Deeptoai RAG系列教程

参考资料(按篇章汇总)

汇总 bRAG-langchain 各篇 sources,作为权威出处与延伸阅读

[1] 基础设置 sources

  1. LangSmith 文档:https://docs.smith.langchain.com/
  2. RAG 快速开始:https://python.langchain.com/docs/tutorials/rag/
  3. 计算 Token:https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
  4. OpenAI 嵌入:https://python.langchain.com/docs/integrations/text_embedding/openai
  5. 余弦相似度 FAQ:https://platform.openai.com/docs/guides/embeddings/frequently-asked-questions
  6. 文档加载器:https://python.langchain.com/docs/integrations/document_loaders/
  7. 递归切分:https://python.langchain.com/docs/how_to/recursive_text_splitter/
  8. 向量库汇总:https://python.langchain.com/docs/integrations/vectorstores/
  9. RAG 链:https://python.langchain.com/docs/how_to/sequence/

[2] 多查询 sources

  1. LangSmith 文档:https://docs.smith.langchain.com/
  2. MultiQueryRetriever:https://python.langchain.com/docs/how_to/MultiQueryRetriever/
  3. RAG Fusion Cookbook:https://github.com/langchain-ai/langchain/blob/master/cookbook/rag_fusion.ipynb
  4. 博文:Forget RAG, the future is RAG-Fusion:https://medium.com/towards-data-science/forget-rag-the-future-is-rag-fusion-1147298d8ad1
  5. 相关论文:
  6. HyDE Cookbook:https://github.com/langchain-ai/langchain/blob/master/cookbook/hypothetical_document_embeddings.ipynb

[3] 路由与结构化查询 sources

  1. LangSmith 文档:https://docs.smith.langchain.com/
  2. Routing 文档:https://python.langchain.com/docs/how_to/routing/
  3. Trace 示例1:https://smith.langchain.com/public/c2ca61b4-3810-45d0-a156-3d6a73e9ee2a/r
  4. Trace 示例2:https://smith.langchain.com/public/98c25405-2631-4de8-b12a-1891aded3359/r
  5. Query Construction 博文:https://blog.langchain.dev/query-construction/
  6. KG in RAG 博文:https://blog.langchain.dev/enhancing-rag-based-applications-accuracy-by-constructing-and-leveraging-knowledge-graphs/
  7. Query Analysis 文档:https://python.langchain.com/v0.1/docs/use_cases/query_analysis/
  8. Self-Query 文档:https://python.langchain.com/docs/how_to/self_query/

[4] 索引与高级检索 sources

  1. 文档切分视频(Greg Kamradt):https://www.youtube.com/watch?v=8OJC21T2SL4
  2. LangSmith 文档:https://docs.smith.langchain.com/
  3. 半结构化/多模态 RAG:https://blog.langchain.dev/semi-structured-multi-modal-rag/
  4. Multi-Vector 检索:https://python.langchain.com/docs/how_to/multi_vector/
  5. Dense X Retrieval 论文:https://arxiv.org/abs/2312.06648
  6. Parent Document Retriever:https://python.langchain.com/docs/how_to/parent_document_retriever/
  7. 高级检索视频:https://www.youtube.com/watch?v=jbGchdTL7d0
  8. RAPTOR 论文:https://arxiv.org/pdf/2401.18059
  9. RAPTOR 实现:https://github.com/langchain-ai/langchain/blob/master/cookbook/RAPTOR.ipynb

[5] 检索与重排序 sources

  1. LangSmith 文档:https://docs.smith.langchain.com/
  2. Cohere ReRank 文档:https://txt.cohere.com/rerank/
  3. Cohere Rerank 指南:https://python.langchain.com/docs/integrations/retrievers/cohere-reranker#doing-reranking-with-coherererank
  4. CRAG 深入视频:https://www.youtube.com/watch?v=E2shqsYwxck
  5. LangGraph CRAG Notebook:https://github.com/langchain-ai/langgraph/blob/main/examples/rag/langgraph_crag.ipynb
  6. LangGraph RAG 示例聚合:https://github.com/langchain-ai/langgraph/tree/main/examples/rag
  7. 长上下文影响视频:https://www.youtube.com/watch?v=SsHUNfhF32s
  8. Slides:https://docs.google.com/presentation/d/1mJUiPBdtf58NfuSEQ7pVSEQ2Oqmek7F1i4gBwR6JDss/edit#slide=id.g26c0cb8dc66_0_0