LeonardoCofone/cofone

Cofone is a small python library to manage RAG

33
/ 100
Emerging

Combines BM25 and FAISS semantic search for retrieval, with support for 19 LLM providers (OpenAI, Anthropic, Gemini, Groq, Ollama, etc.) and 10 embedding options including fully local inference. Handles diverse sources—files, PDFs, URLs, Wikipedia, YouTube transcripts—with automatic document chunking, chat memory, streaming, and Pydantic-based structured output via a fluent Python API.

Available on PyPI.

Maintenance 10 / 25
Adoption 5 / 25
Maturity 18 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 05, 2026

Commits (30d)

0

Dependencies

5

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/LeonardoCofone/cofone"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.