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
- LangSmith 文档:https://docs.smith.langchain.com/
- RAG 快速开始:https://python.langchain.com/docs/tutorials/rag/
- 计算 Token:https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
- OpenAI 嵌入:https://python.langchain.com/docs/integrations/text_embedding/openai
- 余弦相似度 FAQ:https://platform.openai.com/docs/guides/embeddings/frequently-asked-questions
- 文档加载器:https://python.langchain.com/docs/integrations/document_loaders/
- 递归切分:https://python.langchain.com/docs/how_to/recursive_text_splitter/
- 向量库汇总:https://python.langchain.com/docs/integrations/vectorstores/
- RAG 链:https://python.langchain.com/docs/how_to/sequence/
[2] 多查询 sources
- LangSmith 文档:https://docs.smith.langchain.com/
- MultiQueryRetriever:https://python.langchain.com/docs/how_to/MultiQueryRetriever/
- RAG Fusion Cookbook:https://github.com/langchain-ai/langchain/blob/master/cookbook/rag_fusion.ipynb
- 博文:Forget RAG, the future is RAG-Fusion:https://medium.com/towards-data-science/forget-rag-the-future-is-rag-fusion-1147298d8ad1
- 相关论文:
- Least-To-Most Prompting:https://arxiv.org/pdf/2205.10625.pdf
- IRCoT:https://arxiv.org/abs/2212.10509
- Take A Step Back:https://arxiv.org/pdf/2310.06117.pdf
- HyDE:https://arxiv.org/abs/2212.10496
- 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
- LangSmith 文档:https://docs.smith.langchain.com/
- Routing 文档:https://python.langchain.com/docs/how_to/routing/
- Trace 示例1:https://smith.langchain.com/public/c2ca61b4-3810-45d0-a156-3d6a73e9ee2a/r
- Trace 示例2:https://smith.langchain.com/public/98c25405-2631-4de8-b12a-1891aded3359/r
- Query Construction 博文:https://blog.langchain.dev/query-construction/
- KG in RAG 博文:https://blog.langchain.dev/enhancing-rag-based-applications-accuracy-by-constructing-and-leveraging-knowledge-graphs/
- Query Analysis 文档:https://python.langchain.com/v0.1/docs/use_cases/query_analysis/
- Self-Query 文档:https://python.langchain.com/docs/how_to/self_query/
[4] 索引与高级检索 sources
- 文档切分视频(Greg Kamradt):https://www.youtube.com/watch?v=8OJC21T2SL4
- LangSmith 文档:https://docs.smith.langchain.com/
- 半结构化/多模态 RAG:https://blog.langchain.dev/semi-structured-multi-modal-rag/
- Multi-Vector 检索:https://python.langchain.com/docs/how_to/multi_vector/
- Dense X Retrieval 论文:https://arxiv.org/abs/2312.06648
- Parent Document Retriever:https://python.langchain.com/docs/how_to/parent_document_retriever/
- 高级检索视频:https://www.youtube.com/watch?v=jbGchdTL7d0
- RAPTOR 论文:https://arxiv.org/pdf/2401.18059
- RAPTOR 实现:https://github.com/langchain-ai/langchain/blob/master/cookbook/RAPTOR.ipynb
[5] 检索与重排序 sources
- LangSmith 文档:https://docs.smith.langchain.com/
- Cohere ReRank 文档:https://txt.cohere.com/rerank/
- Cohere Rerank 指南:https://python.langchain.com/docs/integrations/retrievers/cohere-reranker#doing-reranking-with-coherererank
- CRAG 深入视频:https://www.youtube.com/watch?v=E2shqsYwxck
- LangGraph CRAG Notebook:https://github.com/langchain-ai/langgraph/blob/main/examples/rag/langgraph_crag.ipynb
- LangGraph RAG 示例聚合:https://github.com/langchain-ai/langgraph/tree/main/examples/rag
- 长上下文影响视频:https://www.youtube.com/watch?v=SsHUNfhF32s
- Slides:https://docs.google.com/presentation/d/1mJUiPBdtf58NfuSEQ7pVSEQ2Oqmek7F1i4gBwR6JDss/edit#slide=id.g26c0cb8dc66_0_0