incidentfox/OpenRag
Multi-strategy RAG system achieving 74% Recall@10 on MultiHop-RAG. Combines RAPTOR hierarchical retrieval, knowledge graphs, HyDE, BM25, and Cohere neural reranking.
This project helps operations engineers, data scientists, or research analysts quickly get precise answers from large collections of documents. You input a question, and it sifts through your documents, like news articles or technical reports, to deliver highly relevant text snippets or facts, even for complex questions requiring multiple steps of reasoning. It's designed for users who need to find specific information efficiently within their internal knowledge bases or public datasets.
Use this if you need to build a robust question-answering system that can accurately retrieve information from a vast document corpus, even when questions require combining insights from multiple sources.
Not ideal if you primarily need a simple keyword search tool, or if your document set is very small and doesn't require advanced retrieval strategies.
Stars
36
Forks
5
Language
Python
License
MIT
Category
Last pushed
Feb 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/incidentfox/OpenRag"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
HKUDS/LightRAG
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
beir-cellar/beir
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across...
HKUDS/RAG-Anything
"RAG-Anything: All-in-One RAG Framework"
superlinear-ai/raglite
🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL
illuin-tech/vidore-benchmark
Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.