# PAI-RAG

> An easy-to-use framework for modular RAG

- **URL**: https://www.freshcrate.ai/projects/PAI-RAG
- **Author**: aigc-apps
- **Category**: Frameworks
- **Latest version**: `v0.4.3` (2026-02-11)
- **License**: MIT
- **Source**: https://github.com/aigc-apps/PAI-RAG
- **Language**: Python
- **GitHub**: 455 stars, 70 forks
- **Registry**: github
- **Tags**: `python`

## Description

An easy-to-use framework for modular RAG

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v0.4.3` | 2026-02-11 | Low | ## What's Changed * Support English ui * Add simple react agent * Support streamable http mcp server  **Full Changelog**: https://github.com/aigc-apps/PAI-RAG/compare/v0.4.2-20260128...v0.4.3 |
| `v0.4.2-20260128` | 2026-01-28 | Low | ## What's Changed * Add rag trace by @moria97 in https://github.com/aigc-apps/PAI-RAG/pull/803 * Add rerank span operation name by @moria97 in https://github.com/aigc-apps/PAI-RAG/pull/804 * Fix mcp contract and request-id by @moria97 in https://github.com/aigc-apps/PAI-RAG/pull/806 * Fix kb mcp api by @moria97 in https://github.com/aigc-apps/PAI-RAG/pull/807 * Refine rag trace span name by @moria97 in https://github.com/aigc-apps/PAI-RAG/pull/808 * add file parsing and FAQ by @Ceceliachen |
| `v0.4.2-20251230` | 2025-12-30 | Low | 1. Refine knowledgebases: metadata filtering, add knowledgebase mcp server 2. Upgrade code tool  ## What's Changed * Update new docker version by @moria97 in https://github.com/aigc-apps/PAI-RAG/pull/756 * add DashScope reranker by @Ceceliachenen in https://github.com/aigc-apps/PAI-RAG/pull/758 * fix code tool by @Ceceliachenen in https://github.com/aigc-apps/PAI-RAG/pull/757 * Add new pdf parser by @moria97 in https://github.com/aigc-apps/PAI-RAG/pull/760 * add retrieval reranker config |
| `v0.4.1-20251107` | 2025-11-07 | Low | ## ✨ New Feature Code Tool Added: Enables data analysis directly on spreadsheet files (e.g., .xlsx, .csv), empowering users to explore and process structured data programmatically.  ## 🛠️ Improvements Enhanced QA for Attachments: Improved accuracy and responsiveness when performing question-answering over uploaded documents (e.g., images, excel).  ## 🐞 Bug Fixes Fixed a hang issue in evaluation jobs, improving system reliability. Resolved special unicode character handling when persist |
| `v0.4.0-20251024` | 2025-10-27 | Low | 🚀 Introducing Agentic RAG!  We’re excited to announce the release of Agentic RAG — a next-generation, autonomous RAG system designed to tackle complex reasoning tasks while ensuring enterprise-grade control and extensibility.  ✨ Key Highlights:  🧠 Agentic Task Planning Dynamically decompose and execute multi-step reasoning workflows to handle complex, real-world queries. 📁 Advanced Knowledge Base Management Fine-grained file-level access control, secure permissioning, and full lifecy |
| `v0.3.5-20251024` | 2025-10-27 | Low | Bugfixes on v0.3.4 - Fix multimodal file parsing  error - Fix internal image link error - Add streaming canceled error handling - Add correlation-id in log |
| `v0.3.4-20250612` | 2025-06-16 | Low | 1. Separate prompts for websearch/  knowledgebase 2. UI refinement. |
| `v0.3.2-20250410` | 2025-04-10 | Low | 1. Fix excel upload error 2. Fix knowledge base limit 3. Fix elastic search timeout |
| `r-v0.2.0-2-20250219` | 2025-02-19 | Low | # 更新概述 以下为本次版本更新的主要内容，包括每项功能和修复的概述，感谢所有贡献者的辛勤工作。  # 主要更改 - 压缩问题描述：添加了对中文提示的支持，提升了问题描述的简洁性。 - 修复 Poetry 配置：优化了项目的 Poetry 配置。 - 支持 Web 検索意图：增强了对 Web 搜索的意图支持。 - 新增阿里云搜索功能：集成了阿里云搜索服务。 - 优化历史记录功能：对历史记录的管理进行了优化。 - 优化提示模板：改进了提示模板的结构和内容。 - 修复多项问题：进行了一系列问题修复，提升稳定性。 - 修复查询变换及意图检测问题：解决了查询转换中的问题，并移除了意图检测功能。 - 修复 V1 聊天系统提示：更新和修正了聊天功能的系统提示。 - 升级阿里云访问密钥及响应解析：改进了阿里云的访问密钥管理和响应解析。 - 优化聊天记录存储：改进了聊天记录的存储机制。由 @moria97 提交。 - 修复 Markdown 树结构问题：解决了 Markdown 树的弹出问题。 - 将转换后的查询添加到查询字符串：增加了将转换后的查询附加到查询字符串的功 |
| `v0.2.0-20250212` | 2025-02-12 | Low | ## 新功能 - 文档处理增强   - 增加了 PDF 和图像的 OCR 选项，提升了对不同文档类型的支持。   - 添加了 Markdown 树解析器，优化了文档的结构化处理。 - 向量存储扩展   - 引入了 Tablestore 和 Dashvector 向量存储，增强了数据检索和管理能力。 - 搜索功能升级   - 支持 Deepseek 和 Quark 搜索，扩大了搜索的覆盖范围和精确度。 - 多语言支持   - 添加了英文版的提示模板，提升了多语言用户的使用体验。  ## 主要改进 - 架构与性能优化   - 将 Ray 任务替换为 actors，提高了系统的并发处理能力和性能。   - 对 Personal/xi/nl2sql 模块进行了模块化重构，增强了代码的可维护性和扩展性。 - 用户界面优化   - 优化了参考文献的展示界面，提升了用户的浏览体验。   - 改进了聊天页面的功能，修复了相关的显示与交互问题。 - 解析器更新   - 更新了 SQL 解析器和 Markdown 解析器，增强了对复杂语法的支持和解析准确性。  # |

## Dependency audit

- **Score**: 100/100
- **Total deps**: 0
- **Resolved**: 0
- **Unresolved**: 0
- **License conflicts**: 0
- **Warnings**: 0
- **Scanned**: 2026-05-04

## Citation

- HTML: https://www.freshcrate.ai/projects/PAI-RAG
- Markdown: https://www.freshcrate.ai/projects/PAI-RAG.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/PAI-RAG/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._