weizhepei/InstructRAG

[ICLR 2025] InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales

36
/ 100
Emerging

This project helps AI developers build more reliable and trustworthy systems that answer questions using external information. It takes a query and a set of retrieved documents (which might be noisy) and produces a more accurate, verifiable answer by having the system explain its reasoning. AI engineers and researchers working on question-answering systems would use this to improve the quality of their AI's responses.

138 stars. No commits in the last 6 months.

Use this if you are building a question-answering AI and need it to provide more accurate, verifiable responses, especially when dealing with potentially noisy or irrelevant information.

Not ideal if you are looking for a pre-built, end-user application rather than a framework for developing AI models.

AI development natural language processing question answering AI research information retrieval
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

138

Forks

9

Language

Python

License

MIT

Last pushed

Feb 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/weizhepei/InstructRAG"

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