[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-74058":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":8,"htmlUrl":8,"language":9,"languages":8,"totalLinesOfCode":8,"stars":10,"forks":11,"watchers":12,"openIssues":13,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":15,"stars7d":16,"stars30d":17,"stars90d":14,"forks30d":14,"starsTrendScore":18,"compositeScore":19,"rankGlobal":8,"rankLanguage":8,"license":8,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":8,"pushedAt":8,"updatedAt":24,"readmeContent":25,"aiSummary":26,"trendingCount":14,"starSnapshotCount":14,"syncStatus":27,"lastSyncTime":28,"discoverSource":29},74058,"rag-from-scratch","langchain-ai\u002Frag-from-scratch","langchain-ai",null,"Jupyter Notebook",8510,2041,64,24,0,49,112,273,147,109.93,false,"main",true,[],"2026-06-12 04:01:13","# RAG From Scratch\n\nLLMs are trained on a large but fixed corpus of data, limiting their ability to reason about private or recent information. Fine-tuning is one way to mitigate this, but is often [not well-suited for factual recall](https:\u002F\u002Fwww.anyscale.com\u002Fblog\u002Ffine-tuning-is-for-form-not-facts) and [can be costly](https:\u002F\u002Fwww.glean.com\u002Fblog\u002Fhow-to-build-an-ai-assistant-for-the-enterprise).\nRetrieval augmented generation (RAG) has emerged as a popular and powerful mechanism to expand an LLM's knowledge base, using documents retrieved from an external data source to ground the LLM generation via in-context learning. \nThese notebooks accompany a [video playlist](https:\u002F\u002Fyoutube.com\u002Fplaylist?list=PLfaIDFEXuae2LXbO1_PKyVJiQ23ZztA0x&feature=shared) that builds up an understanding of RAG from scratch, starting with the basics of indexing, retrieval, and generation. \n![rag_detail_v2](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Frag-from-scratch\u002Fassets\u002F122662504\u002F54a2d76c-b07e-49e7-b4ce-fc45667360a1)\n \n[Video playlist](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLfaIDFEXuae2LXbO1_PKyVJiQ23ZztA0x)","该项目通过检索增强生成（RAG）技术，扩展了大型语言模型的知识库，使其能够利用外部数据源中的文档进行更准确的信息生成。核心功能包括索引、检索和生成，这些步骤通过一系列Jupyter Notebook详细展示，并辅以配套的视频教程，帮助用户从零开始构建对RAG的理解与应用。特别适用于需要处理私有或最新信息但又希望保持成本效益的企业场景中，比如企业内部知识管理、客服系统等，使得即使在不进行昂贵微调的情况下也能有效提升LLM的事实性回忆能力。",2,"2026-06-11 03:48:36","high_star"]