openextract 0.3.0__tar.gz

openextract-0.3.0/.github/CODEOWNERS

@@ -0,0 +1 @@
+* @colesmcintosh

openextract-0.3.0/.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,68 @@
+name: Bug Report
+description: Report a bug or unexpected behavior
+labels: ["bug"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to report a bug. Please fill out the information below.
+
+  - type: textarea
+    id: description
+    attributes:
+      label: Description
+      description: A clear description of the bug
+      placeholder: What happened?
+    validations:
+      required: true
+
+  - type: textarea
+    id: reproduction
+    attributes:
+      label: Steps to Reproduce
+      description: Minimal code example or steps to reproduce the issue
+      placeholder: |
+        ```python
+        from openextract import extract
+        # your code here
+        ```
+    validations:
+      required: true
+
+  - type: textarea
+    id: expected
+    attributes:
+      label: Expected Behavior
+      description: What did you expect to happen?
+    validations:
+      required: true
+
+  - type: textarea
+    id: actual
+    attributes:
+      label: Actual Behavior
+      description: What actually happened?
+    validations:
+      required: true
+
+  - type: input
+    id: version
+    attributes:
+      label: openextract Version
+      placeholder: "0.1.4"
+    validations:
+      required: true
+
+  - type: input
+    id: python-version
+    attributes:
+      label: Python Version
+      placeholder: "3.12"
+    validations:
+      required: true
+
+  - type: textarea
+    id: additional
+    attributes:
+      label: Additional Context
+      description: Any other relevant information (OS, LLM provider, error messages, etc.)

openextract-0.3.0/.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,5 @@
+blank_issues_enabled: true
+contact_links:
+  - name: Documentation
+    url: https://mellow-artificial-intelligence.github.io/openextract/
+    about: Check the documentation for usage guides and examples

openextract-0.3.0/.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,37 @@
+name: Feature Request
+description: Suggest a new feature or enhancement
+labels: ["enhancement"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for suggesting a feature. Please describe your idea below.
+
+  - type: textarea
+    id: problem
+    attributes:
+      label: Problem Statement
+      description: What problem does this feature solve?
+      placeholder: I'm trying to... but currently...
+    validations:
+      required: true
+
+  - type: textarea
+    id: solution
+    attributes:
+      label: Proposed Solution
+      description: How would you like this to work?
+    validations:
+      required: true
+
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Alternatives Considered
+      description: Any alternative solutions or workarounds you've considered?
+
+  - type: textarea
+    id: additional
+    attributes:
+      label: Additional Context
+      description: Any other context, examples, or references

openextract-0.3.0/.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,21 @@
+## Summary
+
+<!-- Brief description of the changes -->
+
+## Changes
+
+<!-- List of specific changes made -->
+
+-
+
+## Testing
+
+<!-- How were these changes tested? -->
+
+-
+
+## Checklist
+
+- [ ] Tests pass locally (`uv run pytest`)
+- [ ] Linting passes (`uv run ruff check .`)
+- [ ] Documentation updated (if applicable)

openextract-0.3.0/.github/workflows/ci.yml

@@ -0,0 +1,25 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v4
+      - run: uv sync --dev
+      - run: uv run ruff check .
+      - run: uv run ruff format --check .
+
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v4
+      - run: uv sync --dev
+      - run: uv run pytest -v

openextract-0.3.0/.github/workflows/deploy-docs.yml

@@ -0,0 +1,42 @@
+name: Deploy static content to Pages
+
+on:
+  # Runs on pushes targeting the default branch
+  push:
+    branches: ["main"]
+
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+# Sets permissions of the GITHUB_TOKEN to allow deployment to GitHub Pages
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+# Allow only one concurrent deployment, skipping runs queued between the run in-progress and latest queued.
+# However, do NOT cancel in-progress runs as we want to allow these production deployments to complete.
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  # Single deploy job since we're just deploying
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Setup Pages
+        uses: actions/configure-pages@v5
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          # Upload docs directory
+          path: './docs'
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

openextract-0.3.0/.github/workflows/release.yml

@@ -0,0 +1,59 @@
+name: Release
+
+on:
+  push:
+    branches: [main]
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+      id-token: write
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - uses: astral-sh/setup-uv@v4
+
+      - name: Get version from pyproject.toml
+        id: version
+        run: |
+          VERSION=$(grep -Po '(?<=^version = ")[^"]*' pyproject.toml)
+          echo "version=$VERSION" >> $GITHUB_OUTPUT
+          echo "tag=v$VERSION" >> $GITHUB_OUTPUT
+
+      - name: Check if release exists
+        id: check_release
+        run: |
+          VERSION=${{ steps.version.outputs.version }}
+          # Check git tag
+          if git rev-parse "v$VERSION" >/dev/null 2>&1; then
+            echo "exists=true" >> $GITHUB_OUTPUT
+            echo "Tag v$VERSION already exists"
+            exit 0
+          fi
+          # Check PyPI
+          if curl -s "https://pypi.org/pypi/openextract/$VERSION/json" | grep -q '"version"'; then
+            echo "exists=true" >> $GITHUB_OUTPUT
+            echo "Version $VERSION already exists on PyPI"
+          else
+            echo "exists=false" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Build package
+        if: steps.check_release.outputs.exists == 'false'
+        run: uv build
+
+      - name: Publish to PyPI
+        if: steps.check_release.outputs.exists == 'false'
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+      - name: Create GitHub Release
+        if: steps.check_release.outputs.exists == 'false'
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: ${{ steps.version.outputs.tag }}
+          name: ${{ steps.version.outputs.tag }}
+          generate_release_notes: true

openextract-0.3.0/.gitignore

@@ -0,0 +1,14 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv
+
+# Environment files
+.env
+test/test.pdf

openextract-0.3.0/.python-version

@@ -0,0 +1 @@
+3.12

openextract-0.3.0/CHANGELOG.md

@@ -0,0 +1,26 @@
+# Changelog
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
+
+## [0.2.0] - 2026-01-11
+- Landing page redesign and security updates.
+
+## [0.1.4] - 2025-12-21
+- Restructure project as installable Python package.
+- Add tests and error handling.
+- Initial commit: media extraction utility with pydantic-ai.
+
+## [0.1.2] - 2025-09-13
+- Add bytes-only vision API.
+- Render PDFs to images.
+- Support multimodal messaging.
+
+## [0.1.1] - 2025-09-10
+- Merge pull request #12 from Mellow-Artificial-Intelligence/new-release.
+
+[Unreleased]: https://github.com/Mellow-Artificial-Intelligence/openextract/compare/v0.2.0...HEAD
+[0.2.0]: https://github.com/Mellow-Artificial-Intelligence/openextract/compare/v0.1.4...v0.2.0
+[0.1.4]: https://github.com/Mellow-Artificial-Intelligence/openextract/compare/v0.1.2...v0.1.4
+[0.1.2]: https://github.com/Mellow-Artificial-Intelligence/openextract/compare/v0.1.1...v0.1.2
+[0.1.1]: https://github.com/Mellow-Artificial-Intelligence/openextract/releases/tag/v0.1.1

openextract-0.3.0/CONTRIBUTING.md

@@ -0,0 +1,54 @@
+# Contributing to openextract
+
+Thanks for your interest in contributing to openextract!
+
+## Development Setup
+
+1. Clone the repository:
+   ```bash
+   git clone https://github.com/Mellow-Artificial-Intelligence/openextract.git
+   cd openextract
+   ```
+
+2. Install dependencies with uv:
+   ```bash
+   uv sync --dev
+   ```
+
+3. Run tests:
+   ```bash
+   uv run pytest
+   ```
+
+4. Run linting:
+   ```bash
+   uv run ruff check .
+   uv run ruff format --check .
+   ```
+
+## Making Changes
+
+1. Create a new branch from `main`
+2. Make your changes
+3. Ensure tests pass and code is formatted
+4. Submit a pull request
+
+## Pull Request Guidelines
+
+- PRs require approval from a code owner before merging
+- Keep changes focused and atomic
+- Update tests for new functionality
+- Follow existing code style (enforced by ruff)
+
+## Code Style
+
+This project uses [ruff](https://docs.astral.sh/ruff/) for linting and formatting. Run before submitting:
+
+```bash
+uv run ruff check . --fix
+uv run ruff format .
+```
+
+## Questions?
+
+Open an issue on GitHub.

openextract-0.3.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Cole McIntosh
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

openextract-0.3.0/PKG-INFO

@@ -0,0 +1,113 @@
+Metadata-Version: 2.4
+Name: openextract
+Version: 0.3.0
+Summary: Extract structured data from documents, images, audio, and video using LLMs
+Project-URL: Homepage, https://github.com/Mellow-Artificial-Intelligence/openextract
+Project-URL: Documentation, https://mellow-artificial-intelligence.github.io/openextract/
+Project-URL: Repository, https://github.com/Mellow-Artificial-Intelligence/openextract
+Project-URL: Issues, https://github.com/Mellow-Artificial-Intelligence/openextract/issues
+Project-URL: Changelog, https://github.com/Mellow-Artificial-Intelligence/openextract/blob/main/CHANGELOG.md
+Author: Cole McIntosh
+License-Expression: MIT
+License-File: LICENSE
+Keywords: ai,document,extraction,llm,pydantic,structured-data
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.12
+Requires-Dist: pydantic-ai-slim[google,logfire]>=1.37.0
+Requires-Dist: pydantic>=2.12.5
+Requires-Dist: python-dotenv>=1.2.2
+Description-Content-Type: text/markdown
+
+# openextract
+
+[![PyPI version](https://img.shields.io/pypi/v/openextract.svg)](https://pypi.org/project/openextract/)
+[![PyPI downloads](https://img.shields.io/pypi/dm/openextract.svg)](https://pypi.org/project/openextract/)
+[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.python.org/downloads/)
+[![CI](https://github.com/Mellow-Artificial-Intelligence/openextract/actions/workflows/ci.yml/badge.svg)](https://github.com/Mellow-Artificial-Intelligence/openextract/actions/workflows/ci.yml)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Coverage](https://img.shields.io/badge/coverage-100%25-brightgreen.svg)](https://github.com/Mellow-Artificial-Intelligence/openextract)
+[![Pydantic v2](https://img.shields.io/badge/pydantic-v2-E92063.svg)](https://docs.pydantic.dev/)
+[![pydantic-ai](https://img.shields.io/badge/pydantic--ai-1.37+-7C3AED.svg)](https://ai.pydantic.dev/)
+
+Extract structured data from documents, images, audio, and video using LLMs.
+
+## Installation
+
+```bash
+uv add openextract
+```
+
+## Usage
+
+```python
+from pydantic import BaseModel
+from openextract import extract
+
+class PdfInfo(BaseModel):
+    summary: str
+    language: str
+
+result = extract(
+    schema=PdfInfo,
+    model="openai-responses:gpt-5.2",
+    url="https://example.com/document.pdf",
+    instructions="return a 2 sentence summary and the primary language of the document",
+)
+print(result)
+```
+
+## Logging
+
+To enable logfire instrumentation for tracing:
+
+```python
+from openextract import configure_logging
+
+configure_logging()
+```
+
+## Error Handling
+
+```python
+from openextract import (
+    extract,
+    ExtractionError,
+    ModelError,
+    SchemaValidationError,
+    UrlFetchError,
+)
+
+try:
+    result = extract(...)
+except UrlFetchError as e:
+    print(f"Failed to fetch URL: {e}")
+except SchemaValidationError as e:
+    print(f"Output didn't match schema: {e}")
+except ModelError as e:
+    print(f"Model API error: {e}")
+except ExtractionError as e:
+    print(f"Extraction failed: {e}")
+```
+
+## Supported Media Types
+
+| Type | Extensions |
+|------|------------|
+| Documents | `.pdf`, `.doc`, `.docx`, `.txt`, `.html`, `.csv`, `.xls`, `.xlsx` |
+| Images | `.jpg`, `.jpeg`, `.png`, `.gif`, `.webp`, `.bmp`, `.svg` |
+| Audio | `.mp3`, `.wav`, `.ogg`, `.flac`, `.aac`, `.m4a` |
+| Video | `.mp4`, `.mov`, `.avi`, `.mkv`, `.webm`, `.wmv` |
+
+## Changelog
+
+See [CHANGELOG.md](CHANGELOG.md) for release history.
+
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup and guidelines.

openextract-0.3.0/README.md

@@ -0,0 +1,87 @@
+# openextract
+
+[![PyPI version](https://img.shields.io/pypi/v/openextract.svg)](https://pypi.org/project/openextract/)
+[![PyPI downloads](https://img.shields.io/pypi/dm/openextract.svg)](https://pypi.org/project/openextract/)
+[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.python.org/downloads/)
+[![CI](https://github.com/Mellow-Artificial-Intelligence/openextract/actions/workflows/ci.yml/badge.svg)](https://github.com/Mellow-Artificial-Intelligence/openextract/actions/workflows/ci.yml)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Coverage](https://img.shields.io/badge/coverage-100%25-brightgreen.svg)](https://github.com/Mellow-Artificial-Intelligence/openextract)
+[![Pydantic v2](https://img.shields.io/badge/pydantic-v2-E92063.svg)](https://docs.pydantic.dev/)
+[![pydantic-ai](https://img.shields.io/badge/pydantic--ai-1.37+-7C3AED.svg)](https://ai.pydantic.dev/)
+
+Extract structured data from documents, images, audio, and video using LLMs.
+
+## Installation
+
+```bash
+uv add openextract
+```
+
+## Usage
+
+```python
+from pydantic import BaseModel
+from openextract import extract
+
+class PdfInfo(BaseModel):
+    summary: str
+    language: str
+
+result = extract(
+    schema=PdfInfo,
+    model="openai-responses:gpt-5.2",
+    url="https://example.com/document.pdf",
+    instructions="return a 2 sentence summary and the primary language of the document",
+)
+print(result)
+```
+
+## Logging
+
+To enable logfire instrumentation for tracing:
+
+```python
+from openextract import configure_logging
+
+configure_logging()
+```
+
+## Error Handling
+
+```python
+from openextract import (
+    extract,
+    ExtractionError,
+    ModelError,
+    SchemaValidationError,
+    UrlFetchError,
+)
+
+try:
+    result = extract(...)
+except UrlFetchError as e:
+    print(f"Failed to fetch URL: {e}")
+except SchemaValidationError as e:
+    print(f"Output didn't match schema: {e}")
+except ModelError as e:
+    print(f"Model API error: {e}")
+except ExtractionError as e:
+    print(f"Extraction failed: {e}")
+```
+
+## Supported Media Types
+
+| Type | Extensions |
+|------|------------|
+| Documents | `.pdf`, `.doc`, `.docx`, `.txt`, `.html`, `.csv`, `.xls`, `.xlsx` |
+| Images | `.jpg`, `.jpeg`, `.png`, `.gif`, `.webp`, `.bmp`, `.svg` |
+| Audio | `.mp3`, `.wav`, `.ogg`, `.flac`, `.aac`, `.m4a` |
+| Video | `.mp4`, `.mov`, `.avi`, `.mkv`, `.webm`, `.wmv` |
+
+## Changelog
+
+See [CHANGELOG.md](CHANGELOG.md) for release history.
+
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup and guidelines.

openextract-0.3.0/SECURITY.md

@@ -0,0 +1,20 @@
+# Security Policy
+
+## Supported Versions
+
+| Version | Supported          |
+| ------- | ------------------ |
+| 0.2.x   | :white_check_mark: |
+| 0.1.x   | :x:                |
+
+## Reporting a Vulnerability
+
+If you discover a security vulnerability, please report it by emailing the maintainers directly rather than opening a public issue.
+
+**Please include:**
+- Description of the vulnerability
+- Steps to reproduce
+- Potential impact
+- Any suggested fixes (optional)
+
+We will acknowledge receipt within 48 hours and aim to provide a fix within 7 days for critical issues.

openextract-0.3.0/docs/_config.yml

@@ -0,0 +1,18 @@
+title: openextract Documentation
+description: Open-source framework that extracts structured data from PDFs
+baseurl: "/openextract"
+url: "https://mellow-artificial-intelligence.github.io"
+
+markdown: kramdown
+highlighter: rouge
+theme: minima
+
+plugins:
+  - jekyll-feed
+  - jekyll-sitemap
+
+exclude:
+  - Gemfile
+  - Gemfile.lock
+  - node_modules
+  - vendor