作者： 老刘说NLP 来源： 老刘说NLP

今天是2024年1月17日，星期三，北京，天气阴。

我们再来谈谈RAG方面的一些事情，再总结一下。

最近看到一个比较好的总结归档项目：https://github.com/lizhe2004/Awesome-LLM-RAG-Application，其中整理了一些有趣的RAG相关资料，对增强我们对RAG的理解会有一些帮助，分享出来，供大家一起参考。

具体包括RAG评估、RAG应用参考、开源RAG框架、RAG操作实践总结。

一、RAG评估

1、Evaluating RAG Applications with RAGAs

https://towardsdatascience.com/evaluating-rag-applications-with-ragas-81d67b0ee31a

2、用 RAGAs（检索增强生成评估）评估 RAG（检索增强型生成）应用

https://baoyu.io/translations/rag/evaluating-rag-applications-with-ragas

3、Best Practices for LLM Evaluation of RAG Applications

https://www.databricks.com/blog/LLM-auto-eval-best-practices-RAG

4、RAG应用的LLM评估最佳实践（译）

https://tczjw7bsp1.feishu.cn/docx/TQJcdzfcfomL4QxqgkfchvbOnog?from=from_copylink

5、Exploring End-to-End Evaluation of RAG Pipelines

https://webcache.googleusercontent.com/search?q=cache:https://betterprogramming.pub/exploring-end-to-end-evaluation-of-rag-pipelines-e4c03221429

6、探索 RAG 管道的端到端评估

https://tczjw7bsp1.feishu.cn/wiki/XL8WwjYU9i1sltkawl1cYOounOg?from=from_copylink

7、Evaluating Multi-Modal Retrieval-Augmented Generation

https://blog.llamaindex.ai/evaluating-multi-modal-retrieval-augmented-generation-db3ca824d428

8、评估多模态检索增强生成

https://tczjw7bsp1.feishu.cn/docx/DrDQdj29DoDhahx9439cjb30nrd?from=from_copylink

9、RAG Evaluation

https://cobusgreyling.medium.com/rag-evaluation-9813a931b3d4

10、RAG评估

https://tczjw7bsp1.feishu.cn/wiki/WzPnwFMgbisICCk9BFrc9XYanme?from=from_copylink

11、Evaluation - LlamaIndex

https://docs.llamaindex.ai/en/stable/module_guides/evaluating/root.html

12、评估-LlamaIndex

https://tczjw7bsp1.feishu.cn/wiki/KiSow8rXviiHDWki4kycULRWnqg?from=from_copylink

13、框架ragas https://github.com/explodinggradients/ragas?tab=readme-ov-file

14、框架tonic_validate

https://github.com/TonicAI/tonic_validate

15、框架deepeval

https://github.com/confident-ai/deepeval

16、框架trulens

https://github.com/truera/trulens

17、框架langchain-evaluation

https://python.langchain.com/docs/guides/evaluation/

18、框架Llamaindex-evaluation

https://docs.llamaindex.ai/en/stable/optimizing/evaluation/evaluation.html

二、RAG应用参考

1、Kimi Chat

https://kimi.moonshot.cn/

2、GPTs

https://chat.openai.com/gpts/mine

3、百川知识库

https://platform.baichuan-ai.com/knowledge

4、COZE

https://www.coze.com/

三、开源RAG框架

1、LangChain

https://github.com/langchain-ai/langchain/

2、langchain4j

https://github.com/langchain4j/langchain4j

3、LlamaIndex

https://github.com/run-llama/llama_index/

4、Unstructured

https://github.com/Unstructured-IO/unstructured 和预处理，使其能够适应不同的平台，并有效地将非结构化数据转换为结构化输出。

5、GPT-RAG

https://github.com/Azure/GPT-RAG

6、QAnything

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

7、Quivr

https://github.com/StanGirard/quivr

8、Dify

https://github.com/langgenius/dify

9、Verba

https://github.com/weaviate/Verba

10、danswer https://github.com/danswer-ai/danswer

四、51篇RAG操作实践

1、Retrieval-Augmented Generation (RAG: From Theory to LangChain Implementation)

https://towardsdatascience.com/retrieval-augmented-generation-rag-from-theory-to-langchain-implementation-4e9bd5f6a4f2

2、中译版 检索增强生成（RAG）：从理论到 LangChain 实践

https://baoyu.io/translations/rag/retrieval-augmented-generation-rag-from-theory-to-langchain-implementation

3、A Guide on 12 Tuning Strategies for Production-Ready RAG Applications

https://towardsdatascience.com/a-guide-on-12-tuning-strategies-for-production-ready-rag-applications-7ca646833439

4、12 种调整策略指南：为生产环境打造高效的 RAG 应用

https://baoyu.io/translations/rag/a-guide-on-12-tuning-strategies-for-production-ready-rag-applications

5、Building Performant RAG Applications for Production

https://docs.llamaindex.ai/en/stable/optimizing/production_rag.html

6、构建用于生产环境的高性能 RAG 应用程序

https://tczjw7bsp1.feishu.cn/wiki/VT5qwPOwQimGAqkzAVWc1PQmnfe?from=from_copylink

7、Practical Considerations in RAG Application Design

https://pub.towardsai.net/practical-considerations-in-rag-application-design-b5d5f0b2d19b

8、RAG 应用程序设计中的实用注意事项

https://tczjw7bsp1.feishu.cn/docx/QODydp3wSo3QohxZwZucIbL8nHc?from=from_copylink

9、Building RAG-based LLM Applications for Production

https://www.anyscale.com/blog/a-comprehensive-guide-for-building-rag-based-llm-applications-part-1#reranking-experiments

10、搭建基于RAG的用于生产环境的LLM应用

https://tczjw7bsp1.feishu.cn/docx/MJnPdkuTnoN5TYxqzHecNTUEnee?from=from_copylink

11、Why Your RAG is Not Reliable in a Production

https://webcache.googleusercontent.com/search?q=cache:https://towardsdatascience.com/why-your-rag-is-not-reliable-in-a-production-environment-9e6a73b3eddb

12、为什么你的RAG应用在生产环境中不可靠

https://tczjw7bsp1.feishu.cn/docx/RjsCdsDbro6JxExAeWPcgap1nTc?from=from_copylink

13、Why do RAG pipelines fail? Advanced RAG Patterns — Part1

https://cloudatlas.me/why-do-rag-pipelines-fail-advanced-rag-patterns-part1-841faad8b3c2

14、为什么 RAG 流水线会失败？高级 RAG 模式 — 第 1 部分

https://tczjw7bsp1.feishu.cn/docx/KHkwdRrg9oAcd1xTNMDcsmBqnSp?from=from_copylink

15、How to improve RAG peformance — Advanced RAG Patterns — Part2

https://cloudatlas.me/how-to-improve-rag-peformance-advanced-rag-patterns-part2-0c84e2df66e6

16、如何提高 RAG 性能 — 高级 RAG 模式

https://tczjw7bsp1.feishu.cn/docx/H5pDd8g8Lo2wanxuUaGcCkEjnYg?from=from_copylink

17、Multi-Modal RAG

https://blog.llamaindex.ai/multi-modal-rag-621de7525fea

18、多模态RAG

https://tczjw7bsp1.feishu.cn/docx/OwXadpyWIopYc5xNvv9cErEZnLc?from=from_copylink

19、10 Ways to Improve the Performance of Retrieval Augmented Generation Systems

https://towardsdatascience.com/10-ways-to-improve-the-performance-of-retrieval-augmented-generation-systems-5fa2cee7cd5c

20、提高检索增强生成（RAG）系统性能的 10 种方法

https://tczjw7bsp1.feishu.cn/docx/ChhJdoSH8oLIHix6Nr6cZE12nqg

21、The Complete Guide to Retrieval Augmented Generation (RAG）

https://webcache.googleusercontent.com/search?q=cache:https://medium.com/@alcarazanthony1/the-complete-guide-to-retrieval-augmented-generation-rag-3ce54a57d8be

22、检索增强生成（RAG）完整指南

https://tczjw7bsp1.feishu.cn/wiki/WKawwO7lmir7BqkH39jcz4hdnAe

23、Crafting Knowledgeable AI with Retrieval Augmentation: A Guide to Best Practices

https://webcache.googleusercontent.com/search?q=cache:https://ai.plainenglish.io/crafting-knowledgeable-ai-with-retrieval-augmentation-a-guide-to-best-practices-33c84626be1e

24、使用检索增强打造知识渊博的 AI：最佳实践指南

https://tczjw7bsp1.feishu.cn/docx/TEXbdfcYToU4QFxSeJzcTDRTnMe?from=from_copylink

25、Optimizing RAG for LLMs Apps

https://medium.com/@bijit211987/optimizing-rag-for-llms-apps-53f6056d8118

26、优化 RAG服务于为 LLM 应用

https://tczjw7bsp1.feishu.cn/docx/ES1PdAve3ocNb0x9pU3cNOtDngG

27、Fueling the RAG Engine : The Data Flywheel

https://webcache.googleusercontent.com/search?q=cache:https://medium.com/@alcarazanthony1/fueling-the-rag-engine-the-data-flywheel-fc958c6d68d8

28、为 RAG 引擎提供动力：数据飞轮

https://tczjw7bsp1.feishu.cn/docx/S4bodAeEuovzHDxQHMccqEUinnb?from=from_copylink

29、How Self-RAG Could Revolutionize Industrial LLMs

https://webcache.googleusercontent.com/search?q=cache:https://towardsdatascience.com/how-self-rag-could-revolutionize-industrial-llms-b33d9f810264

30、Self-RAG 如何彻底改变行业LLM

https://tczjw7bsp1.feishu.cn/docx/KoZ6dCtG9oBG8KxtclgcSE4HnKu?from=from_copylink

31、Best practices for your ChatGPT ‘on your data’ solution

https://medium.com/@imicknl/how-to-improve-your-chatgpt-on-your-data-solution-d1e842d87404

32、您的 ChatGPT “数据 “解决方案的最佳实践

https://tczjw7bsp1.feishu.cn/wiki/ZkrXwLfKui9VeskV6b7crHHwncJ?from=from_copylink

33、How an LLM Chatbot Works: Exploring Chat with Retrieval-Augmented Generation (RAG）

https://tczjw7bsp1.feishu.cn/docx/FQGcda7PDo307Zx3BF0cdX2SnKe?from=from_copylink

34、Pinecone-Retrieval Augmented Generation (RAG: Reducing Hallucinations in GenAI Applications）

https://www.pinecone.io/learn/retrieval-augmented-generation/

35、检索增强生成（RAG）：减少生成式AI应用的幻觉问题

https://tczjw7bsp1.feishu.cn/wiki/C7YcwmAp7iNa0TkTTUAcS6evn8e?from=from_copylink

36、RAG for Everyone: A Beginner’s Guide to Embedding & Similarity Search

https://blog.gopenai.com/rag-for-everyone-a-beginners-guide-to-embedding-similarity-search-and-vector-db-423946475c90

37、RAG适用于所有人：嵌入和相似性搜索初学者指南

https://tczjw7bsp1.feishu.cn/wiki/K4l1wWHMyiAqkskGBJwcs4W5n14?from=from_copylink

38、Retrieval Augmented Generation: Grounding AI Responses in Factual Data

https://medium.com/@minh.hoque/retrieval-augmented-generation-grounding-ai-responses-in-factual-data-b7855c059322

39、检索增强生成：将AI响应建立在事实数据的基础上

https://tczjw7bsp1.feishu.cn/wiki/OJkFwPDhgilHD4k9RrdcE0QCnTh?from=from_copylink

40、Leveraging LLMs on your domain-specific knowledge base

https://www.ml6.eu/blogpost/leveraging-llms-on-your-domain-specific-knowledge-base

41、在您的特定领域知识库上利用LLM

https://tczjw7bsp1.feishu.cn/wiki/SqfIwjdEGiHNEgk4o46ceuFJnOd?from=from_copylink

42、Build More Capable LLMs with Retrieval Augmented Generation

https://webcache.googleusercontent.com/search?q=cache:https://towardsdatascience.com/build-more-capable-llms-with-retrieval-augmented-generation-99d5f86e9779

43、通过检索增强生成构建功能更强大的 LLM

https://tczjw7bsp1.feishu.cn/wiki/SOL0wWptTihTUQk3Eogc4NpHnmc?from=from_copylink

44、LLM’s for Enterprises- Generative Q&A on Your Private Knowledge Base

https://webcache.googleusercontent.com/search?q=cache:https://medium.com/towards-generative-ai/llms-for-enterprises-architecture-for-generative-q-a-on-your-private-knowledge-base-a7c2e07690e8

45、LLM for Enterprise – 您的私人知识库上的生成问答

https://tczjw7bsp1.feishu.cn/wiki/RZIdwMpMti64PEkxzp1cdOewnze?from=from_copylink

46、Retrieval Augmented Generation (RAG& LLM: Examples）

https://vitalflux.com/retrieval-augmented-generation-rag-llm-examples/

47、检索增强生成（RAG）和LLM：示例

https://vitalflux.com/retrieval-augmented-generation-rag-llm-examples/

48、RAG Pipeline modeling

https://uxplanet.org/rag-pipeline-modeling-011e3e6cc803

49、RAG流水线模型

https://tczjw7bsp1.feishu.cn/docx/A5JFd3vcGokY94xcNogcfuNSnJb?from=from_copylink

50、Optimizing RAG for LLMs Apps

https://medium.com/@bijit211987/optimizing-rag-for-llms-apps-53f6056d8118

51、NVIDIA Advanced Document Question-Answering with LlamaIndex

https://github.com/NVIDIA/GenerativeAIExamples/blob/main/notebooks/04_llamaindex_hier_node_parser.ipynb

参考文献

1、https://github.com/lizhe2004/Awesome-LLM-RAG-Application

关于我们

老刘，刘焕勇，NLP开源爱好者与践行者，主页：https://liuhuanyong.github.io。

老刘说NLP，将定期发布语言资源、工程实践、技术总结等内容，欢迎关注。

对于想加入更优质的知识图谱、事件图谱、大模型AIGC实践、相关分享的，可关注公众号，在后台菜单栏中点击会员社区->会员入群加入。

​

更多AI工具，参考Github-AiBard123，国内AiBard123