Content Processing API

Web API for content extraction and analysis using GPT and vector search.

• Content extraction from URLs using Playwright
• Text analysis with OpenAI GPT-4
• Semantic search with ChromaDB and LangChain
• REST API with FastAPI
• Web UI with Bootstrap 5
• Comprehensive test coverage
• CI/CD with GitHub Actions

• Python 3.11+
• FastAPI + Pydantic
• OpenAI GPT-4
• ChromaDB + LangChain
• Playwright

• Bootstrap 5
• Jinja2 Templates
• Vanilla JavaScript

1. Clone the repository:

git clone <repo>
cd <project-dir>

2. Configure environment:

cp .env.example .env
# Edit .env with your OpenAI API key

3. Build and run with Docker Compose:

docker-compose up --build

The API will be available at http://localhost:8000

Run the test suite in a Docker container:

# Run all tests
docker-compose run --rm app pytest

src/
├── api/ # API routes
├── core/ # Core functionality
├── models/ # Data models
├── services/ # Business logic
├── web/ # Web interface
└── tests/ # Test suites

POST /api/content/process
Content-Type: application/json
{
 "url": "string" | "urls": ["string"]
}

GET /api/search/content?query=string&limit=number

See API Documentation for complete reference.

MIT

• OpenAI for GPT models
• ChromaDB team
• FastAPI framework
• Playwright project