ictnlp/LevelRAG

The official implementation of "LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers"

36
/ 100
Emerging

This helps with answering complex, knowledge-intensive questions by finding and combining information from various sources. You input a multi-part question, and it breaks it down, searches different databases (like Wikipedia or the web), and then synthesizes a comprehensive answer. It's designed for researchers, analysts, or anyone who needs detailed, accurate answers from vast amounts of text.

No commits in the last 6 months.

Use this if you frequently need to answer complex questions that require stitching together facts from multiple documents or the internet, where a simple keyword search isn't enough.

Not ideal if your questions are simple, single-fact lookups or if you only need answers from a very limited, static set of documents.

knowledge-retrieval question-answering information-synthesis research-automation data-sourcing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

51

Forks

6

Language

Python

License

MIT

Last pushed

Apr 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/ictnlp/LevelRAG"

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