Home/Data & Retrieval/rag-fusion

rag-fusion

Raudaschl/rag-fusion

multi-query generation + Reciprocal Rank Fusion for retrieval-augmented generation

GitHub

GraphCanon updated today · GitHub synced today

952 stars115 forksLast push 3mo Python MIT

Decision brief

RAG-Fusion leverages multi-query generation and Reciprocal Rank Fusion for enhanced retrieval-augmented generation tasks, supporting evaluations via NFCorpus/BEIR.

Good fit when

For enhancing precision in retrieval-augmented generation tasks needing complex query processing
When using BEIR or similar datasets to benchmark your generation models

Avoid when

If you require real-time performance, as multi-query generation may introduce latency
In scenarios where only simple keyword-based search suffices without the need for advanced fusion techniques

Observed Jul 15, 2026 · Source: enrich:decision_facts

rag-fusion alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Slowing (118d since push); As of today
Provenance: Not a fork · Personal account; As of today
Security (OSV): No lockfile; As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install rag-fusion

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

RAG_Techniques

Showcases advanced techniques for Retrieval-Augmented Generation (RAG) systems with detailed notebook tutorials.

29k★

awesome-ai-apps

A curated list of AI applications showcasing RAG, agents, and workflows.

13k★

paper-qa

High accuracy RAG for answering questions from scientific documents with citations

9.0k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

RAG-Fusion uses multi-query generation and Reciprocal Rank Fusion to improve retrieval-augmented generation applications. It provides an evaluation framework using NFCorpus/BEIR.

Capability facts

Languages: python
Source: github.language · Aug 23, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

OpenAI APIOpenAI API

Source: README excerpt (regex_v1, Aug 23, 2026)

2. Set up your OpenAI API key:

Source link

Python runtimePython

Source: README excerpt (regex_v1, Aug 23, 2026)

pip install openai chromadb python-dotenv tqdm tabulate rank_bm25

Source link

README

Getting Started

Install dependencies:

pip install openai chromadb python-dotenv tqdm tabulate rank_bm25

Set up your OpenAI API key:
```
cp .env.example .env
```
Then edit .env and replace your-key-here with your actual key.
Run the demo:
```
python main.py
```
Run the tests (no API key needed):
```
python -m pytest test_main.py -v
```

For agents

This page has a .md twin and JSON over the API.

/tools/raudaschl-rag-fusion.md GET /api/graphcanon/tools/raudaschl-rag-fusion GET /api/graphcanon/graph?tool=raudaschl-rag-fusion