup Baseline Index\n",
+    "\n",
+    "For comparison, we setup a naive RAG pipeline with default parsing and standard chunking, indexing, retrieval."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import VectorStoreIndex\n",
+    "\n",
+    "baseline_index = VectorStoreIndex.from_documents(baseline_documents)\n",
+    "baseline_query_engine = baseline_index.as_query_engine(similarity_top_k=3)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup our LlamaParse Indexes\n",
+    "\n",
+    "Using both the markdown and screenshot images, we can build two different indexes.\n",
+    "\n",
+    "1. An index over just the markdown documents\n",
+    "2. A custom index that uses the markdown + screenshot images to help with response quality."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import VectorStoreIndex\n",
+    "\n",
+    "markdown_index = VectorStoreIndex(nodes=markdown_nodes)\n",
+    "markdown_query_engine = markdown_index.as_query_engine(similarity_top_k=3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.indices import MultiModalVectorStoreIndex\n",
+    "from llama_index.embeddings.huggingface import HuggingFaceEmbedding\n",
+    "from llama_index.core import Settings\n",
+    "\n",
+    "# could also use other API-based multimodal models like voyageai or jinaai\n",
+    "# Note: this may take quite a while if running on CPU!\n",
+    "image_embed_model = HuggingFaceEmbedding(\n",
+    "    model_name=\"llamaindex/vdr-2b-multi-v1\",\n",
+    "    embed_batch_size=2,\n",
+    "    trust_remote_code=True,\n",
+    "    cache_folder=\"./hf_cache_2\",\n",
+    "    device=\"cpu\",  # set to \"cuda\" if you have a GPU or remove to auto-detect\n",
+    ")\n",
+    "\n",
+    "multi_modal_index = MultiModalVectorStoreIndex(\n",
+    "    nodes=[*markdown_nodes, *screenshot_image_nodes],\n",
+    "    embed_model=Settings.embed_model,\n",
+    "    image_embed_model=image_embed_model,\n",
+    "    show_progress=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Below, we will create a custom query engine that does a few things\n",
+    "1. Retrieves both image nodes and text nodes\n",
+    "2. Combines them into two lists -- one where images and texts come from the same page, and one where we have texts alone\n",
+    "3. Use a Jinja-based `RichPromptTemplate` to format the retrieved content automatically into a list of multimodal chat messages\n",
+    "4. Send our messages to the LLM and return a result\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.async_utils import asyncio_run\n",
+    "from llama_index.core.llms import LLM\n",
+    "from llama_index.core.query_engine import CustomQueryEngine\n",
+    "from llama_index.core.prompts import RichPromptTemplate\n",
+    "from llama_index.core.response import Response\n",
+    "from llama_index.core.schema import NodeWithScore\n",
+    "from llama_index.core import Settings\n",
+    "\n",
+    "TEXT_IMAGE_PROMPT_TEMPLATE = RichPromptTemplate(\n",
+    "    \"\"\"\n",
+    "<context>\n",
+    "Here is some retrieved content from a knowledge base:\n",
+    "{% for image_path, text in images_and_texts %}\n",
+    "<page>\n",
+    "<text>{{ text }}</text>\n",
+    "<image>{{ image_path | image }}</image>\n",
+    "</page>\n",
+    "{% endfor %}\n",
+    "{% for text in texts %}\n",
+    "<page>\n",
+    "<text>{{ text }}</text>\n",
+    "</page>\n",
+    "{% endfor %}\n",
+    "</context>\n",
+    "\n",
+    "Using the context, answer the following question:\n",
+    "<query>{{ query_str }}</query>\n",
+    "\"\"\"\n",
+    ")\n",
+    "\n",
+    "\n",
+    "class SimpleMultiModalQueryEngine(CustomQueryEngine):\n",
+    "    def __init__(\n",
+    "        self,\n",
+    "        index: MultiModalVectorStoreIndex,\n",
+    "        image_top_k: int = 4,\n",
+    "        text_top_k: int = 4,\n",
+    "        llm: LLM | None = None,\n",
+    "        **kwargs\n",
+    "    ):\n",
+    "        super().__init__(**kwargs)\n",
+    "        self._retriever = index.as_retriever(\n",
+    "            similarity_top_k=text_top_k, image_similarity_top_k=image_top_k\n",
+    "        )\n",
+    "        self._llm = llm or Settings.llm\n",
+    "\n",
+    "    def _match_images_and_texts(\n",
+    "        self, text_results: list[NodeWithScore], image_results: list[NodeWithScore]\n",
+    "    ) -> tuple[list[NodeWithScore], list[NodeWithScore]]:\n",
+    "        # combine results, prioritize images and texts\n",
+    "        # if both an image and matching text was retrieved, that is a strong indicator\n",
+    "        images_and_texts = []\n",
+    "        text_keys = {\n",
+    "            (x.metadata[\"page_number\"], x.metadata[\"file_name\"]): x\n",
+    "            for x in text_results\n",
+    "        }\n",
+    "        for image_result in image_results:\n",
+    "            key = (\n",
+    "                image_result.metadata[\"page_number\"],\n",
+    "                image_result.metadata[\"file_name\"],\n",
+    "            )\n",
+    "            # add matching text to results if available\n",
+    "            if key in text_keys:\n",
+    "                text_result = text_keys[key]\n",
+    "                images_and_texts.append(\n",
+    "                    (image_result.node.image_path, text_result.node.text)\n",
+    "                )\n",
+    "\n",
+    "                # remove from list\n",
+    "                text_keys.pop(key)\n",
+    "\n",
+    "        # get the remaining texts as a fallback\n",
+    "        texts = [result.node.text for result in text_keys.values()]\n",
+    "\n",
+    "        return images_and_texts, texts\n",
+    "\n",
+    "    def custom_query(self, query_str: str) -> Response:\n",
+    "        # wrap the async method to avoid code duplication\n",
+    "        # asyncio_run is a slightly safer asyncio.run() call\n",
+    "        return asyncio_run(self.acustom_query(query_str))\n",
+    "\n",
+    "    async def acustom_query(self, query_str: str) -> Response:\n",
+    "        text_results = await self._retriever.atext_retrieve(query_str)\n",
+    "        image_results = await self._retriever.atext_to_image_retrieve(query_str)\n",
+    "\n",
+    "        images_and_texts, texts = self._match_images_and_texts(\n",
+    "            text_results, image_results\n",
+    "        )\n",
+    "        messages = TEXT_IMAGE_PROMPT_TEMPLATE.format_messages(\n",
+    "            images_and_texts=images_and_texts, texts=texts, query_str=str(query_str)\n",
+    "        )\n",
+    "\n",
+    "        response = await self._llm.achat(messages)\n",
+    "\n",
+    "        return Response(\n",
+    "            response.message.content, source_nodes=[*text_results, *image_results]\n",
+    "        )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "multimodal_query_engine = SimpleMultiModalQueryEngine(\n",
+    "    index=multi_modal_index,\n",
+    "    image_top_k=3,\n",
+    "    text_top_k=3,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Try out the Query Engines and Compare!\n",
+    "\n",
+    "Now with our three query engines assembled, we can compare each approach with a rough \"vibes-based\" evaluation."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "***********Baseline Query Engine***********\n",
+      "The total fair value of marketable securities in 2020 was $190,516 million.\n",
+      "\n",
+      "***********Markdown Query Engine***********\n",
+      "The total fair value of marketable securities in 2020 was $191,830 million.\n",
+      "\n",
+      "***********MultiModal Query Engine***********\n",
+      "The total fair value of marketable securities in 2020 was $191,830 million.\n"
+     ]
+    }
+   ],
+   "source": [
+    "query = \"What were the total fair value of marketable securities in 2020\"\n",
+    "\n",
+    "response_1 = await baseline_query_engine.aquery(query)\n",
+    "print(\"\\n***********Baseline Query Engine***********\")\n",
+    "print(response_1)\n",
+    "\n",
+    "response_2 = await markdown_query_engine.aquery(query)\n",
+    "print(\"\\n***********Markdown Query Engine***********\")\n",
+    "print(response_2)\n",
+    "\n",
+    "response_3 = await multimodal_query_engine.aquery(query)\n",
+    "print(\"\\n***********MultiModal Query Engine***********\")\n",
+    "print(response_3)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "As we can see, the multimodal and markdown query engines are able to retrieve the correct content, while the default query engine struggles to find the correct total value."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We can also inspect the source nodes, and see the pages that were retrieved. Here is the correct page for the total fair value of marketable securities in 2020:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'images/page_41.jpg'"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "response_3.source_nodes[4].node.image_path"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Lets try a few more queries to see how the query engines perform."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "***********Baseline Query Engine***********\n",
+      "The effective interest rates for the debt issuances in 2021 were as follows:\n",
+      "\n",
+      "- Floating-rate notes: 0.48% – 0.63%\n",
+      "- Fixed-rate notes: 0.03% – 4.78% for maturities from 2022 to 2060\n",
+      "- Fixed-rate notes issued in the second quarter: 0.75% – 2.81% for maturities from 2026 to 2061\n",
+      "- Fixed-rate notes issued in the fourth quarter: 1.43% – 2.86% for maturities from 2028 to 2061\n",
+      "\n",
+      "***********Markdown Query Engine***********\n",
+      "The effective interest rates for the debt issuances in 2021 were as follows:\n",
+      "\n",
+      "- Floating-rate notes: 0.48% – 0.63%\n",
+      "- Fixed-rate notes: 0.03% – 4.78% for the 0.000% – 4.650% notes, 0.75% – 2.81% for the 0.700% – 2.800% notes, and 1.43% – 2.86% for the 1.400% – 2.850% notes.\n",
+      "\n",
+      "***********MultiModal Query Engine***********\n",
+      "The effective interest rates of all debt issuances in 2021 were as follows:\n",
+      "\n",
+      "1. **Floating-rate notes**: 0.48% – 0.63%\n",
+      "2. **Fixed-rate 0.000% – 4.650% notes**: 0.03% – 4.78%\n",
+      "3. **Fixed-rate 0.700% – 2.800% notes**: 0.75% – 2.81%\n",
+      "4. **Fixed-rate 1.400% – 2.850% notes**: 1.43% – 2.86%\n"
+     ]
+    }
+   ],
+   "source": [
+    "query = \"What were the effective interest rates of all debt issuances in 2021\"\n",
+    "\n",
+    "response_1 = await baseline_query_engine.aquery(query)\n",
+    "print(\"\\n***********Baseline Query Engine***********\")\n",
+    "print(response_1)\n",
+    "\n",
+    "response_2 = await markdown_query_engine.aquery(query)\n",
+    "print(\"\\n***********Markdown Query Engine***********\")\n",
+    "print(response_2)\n",
+    "\n",
+    "response_3 = await multimodal_query_engine.aquery(query)\n",
+    "print(\"\\n***********MultiModal Query Engine***********\")\n",
+    "print(response_3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "***********Baseline Query Engine***********\n",
+      "The federal deferred tax amounts for the years 2019 to 2021 are as follows (in millions):\n",
+      "\n",
+      "- **2019**: $(2,939)\n",
+      "- **2020**: $(3,619)\n",
+      "- **2021**: $(7,176)\n",
+      "\n",
+      "These figures represent the deferred tax expense for each respective year.\n",
+      "\n",
+      "***********Markdown Query Engine***********\n",
+      "As of September 25, 2021, the total deferred tax assets and liabilities for the years 2021 and 2020 are as follows:\n",
+      "\n",
+      "**Deferred Tax Assets:**\n",
+      "- 2021: $25,176 million\n",
+      "- 2020: $19,336 million\n",
+      "\n",
+      "**Deferred Tax Liabilities:**\n",
+      "- 2021: $7,200 million\n",
+      "- 2020: $10,138 million\n",
+      "\n",
+      "**Net Deferred Tax Assets:**\n",
+      "- 2021: $13,073 million\n",
+      "- 2020: $8,157 million\n",
+      "\n",
+      "The information for 2019 is not provided in the context.\n",
+      "\n",
+      "***********MultiModal Query Engine***********\n",
+      "The federal deferred tax assets and liabilities for the years 2019 to 2021 are as follows:\n",
+      "\n",
+      "### Deferred Tax Assets (in millions):\n",
+      "- **2021**: $25,176\n",
+      "- **2020**: $19,336\n",
+      "- **2019**: Not specified in the provided content.\n",
+      "\n",
+      "### Deferred Tax Liabilities (in millions):\n",
+      "- **2021**: $7,200\n",
+      "- **2020**: $10,138\n",
+      "- **2019**: Not specified in the provided content.\n",
+      "\n",
+      "### Net Deferred Tax Assets (in millions):\n",
+      "- **2021**: $13,073\n",
+      "- **2020**: $8,157\n",
+      "- **2019**: Not specified in the provided content.\n",
+      "\n",
+      "The significant components of deferred tax assets and liabilities reflect the effects of tax credits and temporary differences between financial statement carrying amounts and their respective tax bases.\n"
+     ]
+    }
+   ],
+   "source": [
+    "query = \"federal deferred tax in 2019-2021\"\n",
+    "\n",
+    "response_1 = await baseline_query_engine.aquery(query)\n",
+    "print(\"\\n***********Baseline Query Engine***********\")\n",
+    "print(response_1)\n",
+    "\n",
+    "response_2 = await markdown_query_engine.aquery(query)\n",
+    "print(\"\\n***********Markdown Query Engine***********\")\n",
+    "print(response_2)\n",
+    "\n",
+    "response_3 = await multimodal_query_engine.aquery(query)\n",
+    "print(\"\\n***********MultiModal Query Engine***********\")\n",
+    "print(response_3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "***********Baseline Query Engine***********\n",
+      "The current state taxes for the years 2019 to 2021 are as follows (in millions):\n",
+      "\n",
+      "- 2021: $1,620\n",
+      "- 2020: $455\n",
+      "- 2019: $475\n",
+      "\n",
+      "This indicates an increase of $1,165 million from 2020 to 2021, a decrease of $20 million from 2018 to 2019, and an increase of $80 million from 2019 to 2020.\n",
+      "\n",
+      "***********Markdown Query Engine***********\n",
+      "The current state taxes for the years 2019 to 2021 are as follows (in millions):\n",
+      "\n",
+      "- **2021**: $1,620\n",
+      "- **2020**: $455\n",
+      "- **2019**: $475\n",
+      "\n",
+      "The changes in current state taxes from year to year are:\n",
+      "\n",
+      "- From 2019 to 2020: Decrease of $20 million\n",
+      "- From 2020 to 2021: Increase of $1,165 million\n",
+      "\n",
+      "***********MultiModal Query Engine***********\n",
+      "The current state taxes for the years 2019 to 2021 are as follows (in millions):\n",
+      "\n",
+      "- **2021**: $1,620\n",
+      "- **2020**: $455\n",
+      "- **2019**: $475\n",
+      "\n",
+      "So, the changes are:\n",
+      "- From 2019 to 2020: Decrease of $20 million\n",
+      "- From 2020 to 2021: Increase of $1,165 million\n"
+     ]
+    }
+   ],
+   "source": [
+    "query = \"current state taxes per year in 2019-2021 (include +/-)\"\n",
+    "\n",
+    "response_1 = await baseline_query_engine.aquery(query)\n",
+    "print(\"\\n***********Baseline Query Engine***********\")\n",
+    "print(response_1)\n",
+    "\n",
+    "response_2 = await markdown_query_engine.aquery(query)\n",
+    "print(\"\\n***********Markdown Query Engine***********\")\n",
+    "print(response_2)\n",
+    "\n",
+    "response_3 = await multimodal_query_engine.aquery(query)\n",
+    "print(\"\\n***********MultiModal Query Engine***********\")\n",
+    "print(response_3)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama-parse-aNC435Vv-py3.10",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

examples/parse/demo_api.ipynb

@@ -11,7 +11,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -38,7 +38,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -47,7 +47,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -88,7 +88,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -128,10 +128,8 @@
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.5"
-  },
-  "orig_nbformat": 4
+   "pygments_lexer": "ipython3"
+  }
  },
  "nbformat": 4,
  "nbformat_minor": 2

examples/parse/demo_basic.ipynb

@@ -0,0 +1,196 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# LlamaParse Usage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-index llama-cloud-services"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!wget \"https://arxiv.org/pdf/1706.03762.pdf\" -O \"./attention.pdf\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"llx-...\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id 79ae653c-4598-4bd0-ba6e-b3dab7eab57e\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_cloud_services import LlamaParse\n",
+    "\n",
+    "result = await LlamaParse().aparse(\"./attention.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1   Introduction\n",
+      "Recurrent neural networks, long short-term memory [13] and gated recurrent [7] neural networks\n",
+      "in particular, have been firmly established as state of the art approaches in sequence modeling and\n",
+      "transduction problems such as language modeling and machine translation [35, 2, 5]. Numerous\n",
+      "efforts have since continued to push the boundaries of recurrent language models and encoder-decoder\n",
+      "architectures [38, 24, 15].\n",
+      "Recurrent models typically factor computation along the symbol positions of the input and output\n",
+      "sequences. Aligning the positions to steps in computation time, they generate a sequence of hidden\n",
+      "states ht, as a function of the previous hidden state ht−1 and the input for position t. This inherently\n",
+      "sequential nature precludes parallelization within training examples, which becomes critical at longer\n",
+      "sequence lengths, as memory constraints limit batching across examples. Recent work has achieved\n",
+      "significant improvements in computational efficiency through factorization tricks [21] and conditional\n",
+      "computation [32], while also improving model performance in case of the latter. The fundamental\n",
+      "constraint of sequential computation, however, remains.\n",
+      "Attention mechanisms have become an integral part of compelling sequence modeling and transduc-\n",
+      "tion models in various tasks, allowing modeling of dependencies without regard to their distance in\n",
+      "the input or output sequences [2, 19]. In all but a few cases [27], however, such attention mechanisms\n",
+      "are used in conjunction with a recurrent network.\n",
+      "In this work we propose the Transformer, a model architecture eschewing recurrence and instead\n",
+      "relying entirely on an attention mechanism to draw global dependencies between input and output.\n",
+      "The Transformer allows for significantly more parallelization and can reach a new state of the art in\n",
+      "translation quality after being trained for as little as twelve hours on eight P100 GPUs.\n",
+      "2   Background\n",
+      "The goal of reducing sequential computation also forms the foundation of the Extended Neural GPU\n",
+      "[16], ByteNet [18] and ConvS2S [9], all of which use convolutional neural networks as basic building\n",
+      "block, computing hidden representations in parallel for all input and output positions. In these models,\n",
+      "the number of operations required to relate signals from two arbitrary input or output positions grows\n",
+      "in the distance between positions, linearly for ConvS2S and logarithmically for ByteNet. This makes\n",
+      "it more difficult to learn dependencies between distant positions [12]. In the Transformer this is\n",
+      "reduced to a constant number of operations, albeit at the cost of reduced effective resolution due\n",
+      "to averaging attention-weighted positions, an effect we counteract with Multi-Head Attention as\n",
+      "described in section 3.2.\n",
+      "Self-attention, sometimes called intra-attention is an attention mechanism relating different positions\n",
+      "of a single sequence in order to compute a representation of the sequence. Self-attention has been\n",
+      "used successfully in a variety of tasks including reading comprehension, abstractive summarization,\n",
+      "textual entailment and learning task-independent sentence representations [4, 27, 28, 22].\n",
+      "End-to-end memory networks are based on a recurrent attention mechanism instead of sequence-\n",
+      "aligned recurrence and have been shown to perform well on simple-language question answering and\n",
+      "language modeling tasks [34].\n",
+      "To the best of our knowledge, however, the Transformer is the first transduction model relying\n",
+      "entirely on self-attention to compute representations of its input and output without using sequence-\n",
+      "aligned RNNs or convolution. In the following sections, we will describe the Transformer, motivate\n",
+      "self-attention and discuss its advantages over models such as [17, 18] and [9].\n",
+      "3   Model Architecture\n",
+      "Most competitive neural sequence transduction models have an encoder-decoder structure [5, 2, 35].\n",
+      "Here, the encoder maps an input sequence of symbol representations (x1, ..., xn) to a sequence\n",
+      "of continuous representations z = (z1, ..., zn). Given z, the decoder then generates an output\n",
+      "sequence (y1, ..., ym) of symbols one element at a time. At each step the model is auto-regressive\n",
+      "[10], consuming the previously generated symbols as additional input when generating the next.\n",
+      "                                                2\n"
+     ]
+    }
+   ],
+   "source": [
+    "documents = result.get_text_documents(split_by_page=True)\n",
+    "print(documents[1].text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "arXiv:1706.03762v7  [cs.CL]  2 Aug 2023\n",
+      "\n",
+      "Provided proper attribution is provided, Google hereby grants permission to reproduce the tables and figures in this paper solely for use in journalistic or scholarly works.\n",
+      "\n",
+      "# Attention Is All You Need\n",
+      "\n",
+      "Ashish Vaswani∗        Noam Shazeer∗           Niki Parmar∗        Jakob Uszkoreit∗\n",
+      "\n",
+      "Google Brain        Google Brain         Google Research       Google Research\n",
+      "\n",
+      "avaswani@google.com   noam@google.com        nikip@google.com      usz@google.com\n",
+      "\n",
+      "Llion Jones∗                Aidan N. Gomez∗ †               Łukasz Kaiser∗\n",
+      "\n",
+      "Google Research         University of Toronto                Google Brain\n",
+      "\n",
+      "llion@google.com      aidan@cs.toronto.edu           lukaszkaiser@google.com\n",
+      "\n",
+      "Illia Polosukhin∗ ‡\n",
+      "\n",
+      "illia.polosukhin@gmail.com\n",
+      "\n",
+      "# Abstract\n",
+      "\n",
+      "The dominant sequence transduction models are based on complex recurrent or convolutional neural networks that include an encoder and a decoder. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles, by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.\n",
+      "\n",
+      "∗Equal contribution. Listing order is random. Jakob proposed replacing RNNs with self-attention and started the effort to evaluate this idea. Ashish, with Illia, designed and implemented the first Transformer models and has been crucially involved in every aspect of this work. Noam proposed scaled dot-product attention, multi-head attention and the parameter-free position representation and became the other person involved in nearly every detail. Niki designed, implemented, tuned and evaluated countless model variants in our original codebase and tensor2tensor. Llion also experimented with novel model variants, was responsible for our initial codebase, and efficient inference and visualizations. Lukasz and Aidan spent countless long days designing various parts of and implementing tensor2tensor, replacing our earlier codebase, greatly improving results and massively accelerating our research.\n",
+      "\n",
+      "†Work performed while at Google Brain.\n",
+      "\n",
+      "‡Work performed while at Google Research.\n",
+      "\n",
+      "31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.\n"
+     ]
+    }
+   ],
+   "source": [
+    "documents = result.get_markdown_documents(split_by_page=True)\n",
+    "print(documents[0].text)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

examples/parse/demo_insurance.ipynb

@@ -0,0 +1,531 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# LlamaParse - Fast checking Insurance Contract for Coverage\n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/demo_insurance.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "In this notebook we will look at how LlamaParse can be used to extract structured coverage information from an insurance policy."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Installation of required packages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-index llama-parse"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Download an insurance policy fron IRDAI\n",
+    "\n",
+    "The Insurance Regulatory and Development Authority of India (IRDAI) maintains a great resource: https://policyholder.gov.in/web/guest/non-life-insurance-products where all insurance policies available in India are publicly available for download! Let's download a complex health insurance policy as an example."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!wget \"https://policyholder.gov.in/documents/37343/931203/NBHTGBP22011V012223.pdf/c392bcc1-f6a8-cadd-ab84-495b3273d2c3?version=1.0&t=1669350459879&download=true\" -O \"./policy.pdf\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Initializing LlamaIndex and LlamaParse"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# llama-parse is async-first, running the sync code in a notebook requires the use of nest_asyncio\n",
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"llx-...\"\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"sk-...\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.llms.openai import OpenAI\n",
+    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
+    "from llama_index.core import VectorStoreIndex\n",
+    "from llama_index.core import Settings\n",
+    "\n",
+    "# for the purpose of this example, we will use the small model embedding and gpt3.5\n",
+    "embed_model = OpenAIEmbedding(model=\"text-embedding-3-small\")\n",
+    "llm = OpenAI(model=\"gpt-3.5-turbo-0125\")\n",
+    "\n",
+    "Settings.llm = llm"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Vanilla Approach - Parse the Policy with LlamaParse into Markdown"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id b8946573-c911-4e00-8921-1bad1cda3d64\n",
+      "......"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_cloud_services import LlamaParse\n",
+    "\n",
+    "documents = LlamaParse(result_type=\"markdown\").load_data(\"./policy.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "## Preamble\n",
+      "\n",
+      "This ‘Travel Infinity’ Policy is a contract of insurance between You and Us which is subject to payment of full premium in advance and the terms, conditions and exclusions of this Policy. Expense incurred outside the policy period will NOT be covered. Unutilized Sum Insured will expire at the end of the policy year. All applicable benefits, details and limits are mentioned in your Certificate of insurance. We will cover only allopathic treatments in this policy.\n",
+      "\n",
+      "## Defined Terms\n",
+      "\n",
+      "The terms listed below in this Section and used elsewhere in the Policy in Initial Capitals shall have the meaning set out against them in this Section.\n",
+      "\n",
+      "### Standard Definitions\n",
+      "\n",
+      "|2.1|Accident or Accidental|means sudden, unforeseen and involuntary event caused by external, visible and violent means.|\n",
+      "|---|---|---|\n",
+      "|2.2|Co-payment|means a cost sharing requirement under a health insurance policy that provides that the policyholder/insured will bear a specified percentage of the admissible claims a\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(documents[0].text[0:1000])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Markdown Element Node Parser\n",
+    "Our markdown element node parser works well for parsing the markdown output of LlamaParse into a set of table and text nodes."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.node_parser import MarkdownElementNodeParser\n",
+    "\n",
+    "node_parser = MarkdownElementNodeParser(\n",
+    "    llm=OpenAI(model=\"gpt-3.5-turbo-0125\"), num_workers=8\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nodes = node_parser.get_nodes_from_documents(documents)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_nodes, objects = node_parser.get_nodes_and_objects(nodes)\n",
+    "\n",
+    "recursive_index = VectorStoreIndex(nodes=base_nodes + objects)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_engine = recursive_index.as_query_engine(similarity_top_k=25)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Querying the model for coverage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "You are covered for the expenses incurred on any alternate travel booking under any mode of transport, up to the limit of the Sum Insured as mentioned in the Certificate of insurance, if the delay of the airlines was caused due to specific reasons outlined in the policy. The amount you are covered for will depend on the specific terms and conditions of your policy, including the maximum coverage limit specified in the Certificate of insurance.\n"
+     ]
+    }
+   ],
+   "source": [
+    "query_1 = \"My trip was delay and I paid 45, how much am I cover for?\"\n",
+    "\n",
+    "response_1 = query_engine.query(query_1)\n",
+    "print(str(response_1))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The information is split across the document which leads to retrieval issues. Let's try some parsing instructions to improve our result."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id ec9e77c9-6ad9-4c9b-9efb-c9f659b0d481\n",
+      "....."
+     ]
+    }
+   ],
+   "source": [
+    "documents_with_instruction = LlamaParse(\n",
+    "    result_type=\"markdown\",\n",
+    "    parsing_instruction=\"\"\"\n",
+    "This document is an insurance policy.\n",
+    "When a benefits/coverage/exlusion is describe in the document ammend to it add a text in the follwing benefits string format (where coverage could be an exclusion).\n",
+    "\n",
+    "For {nameofrisk} and in this condition {whenDoesThecoverageApply} the coverage is {coverageDescription}. \n",
+    "                                        \n",
+    "If the document contain a benefits TABLE that describe coverage amounts, do not ouput it as a table, but instead as a list of benefits string.\n",
+    "                                       \n",
+    "\"\"\",\n",
+    ").load_data(\"./policy.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Let see how the 2 parsing compare (change target page to explore)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "## Inpatient treatment\n",
+      "\n",
+      "Claim Form (filled and signed by pe Insured)\n",
+      "Hospital Daily Cash\n",
+      "Release of Medical information Form (filled and signed by pe Insured)\n",
+      "Waiver of Deductible\n",
+      "Original papological and diagnostic reports, discharge summary indoor case papers (if any) and prescriptions issued by pe treating Medical practitioner or Network Provider\n",
+      "Optional Co-payment\n",
+      "Adventure Sports Cover\n",
+      "Home to Home Cover\n",
+      "Passport and Visa copy wip Entry Stamp of Country of Visit and exit Stamp from India\n",
+      "Extension to in-patient care\n",
+      "Ambulance Charge\n",
+      "FIR report of police (if applicable)\n",
+      "\n",
+      "## Out-patient treatment\n",
+      "\n",
+      "Cancer Screening & Mammographic Examination\n",
+      "Original bills and receipts for:\n",
+      "1. Charges paid towards Hospital accommodation, nursing facilities, and oper medical services rendered\n",
+      "2. Fees paid to pe Medical Practitioner and for special nursing charges\n",
+      "3. Charges incurred towards any and all test and / or examinations rendered in connection wip pe treatment\n",
+      "4. Charges incurred towards medicines or drugs purchased from a registered pharmacy oper pan pe Network provider duly supported by pe prescriptions of pe Medical Practitioner attending to pe Insured Person\n",
+      "5. Any oper document as required by pe Company to assist pe Claim\n",
+      "\n",
+      "## Medical evacuation\n",
+      "\n",
+      "Medical reports and transportation details issued by the evacuation agency, prescriptions and medical report by the attending Medical Practitioner furnishing the name of the Insured Person and details of treatment rendered along with the statement confirming the necessity of evacuation.\n",
+      "\n",
+      "Documentary proof for expenses incurred towards the Medical Evacuation.\n",
+      "\n",
+      "## Compassionate visit\n",
+      "\n",
+      "A certificate from the Medical Practitioner recommending the presence in the form of special assistance to be rendered by an additional member during the entire period of hospitalization. The certificate shall also specify the minimum period in which person is admitted in the hospital.\n",
+      "\n",
+      "Discharge summary of the Hospital furnishing details including the date of admission and date of discharge.\n",
+      "\n",
+      "Stamped boarding pass with invoice used for the travel by the Immediate Family Member.\n",
+      "\n",
+      "Copy passport of Immediate Family Member with entry and exit stamp.\n",
+      "\n",
+      "## Escort of Minor Child\n",
+      "\n",
+      "A certificate from the Medical Practitioner specifying the minimum period of Hospitalization.\n",
+      "\n",
+      "Discharge summary of the Hospital furnishing details including the date of admission and date of discharge.\n",
+      "\n",
+      "Stamped Boarding pass used for the return travel of the child to the Country of Residence.\n",
+      "\n",
+      "Stamped Boarding pass of the attendant from the Country of Residence to the place of hospitalization (if attendant is necessary).\n",
+      "\n",
+      "Copy of passport of the child with entry and exit stamp.\n",
+      "\n",
+      "## Upgradation to Business Class\n",
+      "\n",
+      "A certificate from the Medical Practitioner specifying the minimum period of Hospitalization.\n",
+      "\n",
+      "Discharge summary of the Hospital furnishing the details including the date of admission and date of discharge.\n",
+      "\n",
+      "Product Name: Travel infinity | Product UIN: NBHTGBP22011V012223\n",
+      "\n",
+      "\n",
+      "=========================================================\n",
+      "\n",
+      "\n",
+      "# Insurance Policy\n",
+      "\n",
+      "## Benefits:\n",
+      "\n",
+      "- For Inpatient treatment and in this condition when admitted to a hospital, the coverage is reimbursement for medical expenses incurred.\n",
+      "- For Hospital Daily Cash and in this condition when hospitalized, the coverage is daily cash benefit.\n",
+      "- For Waiver of Deductible and in this condition when a deductible is applicable, the coverage is waiver of the deductible amount.\n",
+      "- For Optional Co-payment and in this condition when a co-payment is required, the coverage is optional co-payment.\n",
+      "- For Adventure Sports Cover and in this condition when participating in adventure sports, the coverage is coverage for injuries related to adventure sports.\n",
+      "- For Home to Home Cover and in this condition when requiring medical evacuation, the coverage is assistance for repatriation to home country.\n",
+      "- For Extension to in-patient care and in this condition when extended hospital stay is necessary, the coverage is extension of coverage for in-patient care.\n",
+      "- For Ambulance Charge and in this condition when ambulance services are utilized, the coverage is reimbursement for ambulance charges.\n",
+      "- For Out-patient treatment and in this condition when receiving outpatient medical care, the coverage is reimbursement for outpatient medical expenses.\n",
+      "- For Cancer Screening & Mammographic Examination and in this condition when undergoing cancer screening or mammographic examination, the coverage is coverage for these preventive services.\n",
+      "- For New Born baby Cover and in this condition when a newborn is covered under the policy, the coverage is medical expenses coverage for the newborn.\n",
+      "- For Maternity and in this condition when maternity services are required, the coverage is coverage for maternity expenses.\n",
+      "- For Complete pre-existing disease cover and in this condition when seeking treatment for pre-existing conditions, the coverage is coverage for pre-existing conditions.\n",
+      "- For Medical sum insured replenishment in case of hospitalization due to accident and in this condition when hospitalized due to an accident, the coverage is replenishment of the sum insured.\n",
+      "- For Waiver of sublimit for insured above 60 years of age and in this condition when the insured is above 60 years of age, the coverage is waiver of sublimits.\n",
+      "- For Psychiatric Counseling and in this condition when seeking psychiatric counseling, the coverage is coverage for psychiatric counseling services.\n",
+      "- For Physiotherapy and in this condition when undergoing physiotherapy, the coverage is coverage for physiotherapy sessions.\n",
+      "- For Terrorism cover and in this condition when affected by terrorism, the coverage is coverage for medical expenses related to terrorism incidents.\n",
+      "- For Medical tele-consultation and in this condition when consulting a medical practitioner remotely, the coverage is coverage for tele-consultation services.\n",
+      "- For Medical evacuation and in this condition when requiring medical evacuation, the coverage is coverage for medical evacuation services.\n",
+      "- For Compassionate visit and in this condition when requiring a compassionate visit, the coverage is coverage for travel expenses for a family member to visit.\n",
+      "- For Escort of Minor Child and in this condition when escorting a minor child for medical treatment, the coverage is coverage for escort services for the child.\n",
+      "- For Upgradation to Business Class and in this condition when requiring upgradation to business class for medical travel, the coverage is coverage for upgradation to business class.\n"
+     ]
+    }
+   ],
+   "source": [
+    "target_page = 45\n",
+    "pages_vanilla = documents[0].text.split(\"\\n---\\n\")\n",
+    "pages_with_instructions = documents_with_instruction[0].text.split(\"\\n---\\n\")\n",
+    "\n",
+    "print(pages_vanilla[target_page])\n",
+    "print(\"\\n\\n=========================================================\\n\\n\")\n",
+    "print(pages_with_instructions[target_page])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "node_parser_instruction = MarkdownElementNodeParser(\n",
+    "    llm=OpenAI(model=\"gpt-3.5-turbo-0125\"), num_workers=8\n",
+    ")\n",
+    "nodes_instruction = node_parser.get_nodes_from_documents(documents_with_instruction)\n",
+    "(\n",
+    "    base_nodes_instruction,\n",
+    "    objects_instruction,\n",
+    ") = node_parser_instruction.get_nodes_and_objects(nodes_instruction)\n",
+    "\n",
+    "recursive_index_instruction = VectorStoreIndex(\n",
+    "    nodes=base_nodes_instruction + objects_instruction\n",
+    ")\n",
+    "query_engine_instruction = recursive_index_instruction.as_query_engine(\n",
+    "    similarity_top_k=25\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Comparing Instruction-Augmented Parsing vs. Vanilla Parsing\n",
+    "\n",
+    "When we parse the document with natural language instructions to add context on insurance coverage, we are able to correctly answer a wide range of queries in our RAG pipeline. In contrast, a RAG pipeline built with the vanilla method is not able to answer these queries."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Vanilla:\n",
+      "You are covered for the amount you paid due to the trip delay, up to the limit specified in the certificate of insurance.\n",
+      "With instructions:\n",
+      "For Trip Delay coverage, you are covered for a fixed benefit amount as mentioned in the certificate of insurance for every block of hours of delay.\n"
+     ]
+    }
+   ],
+   "source": [
+    "query_1 = \"My trip was delayed and I paid 45, how much am I covered for?\"\n",
+    "\n",
+    "response_1 = query_engine.query(query_1)\n",
+    "print(\"Vanilla:\")\n",
+    "print(response_1)\n",
+    "\n",
+    "print(\"With instructions:\")\n",
+    "response_1_i = query_engine_instruction.query(query_1)\n",
+    "print(response_1_i)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Looking at the policy it says in list I that one expense not covered is Baby food"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Vanilla:\n",
+      "Baby food is not explicitly mentioned in the provided context information regarding insurance coverages and benefits.\n",
+      "With instructions:\n",
+      "Baby food is excluded from coverage according to the policy terms.\n"
+     ]
+    }
+   ],
+   "source": [
+    "query_2 = \"I just had a baby, is baby food covered?\"\n",
+    "\n",
+    "response_2 = query_engine.query(query_2)\n",
+    "print(\"Vanilla:\")\n",
+    "print(response_2)\n",
+    "\n",
+    "print(\"With instructions:\")\n",
+    "response_2_i = query_engine_instruction.query(query_2)\n",
+    "print(response_2_i)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Vanilla:\n",
+      "Gauze used in your operation would typically be covered under the \"Emergency In-patient Medical Treatment\" or \"Emergency In-patient Medical Treatment with OPD\" benefits of the policy.\n",
+      "With instructions:\n",
+      "Gauze is not covered for use in your operation as it falls under the category of items that are excluded from coverage in the insurance policy.\n"
+     ]
+    }
+   ],
+   "source": [
+    "query_3 = \"How is gauze used in my operation covered?\"\n",
+    "\n",
+    "response_3 = query_engine.query(query_3)\n",
+    "print(\"Vanilla:\")\n",
+    "print(response_3)\n",
+    "\n",
+    "print(\"With instructions:\")\n",
+    "response_3_i = query_engine_instruction.query(query_3)\n",
+    "print(response_3_i)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama_parse",
+   "language": "python",
+   "name": "llama_parse"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

examples/parse/demo_json.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# LlamaParse JSON Mode + Multimodal RAG\n",
     "\n",
-    "<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/demo_json.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/parse/demo_json.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
     "\n",
     "This notebook shows you how to use LlamaParse JSON mode with LlamaIndex to build a simple multimodal RAG pipeline.\n",
     "\n",
@@ -31,27 +31,22 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install llama-index\n",
-    "!pip install llama-index-core\n",
-    "!pip install llama-index-llms-anthropic llama-index-multi-modal-llms-anthropic\n",
-    "!pip install llama-index-embeddings-huggingface\n",
-    "!pip install llama-parse"
+    "%pip install llama-index\n",
+    "%pip install llama-index-core\n",
+    "%pip install llama-index-llms-anthropic\n",
+    "%pip install llama-index-embeddings-huggingface\n",
+    "%pip install llama-cloud-services"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "0879301c-ff91-4431-941a-6c0ef7cd8fe2",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
-    "# llama-parse is async-first, running the async code in a notebook requires the use of nest_asyncio\n",
-    "import nest_asyncio\n",
-    "nest_asyncio.apply()\n",
-    "\n",
     "import os\n",
+    "\n",
     "# API access to llama-cloud\n",
     "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"llx-\"\n",
     "\n",
@@ -63,23 +58,19 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "391e2d95-5569-4d73-9f16-5b59d7326f8d",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "from llama_index.llms.anthropic import Anthropic\n",
     "\n",
-    "llm = Anthropic(model=\"claude-3-opus-20240229\", temperature=0.0)"
+    "llm = Anthropic(model=\"claude-3-5-sonnet-20241022\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "id": "700f48e8-8b52-41f3-90f9-144d5fdd5c52",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "from llama_index.core import Settings\n",
@@ -102,12 +93,10 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "c39d408f-e885-4940-85c7-b09ca3bc7cb7",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
-    "!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/10q/uber_10q_march_2022.pdf' -O './uber_10q_march_2022.pdf'"
+    "!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/10q/uber_10q_march_2022.pdf' -O './uber_10q_march_2022.pdf'"
    ]
   },
   {
@@ -122,11 +111,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "9c9cd670-8229-4ad6-99a9-845bd82b7ec1",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -137,49 +124,25 @@
     }
    ],
    "source": [
-    "from llama_parse import LlamaParse\n",
+    "from llama_cloud_services import LlamaParse\n",
     "\n",
-    "parser = LlamaParse(verbose=True)\n",
-    "json_objs = parser.get_json_result(\"./uber_10q_march_2022.pdf\")\n",
-    "json_list = json_objs[0][\"pages\"]"
+    "parser = LlamaParse(take_screenshot=True)\n",
+    "result = await parser.aparse(\"./uber_10q_march_2022.pdf\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "id": "b26d21d1-05b5-4f49-b937-c13106a84015",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from llama_index.core.schema import TextNode\n",
-    "from typing import List\n",
-    "\n",
-    "\n",
-    "def get_text_nodes(json_list: List[dict]):\n",
-    "    text_nodes = []\n",
-    "    for idx, page in enumerate(json_list):\n",
-    "        text_node = TextNode(\n",
-    "            text=page[\"text\"],\n",
-    "            metadata={\n",
-    "                \"page\": page[\"page\"]\n",
-    "            }\n",
-    "        )\n",
-    "        text_nodes.append(text_node)\n",
-    "    return text_nodes"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "id": "364a3276-d2db-4aee-9bc6-617ffd726d25",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
-    "text_nodes = get_text_nodes(json_list)"
+    "text_nodes = await result.aget_text_nodes(split_by_page=True)\n",
+    "image_nodes = await result.aget_image_nodes(\n",
+    "    include_screenshot_images=True,\n",
+    "    include_object_images=True,\n",
+    "    image_download_dir=\"./uber_10q_images\",\n",
+    ")"
    ]
   },
   {
@@ -189,12 +152,12 @@
    "source": [
     "## Extract/Index images from image dicts\n",
     "\n",
-    "Here we use a multimodal model to extract and index images from image dictionaries."
+    "Here we use a multimodal model to caption images and create text nodes for indexing."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "id": "36012145-5521-4ddb-a53e-df9ebd1ca8dd",
    "metadata": {},
    "outputs": [
@@ -207,30 +170,32 @@
     }
    ],
    "source": [
-    "# call get_images on parser, convert to ImageDocuments\n",
-    "!mkdir llama2_images\n",
+    "!mkdir -p llama2_images\n",
     "\n",
-    "from llama_index.core.schema import ImageDocument\n",
-    "from llama_index.multi_modal_llms.anthropic import AnthropicMultiModal\n",
+    "from llama_index.core.llms import ChatMessage, ImageBlock, TextBlock\n",
+    "from llama_index.core.schema import ImageNode, TextNode\n",
+    "from llama_index.llms.anthropic import Anthropic\n",
     "\n",
     "\n",
-    "def get_image_text_nodes(json_objs: List[dict]):\n",
+    "def get_image_text_nodes(image_nodes: list[ImageNode]):\n",
     "    \"\"\"Extract out text from images using a multimodal model.\"\"\"\n",
-    "    anthropic_mm_llm = AnthropicMultiModal(max_tokens=300)\n",
-    "    image_dicts = parser.get_images(json_objs, download_path=\"llama2_images\")\n",
-    "    image_documents = []\n",
+    "    llm = Anthropic(model=\"claude-3-5-haiku-20241022\", max_tokens=300)\n",
     "    img_text_nodes = []\n",
-    "    for image_dict in image_dicts:\n",
-    "        image_doc = ImageDocument(image_path=image_dict[\"path\"])\n",
-    "        response = anthropic_mm_llm.complete(\n",
-    "            prompt=\"Describe the images as an alternative text\",\n",
-    "            image_documents=[image_doc],\n",
+    "    for image_node in image_nodes:\n",
+    "        image_path = image_node.image_path\n",
+    "        message = ChatMessage(\n",
+    "            role=\"user\",\n",
+    "            blocks=[\n",
+    "                TextBlock(text=\"Describe the images as alt text\"),\n",
+    "                ImageBlock(path=image_path),\n",
+    "            ],\n",
     "        )\n",
+    "        response = llm.chat([message])\n",
     "        text_node = TextNode(\n",
-    "            text=str(response),\n",
-    "            metadata={\"path\": image_dict[\"path\"]}\n",
+    "            text=str(response.message.content), metadata={\"path\": image_path}\n",
     "        )\n",
     "        img_text_nodes.append(text_node)\n",
+    "\n",
     "    return img_text_nodes"
    ]
   },
@@ -238,21 +203,17 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "38f25045-6102-4920-9cd0-42b0ae6c872f",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
-    "image_text_nodes = get_image_text_nodes(json_objs)"
+    "image_text_nodes = get_image_text_nodes(image_nodes)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 60,
+   "execution_count": null,
    "id": "4683c97a-da06-408a-9fe9-7e3c0aceb77d",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -260,7 +221,7 @@
        "'The image shows a bar graph titled \"Monthly Active Platform Consumers (in millions)\". The graph displays data from Q2 2020 to Q1 2022 over 8 quarters. The number of monthly active platform consumers starts at 55 million in Q2 2020 and steadily increases each quarter, reaching 115 million by Q1 2022. The graph illustrates consistent quarter-over-quarter growth in this metric over the nearly 2 year time period shown.'"
       ]
      },
-     "execution_count": 60,
+     "execution_count": null,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -281,7 +242,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 68,
+   "execution_count": null,
    "id": "939aec6c-064a-4319-b2dc-70cc4a304c06",
    "metadata": {},
    "outputs": [],
@@ -293,7 +254,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
+   "execution_count": null,
    "id": "529340d5-9319-4cdf-8ee1-bbd01ed00226",
    "metadata": {},
    "outputs": [],
@@ -303,11 +264,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 71,
+   "execution_count": null,
    "id": "81d7ff30-5a87-44da-880d-4b1f41434d90",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -320,18 +279,18 @@
     }
    ],
    "source": [
-    "# ask question over image! \n",
-    "response = query_engine.query(\"What does the bar graph titled 'Monthly Active Platform Consumers' show?\") \n",
-    "print(str(response)) "
+    "# ask question over image!\n",
+    "response = query_engine.query(\n",
+    "    \"What does the bar graph titled 'Monthly Active Platform Consumers' show?\"\n",
+    ")\n",
+    "print(str(response))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 72,
+   "execution_count": null,
    "id": "c4f14ad8-6bfd-49d9-b3d5-7215cf0e4ac1",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -360,25 +319,17 @@
     }
    ],
    "source": [
-    "# ask question over text! \n",
-    "response = query_engine.query(\"What are the main risk factors for Uber?\") \n",
-    "print(str(response)) "
+    "# ask question over text!\n",
+    "response = query_engine.query(\"What are the main risk factors for Uber?\")\n",
+    "print(str(response))"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "82ea880b-a0c7-410c-94c7-8fb3ac96c30c",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "llama_parse",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "name": "llama_parse"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -389,8 +340,7 @@
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.8"
+   "pygments_lexer": "ipython3"
   }
  },
  "nbformat": 4,

examples/parse/demo_json_tour.ipynb

@@ -0,0 +1,553 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "d27f1082-cd10-405e-9570-6f0e934bba8b",
+   "metadata": {},
+   "source": [
+    "# LlamaParse `JobResult` Tour\n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/demo_json.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "The `JobResult` object is the main object returned by the LlamaParse API. It contains all the information about the job, including the parsed data, metadata, and any errors.\n",
+    "\n",
+    "This notebook walks through each component of the `JobResult` object and shows you what it contains."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a004db48-8d3f-421c-915a-477692f71b90",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "Let's bring in our imports and set up our API keys."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bc6a7a4b-b568-4db5-bcba-62f5c517ff3a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-cloud-services"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0879301c-ff91-4431-941a-6c0ef7cd8fe2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "# API access to llama-cloud\n",
+    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"llx-..\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b411d2ee-3e6b-45b0-b532-4a8e3abcdea0",
+   "metadata": {},
+   "source": [
+    "## Load Data\n",
+    "\n",
+    "Let's load a large and complex PDF, San Francisco's 2023 proposed budget."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c39d408f-e885-4940-85c7-b09ca3bc7cb7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!wget 'https://www.dropbox.com/scl/fi/vip161t63s56vd94neqlt/2023-CSF_Proposed_Budget_Book_June_2023_Master_Web.pdf?rlkey=hemoce3w1jsuf6s2bz87g549i&dl=0' -O './san_francisco_budget_2023.pdf'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c2f42af8-afb3-4b3b-82d3-6b332fb38aa4",
+   "metadata": {},
+   "source": [
+    "## Using LlamaParse for Basic PDF Parsing\n",
+    "\n",
+    "Let's parse our document!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9c9cd670-8229-4ad6-99a9-845bd82b7ec1",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id d12d419a-52fc-400c-9f88-f61b352d3fb2\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_cloud_services import LlamaParse\n",
+    "\n",
+    "parser = LlamaParse()\n",
+    "result = await parser.aparse(\"./san_francisco_budget_2023.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "11c22bab",
+   "metadata": {},
+   "source": [
+    "Every job will come back with some metadata about the job:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c588c578",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "JobMetadata(job_credits_usage=0, job_pages=0, job_auto_mode_triggered_pages=0, job_is_cache_hit=True)"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result.job_metadata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1e96b7c9",
+   "metadata": {},
+   "source": [
+    "Since this was a re-run, I can see that a cache hit occurred. Jobs are cached for 48 hours by default."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6543d2c6",
+   "metadata": {},
+   "source": [
+    "Beyond this, we can explore the parsed data per-page:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "af9f3717",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "362\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(len(result.pages))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f8845fac",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "dict_keys(['page', 'text', 'md', 'images', 'charts', 'tables', 'layout', 'items', 'status', 'links', 'width', 'height', 'triggeredAutoMode', 'parsingMode', 'structuredData', 'noStructuredContent', 'noTextContent'])\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(result.pages[0].model_dump().keys())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6261f5e3",
+   "metadata": {},
+   "source": [
+    "Inside the page object, you can see nearly every detail about the page.\n",
+    "\n",
+    "Most of these will depend on the settings you used when parsing. Since we used the default settings, we get the text and markdown for each page, as well as a list of all the elements on the page.\n",
+    "\n",
+    "* `page`: this is simply the page number, starting at 1.\n",
+    "* `text`: this is the text of the page, as extracted by the parser.\n",
+    "* `images`: this is an array of all the images on the page, including metadata and text OCRed out of the images, as well as a full-page screenshot of the entire page.\n",
+    "* `charts`: this is an array of all the charts on the page, including metadata and text OCRed out of the charts, as well as a full-page screenshot of the entire chart.\n",
+    "* `layout`: this is an array of all the layout elements on the page, if you are using layout mode.\n",
+    "* `items`: This is an array of all the parsed elements on the page, as used to render the markdown, but separated out into their own objects. This is useful if you want to do more processing on the data.\n",
+    "* `links`: this is an array of all the links on the page, if you are used `annotate_links=True`\n",
+    "* `status`: this is the status of the page, which is usually \"OK\" unless there was an error processing the page.\n",
+    "* `width` and `height`: these are the dimensions of the page in pixels.\n",
+    "* `parsingMode`: Contains the specific parsing mode that was used for the page.\n",
+    "* `triggeredAutoMode`: this indicates whether the page triggered auto mode; see [LlamaParse docs](https://docs.cloud.llamaindex.ai/llamaparse/getting_started) for more details.\n",
+    "* `structuredData`/`noStructuredContent`: these are set if you are using structured mode; see [LlamaParse docs](https://docs.cloud.llamaindex.ai/llamaparse/getting_started) for more details.\n",
+    "* `noTextContent`: this is true if the page was empty of text.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7a4cc901",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                        CITY & COUNTY OF SAN FRANCISCO, CALIFORNIA\n",
+      " PROPOSED BUDGET\n",
+      "                                                              FISCAL YEARS 2023-2024 & 2024-2025\n",
+      "                                                                                LONDON  N. BREED\n",
+      "               MAYOR’S OFFICE OF PUBLIC POLICY AND FINANCE\n",
+      "         Anna Duning, Director of Mayor’s                                   Fisher Zhu, Fiscal and Policy Analyst\n",
+      "         Office of Public Policy and Finance                             Anya Shutovska, Fiscal and Policy Analyst\n",
+      "         Sally Ma, Deputy Budget Director\n",
+      "Radhika Mehlotra, Senior Fiscal and Policy Analyst                        Jack English, Fiscal and Policy Analyst\n",
+      "     Damon Daniels, Fiscal and Policy Analyst                           Xang Hang, Junior Fiscal and Policy Analyst\n",
+      "    Matthew Puckett, Fiscal and Policy Analyst                       Tabitha Romero-Bothi, Fiscal and Policy Assistant\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(result.pages[0].text[:1000])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2d5a5bc2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "# CITY & COUNTY OF SAN FRANCISCO, CALIFORNIA\n",
+      "\n",
+      "# PROPOSED BUDGET\n",
+      "\n",
+      "# FISCAL YEARS 2023-2024 & 2024-2025\n",
+      "\n",
+      "# LONDON N. BREED\n",
+      "\n",
+      "# MAYOR’S OFFICE OF PUBLIC POLICY AND FINANCE\n",
+      "\n",
+      "Anna Duning, Director of Mayor’s Office of Public Policy and Finance\n",
+      "\n",
+      "Fisher Zhu, Fiscal and Policy Analyst\n",
+      "\n",
+      "Anya Shutovska, Fiscal and Policy Analyst\n",
+      "\n",
+      "Sally Ma, Deputy Budget Director\n",
+      "\n",
+      "Radhika Mehlotra, Senior Fiscal and Policy Analyst\n",
+      "\n",
+      "Jack English, Fiscal and Policy Analyst\n",
+      "\n",
+      "Damon Daniels, Fiscal and Policy Analyst\n",
+      "\n",
+      "Xang Hang, Junior Fiscal and Policy Analyst\n",
+      "\n",
+      "Matthew Puckett, Fiscal and Policy Analyst\n",
+      "\n",
+      "Tabitha Romero-Bothi, Fiscal and Policy Assistant\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(result.pages[0].md[:1000])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "32de4c62",
+   "metadata": {},
+   "source": [
+    "## Images\n",
+    "\n",
+    "By default, images embedded in documents that can be extracted are part of the result object."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "802d4a98",
+   "metadata": {},
+   "source": [
+    "We can also specify to take screenshots of every page:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2ee78f2f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id e6332422-803b-404d-8d0d-ad510fa56c09\n",
+      "..."
+     ]
+    }
+   ],
+   "source": [
+    "parser = LlamaParse(take_screenshot=True)\n",
+    "result = await parser.aparse(\"./san_francisco_budget_2023.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fab32886",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ImageItem(name='page_1.jpg', height=792.0, width=612.0, x=0.0, y=0.0, original_width=1236, original_height=1600, type='full_page_screenshot')]\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(result.pages[0].images)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9eba9e52",
+   "metadata": {},
+   "source": [
+    "We can download images (either their bytes or to a local file) using the `JobResult` object as well!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a7aa0a29",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# single image\n",
+    "image_data = await result.aget_image_data(result.pages[0].images[0].name)\n",
+    "\n",
+    "# save an image to a file\n",
+    "output_path = await result.asave_image(\n",
+    "    result.pages[0].images[0].name, \"./json_tour_screenshots\"\n",
+    ")\n",
+    "\n",
+    "# save all images\n",
+    "output_paths = await result.asave_all_images(\"./json_tour_screenshots\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eae4ece3",
+   "metadata": {},
+   "source": [
+    "## Items\n",
+    "\n",
+    "This is an array of all the parsed elements on the page, as used to render the markdown, but separated out into their own objects. This is useful if you want to do more processing on the data. Let's take a look:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c10b9d7d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "type='heading' lvl=1 value='CITY & COUNTY OF SAN FRANCISCO, CALIFORNIA' md='# CITY & COUNTY OF SAN FRANCISCO, CALIFORNIA' rows=None bBox=BBox(x=176.0, y=52.0, w=277.0, h=12.0)\n"
+     ]
+    }
+   ],
+   "source": [
+    "import json\n",
+    "\n",
+    "print(result.pages[0].items[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dcb9f832",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "type='heading' lvl=1 value='PROPOSED BUDGET' md='# PROPOSED BUDGET' rows=None bBox=BBox(x=89.0, y=118.0, w=451.0, h=47.0)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(result.pages[0].items[1])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a7f64443",
+   "metadata": {},
+   "source": [
+    "As you can see you get different element types: text, headings, and tables. Each comes with its own `md` key containing a Markdown representation of that element, allowing you to easily summarize with only headings, tables only, etc..\n",
+    "\n",
+    "The ability to extract tables from visual data is really powerful. Let's take a look at page 35, which has some bar charts that get automatically converted into tables:\n",
+    "\n",
+    "<img src=\"./json_tour_screenshots/page_35.png\" alt=\"Page 35\" width=\"300\"/>\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e4ccee76",
+   "metadata": {},
+   "source": [
+    "The bar chart has been converted into a table, and even though explicit values are not included, the bar chart has been read and approximate values for each bar on the chart have been included!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7d6404a5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "type='table' lvl=None value=None md=\"Source: U.S. Census Bureau, 2017-2021 American Community Survey 5-years Estimate.\\n|Race|Educational Level|Number of Residents| | | | |\\n|---|---|---|---|---|---|---|\\n|Age Group| | | | | | |\\n|Under 5 Years|5 to 19 Years|20 to 34 Years|35 to 59 Years|60 and Over| | |\\n|Graduate or professional degree|Bachelor's degree|Associate's degree|Some college, no degree|High school graduate (includes equivalency)|9th to 12th grade, no diploma|Less than 9th grade|\" rows=[[], ['Race', 'Educational Level', 'Number of Residents', '', '', '', ''], ['---', '---', '---', '---', '---', '---', '---'], ['Age Group', '', '', '', '', '', ''], ['Under 5 Years', '5 to 19 Years', '20 to 34 Years', '35 to 59 Years', '60 and Over', '', ''], ['Graduate or professional degree', \"Bachelor's degree\", \"Associate's degree\", 'Some college, no degree', 'High school graduate (includes equivalency)', '9th to 12th grade, no diploma', 'Less than 9th grade']] bBox=BBox(x=68.0, y=129.0, w=613.0, h=3067.0)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(result.pages[34].items[6])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9570d3b8",
+   "metadata": {},
+   "source": [
+    "### `links`\n",
+    "\n",
+    "Our budget PDF doesn't have any links, so let's load a different PDF with links and see what we get.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fb0da11a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!wget 'https://www.dropbox.com/scl/fi/hay06lyxc49gkuh91oek6/basic-link-1.pdf?rlkey=uije7yb0lxqgqwk7p7hnqepdx&dl=0' -O './basic-link-1.pdf'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e7e393e6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id 9b2df975-af3c-4868-99e2-520ce0b21f4d\n"
+     ]
+    }
+   ],
+   "source": [
+    "parser = LlamaParse(annotate_links=True)\n",
+    "result = await parser.aparse(\"./basic-link-1.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "701ada4b",
+   "metadata": {},
+   "source": [
+    "This is a very simple document with some internal and external links:\n",
+    "\n",
+    "<img src=\"./json_tour_screenshots/links_page.png\" alt=\"Page 1\" width=\"300\"/>\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2e4de7de",
+   "metadata": {},
+   "source": [
+    "The parser finds the external links and their labels and includes them in the `links` section:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "29bf7e3c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[{'url': 'https://www.antennahouse.com/', 'text': 'Antenna House, Inc.'}, {'url': 'https://www.antennahouse.com/', 'text': 'Linking to a website (https://www.antennahouse.com/)'}]\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(result.pages[0].links)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ac9088a2",
+   "metadata": {},
+   "source": [
+    "This concludes our tour! I hope this makes clear the power of JSON mode and the flexibility it gives you over what parts of your documents you can use."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/parse/demo_languages.ipynb

@@ -9,7 +9,7 @@
     "\n",
     "LlamaParse supports users to specify a `language` parameter before uploading documents, giving users better OCR capabilities over non-English PDFs, parsing images into more accurate representations.\n",
     "\n",
-    "You can specify 80+ different languages: see this file for a full list of supported languages: https://github.com/run-llama/llama_parse/blob/main/llama_parse/base.py.\n",
+    "You can specify 80+ different languages: see this file for a full list of supported languages: https://github.com/run-llama/llama_cloud_services/blob/main/llama_parse/base.py.\n",
     "\n",
     "This notebook shows a demo of this in action. "
    ]
@@ -21,25 +21,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install llama-index llama-parse"
+    "%pip install llama-index llama-parse"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "87322210-c21c-43d6-b459-2e8a828ac576",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
-    "# llama-parse is async-first, running the sync code in a notebook requires the use of nest_asyncio\n",
-    "import nest_asyncio\n",
-    "\n",
-    "nest_asyncio.apply()\n",
-    "\n",
     "import os\n",
-    "# os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"llx-...\""
+    "\n",
+    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"llx-...\""
    ]
   },
   {
@@ -56,9 +50,7 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "e81e0a08-3a99-42e6-adcc-00bb4ce1c3d4",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "!wget \"https://www.dropbox.com/scl/fi/fxg17log5ydwoflhxmgrb/treasury_report.pdf?rlkey=mdintk0o2uuzkple26vc4v6fd&dl=1\" -O treasury_report.pdf"
@@ -66,11 +58,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "id": "ecfc578c-3c7f-4ec1-aa06-51565c28632b",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -82,22 +72,18 @@
     }
    ],
    "source": [
-    "from llama_parse import LlamaParse\n",
+    "from llama_cloud_services import LlamaParse\n",
     "\n",
-    "parser = LlamaParse(\n",
-    "    result_type=\"text\",\n",
-    "    language=\"fr\"\n",
-    ")\n",
-    "documents = parser.load_data(\"./treasury_report.pdf\")"
+    "parser = LlamaParse(language=\"fr\")\n",
+    "result = await parser.aparse(\"./treasury_report.pdf\")\n",
+    "documents = result.get_text_documents(split_by_page=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "id": "0c37db27-3496-4a59-918b-701c9ad7706d",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -209,11 +195,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": null,
    "id": "ac332ea3-cfff-4216-b292-62410a26c336",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -248,11 +232,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": null,
    "id": "45235b17-08f0-48f1-92aa-06711225860b",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -264,22 +246,18 @@
     }
    ],
    "source": [
-    "from llama_parse import LlamaParse\n",
+    "from llama_cloud_services import LlamaParse\n",
     "\n",
-    "parser = LlamaParse(\n",
-    "    result_type=\"text\",\n",
-    "    language=\"ch_sim\"\n",
-    ")\n",
-    "documents = parser.load_data(\"./chinese_pdf.pdf\")"
+    "parser = LlamaParse(language=\"ch_sim\")\n",
+    "result = await parser.aparse(\"./chinese_pdf.pdf\")\n",
+    "documents = result.get_text_documents(split_by_page=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": null,
    "id": "f0d546cc-6549-4cf5-8b37-0896f4e8d43d",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -401,9 +379,7 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "640f0679-7f7e-4b0a-a46d-b099ae382fe2",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "# download another copy with a different name to avoid hitting pdf cache\n",
@@ -412,11 +388,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": null,
    "id": "bfcacf90-ca67-4bfd-b023-be0af2cb18c5",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -427,34 +401,22 @@
     }
    ],
    "source": [
-    "from llama_parse import LlamaParse\n",
+    "from llama_cloud_services import LlamaParse\n",
     "\n",
-    "base_parser = LlamaParse(\n",
-    "    result_type=\"text\",\n",
-    "    language=\"en\"\n",
-    ")\n",
-    "base_documents = parser.load_data(\"./chinese_pdf2.pdf\")"
+    "base_parser = LlamaParse(language=\"en\")\n",
+    "result = await base_parser.aparse(\"./chinese_pdf2.pdf\")\n",
+    "base_documents = result.get_text_documents(split_by_page=False)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "id": "b264ed4e-647a-4f51-9f79-fdf82b76762a",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "print(base_documents[0].get_content()[1000:10000])"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "d9f02762-bb97-4e0e-8268-ccc00612a974",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -472,8 +434,7 @@
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.8"
+   "pygments_lexer": "ipython3"
   }
  },
  "nbformat": 4,

examples/parse/demo_mongodb.ipynb

@@ -0,0 +1,364 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# LlamaParse With MongoDB\n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/parse/demo_mongodb.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "In this notebook, we provide a straightforward example of using LlamaParse with MongoDB Atlas VectorSearch.\n",
+    "\n",
+    "We illustrate the process of using llama-parse to parse a PDF document, then index the document with a MongoDB vector store, and subsequently perform basic queries against this store.\n",
+    "\n",
+    "This notebook is structured similarly to quick start guides, aiming to introduce users to utilizing llama-parse in conjunction with a MongoDB Atlas VectorSearch."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-index llama-parse\n",
+    "%pip install llama-index-vector-stores-mongodb llama-index-llms-openai"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Setup API Keys"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\n",
+    "    \"LLAMA_CLOUD_API_KEY\"\n",
+    "] = \"\"  # Get it from https://cloud.llamaindex.ai/api-key\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"\"  # Get it from https://platform.openai.com/api-keys"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "import pymongo\n",
+    "\n",
+    "from llama_index.vector_stores.mongodb import MongoDBAtlasVectorSearch\n",
+    "from llama_cloud_services import LlamaParse\n",
+    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
+    "from llama_index.core import VectorStoreIndex, StorageContext\n",
+    "from llama_index.core.node_parser import SentenceSplitter"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Download Document\n",
+    "\n",
+    "We will use `Attention is all you need` paper."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Download complete.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# The URL of the file you want to download\n",
+    "url = \"https://arxiv.org/pdf/1706.03762.pdf\"\n",
+    "# The local path where you want to save the file\n",
+    "file_path = \"./attention.pdf\"\n",
+    "\n",
+    "# Perform the HTTP request\n",
+    "response = requests.get(url)\n",
+    "\n",
+    "# Check if the request was successful\n",
+    "if response.status_code == 200:\n",
+    "    # Open the file in binary write mode and save the content\n",
+    "    with open(file_path, \"wb\") as file:\n",
+    "        file.write(response.content)\n",
+    "    print(\"Download complete.\")\n",
+    "else:\n",
+    "    print(\"Error downloading the file.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Parse the document using `LlamaParse`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id 09a49745-9f21-4190-9de8-27e4e1a4bdf5\n"
+     ]
+    }
+   ],
+   "source": [
+    "result = await LlamaParse().aparse(file_path)\n",
+    "documents = result.get_text_documents(split_by_page=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "rmer - model architecture.\n",
+      "The Transformer follows this overall architecture using stacked self-attention and point-wise, fully\n",
+      "connected layers for both the encoder and decoder, shown in the left and right halves of Figure 1,\n",
+      "respectively.\n",
+      "3.1   Encoder and Decoder Stacks\n",
+      "Encoder:     The encoder is composed of a stack of N = 6 identical layers. Each layer has two\n",
+      "sub-layers. The first is a multi-head self-attention mechanism, and the second is a simple, position-\n",
+      "wise fully connected feed-forward network. We employ a residual connection [11] around each of\n",
+      "the two sub-layers, followed by layer normalization [1]. That is, the output of each sub-layer is\n",
+      "LayerNorm(x + Sublayer(x)), where Sublayer(x) is the function implemented by the sub-layer\n",
+      "itself. To facilitate these residual connections, all sub-layers in the model, as well as the embedding\n",
+      "layers, produce outputs of dimension dmodel = 512.\n",
+      "Decoder:    The decoder is also composed of a stack of N = 6 identical layers. In addition \n"
+     ]
+    }
+   ],
+   "source": [
+    "# Take a quick look at some of the parsed text from the document:\n",
+    "print(documents[0].get_content()[10000:11000])"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create `MongoDBAtlasVectorSearch`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mongo_uri = os.environ[\"MONGO_URI\"]\n",
+    "\n",
+    "mongodb_client = pymongo.MongoClient(mongo_uri)\n",
+    "mongodb_vector_store = MongoDBAtlasVectorSearch(mongodb_client)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create nodes."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "node_parser = SentenceSplitter()\n",
+    "\n",
+    "nodes = node_parser.get_nodes_from_documents(documents)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create Index and Query Engine."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "storage_context = StorageContext.from_defaults(vector_store=mongodb_vector_store)\n",
+    "\n",
+    "index = VectorStoreIndex(\n",
+    "    nodes=nodes,\n",
+    "    storage_context=storage_context,\n",
+    "    embed_model=OpenAIEmbedding(),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_engine = index.as_query_engine(similarity_top_k=2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test Query"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "***********New LlamaParse+ Basic Query Engine***********\n",
+      "The BLEU score on the WMT 2014 English-to-German translation task is 28.4.\n"
+     ]
+    }
+   ],
+   "source": [
+    "query = \"What is BLEU score on the WMT 2014 English-to-German translation task?\"\n",
+    "\n",
+    "response = query_engine.query(query)\n",
+    "print(\"\\n***********New LlamaParse+ Basic Query Engine***********\")\n",
+    "print(response)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "We varied the learning\n",
+      "rate over the course of training, according to the formula:\n",
+      "               lrate = d−0.5                                                                          (3)\n",
+      "                         model · min(step_num−0.5, step_num · warmup_steps−1.5)\n",
+      "This corresponds to increasing the learning rate linearly for the first warmup_steps training steps,\n",
+      "and decreasing it thereafter proportionally to the inverse square root of the step number. We used\n",
+      "warmup_steps = 4000.\n",
+      "5.4   Regularization\n",
+      "We employ three types of regularization during training:\n",
+      "                                                    7\n",
+      "---\n",
+      "Table 2: The Transformer achieves better BLEU scores than previous state-of-the-art models on the\n",
+      "English-to-German and English-to-French newstest2014 tests at a fraction of the training cost.\n",
+      "        Model                                          BLEU               Training Cost (FLOPs)\n",
+      "                                                 EN-DE      EN-FR          EN-DE         EN-FR\n",
+      "        ByteNet [18]                              23.75\n",
+      "        Deep-Att + PosUnk [39]                               39.2                       1.0 · 1020\n",
+      "        GNMT + RL [38]                            24.6       39.92        2.3 · 1019    1.4 · 1020\n",
+      "        ConvS2S [9]                               25.16      40.46        9.6 · 1018    1.5 · 1020\n",
+      "        MoE [32]                                  26.03      40.56        2.0 · 1019    1.2 · 1020\n",
+      "        Deep-Att + PosUnk Ensemble [39]                      40.4                       8.0 · 1020\n",
+      "        GNMT + RL Ensemble [38]                   26.30      41.16        1.8 · 1020    1.1 · 1021\n",
+      "        ConvS2S Ensemble [9]                      26.36      41.29        7.7 · 1019    1.2 · 1021\n",
+      "        Transformer (base model)                  27.3       38.1               3.3 · 1018\n",
+      "        Transformer (big)                         28.4       41.8                2.3 · 1019\n",
+      "Residual Dropout       We apply dropout [33] to the output of each sub-layer, before it is added to the\n",
+      "sub-layer input and normalized. In addition, we apply dropout to the sums of the embeddings and the\n",
+      "positional encodings in both the encoder and decoder stacks. For the base model, we use a rate of\n",
+      "Pdrop = 0.1.\n",
+      "Label Smoothing        During training, we employed label smoothing of value ϵls = 0.1 [36]. This\n",
+      "hurts perplexity, as the model learns to be more unsure, but improves accuracy and BLEU score.\n",
+      "6    Results\n",
+      "6.1   Machine Translation\n",
+      "On the WMT 2014 English-to-German translation task, the big transformer model (Transformer (big)\n",
+      "in Table 2) outperforms the best previously reported models (including ensembles) by more than 2.0\n",
+      "BLEU, establishing a new state-of-the-art BLEU score of 28.4. The configuration of this model is\n",
+      "listed in the bottom line of Table 3. Training took 3.5 days on 8 P100 GPUs. Even our base model\n",
+      "surpasses all previously published models and ensembles, at a fraction of the training cost of any of\n",
+      "the competitive models.\n",
+      "On the WMT 2014 English-to-French translation task, our big model achieves a BLEU score of 41.0,\n",
+      "outperforming all of the previously published single models, at less than 1/4 the training cost of the\n",
+      "previous state-of-the-art model. The Transformer (big) model trained for English-to-French used\n",
+      "dropout rate Pdrop = 0.1, instead of 0.3.\n",
+      "For the base models, we used a single model obtained by averaging the last 5 checkpoints, which\n",
+      "were written at 10-minute intervals. For the big models, we averaged the last 20 checkpoints. We\n",
+      "used beam search with a beam size of 4 and length penalty α = 0.6 [38]. These hyperparameters\n",
+      "were chosen after experimentation on the development set. We set the maximum output length during\n",
+      "inference to input length + 50, but terminate early when possible [38].\n",
+      "Table 2 summarizes our results and compares our translation quality and training costs to other model\n",
+      "architectures from the literature.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Take a look at one of the source nodes from the response\n",
+    "print(response.source_nodes[0].get_content())"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "anthropic_env",
+   "language": "python",
+   "name": "anthropic_env"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "b0fa6594d8f4cbf19f97940f81e996739fb7646882a419484c72d19e05852a7e"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

examples/parse/demo_starter_multimodal.ipynb

@@ -0,0 +1,312 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "97c79c38-38a3-40f3-ba2e-250649347d63",
+   "metadata": {},
+   "source": [
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/parse/demo_starter_multimodal.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4e081457",
+   "metadata": {},
+   "source": [
+    "# Multimodal Parsing using LlamaParse\n",
+    "\n",
+    "This cookbook shows you how to use LlamaParse to parse any document with the multimodal capabilities of Multi-Modal LLMs from Anthropic/ OpenAI.\n",
+    "\n",
+    "LlamaParse allows you to plug in external, multimodal model vendors for parsing - we handle the error correction, validation, and scalability/reliability for you.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "qOdqBxCS51Ow",
+   "metadata": {},
+   "source": [
+    "### Installation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "H_Vqcylb50vm",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install llama-cloud-services"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "15e60ecf-519c-41fc-911b-765adaf8bad4",
+   "metadata": {},
+   "source": [
+    "### Setup\n",
+    "\n",
+    "Here we setup `LLAMA_CLOUD_API_KEY` for using `LlamaParse`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "91a9e532-1454-40e0-bbf0-fd442c350121",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "# API access to llama-cloud\n",
+    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"<YOUR LLAMACLOUD API KEY>\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "LGwBNPNotZRQ",
+   "metadata": {},
+   "source": [
+    "## Download Data\n",
+    "\n",
+    "For this demonstration, we will use OpenAI's recent paper `Evaluation of OpenAI o1: Opportunities and Challenges of AGI`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "IjtKDQRLrylI",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!wget \"https://arxiv.org/pdf/2409.18486\" -O \"o1.pdf\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4e29a9d7-5bd9-4fb8-8ec1-4c128a748662",
+   "metadata": {},
+   "source": [
+    "## Initialize LlamaParse\n",
+    "\n",
+    "Initialize LlamaParse in multimodal mode, and specify the vendor.\n",
+    "\n",
+    "**NOTE**: optionally you can specify the Anthropic/ OpenAI API key. If you choose to do so LlamaParse will only charge you 1 credit (0.3c) per page. \n",
+    "\n",
+    "\n",
+    "Using your own API key may incur additional costs from your model provider and could result in failed pages or documents if you do not have sufficient usage limits."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1b5d6da6",
+   "metadata": {},
+   "source": [
+    "### With anthropic-sonnet-3.5"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f2e9d9cf-8189-4fcb-b34f-cde6cc0b59c8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id dd9d5e0f-160e-486a-89a2-6005e5a1c2ac\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_cloud_services import LlamaParse\n",
+    "\n",
+    "parser = LlamaParse(\n",
+    "    use_vendor_multimodal_model=True,\n",
+    "    vendor_multimodal_model_name=\"anthropic-sonnet-3.5\",\n",
+    "    target_pages=\"24\"\n",
+    "    # invalidate_cache=True\n",
+    ")\n",
+    "result = await parser.aparse(\"o1.pdf\")\n",
+    "nodes = result.get_text_nodes(split_by_page=False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4f3c51b0-7878-48d7-9bc3-02b516500128",
+   "metadata": {},
+   "source": [
+    "### With GPT-4o\n",
+    "\n",
+    "For comparison, we will also parse the document using GPT-4o."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6fc3f258-50ae-4988-b904-c105463a498f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id 6a4dea44-4f90-406b-b290-9e98620b1232\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_cloud_services import LlamaParse\n",
+    "\n",
+    "parser_gpt4o = LlamaParse(\n",
+    "    use_vendor_multimodal_model=True,\n",
+    "    vendor_multimodal_model=\"openai-gpt4o\",\n",
+    "    target_pages=\"24\",\n",
+    "    # invalidate_cache=True\n",
+    ")\n",
+    "result = await parser_gpt4o.aparse(\"o1.pdf\")\n",
+    "nodes = result.get_markdown_nodes(split_by_page=False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "44c20f7a-2901-4dd0-b635-a4b33c5664c1",
+   "metadata": {},
+   "source": [
+    "### View Results\n",
+    "\n",
+    "Let's visualize the results along with the original document page."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "778698aa-da7e-4081-b3b5-0372f228536f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "page: 25\n",
+      "\n",
+      "| Participant_ID | clinical Description Reference |\n",
+      "|-----------------|----------------------------------|\n",
+      "| Attribute | Value | Basic Personal Information: Subject 098_S_0896 is a 72.0-year-old Female who has completed 15 years of education. The ethnicity is Not Hisp/Latino and race is White. Marital status is Married. Initially diagnosed as AD, as of the date 2007-10-24, the final diagnosis was Dementia. |\n",
+      "| Age | 72.0 |\n",
+      "| Sex | Female |\n",
+      "| Education | 15 |\n",
+      "| Race | White | Biomarker Measurements: The subject's genetic profile includes an ApoE4 status of 0.0... |\n",
+      "| DX_bl | AD |\n",
+      "| DX | Dementia |\n",
+      "| ... | ... | Cognitive and Neurofunctional Assessments: The Mini-Mental State Examination score stands at 29.0. The Clinical Dementia Rating, sum of boxes, is 1.0. ADAS 11 and 13 scores are 4.67 and 4.67 respectively, with a score of 1.0 in delayed word recall... |\n",
+      "| APOE4 | 1.0 |\n",
+      "| TAU | 212.5 |\n",
+      "| ... | ... |\n",
+      "| MMSE | 29.0 | Volumetric Data: Under MRI conditions at a field strength of 1.5 Tesla MRI Tesla, using Cross Sectional FreeSurfer (FreeSurfer Version 4.3), the imaging data recorded includes ventricles volume at 54422.0, hippocampus volume at 6677.0, whole brain volume at 1147980.0, entorhinal cortex volume at 2782.0, fusiform gyrus volume at 19432.0, and middle temporal area volume at 24951.0. The intracranial volume measured is 1799580.0.... |\n",
+      "| CDRSB | 0.0 |\n",
+      "| ... | ... |\n",
+      "| FLDSTRENG | 1.5 Tesla MRI |\n",
+      "| Ventricles | 84599 |\n",
+      "| Hippocampus | 5319 |\n",
+      "| ... | ... |\n",
+      "\n",
+      "Figure 2: An example of a patient table and its corresponding clinical description.\n",
+      "\n",
+      "skills. Mathematics, as a highly structured and logic-driven discipline, provides an ideal testing ground for evaluating this reasoning ability. To investigate o1-preview's performance, we designed a series of tests covering various difficulty levels. We begin with high school-level math competition problems in this section, followed by college-level mathematics problems in the next section, allowing us to observe the model's logical reasoning across varying levels of complexity.\n",
+      "\n",
+      "In this section, we selected two primary areas of mathematics: algebra and counting and probability in this section. We chose these two topics because of their heavy reliance on problem-solving skills and their frequent use in assessing logical and abstract thinking [46]. The dataset used in testing is from the MATH dataset [46]. The problems in the dataset cover a wide range of subjects, including Prealgebra, Intermediate Algebra, Algebra, Geometry, Counting and Probability, Number Theory, and Precalculus. Each problem is categorized based on difficulty, ranked from level 1 to 5, according to the Art of Problem Solving (AoPS). The dataset mainly comprises problems from various high school math competitions, including the American Mathematics Competitions (AMC) 10 and 12, as well as the American Invitational Mathematics Examination (AIME), and other similar contests. Each problem comes with detailed reference solutions, allowing for a comprehensive comparison of o1-preview's solutions.\n",
+      "\n",
+      "In addition to evaluating the final answers produced by o1-preview, our analysis delves into the step-by-step reasoning process of the o1-preview's solutions. By comparing o1-preview's solutions with the dataset's solutions, we assess its ability to engage in logical reasoning, handle abstract problem-solving tasks, and apply structured approaches to reach correct answers. This deeper analysis offers insights into o1-preview's overall reasoning capabilities, using mathematics as a reliable indicator for logical and structured thought processes.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# using Sonnet-3.5\n",
+    "print(nodes[0].get_content(metadata_mode=\"all\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1511a30f-3efc-4142-9668-7dc056a24d0c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "page: 25\n",
+      "\n",
+      "\n",
+      "| Participant_ID | clinical Description Reference |\n",
+      "|----------------|--------------------------------|\n",
+      "| **Attribute**  | **Value**                      |\n",
+      "| Age            | 72.0                           |\n",
+      "| Sex            | Female                         |\n",
+      "| Education      | 15                             |\n",
+      "| Race           | White                          |\n",
+      "| DX_bl          | AD                             |\n",
+      "| DX             | Dementia                       |\n",
+      "| ...            | ...                            |\n",
+      "| APOE4          | 1.0                            |\n",
+      "| TAU            | 212.5                          |\n",
+      "| ...            | ...                            |\n",
+      "| MMSE           | 29.0                           |\n",
+      "| CDRSB          | 0.0                            |\n",
+      "| ...            | ...                            |\n",
+      "| FLDSTRENG      | 1.5 Tesla MRI                  |\n",
+      "| Ventricles     | 84599                          |\n",
+      "| Hippocampus    | 5319                           |\n",
+      "| ...            | ...                            |\n",
+      "\n",
+      "**Basic Personal Information:** Subject 098_S_0896 is a 72.0-year-old Female who has completed 15 years of education. The ethnicity is Not Hisp/Latino and race is White. Marital status is Married. Initially diagnosed as AD, as of the date 2007-10-24, the final diagnosis was Dementia.\n",
+      "\n",
+      "**Biomarker Measurements:** The subject's genetic profile includes an ApoE4 status of 0.0...\n",
+      "\n",
+      "**Cognitive and Neurofunctional Assessments:** The Mini-Mental State Examination score stands at 29.0. The Clinical Dementia Rating, sum of boxes, is 1.0. ADAS 11 and 13 scores are 4.67 and 4.67 respectively, with a score of 1.0 in delayed word recall...\n",
+      "\n",
+      "**Volumetric Data:** Under MRI conditions at a field strength of 1.5 Tesla MRI Tesla, using Cross-Sectional FreeSurfer (FreeSurfer Version 4.3), the imaging data recorded includes ventricles volume at 84422.0, hippocampus volume at 6677.0, whole brain volume at 1147980.0, entorhinal cortex volume at 27820.0, fusiform gyrus volume at 19432.0, and middle temporal area volume at 24951.0. The intracranial volume measured is 1799580.0...\n",
+      "\n",
+      "Figure 2: An example of a patient table and its corresponding clinical description.\n",
+      "\n",
+      "----\n",
+      "\n",
+      "Skills. Mathematics, as a highly structured and logic-driven discipline, provides an ideal testing ground for evaluating this reasoning ability. To investigate o1-preview’s performance, we designed a series of tests covering various difficulty levels. We begin with high school-level math competition problems in this section, followed by college-level mathematics problems in the next section, allowing us to observe the model’s logical reasoning across varying levels of complexity.\n",
+      "\n",
+      "In this section, we selected two primary areas of mathematics: algebra and counting and probability in this section. We chose these two topics because of their heavy reliance on problem-solving skills and their frequent use in assessing logical and abstract thinking [46]. The dataset used in testing is from the MATH dataset [46]. The problems in the dataset cover a wide range of subjects, including Prealgebra, Intermediate Algebra, Algebra, Geometry, Counting and Probability, Number Theory, and Precalculus. Each problem is categorized based on difficulty, ranked from level 1 to 5, according to the Art of Problem Solving (AoPS). The dataset mainly comprises problems from various high school math competitions, including the American Mathematics Competitions (AMC) 10 and 12, as well as the American Invitational Mathematics Examination (AIME), and other similar contests. Each problem comes with detailed reference solutions, allowing for a comprehensive comparison of o1-preview’s solutions.\n",
+      "\n",
+      "In addition to evaluating the final answers produced by o1-preview, our analysis delves into the step-by-step reasoning process of the o1-preview’s solutions. By comparing o1-preview’s solutions with the dataset’s solutions, we assess its ability to engage in logical reasoning, handle abstract problem-solving tasks, and apply structured approaches to reach correct answers. This deeper analysis offers insights into o1-preview’s overall reasoning capabilities, using mathematics as a reliable indicator for logical and structured thought processes.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# using GPT-4o\n",
+    "print(nodes[0].get_content(metadata_mode=\"all\"))"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "llamacloud",
+   "language": "python",
+   "name": "llamacloud"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/parse/demo_starter_parse_selected_pages.ipynb

@@ -0,0 +1,148 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/parse/demo_starter_parse_selected_pages.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Parse Selected Pages \n",
+    "\n",
+    "In this notebook we will demonstrate how to parse selected pages in a document using LlamaParse."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "Here we install `llama-parse` used for parsing the document"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install llama-cloud-services"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Set API Key"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "# API access to llama-cloud\n",
+    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"<YOUR LLAMACLOUD API KEY>\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Download Data\n",
+    "\n",
+    "Here we download Uber 2021 10K SEC filings data for the demonstration."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/10k/uber_2021.pdf' -O './uber_2021.pdf'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Parse the PDF file in selected pages\n",
+    "\n",
+    "Here we will parse the PDF file in selected pages and get the text in `markdown` format."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id ad1087c1-b085-4dc7-9aa8-d13cdd440f2b\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_cloud_services import LlamaParse\n",
+    "\n",
+    "parser = LlamaParse(target_pages=\"0,1,2\")\n",
+    "\n",
+    "results = await parser.aparse(\"./uber_2021.pdf\")\n",
+    "documents = results.get_text_documents(split_by_page=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(id_='d0b34f4a-27ef-48e2-a92a-386e5e265f4c', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, metadata_template='{key}: {value}', metadata_separator='\\n', text='# UNITED STATES SECURITIES AND EXCHANGE COMMISSION\\n\\n# Washington, D.C. 20549\\n\\n# FORM 10-K\\n\\n(Mark One)\\n\\n☒ ANNUAL REPORT PURSUANT TO SECTION 13 OR 15(d) OF THE SECURITIES EXCHANGE ACT OF 1934\\n\\nFor the fiscal year ended December 31, 2021\\n\\nOR\\n\\n☐ TRANSITION REPORT PURSUANT TO SECTION 13 OR 15(d) OF THE SECURITIES EXCHANGE ACT OF 1934\\n\\nFor the transition period from _____ to _____\\n\\nCommission File Number: 001-38902\\n\\n# UBER TECHNOLOGIES, INC.\\n\\n(Exact name of registrant as specified in its charter)\\n\\nDelaware\\n\\n45-2647441\\n\\n(State or other jurisdiction of incorporation or organization) (I.R.S. Employer Identification No.)\\n\\n1515 3rd Street\\n\\nSan Francisco, California 94158\\n\\n(Address of principal executive offices, including zip code)\\n\\n(415) 612-8582\\n\\n(Registrant’s telephone number, including area code)\\n\\n# Securities registered pursuant to Section 12(b) of the Act:\\n\\n|Title of each class|Trading Symbol(s)|Name of each exchange on which registered|\\n|---|---|---|\\n|Common Stock, par value $0.00001 per share|UBER|New York Stock Exchange|\\n\\nSecurities registered pursuant to Section 12(g) of the Act: None\\n\\nIndicate by check mark whether the registrant is a well-known seasoned issuer, as defined in Rule 405 of the Securities Act. Yes ☒ No ☐\\n\\nIndicate by check mark whether the registrant is not required to file reports pursuant to Section 13 or Section 15(d) of the Act. Yes ☐ No ☒\\n\\nIndicate by check mark whether the registrant (1) has filed all reports required to be filed by Section 13 or 15(d) of the Securities Exchange Act of 1934 during the preceding 12 months (or for such shorter period that the registrant was required to file such reports), and (2) has been subject to such filing requirements for the past 90 days. Yes ☒ No ☐\\n\\nIndicate by check mark whether the registrant has submitted electronically every Interactive Data File required to be submitted pursuant to Rule 405 of Regulation S-T (§232.405 of this chapter) during the preceding 12 months (or for such shorter period that the registrant was required to submit such files). Yes ☒ No ☐\\n\\nIndicate by check mark whether the registrant is a large accelerated filer, an accelerated filer, a non-accelerated filer, a smaller reporting company, or an emerging growth company. See the definitions of “large accelerated filer,” “accelerated filer,” “smaller reporting company,” and “emerging growth company” in Rule 12b-2 of the Exchange Act.', mimetype='text/plain', start_char_idx=None, end_char_idx=None, metadata_seperator='\\n', text_template='{metadata_str}\\n\\n{content}'),\n",
+       " Document(id_='253b1141-a260-466e-b164-b39df67ef799', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, metadata_template='{key}: {value}', metadata_separator='\\n', text=\"# Large accelerated filer\\n\\n☒\\n\\n# Accelerated filer\\n\\n☐\\n\\n# Non-accelerated filer\\n\\n☐\\n\\n# Smaller reporting company\\n\\n☐\\n\\n# Emerging growth company\\n\\n☐\\n\\nIf an emerging growth company, indicate by check mark if the registrant has elected not to use the extended transition period for complying with any new or revised financial accounting standards provided pursuant to Section 13(a) of the Exchange Act.\\n\\n☐\\n\\nIndicate by check mark whether the registrant has filed a report on and attestation to its management’s assessment of the effectiveness of its internal control over financial reporting under Section 404(b) of the Sarbanes-Oxley Act (15 U.S.C. 7262(b)) by the registered public accounting firm that prepared or issued\\n\\n☒\\n\\nIndicate by check mark whether the registrant is a shell company (as defined in Rule 12b-2 of the Exchange Act). Yes\\n\\n☐\\n\\nNo\\n\\n☒\\n\\nThe aggregate market value of the voting and non-voting common equity held by non-affiliates of the registrant as of June 30, 2021, the last business day of the registrant's most recently completed second fiscal quarter, was approximately $90.5 billion based upon the closing price reported for such date on the New York Stock Exchange.\\n\\nThe number of shares of the registrant's common stock outstanding as of February 22, 2022 was 1,954,464,088.\\n\\n# DOCUMENTS INCORPORATED BY REFERENCE\\n\\nPortions of the registrant’s Definitive Proxy Statement relating to the Annual Meeting of Stockholders are incorporated by reference into Part III of this Annual Report on Form 10-K where indicated. Such Definitive Proxy Statement will be filed with the Securities and Exchange Commission within 120 days after the end of the registrant’s fiscal year ended December 31, 2021.\", mimetype='text/plain', start_char_idx=None, end_char_idx=None, metadata_seperator='\\n', text_template='{metadata_str}\\n\\n{content}'),\n",
+       " Document(id_='ad988239-3ab5-498d-85ba-a29241db24d4', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, metadata_template='{key}: {value}', metadata_separator='\\n', text='# UBER TECHNOLOGIES, INC.\\n\\n# TABLE OF CONTENTS\\n\\n|Special Note Regarding Forward-Looking Statements|2|\\n|---|---|\\n|PART I|PART I|\\n|Item 1. Business|4|\\n|Item 1A. Risk Factors|11|\\n|Item 1B. Unresolved Staff Comments|46|\\n|Item 2. Properties|46|\\n|Item 3. Legal Proceedings|46|\\n|Item 4. Mine Safety Disclosures|47|\\n|PART II|PART II|\\n|Item 5. Market for Registrant’s Common Equity, Related Stockholder Matters and Issuer Purchases of Equity Securities|47|\\n|Item 6. [Reserved]|48|\\n|Item 7. Management’s Discussion and Analysis of Financial Condition and Results of Operations|48|\\n|Item 7A. Quantitative and Qualitative Disclosures About Market Risk|69|\\n|Item 8. Financial Statements and Supplementary Data|70|\\n|Item 9. Changes in and Disagreements with Accountants on Accounting and Financial Disclosure|146|\\n|Item 9A. Controls and Procedures|147|\\n|Item 9B. Other Information|147|\\n|Item 9C. Disclosure Regarding Foreign Jurisdictions that Prevent Inspections|147|\\n|PART III|PART III|\\n|Item 10. Directors, Executive Officers and Corporate Governance|147|\\n|Item 11. Executive Compensation|147|\\n|Item 12. Security Ownership of Certain Beneficial Owners and Management and Related Stockholder Matters|148|\\n|Item 13. Certain Relationships and Related Transactions, and Director Independence|148|\\n|Item 14. Principal Accounting Fees and Services|148|\\n|PART IV|PART IV|\\n|Item 15. Exhibits, Financial Statement Schedules|148|\\n|Item 16. Form 10-K Summary|148|\\n|Exhibit Index|149|\\n|Signatures|152|', mimetype='text/plain', start_char_idx=None, end_char_idx=None, metadata_seperator='\\n', text_template='{metadata_str}\\n\\n{content}')]"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "documents"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llamacloud",
+   "language": "python",
+   "name": "llamacloud"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

examples/parse/demo_table_extraction.ipynb

@@ -0,0 +1,516 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Table Extraction with LlamaParse\n",
+    "\n",
+    "This notebook will show you how to extract tables and save them as CSV files thanks to LlamaParse advanced parsing capabilities."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**1. Install needed dependencies**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! pip install llama-cloud-services pandas"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**2. Set you LLAMA_CLOUD_API_KEY as env variable**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "LLAMA_CLOUD_API_KEY: ··········\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = getpass(\"LLAMA_CLOUD_API_KEY: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**3. Initialiaze the parser**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_cloud_services import LlamaParse\n",
+    "\n",
+    "parser = LlamaParse(result_type=\"markdown\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**4. Get data**\n",
+    "\n",
+    "This is a PDF with _lots_ of tables!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "--2025-07-16 16:20:41--  https://assets.accessible-digital-documents.com/uploads/2017/01/sample-tables.pdf\n",
+      "Resolving assets.accessible-digital-documents.com (assets.accessible-digital-documents.com)... 3.166.135.2, 3.166.135.62, 3.166.135.51, ...\n",
+      "Connecting to assets.accessible-digital-documents.com (assets.accessible-digital-documents.com)|3.166.135.2|:443... connected.\n",
+      "HTTP request sent, awaiting response... 200 OK\n",
+      "Length: 145494 (142K) [application/pdf]\n",
+      "Saving to: ‘sample-tables.pdf’\n",
+      "\n",
+      "sample-tables.pdf   100%[===================>] 142.08K  --.-KB/s    in 0.04s   \n",
+      "\n",
+      "2025-07-16 16:20:41 (3.72 MB/s) - ‘sample-tables.pdf’ saved [145494/145494]\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "! wget https://assets.accessible-digital-documents.com/uploads/2017/01/sample-tables.pdf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**5. Parse document**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id b53949f7-9017-4b6a-b30c-be6227271ed2\n"
+     ]
+    }
+   ],
+   "source": [
+    "json_result = parser.get_json_result(\"sample-tables.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**6. Get tables!**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tables = parser.get_tables(json_result, \"tables/\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**7. Load tables**\n",
+    "\n",
+    "Let's show one example table!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.google.colaboratory.intrinsic+json": {
+       "summary": "{\n  \"name\": \"display(df\",\n  \"rows\": 8,\n  \"fields\": [\n    {\n      \"column\": \"Rainfall\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"Average\",\n          \"\",\n          \"24 hour high\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Americas\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 908,\n        \"min\": 9,\n        \"max\": 2010,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          104,\n          133,\n          2010\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Asia\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"num_unique_values\": 7,\n        \"samples\": [\n          \"\",\n          201.0,\n          28.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Europe\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"num_unique_values\": 7,\n        \"samples\": [\n          \"\",\n          193.0,\n          29.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Africa\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"num_unique_values\": 7,\n        \"samples\": [\n          \"\",\n          144.0,\n          20.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
+       "type": "dataframe"
+      },
+      "text/html": [
+       "\n",
+       "  <div id=\"df-94a74c8f-1062-4a80-8d3f-32f0fbadf7bb\" class=\"colab-df-container\">\n",
+       "    <div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Rainfall</th>\n",
+       "      <th>Americas</th>\n",
+       "      <th>Asia</th>\n",
+       "      <th>Europe</th>\n",
+       "      <th>Africa</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>(inches)</td>\n",
+       "      <td>2010</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Average</td>\n",
+       "      <td>104</td>\n",
+       "      <td>201.0</td>\n",
+       "      <td>193.0</td>\n",
+       "      <td>144.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>24 hour high</td>\n",
+       "      <td>15</td>\n",
+       "      <td>26.0</td>\n",
+       "      <td>27.0</td>\n",
+       "      <td>18.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>12 hour high</td>\n",
+       "      <td>9</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>11.0</td>\n",
+       "      <td>12.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td></td>\n",
+       "      <td>2009</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>Average</td>\n",
+       "      <td>133</td>\n",
+       "      <td>244.0</td>\n",
+       "      <td>155.0</td>\n",
+       "      <td>166.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>24 hour high</td>\n",
+       "      <td>27</td>\n",
+       "      <td>28.0</td>\n",
+       "      <td>29.0</td>\n",
+       "      <td>20.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>12 hour high</td>\n",
+       "      <td>11</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>13.0</td>\n",
+       "      <td>16.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>\n",
+       "    <div class=\"colab-df-buttons\">\n",
+       "\n",
+       "  <div class=\"colab-df-container\">\n",
+       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-94a74c8f-1062-4a80-8d3f-32f0fbadf7bb')\"\n",
+       "            title=\"Convert this dataframe to an interactive table.\"\n",
+       "            style=\"display:none;\">\n",
+       "\n",
+       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
+       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
+       "  </svg>\n",
+       "    </button>\n",
+       "\n",
+       "  <style>\n",
+       "    .colab-df-container {\n",
+       "      display:flex;\n",
+       "      gap: 12px;\n",
+       "    }\n",
+       "\n",
+       "    .colab-df-convert {\n",
+       "      background-color: #E8F0FE;\n",
+       "      border: none;\n",
+       "      border-radius: 50%;\n",
+       "      cursor: pointer;\n",
+       "      display: none;\n",
+       "      fill: #1967D2;\n",
+       "      height: 32px;\n",
+       "      padding: 0 0 0 0;\n",
+       "      width: 32px;\n",
+       "    }\n",
+       "\n",
+       "    .colab-df-convert:hover {\n",
+       "      background-color: #E2EBFA;\n",
+       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+       "      fill: #174EA6;\n",
+       "    }\n",
+       "\n",
+       "    .colab-df-buttons div {\n",
+       "      margin-bottom: 4px;\n",
+       "    }\n",
+       "\n",
+       "    [theme=dark] .colab-df-convert {\n",
+       "      background-color: #3B4455;\n",
+       "      fill: #D2E3FC;\n",
+       "    }\n",
+       "\n",
+       "    [theme=dark] .colab-df-convert:hover {\n",
+       "      background-color: #434B5C;\n",
+       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+       "      fill: #FFFFFF;\n",
+       "    }\n",
+       "  </style>\n",
+       "\n",
+       "    <script>\n",
+       "      const buttonEl =\n",
+       "        document.querySelector('#df-94a74c8f-1062-4a80-8d3f-32f0fbadf7bb button.colab-df-convert');\n",
+       "      buttonEl.style.display =\n",
+       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+       "\n",
+       "      async function convertToInteractive(key) {\n",
+       "        const element = document.querySelector('#df-94a74c8f-1062-4a80-8d3f-32f0fbadf7bb');\n",
+       "        const dataTable =\n",
+       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+       "                                                    [key], {});\n",
+       "        if (!dataTable) return;\n",
+       "\n",
+       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
+       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+       "          + ' to learn more about interactive tables.';\n",
+       "        element.innerHTML = '';\n",
+       "        dataTable['output_type'] = 'display_data';\n",
+       "        await google.colab.output.renderOutput(dataTable, element);\n",
+       "        const docLink = document.createElement('div');\n",
+       "        docLink.innerHTML = docLinkHtml;\n",
+       "        element.appendChild(docLink);\n",
+       "      }\n",
+       "    </script>\n",
+       "  </div>\n",
+       "\n",
+       "\n",
+       "    <div id=\"df-54b2aa43-838b-47d3-9209-2fb18153cf87\">\n",
+       "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-54b2aa43-838b-47d3-9209-2fb18153cf87')\"\n",
+       "                title=\"Suggest charts\"\n",
+       "                style=\"display:none;\">\n",
+       "\n",
+       "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
+       "     width=\"24px\">\n",
+       "    <g>\n",
+       "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
+       "    </g>\n",
+       "</svg>\n",
+       "      </button>\n",
+       "\n",
+       "<style>\n",
+       "  .colab-df-quickchart {\n",
+       "      --bg-color: #E8F0FE;\n",
+       "      --fill-color: #1967D2;\n",
+       "      --hover-bg-color: #E2EBFA;\n",
+       "      --hover-fill-color: #174EA6;\n",
+       "      --disabled-fill-color: #AAA;\n",
+       "      --disabled-bg-color: #DDD;\n",
+       "  }\n",
+       "\n",
+       "  [theme=dark] .colab-df-quickchart {\n",
+       "      --bg-color: #3B4455;\n",
+       "      --fill-color: #D2E3FC;\n",
+       "      --hover-bg-color: #434B5C;\n",
+       "      --hover-fill-color: #FFFFFF;\n",
+       "      --disabled-bg-color: #3B4455;\n",
+       "      --disabled-fill-color: #666;\n",
+       "  }\n",
+       "\n",
+       "  .colab-df-quickchart {\n",
+       "    background-color: var(--bg-color);\n",
+       "    border: none;\n",
+       "    border-radius: 50%;\n",
+       "    cursor: pointer;\n",
+       "    display: none;\n",
+       "    fill: var(--fill-color);\n",
+       "    height: 32px;\n",
+       "    padding: 0;\n",
+       "    width: 32px;\n",
+       "  }\n",
+       "\n",
+       "  .colab-df-quickchart:hover {\n",
+       "    background-color: var(--hover-bg-color);\n",
+       "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+       "    fill: var(--button-hover-fill-color);\n",
+       "  }\n",
+       "\n",
+       "  .colab-df-quickchart-complete:disabled,\n",
+       "  .colab-df-quickchart-complete:disabled:hover {\n",
+       "    background-color: var(--disabled-bg-color);\n",
+       "    fill: var(--disabled-fill-color);\n",
+       "    box-shadow: none;\n",
+       "  }\n",
+       "\n",
+       "  .colab-df-spinner {\n",
+       "    border: 2px solid var(--fill-color);\n",
+       "    border-color: transparent;\n",
+       "    border-bottom-color: var(--fill-color);\n",
+       "    animation:\n",
+       "      spin 1s steps(1) infinite;\n",
+       "  }\n",
+       "\n",
+       "  @keyframes spin {\n",
+       "    0% {\n",
+       "      border-color: transparent;\n",
+       "      border-bottom-color: var(--fill-color);\n",
+       "      border-left-color: var(--fill-color);\n",
+       "    }\n",
+       "    20% {\n",
+       "      border-color: transparent;\n",
+       "      border-left-color: var(--fill-color);\n",
+       "      border-top-color: var(--fill-color);\n",
+       "    }\n",
+       "    30% {\n",
+       "      border-color: transparent;\n",
+       "      border-left-color: var(--fill-color);\n",
+       "      border-top-color: var(--fill-color);\n",
+       "      border-right-color: var(--fill-color);\n",
+       "    }\n",
+       "    40% {\n",
+       "      border-color: transparent;\n",
+       "      border-right-color: var(--fill-color);\n",
+       "      border-top-color: var(--fill-color);\n",
+       "    }\n",
+       "    60% {\n",
+       "      border-color: transparent;\n",
+       "      border-right-color: var(--fill-color);\n",
+       "    }\n",
+       "    80% {\n",
+       "      border-color: transparent;\n",
+       "      border-right-color: var(--fill-color);\n",
+       "      border-bottom-color: var(--fill-color);\n",
+       "    }\n",
+       "    90% {\n",
+       "      border-color: transparent;\n",
+       "      border-bottom-color: var(--fill-color);\n",
+       "    }\n",
+       "  }\n",
+       "</style>\n",
+       "\n",
+       "      <script>\n",
+       "        async function quickchart(key) {\n",
+       "          const quickchartButtonEl =\n",
+       "            document.querySelector('#' + key + ' button');\n",
+       "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
+       "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
+       "          try {\n",
+       "            const charts = await google.colab.kernel.invokeFunction(\n",
+       "                'suggestCharts', [key], {});\n",
+       "          } catch (error) {\n",
+       "            console.error('Error during call to suggestCharts:', error);\n",
+       "          }\n",
+       "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
+       "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
+       "        }\n",
+       "        (() => {\n",
+       "          let quickchartButtonEl =\n",
+       "            document.querySelector('#df-54b2aa43-838b-47d3-9209-2fb18153cf87 button');\n",
+       "          quickchartButtonEl.style.display =\n",
+       "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+       "        })();\n",
+       "      </script>\n",
+       "    </div>\n",
+       "\n",
+       "    </div>\n",
+       "  </div>\n"
+      ],
+      "text/plain": [
+       "       Rainfall  Americas   Asia Europe Africa\n",
+       "0      (inches)      2010                     \n",
+       "1       Average       104  201.0  193.0  144.0\n",
+       "2  24 hour high        15   26.0   27.0   18.0\n",
+       "3  12 hour high         9   10.0   11.0   12.0\n",
+       "4                    2009                     \n",
+       "5       Average       133  244.0  155.0  166.0\n",
+       "6  24 hour high        27   28.0   29.0   20.0\n",
+       "7  12 hour high        11   12.0   13.0   16.0"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "from IPython.display import display\n",
+    "\n",
+    "df = pd.read_csv(\n",
+    "    \"/content/tables/table_2025_16_07_16_30_01_569.csv\",\n",
+    ")\n",
+    "display(df.fillna(\"\"))"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

examples/parse/excel/dcf_rag.ipynb

@@ -0,0 +1,493 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "0db58db5-d4ee-4631-af5b-4fc53eb05170",
+   "metadata": {},
+   "source": [
+    "# RAG with Excel Spreadsheet using LlamaPrase\n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/parse/excel/dcf_rag.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "This notebook constructs a RAG pipeline over a simple DCF template [here](https://eqvista.com/app/uploads/2020/09/Eqvista_DCF-Excel-Template.xlsx).\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5f7d99ad-6ebd-47d0-92a7-566630b0c22a",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "We first setup and load the data. If you haven't already, [download the template](https://eqvista.com/app/uploads/2020/09/Eqvista_DCF-Excel-Template.xlsx) and name it `dcf_template.xlxs` locally."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d867d1a6-cfcf-4f53-952a-f4a6ff2fa205",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-index\n",
+    "%pip install llama-cloud-services"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "103c7983-56d3-45be-b763-d1828d07c43e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7b694b56-e04b-4d87-aa37-f0725d6b3adb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_cloud_services import LlamaParse\n",
+    "\n",
+    "# api_key = \"llx-\"  # get from cloud.llamaindex.ai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9c4693c7-c1c8-47b4-8a8c-25d7e9ef9d2c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id cac11eca-d5da-4d46-90e6-321f40e11611\n",
+      "Started parsing the file under job_id cac11eca-5450-4847-9da0-fa6879c4cf3a\n"
+     ]
+    }
+   ],
+   "source": [
+    "parser = LlamaParse(\n",
+    "    # api_key=api_key,  # can also be set in your env as LLAMA_CLOUD_API_KEY\n",
+    "    result_type=\"markdown\",\n",
+    ")\n",
+    "docs = parser.load_data(\"./dcf_template.xlsx\")\n",
+    "# docs_txt = LlamaParse(result_type=\"text\").load_data(\"./dcf_template.xlsx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7302f1c8-e405-4cda-8ff7-1d55185816f7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "# Cover Page\n",
+      "\n",
+      "|Thank you for downloading our DCF Model excel template. This DCF Model excel template helps you to value your business using Discounted Free Cash Flow or DCF Method. |                                                                                                                                                                                  |\n",
+      "|----------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n",
+      "|                                                                                                                                                                      |                                                                                                                                                                                  |\n",
+      "|                                                                                                                                                                      |Eqvista is an equity management software that allows companies, investors and company shareholders to track, manage, and make intelligent decisions about their companies’ equity.|\n",
+      "|                                                                                                                                                                      |                                                                                                                                                                                  |\n",
+      "|                                                                                                                                                                      |GET STARTED- IT'S FREE                                                                                                                                                            |\n",
+      "|                                                                                                                                                                      |                                                                                                                                                                                  |\n",
+      "|                                                                                                                                                                      |Note: This template is not professional advice and not a substitute for professional advice.                                                                                      |\n",
+      "|Accordingly, before taking any actions based upon such information, we encourage you to consult with the appropriate professionals.                                   |                                                                                                                                                                                  |\n",
+      "|                                                                                                                                                                      |                                                                                                                                                                                  |\n",
+      "|                                                                                                                                                                      |@Eqvista Inc. All Rights Reserved                                                                                                                                                 |\n",
+      "---\n",
+      "# DCF Model\n",
+      "\n",
+      "|Discounted Cash Flow Excel Template                                                                                                                                                        |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------|-----------|-----------|-----------------------|-----------|-----------------------|--------------|-----------|-----------|-----------|--------------|\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Here is a simple discounted cash flow excel template for estimating your company value based on this income valuation approach                                                             |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Instructions:                                                                                                                                                                              |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|1) Fill out the two assumptions in yellow highlight                                                                                                                                        |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|2) Fill in either the 5 year or 3 year weighted average figures in yellow highlight                                                                                                        |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Assumptions                                                                                                                                                                                |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Tax Rate                                                                                                                                                                                   |20%                           |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Discount Rate                                                                                                                                                                              |15%                           |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|5 Year Weighted Moving Average                                                                                                                                                             |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Indication of Company Value                                                                                                                                                                |$242,995.43                   |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|3 Year Weighted Moving Average                                                                                                                                                             |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Indication of Company Value                                                                                                                                                                |$158,651.07                   |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |5 Year Weighted Moving Average|           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |Past Years                    |           |           |                       |           |Forecasted Future Years|              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |Year 1                        |Year 2     |Year 3     |Year 4                 |Year 5     |Year 6                 |Year 7        |Year 8     |Year 9     |Year 10    |Terminal Value|\n",
+      "|Pre-tax income                                                                                                                                                                             |50,000.00                     |55,000.00  |45,000.00  |52,000.00              |60,000.00  |                       |              |           |           |           |              |\n",
+      "|Income Taxes                                                                                                                                                                               |10,000.00                     |11,000.00  |9,000.00   |10,400.00              |12,000.00  |                       |              |           |           |           |              |\n",
+      "|Net Income                                                                                                                                                                                 |40,000.00                     |44,000.00  |36,000.00  |41,600.00              |48,000.00  |                       |              |           |           |           |              |\n",
+      "|Depreciation Expense                                                                                                                                                                       |5,000.00                      |4,000.00   |3,000.00   |2,000.00               |1,000.00   |                       |              |           |           |           |              |\n",
+      "|Capital Expenditures                                                                                                                                                                       |10,000.00                     |8,000.00   |5,000.00   |5,000.00               |7,000.00   |                       |              |           |           |           |              |\n",
+      "|Debt Repayments                                                                                                                                                                            |5,000.00                      |5,000.00   |5,000.00   |5,000.00               |5,000.00   |                       |              |           |           |           |              |\n",
+      "|Net Cash Flow                                                                                                                                                                              |20,000.00                     |27,000.00  |23,000.00  |29,600.00              |35,000.00  |29,093.33              |29,817.78     |30,177.48  |30,469.23  |30,379.74  |287,188.00    |\n",
+      "|Discounting Factor                                                                                                                                                                         |                              |           |           |                       |           |0.8696                 |0.7561        |0.6575     |0.5718     |0.4972     |0.4972        |\n",
+      "|Present Value of Future Cash Flow                                                                                                                                                          |                              |           |           |                       |           |25,298.55              |22,546.52     |19,842.18  |17,420.88  |15,104.10  |142,783.19    |\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |3 Year Weighted Moving Average|           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |Past Years                    |           |           |Forecasted Future Years|           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |Year 1                        |Year 2     |Year 3     |Year 4                 |Year 5     |Year 6                 |Terminal Value|           |           |           |              |\n",
+      "|Pre-tax income                                                                                                                                                                             |50,000.00                     |55,000.00  |45,000.00  |                       |           |                       |              |           |           |           |              |\n",
+      "|Income Taxes                                                                                                                                                                               |10,000.00                     |11,000.00  |9,000.00   |                       |           |                       |              |           |           |           |              |\n",
+      "|Net Income                                                                                                                                                                                 |40,000.00                     |44,000.00  |36,000.00  |                       |           |                       |              |           |           |           |              |\n",
+      "|Depreciation Expense                                                                                                                                                                       |5,000.00                      |4,000.00   |3,000.00   |                       |           |                       |              |           |           |           |              |\n",
+      "|Capital Expenditures                                                                                                                                                                       |10,000.00                     |8,000.00   |5,000.00   |                       |           |                       |              |           |           |           |              |\n",
+      "|Debt Repayments                                                                                                                                                                            |5,000.00                      |5,000.00   |5,000.00   |                       |           |                       |              |           |           |           |              |\n",
+      "|Net Cash Flow                                                                                                                                                                              |20,000.00                     |27,000.00  |23,000.00  |23,833.33              |24,083.33  |23,819.44              |158,253.59    |           |           |           |              |\n",
+      "|Discounting Factor                                                                                                                                                                         |                              |           |           |0.8696                 |0.7561     |0.6575                 |0.6575        |           |           |           |              |\n",
+      "|Present Value of Future Cash Flow                                                                                                                                                          |                              |           |           |20,724.64              |18,210.46  |15,661.67              |104,054.30    |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Notes:                                                                                                                                                                                     |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|-We based this simple discounted cash flow excel model based on the weighted moving averages (5 year or 3 year) for simplicity, in case a constant growth rate cannot be easily determined.|                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|-The factors such as Depreciation Expense, Capital Expense and Debt Repayments remain constant, so consider this when looking at the forecasted figures.                                   |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|-For the terminal value constant growth rate, we make the assumption of the growth from the last forecasted year compared to the first forecasted year. Adjust in the formula as needed.   |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[0].get_content())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1aedd4bb-7939-4fbc-8f07-d362e24d9772",
+   "metadata": {},
+   "source": [
+    "## Configure LLM, Setup Basic Summary Engine\n",
+    "\n",
+    "We setup a basic summary engine which retrieves the entire document as context to put into the prompt."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f7c056a8-d098-4ebe-9341-d9f07081067c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.llms.openai import OpenAI\n",
+    "from llama_index.core import Settings\n",
+    "\n",
+    "llm = OpenAI(model=\"gpt-4-turbo-preview\")\n",
+    "Settings.llm = llm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c0fa2630-ee1b-4ce7-91e9-f9ffff8347f9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import SummaryIndex\n",
+    "\n",
+    "index = SummaryIndex.from_documents(docs)\n",
+    "# index = SummaryIndex.from_documents(docs_txt)\n",
+    "\n",
+    "query_engine = index.as_query_engine()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1d39a075-46b8-4dcb-8aee-abd10343bedd",
+   "metadata": {},
+   "source": [
+    "## Define Baseline\n",
+    "\n",
+    "Let's define a baseline query engine over this data, using a naive parser (our PandasExcelReader, available on LlamaHub)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "632f918e-7811-4931-8a5f-4aa4850718db",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Collecting openpyxl\n",
+      "  Downloading openpyxl-3.1.3-py2.py3-none-any.whl (251 kB)\n",
+      "\u001b[2K     \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m251.3/251.3 kB\u001b[0m \u001b[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\n",
+      "\u001b[?25hCollecting et-xmlfile\n",
+      "  Using cached et_xmlfile-1.1.0-py3-none-any.whl (4.7 kB)\n",
+      "Installing collected packages: et-xmlfile, openpyxl\n",
+      "Successfully installed et-xmlfile-1.1.0 openpyxl-3.1.3\n",
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip available: \u001b[0m\u001b[31;49m22.2.2\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install llama-index-readers-file\n",
+    "!pip install openpyxl"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "85ff09fd-8a99-4aa4-8182-8d0cf30f7b85",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.readers.file import PandasExcelReader\n",
+    "import importlib\n",
+    "from pathlib import Path\n",
+    "\n",
+    "base_reader = PandasExcelReader()\n",
+    "base_docs = base_reader.load_data(Path(\"dcf_template.xlsx\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ba45f806-58be-4f57-bf42-2721555136cb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Discounted Cash Flow Excel Template           \n",
+      "           \n",
+      "Here is a simple discounted cash flow excel template for estimating your company value based on this income valuation approach           \n",
+      "           \n",
+      "Instructions:           \n",
+      "1) Fill out the two assumptions in yellow highlight           \n",
+      "2) Fill in either the 5 year or 3 year weighted average figures in yellow highlight           \n",
+      "           \n",
+      "           \n",
+      "           \n",
+      "           \n",
+      "Assumptions           \n",
+      "Tax Rate 0.2          \n",
+      "Discount Rate 0.15          \n",
+      "           \n",
+      "5 Year Weighted Moving Average           \n",
+      "Indication of Company Value 242995.4347636059          \n",
+      "           \n",
+      "3 Year Weighted Moving Average           \n",
+      "Indication of Company Value 158651.0723286644          \n",
+      "           \n",
+      " 5 Year Weighted Moving Average          \n",
+      " Past Years     Forecasted Future Years     \n",
+      " Year 1 Year 2 Year 3 Year 4 Year 5 Year 6 Year 7 Year 8 Year 9 Year 10 Terminal Value\n",
+      "Pre-tax income 50000 55000 45000 52000 60000      \n",
+      "Income Taxes 10000 11000 9000 10400 12000      \n",
+      "Net Income 40000 44000 36000 41600 48000      \n",
+      "Depreciation Expense 5000 4000 3000 2000 1000      \n",
+      "Capital Expenditures 10000 8000 5000 5000 7000      \n",
+      "Debt Repayments 5000 5000 5000 5000 5000      \n",
+      "Net Cash Flow 20000 27000 23000 29600 35000 29093.333333333332 29817.777777777774 30177.481481481478 30469.234567901232 30379.73991769547 287188.0007003137\n",
+      "Discounting Factor      0.8695652173913044 0.7561436672967865 0.6575162324319883 0.5717532455930334 0.4971767352982899 0.4971767352982899\n",
+      "Present Value of Future Cash Flow      25298.550724637684 22546.523839529513 19842.183927989798 17420.883754932976 15104.099911490972 142783.19260502496\n",
+      "           \n",
+      "           \n",
+      " 3 Year Weighted Moving Average          \n",
+      " Past Years   Forecasted Future Years       \n",
+      " Year 1 Year 2 Year 3 Year 4 Year 5 Year 6 Terminal Value    \n",
+      "Pre-tax income 50000 55000 45000        \n",
+      "Income Taxes 10000 11000 9000        \n",
+      "Net Income 40000 44000 36000        \n",
+      "Depreciation Expense 5000 4000 3000        \n",
+      "Capital Expenditures 10000 8000 5000        \n",
+      "Debt Repayments 5000 5000 5000        \n",
+      "Net Cash Flow 20000 27000 23000 23833.333333333332 24083.333333333332 23819.44444444444 158253.58851674633    \n",
+      "Discounting Factor    0.8695652173913044 0.7561436672967865 0.6575162324319883 0.6575162324319883    \n",
+      "Present Value of Future Cash Flow    20724.63768115942 18210.459987397608 15661.671369734164 104054.30329037321    \n",
+      "           \n",
+      "           \n",
+      "Notes:           \n",
+      "-We based this simple discounted cash flow excel model based on the weighted moving averages (5 year or 3 year) for simplicity, in case a constant growth rate cannot be easily determined.           \n",
+      "-The factors such as Depreciation Expense, Capital Expense and Debt Repayments remain constant, so consider this when looking at the forecasted figures.           \n",
+      "-For the terminal value constant growth rate, we make the assumption of the growth from the last forecasted year compared to the first forecasted year. Adjust in the formula as needed.           \n"
+     ]
+    }
+   ],
+   "source": [
+    "print(base_docs[1].get_content())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ff6e812f-fa94-4b0f-8907-ee70983e53f1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import SummaryIndex\n",
+    "\n",
+    "base_index = SummaryIndex.from_documents([base_docs[1]])\n",
+    "\n",
+    "base_query_engine = base_index.as_query_engine()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fa75f1bc-6fed-4721-ba5e-dc5408395618",
+   "metadata": {},
+   "source": [
+    "## Ask Questions over this Data\n",
+    "\n",
+    "Let's now ask questions over this data, using both the LlamaParse-powered pipeline and naive pipeline."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a875a20e-a6b6-46b7-80d4-614546215ffc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_str = \"Tell me about the income taxes in the past years (year 3-5) for the 5 year WMA table\"\n",
+    "response = query_engine.query(query_str)\n",
+    "base_response = base_query_engine.query(query_str)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "06b0b072-f159-47c4-9cad-9f0cc0d56b28",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "******* LlamaParse RAG *******\n",
+      "The income taxes in the past years (year 3 to 5) for the 5-year Weighted Moving Average table were $9,000.00 in Year 3, $10,400.00 in Year 4, and $12,000.00 in Year 5.\n",
+      "******* Naive RAG *******\n",
+      "The income taxes in the past years (year 3-5) for the 5 year WMA table were $9,000, $10,400, and $12,000, respectively.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"******* LlamaParse RAG *******\")\n",
+    "print(str(response))\n",
+    "print(\"******* Naive RAG *******\")\n",
+    "print(str(base_response))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8bd0998f-4f7f-46f9-9b51-cfb510f384ee",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(response.source_nodes[0].get_content())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7a93af5f-fcea-4f14-80eb-5dfad230cd8a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_str = \"Tell me about the discounting factors in year 5 for the 3 year WMA\"\n",
+    "response = query_engine.query(query_str)\n",
+    "base_response = base_query_engine.query(query_str)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c6d3a5fb-c32c-4dea-8f2e-956af85456a4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "******* LlamaParse RAG *******\n",
+      "The discounting factor in year 5 for the 3-year Weighted Moving Average (WMA) is 0.7561.\n",
+      "******* Naive RAG *******\n",
+      "The discounting factor in year 5 for the 3-year Weighted Moving Average is 0.6575162324319883.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"******* LlamaParse RAG *******\")\n",
+    "print(str(response))\n",
+    "print(\"******* Naive RAG *******\")\n",
+    "print(str(base_response))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b96f3a9b-6e99-4192-b6d6-447319d3c4fa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_str = \"Tell me about the projected net cash flow in years 7-9 for the 5 year WMA\"\n",
+    "response = query_engine.query(query_str)\n",
+    "base_response = base_query_engine.query(query_str)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "92b419b9-25ee-4d69-98d9-56c0a45b24af",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "******* LlamaParse RAG *******\n",
+      "The projected net cash flow for years 7 to 9 in the 5-year Weighted Moving Average scenario is as follows: Year 7 is $29,817.78, Year 8 is $30,177.48, and Year 9 is $30,469.23.\n",
+      "******* Naive RAG *******\n",
+      "The projected net cash flow for years 7 to 9 in the 5-year weighted moving average scenario is as follows: Year 7 is $29,093.33, Year 8 is $29,817.78, and Year 9 is $30,177.48.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"******* LlamaParse RAG *******\")\n",
+    "print(str(response))\n",
+    "print(\"******* Naive RAG *******\")\n",
+    "print(str(base_response))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama_parse",
+   "language": "python",
+   "name": "llama_parse"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}