Data

Tools

Indexes

Applications

Experiments

Open Source Science

flexrag

FlexRAG: A RAG Framework for Information Retrieval and Generation.

https://github.com/ictnlp/flexrag

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 4 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.5%) to scientific vocabulary

Keywords

llms nlp rag
Last synced: 6 months ago · JSON representation ·

Repository

FlexRAG: A RAG Framework for Information Retrieval and Generation.

Basic Info
Statistics
  • Stars: 214
  • Watchers: 6
  • Forks: 20
  • Open Issues: 6
  • Releases: 15
Topics
llms nlp rag
Created about 1 year ago · Last pushed 8 months ago
Metadata Files
Readme License Citation

README-zh.md

Language Code Style Imports: isort github license Read the Docs Read the Docs PyPI - Version DOI

| 介绍视频 | README (english) | 文档 | 检索器 | 示例 |

FlexRAG 是一个创新的开源框架，旨在简化 RAG（检索增强生成）系统的快速复现、开发和评估。它全面支持多种 RAG 场景，包括 基于文本的、多模态的以及可通过 Web 访问的 RAG 。借助从数据准备到系统评估的端到端流水线，FlexRAG 能够帮助研究人员高效地与社区共享他们的工作，并快速基于自己的算法开发演示原型。

📖 目录

✨ 框架特色

📢 最新消息

  • 2025-03-24: 中文文档上线啦！请访问 文档 查看。
  • 2025-02-25: FlexRAG 的 LocalRetriever 现在支持从 HuggingFace Hub 上加载啦！
  • 2025-01-22: 新的命令行入口 run_retriever 以及大量新的信息检索指标（如 RetrievalMAP ）现已上线，请阅读文档以获取更多信息。
  • 2025-01-08: FlexRAG 现已支持 Windows 系统，您可以直接通过 pip install flexrag 来安装。
  • 2025-01-08: FlexRAG 在单跳QA数据集上的基准测试现已公开，详情请参考 benchmarks 页面。
  • 2025-01-05: FlexRAG 的文档现已上线。

🚀 框架入门

从 pip 安装 FlexRAG: bash pip install flexrag

访问我们的文档以了解更多信息。 - 安装 - 快速入门 - 教程

🏗️ FlexRAG 架构

FlexRAG 采用模块化架构设计，让您可以轻松定制和扩展框架以满足您的特定需求。下图说明了 FlexRAG 的架构：

📊 基准测试

我们利用 FlexRAG 进行了大量的基准测试，详情请参考 benchmarks 页面。

🏷️ 许可证

本仓库采用 MIT License 开源协议. 详情请参考 LICENSE 文件。

🖋️ 引用

如果您在研究中使用了 FlexRAG，请引用我们的项目： bibtex @software{Zhang_FlexRAG_2025, author = {Zhang, Zhuocheng and Feng, Yang and Zhang, Min}, doi = {10.5281/zenodo.14593327}, month = jan, title = {{FlexRAG}}, url = {https://github.com/ictnlp/FlexRAG}, year = {2025} }

❤️ 致谢

下面的开源项目对本项目有所帮助: - Faiss - FlashRAG - LanceDB - ANN Benchmarks - Chonkie - rerankers

Owner

  • Name: ICTNLP
  • Login: ictnlp
  • Kind: organization
  • Email: ict_nlp@ict.ac.cn
  • Location: Beijing, China

Natural Language Processing Group, Institute of Computing Technology, Chinese Academy of Sciences

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - family-names: "Zhang"
    given-names: "Zhuocheng"
    orcid: "https://orcid.org/0009-0004-4131-7968"
  - family-names: "Feng"
    given-names: "Yang"
  - family-names: "Zhang"
    given-names: "Min"
title: "FlexRAG"
doi: 10.5281/zenodo.14306983
url: "https://github.com/ictnlp/FlexRAG"

GitHub Events

Total
  • Create event: 8
  • Release event: 1
  • Issues event: 11
  • Watch event: 71
  • Delete event: 4
  • Issue comment event: 12
  • Push event: 23
  • Pull request event: 11
  • Fork event: 4
Last Year
  • Create event: 8
  • Release event: 1
  • Issues event: 11
  • Watch event: 71
  • Delete event: 4
  • Issue comment event: 12
  • Push event: 23
  • Pull request event: 11
  • Fork event: 4

Committers

Last synced: 7 months ago

All Time
  • Total Commits: 316
  • Total Committers: 2
  • Avg Commits per committer: 158.0
  • Development Distribution Score (DDS): 0.003
Past Year
  • Commits: 228
  • Committers: 2
  • Avg Commits per committer: 114.0
  • Development Distribution Score (DDS): 0.004
Top Committers
Name Email Commits
zhangzhuocheng z****g@1****m 315
Vincent XU k****g@g****m 1
Committer Domains (Top 20 + Academic)
163.com: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 13
  • Total pull requests: 20
  • Average time to close issues: 14 days
  • Average time to close pull requests: 17 minutes
  • Total issue authors: 10
  • Total pull request authors: 3
  • Average comments per issue: 1.23
  • Average comments per pull request: 0.0
  • Merged pull requests: 15
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 13
  • Pull requests: 20
  • Average time to close issues: 14 days
  • Average time to close pull requests: 17 minutes
  • Issue authors: 10
  • Pull request authors: 3
  • Average comments per issue: 1.23
  • Average comments per pull request: 0.0
  • Merged pull requests: 15
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • VincentXWD (3)
  • thunderbolt-fire (2)
  • huihuieew (1)
  • Andy-Zyu (1)
  • yangyihui2020 (1)
  • successhaha (1)
  • astrocaster (1)
  • kevin801221 (1)
  • ZhuochengZhang98 (1)
  • Skisses (1)
Pull Request Authors
  • ZhuochengZhang98 (17)
  • VincentXWD (1)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 785 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 0
  • Total versions: 13
  • Total maintainers: 1
pypi.org: flexrag

Flexible RAG (Retrieval-Augmented Generation) framework for building AI applications.

  • Versions: 13
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 785 Last month
Rankings
Dependent packages count: 9.8%
Average: 32.6%
Dependent repos count: 55.3%
Maintainers (1)
zhuocheng
Last synced: 6 months ago

Dependencies

.github/workflows/publish.yaml actions
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
pyproject.toml pypi
requirements.txt pypi
  • accelerate >=0.26.0
  • beautifulsoup4 *
  • bm25s *
  • elasticsearch >=8.14.0
  • hydra-core >=1.3
  • lancedb *
  • lmdb *
  • numpy <2.0.0
  • omegaconf >=2.3.0
  • openai >=1.30.1
  • pandas *
  • pillow *
  • rouge *
  • sacrebleu >=2.4.2
  • tenacity *
  • torch >=2.3.0
  • tqdm *
  • transformers >=4.44.0
  • unidecode *
setup.py pypi
docs/requirements.docs.txt pypi
  • accelerate >=0.26.0
  • beautifulsoup4 *
  • bm25s *
  • elasticsearch >=8.14.0
  • hydra-core >=1.3
  • lmdb *
  • myst-parser ==4.0.0
  • numpy <2.0.0
  • omegaconf >=2.3.0
  • openai >=1.30.1
  • pandas *
  • pillow *
  • pylance *
  • rouge *
  • sacrebleu >=2.4.2
  • sacremoses *
  • sphinx ==8.1.3
  • sphinx-book-theme ==1.1.3
  • sphinx-copybutton ==0.5.2
  • tenacity *
  • torch >=2.3.0
  • transformers >=4.44.0
  • unidecode *