Kenosis01/TinyRag

TinyRag is a minimal Python library for retrieval-augmented generation. It offers easy document ingestion, automatic text extraction, embedding generation, and retrieval with vector stores. Designed for quick setup and flexible provider configuration, TinyRag enables fast, contextual responses from language models.

39
/ 100
Emerging

Supports function-level codebase indexing across 7+ programming languages and plugs into multiple vector store backends (Faiss, ChromaDB, Pickle, in-memory), allowing developers to choose storage trade-offs. Operates entirely offline using all-MiniLM-L6-v2 embeddings by default, with optional AI provider integration (OpenAI, Azure, Anthropic, local models) for augmented chat without mandatory API keys.

No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 2 / 25
Adoption 7 / 25
Maturity 18 / 25
Community 12 / 25

How are scores calculated?

Stars

4

Forks

1

Language

Python

License

MIT

Last pushed

Aug 23, 2025

Monthly downloads

55

Commits (30d)

0

Dependencies

8

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/Kenosis01/TinyRag"

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