经 AI Skill Hub 精选评估，rag-fusion — RAG 知识库工具中文文档 获评「强烈推荐」。这款AI工具在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 8.4 分，适合有一定技术背景的用户使用。
rag-fusion — RAG 知识库工具中文文档 是一款基于 Python 开发的开源工具，专注于 chromadb、information-retrieval、openai 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
rag-fusion — RAG 知识库工具中文文档 是一款基于 Python 开发的开源工具，专注于 chromadb、information-retrieval、openai 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
# 方式一：pip 安装（推荐）
pip install rag-fusion
# 方式二：虚拟环境安装（推荐生产环境）
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install rag-fusion
# 方式三：从源码安装（获取最新功能）
git clone https://github.com/Raudaschl/rag-fusion
cd rag-fusion
pip install -e .
# 验证安装
python -c "import rag_fusion; print('安装成功')"
# 命令行使用
rag-fusion --help
# 基本用法
rag-fusion input_file -o output_file
# Python 代码中调用
import rag_fusion
# 示例
result = rag_fusion.process("input")
print(result)
# rag-fusion 配置文件示例（config.yml） app: name: "rag-fusion" debug: false log_level: "INFO" # 运行时指定配置文件 rag-fusion --config config.yml # 或通过环境变量配置 export RAG_FUSION_API_KEY="your-key" export RAG_FUSION_OUTPUT_DIR="./output"
RAG-Fusion is a search methodology that aims to bridge the gap between traditional search paradigms and the multifaceted dimensions of human queries. Where Retrieval Augmented Generation (RAG) fuses vector search with generative models, RAG-Fusion goes a step further — employing multiple query generation and Reciprocal Rank Fusion to re-rank search results. The aim is to surface relevant material a single phrasing of the query would miss, particularly when the user's vocabulary doesn't match how the corpus is indexed.
For the full story behind the approach, see the article: Forget RAG, the Future is RAG-Fusion.
Where this technique fits, in one line: Properly-configured RAG-Fusion (hybrid_diverse+rerank: BM25 + vector × LLM rewrites, fused via RRF, then cross-encoder reranked) produces measurably better retrieval rankings and better generated answers than baseline retrieval — at proper sample sizes with confidence intervals, on every difficulty bucket, even with a strong reranker. The vector-only fusion variant is a different story — it's roughly a wash on average and net-negative on rich queries at the answer level. If you deploy fusion, deploy the hybrid variant. Detailed empirical writeup — n=200 paired-bootstrap CIs, three rerankers, six fusion variants, end-to-end LLM-judge answer eval, including a replication of arXiv 2603.02153v1 — lives inexperiments/arxiv-2603-02153-replication/.
python evaluate.py --sample 50
1. Install dependencies:
pip install openai chromadb python-dotenv tqdm tabulate rank_bm25
2. Set up your OpenAI API key:
cp .env.example .env
.env and replace your-key-here with your actual key.
3. Run the demo:
python main.py
4. Run the tests (no API key needed):
python -m pytest test_main.py -v
python evaluate.py --sample 10 --methods baseline
python evaluate.py --sample 200 --rerank --candidate-pool 50 \ --methods baseline hybrid rag-fusion rag-fusion-diverse hybrid-diverse
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一，可自由商用、修改、分发，仅需保留版权声明。
AI Skill Hub 点评：rag-fusion — RAG 知识库工具中文文档 的核心功能完整，质量优秀。对于AI 技术爱好者来说，这是一个值得纳入个人工具库的选择。建议先在非生产环境试用，再逐步推广。
| 原始名称 | rag-fusion |
| 原始描述 | RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR. |
| Topics | chromadbinformation-retrievalopenaipythonragrag-fusion |
| GitHub | https://github.com/Raudaschl/rag-fusion |
| License | MIT |
| 语言 | Python |
收录时间：2026-05-22 · 更新时间：2026-05-22 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。