Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
the resources about the application based on LLM with RAG pattern
| Date | Stars |
|---|---|
| 2026-07-31 | 1642 |
| 2026-08-06 | 1644 |
Today
+2 stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<h1>Awesome LLM RAG Application</h1>
<a href="https://awesome.re"><img src="https://awesome.re/badge.svg"/></a>
</div>
Awesome LLM RAG Application is a curated list of application resources based on LLM with RAG pattern.
(latest update: 2025-12-19)
---
- [综述](#综述)
- [论文](#论文)
- [其他资料](#其他资料)
- [介绍](#介绍)
- [比较](#比较)
- [开源工具](#开源工具)
- [RAG框架](#rag框架)
- [预处理](#预处理)
- [路由](#路由)
- [评测框架](#评测框架)
- [Embedding](#embedding)
- [爬虫](#爬虫)
- [安全护栏](#安全护栏)
- [Prompting](#prompting)
- [SQL增强](#sql增强)
- [LLM部署和serving](#llm部署和serving)
- [可观测性](#可观测性)
- [其他](#其他)
- [AI搜索类项目](#ai搜索类项目)
- [应用参考](#应用参考)
- [企业级实践](#企业级实践)
- [知识库建设](#知识库建设)
- [论文](#论文-1)
- [RAG构建策略](#rag构建策略)
- [总览](#总览)
- [预处理](#预处理-1)
- [查询问句分类和微调](#查询问句分类和微调)
- [检索](#检索)
- [查询语句改写](#查询语句改写)
- [检索策略](#检索策略)
- [GraphRAG](#graphrag)
- [检索后处理](#检索后处理)
- [重排序](#重排序)
- [Contextual（Prompt） Compression](#contextualprompt-compression)
- [其他](#其他-1)
- [评估](#评估)
- [幻觉](#幻觉)
- [课程](#课程)
- [视频](#视频)
- [图书](#图书)
- [编码实践](#编码实践)
- [其他](#其他-2)
---
## 综述
### 论文
论文顺序由近及远
- 2025.08.19 基于大模型的Deep Search智能体综述
- [《A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges》](https://arxiv.org/abs/2508.05668)
<details>
<summary>详情</summary>
</details>
- 2025.08.18 Deep Research: 自治型研究智能体综述
- [《Deep Research: A Survey of Autonomous Research Agents》](https://arxiv.org/abs/2508.12752)
<details>
<summary>详情</summary>
</details>
- 2025.08.13 Open Deep Research的优化和演进
- [《Improving and Evaluating Open Deep Research Agents》](https://arxiv.org/abs/2508.10152)
<details>
<summary>详情</summary>
</details>
https://arxiv.org/abs/2507.09477
- 2025.07.03 从网页搜索到智能体特性的深度研究功能：通过推理智能体优化搜索
- [《From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents》](https://arxiv.org/abs/2506.18959)
<details>
<summary>详情</summary>
</details>
- 2025.06.22 Deep Research Agents 总结
- [《Deep Research Agents: A Systematic Examination And Roadmap》](https://arxiv.org/abs/2506.12594)
<details>
<summary>详情</summary>
</details>
- 2025.06.14 Deep Research 总结
- [《A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications》](https://arxiv.org/abs/2506.12594)
<details>
<summary>详情</summary>
</details>
https://arxiv.org/abs/2506.18096
- 2025.02.04 Agentic RAG 总结
- [《Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG》](https://arxiv.org/abs/2501.09136)
<details>
<summary>详情</summary>
https://arxiv.org/abs/2501.09136
- 核心原理与机制：阐释Agentic RAG的基础概念及核心Agentic机制，包括反思（reflection）、规划（planning）、工具调用（tool use） 与多智能体协作（multi-agent collaboration）。
- 系统分类框架：构建Agentic RAG的详细分类体系，涵盖单智能体（single-agent）、多智能体（multi-agent）、层次化（hierarchical）、纠错型（corrective）、自适应（adaptive） 及图结构驱动（graph-based RAG） 等不同架构。
- 横向对比分析：系统比较传统RAG、Agentic RAG与智能体文档工作流（ADW） 的优劣势及适用场景。
- 落地应用案例：探索Agentic RAG在医疗诊断、个性化教育、金融风控、法律合规等行业的实际应用。
- 挑战与发展趋势：探讨该领域面临的系统可扩展性、AI伦理规范、多模态融合、人机协同模式等关键问题及未来方向。
</details>
- 2024.12.23 RAG中的查询优化技术总结
- [《A Survey of Query Optimization in Large Language Models》](https://arxiv.org/abs/2412.17558)
<details>
<summary>详情</summary>
https://arxiv.org/abs/2412.17558
- 对查询优化技术进行了梳理和分类，涵盖了扩展、消歧、分解和抽象四种主要方法。
</details>
- 2024.10.23 RAG技术演进的回顾总结
- [《A Comprehensive Survey of Retrieval-Augmented Generation (RAG: Evolution, Current Landscape and Future Directions》](https://arxiv.org/abs/2410.Excerpt of 64,148 characters
Read on GitHub
83
PSBigBig + MiniPS
1
wangzhihong · Beihang University · China
1
Zhmin Zhao · Software Analysis and Intelligence Lab (SAIL) & Lab on Maintenance, Construction and Intelligence of Software (MCIS) · Canada
1
Mervin Praison
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b80fe6317c8ece4f, llm:Repository title and description: "Awesome-LLM-RAG-Application" - "the resources about the application based on LLM with RAG pattern" indicating collections of resources for LLM applications that use Retrieval-Augmented Generation (RAG).
matched fp:b80fe6317c8ece4f, llm:Repository title and description: "Awesome-LLM-RAG-Application" - "the resources about the application based on LLM with RAG pattern" indicating collections of resources for LLM applications that use Retrieval-Augmented Generation (RAG).
matched fp:b80fe6317c8ece4f, llm:Repository title and description: "Awesome-LLM-RAG-Application" - "the resources about the application based on LLM with RAG pattern" indicating collections of resources for LLM applications that use Retrieval-Augmented Generation (RAG).
matched fp:b80fe6317c8ece4f, llm:Repository title and description: "Awesome-LLM-RAG-Application" - "the resources about the application based on LLM with RAG pattern" indicating collections of resources for LLM applications that use Retrieval-Augmented Generation (RAG).