allen-li1231/treehop-rag

Highly Efficient Query Rewriter for Passage Retrieval in the realm of Retrieval-Augmented Generation (RAG)

36
/ 100
Emerging

This project helps anyone working with AI chatbots or information retrieval systems quickly answer complex questions that require stitching together information from multiple sources. It takes a complex query and an existing database of documents, then efficiently finds and returns the most relevant passages needed to answer the question, even if it requires several 'hops' between related pieces of information. This is ideal for developers building faster and more cost-effective RAG (Retrieval-Augmented Generation) applications.

No commits in the last 6 months.

Use this if you need to make your multi-hop question-answering systems significantly faster and more resource-efficient without sacrificing accuracy.

Not ideal if your queries are always simple and can be answered from a single document, or if you don't mind slower response times and higher computational costs from traditional LLM-based query rewriting.

AI chatbot development information retrieval question answering knowledge management search engine optimization
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 12 / 25

How are scores calculated?

Stars

30

Forks

4

Language

Python

License

MIT

Last pushed

May 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/allen-li1231/treehop-rag"

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