didiergarcia/tiny-rag

TinyRAG is a minimalist Python library that enables developers to rapidly build RAG-powered applications. It supports a flexible range of LLM endpoints and provides a clean API for combining retrieval with generation.

13
/ 100
Experimental

This project helps developers quickly build systems that can answer specific questions using your own documents, even on topics a language model doesn't know about. You input a PDF document and a question, and it gives you a precise answer, drawing information directly from your document. This is for developers prototyping or creating applications that need to provide up-to-date, document-specific answers.

No commits in the last 6 months.

Use this if you need to quickly prototype a system that can answer questions about content in your own PDF documents, especially when working with limited computing resources or needing to update information beyond a language model's training data.

Not ideal if you need a production-ready system with advanced error handling, security, and scalability for a large user base or very complex document sets.

AI-application-development information-retrieval document-querying prototype-development
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 4 / 25
Maturity 7 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Jupyter Notebook

License

Last pushed

Jun 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/didiergarcia/tiny-rag"

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