收藏！RAG入门参考资料开源大总结：RAG综述、介绍、比较、预处理、RAG Embedding等

AI寻奇录，一起来看看AI世界里的那些有趣的科技、有趣的产品、有趣的事件、有趣的人。

我们的第二篇来啦。

今天来看看RAG综述、RAG介绍、RAG比较、RAG预处理、RAG Embedding以及RAG检索的一下开源指引。

整理主要来自https://github.com/lizhe2004/Awesome-LLM-RAG-Application

## 一、RAG综述

**1、论文：Retrieval-Augmented Generation for Large Language Models: A Survey**

https://arxiv.org/abs/2312.10997

**2、面向大语言模型的检索增强生成技术：调查**

https://baoyu.io/translations/ai-paper/2312.10997-retrieval-augmented-generation-for-large-language-models-a-survey

**3、RAG-Survey**

https://github.com/Tongji-KGLLM/RAG-Survey/tree/main

**4、Advanced RAG Techniques: an Illustrated Overview**

https://pub.towardsai.net/advanced-rag-techniques-an-illustrated-overview-04d193d8fec6

**5、中译版 高级 RAG 技术：图解概览**

https://baoyu.io/translations/rag/advanced-rag-techniques-an-illustrated-overview

**6、高级RAG应用构建指南和总结**

https://blog.llamaindex.ai/a-cheat-sheet-and-some-recipes-for-building-advanced-rag-803a9d94c41b

**7、Patterns for Building LLM-based Systems & Products**

https://eugeneyan.com/writing/llm-patterns/

**8、构建LLM系统和应用的模式**

https://tczjw7bsp1.feishu.cn/docx/Z6vvdyAdXou7XmxuXt2cigZUnTb?from=from\_copylink

## 二、RAG介绍

**1、Microsoft=Retrieval Augmented Generation (RAG in Azure AI Search**

https://learn.microsoft.com/en-us/azure/search/retrieval-augmented-generation-overview

**2、Azure AI 搜索之检索增强生成（RAG）**

https://tczjw7bsp1.feishu.cn/docx/JJ7ldrO4Zokjq7xZIJcc5IZjnFh?from=from\_copylink

**3、azure openai design patterns- RAG**

https://github.com/microsoft/azure-openai-design-patterns/tree/main/patterns/03-retrieval-augmented-generation

**4、IBM-What is retrieval-augmented generation-IBM**

https://research.ibm.com/blog/retrieval-augmented-generation-RAG

**5、IBM-什么是检索增强生成**

https://tczjw7bsp1.feishu.cn/wiki/OMUVwsxlSiqjj4k4YkicUQbcnDg?from=from\_copylink

**6、Amazon-Retrieval Augmented Generation (RAG）**

https://docs.aws.amazon.com/sagemaker/latest/dg/jumpstart-foundation-models-customize-rag.html

**7、Nvidia=What Is Retrieval-Augmented Generation?**

https://blogs.nvidia.com/blog/what-is-retrieval-augmented-generation/?ncid=so-twit-174237&=&linkId=100000226744098

**8、英伟达-什么是检索增强生成**

https://tczjw7bsp1.feishu.cn/docx/V6ysdAewzoflhmxJDwTcahZCnYI?from=from\_copylink

**9、Meta-Retrieval Augmented Generation: Streamlining the creation of intelligent natural language processing models**

https://ai.meta.com/blog/retrieval-augmented-generation-streamlining-the-creation-of-intelligent-natural-language-processing-models/

**10、Meta-检索增强生成：简化智能自然语言处理模型的创建**

https://tczjw7bsp1.feishu.cn/wiki/TsL8wAsbtiLfDmk1wFJcQsiGnQb?from=from\_copylink

**11、Disadvantages of RAG**

https://medium.com/@kelvin.lu.au/disadvantages-of-rag-5024692f2c53

**12、RAG的缺点**

https://tczjw7bsp1.feishu.cn/docx/UZCCdKmLEo7VHQxWPdNcGzICnEd?from=from\_copylink

**13、Cohere-Introducing Chat with Retrieval-Augmented Generation (RAG）**

https://txt.cohere.com/chat-with-rag/

**14、Pinecone-Retrieval Augmented Generation**

https://www.pinecone.io/learn/series/rag/

**15、Knowledge Retrieval Takes Center Stage**

https://towardsdatascience.com/knowledge-retrieval-takes-center-stage-183be733c6e8

**14、知识检索成为焦点**

https://tczjw7bsp1.feishu.cn/docx/VELQdaizVoknrrxND3jcLkZZn8d?from=from\_copylink

## 三、RAG比较

**1、Retrieval-Augmented Generation (RAG or Fine-tuning — Which Is the Best Tool to Boost Your LLM Application?**

https://www.linkedin.com/pulse/retrieval-augmented-generation-rag-fine-tuning-which-best-victoria-s-

**2、RAG还是微调，优化LLM应用的最佳工具是哪个？**

https://tczjw7bsp1.feishu.cn/wiki/TEtHwkclWirBwqkWeddcY8HXnZf?chunked=false

**3、提示工程、RAGs 与微调的对比**

https://github.com/lizhe2004/Awesome-LLM-RAG-Application/blob/main/Prompting-RAGs-Fine-tuning.md

**4、RAG vs Finetuning — Which Is the Best Tool to Boost Your LLM Application?**

https://webcache.googleusercontent.com/search?q=cache:https://towardsdatascience.com/rag-vs-finetuning-which-is-the-best-tool-to-boost-your-llm-application-94654b1eaba7

**5、RAG 与微调 — 哪个是提升优化 LLM 应用的最佳工具？**

https://tczjw7bsp1.feishu.cn/wiki/Cs9ywwzJSiFrg9kX2r1ch4Nxnth

**6、A Survey on In-context Learning**

https://arxiv.org/abs/2301.00234

## 四、RAG预处理

**1、From Good to Great: How Pre-processing Documents Supercharges AI’s Output**

https://webcache.googleusercontent.com/search?q=cache:https://medium.com/mlearning-ai/from-good-to-great-how-pre-processing-documents-supercharges-ais-output-cf9ecf1bd18c

**2、从好到优秀：如何预处理文件来加速人工智能的输出**

https://tczjw7bsp1.feishu.cn/docx/HpFOdBVlIo2nE5xHN8GcPqaSnxg?from=from\_copylink

**3、5 Levels Of Text Splitting**

https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/5\_Levels\_Of\_Text\_Splitting.ipynb

**4、Semantic Chunker**

https://github.com/run-llama/llama-hub/blob/main/llama\_hub/llama\_packs/node\_parser/semantic\_chunking/semantic\_chunking.ipynb

## 五、RAG Embedding

**1、BCEmbedding**

https://github.com/netease-youdao/BCEmbedding/tree/master

**2、BGE-Embedding**

https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/baai\_general\_embedding

## 六、RAG检索

**1、Query Transformations**

https://blog.langchain.dev/query-transformations/

**2、基于LLM的RAG应用的问句转换的技巧（译）**

https://tczjw7bsp1.feishu.cn/docx/UaOJdXdIzoUTBTxIuxscRAJLnfh?from=from\_copylink

**3、Query Construction**

https://blog.langchain.dev/query-construction/

**4、查询构造**

https://tczjw7bsp1.feishu.cn/docx/Wo0Sdn23voh0Wqx245zcu1Kpnuf?from=from\_copylink

**5、Improving Retrieval Performance in RAG Pipelines with Hybrid Search**

https://towardsdatascience.com/improving-retrieval-performance-in-rag-pipelines-with-hybrid-search-c75203c2f2f5

**6、在 RAG 流程中提高检索效果：融合传统关键词与现代向量搜索的混合式搜索技术**

https://baoyu.io/translations/rag/improving-retrieval-performance-in-rag-pipelines-with-hybrid-search

**7、Multi-Vector Retriever for RAG on tables, text, and images**

https://blog.langchain.dev/semi-structured-multi-modal-rag/

**8、针对表格、文本和图片的RAG多向量检索器**

https://tczjw7bsp1.feishu.cn/docx/Q8T8dZC0qoV2KRxPh8ScqoHanHg?from=from\_copylink

**9、Relevance and ranking in vector search**

https://learn.microsoft.com/en-us/azure/search/vector-search-ranking#hybrid-search

**10、向量查询中的相关性和排序**

https://tczjw7bsp1.feishu.cn/docx/VJIWd90fUohXLlxY243cQhKCnXf?from=from\_copylink

**11、Boosting RAG: Picking the Best Embedding & Reranker models**

https://blog.llamaindex.ai/boosting-rag-picking-the-best-embedding-reranker-models-42d079022e83

**12、提升优化 RAG：挑选最好的嵌入和重排模型**

https://tczjw7bsp1.feishu.cn/docx/CtLCdwon9oDIF4x49mOchmjxnud?from=from\_copylink

**13、Azure Cognitive Search: Outperforming vector search with hybrid retrieval and ranking capabilities**

https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/azure-cognitive-search-outperforming-vector-search-with-hybrid/ba-p/3929167

**14、Azure认知搜索:通过混合检索和排序功能优于向量搜索**

https://tczjw7bsp1.feishu.cn/docx/CDtGdwQJXo0mYVxaLpecXWuRnLc?from=from\_copylink

**15、Optimizing Retrieval Augmentation with Dynamic Top-K Tuning for Efficient Question Answering**

https://medium.com/@sauravjoshi23/optimizing-retrieval-augmentation-with-dynamic-top-k-tuning-for-efficient-question-answering-11961503d4ae

**16、动态 Top-K 调优优化检索增强功能实现高效的问答**

https://tczjw7bsp1.feishu.cn/docx/HCzAdk2BmoBg3lxA7ZOcn3KlnJb?from=from\_copylink

**17、Building Production-Ready LLM Apps with LlamaIndex: Document Metadata for Higher Accuracy Retrieval**

https://webcache.googleusercontent.com/search?q=cache:https://betterprogramming.pub/building-production-ready-llm-apps-with-llamaindex-document-metadata-for-higher-accuracy-retrieval-a8ceca641fb5

**18、使用 LlamaIndex 构建生产就绪型 LLM 应用程序：用于更高精度检索的文档元数据**

https://tczjw7bsp1.feishu.cn/wiki/St29wfD5QiMcThk8ElncSe90nZe?from=from\_copylink

## 关于我们

AI寻奇录，一起来看看AI世界里的那些有趣的科技、有趣的产品、有趣的事件、有趣的人。

欢迎大家关注，会有收获的。