https://zhuanlan.zhihu.com/p/31747625448
测试18种RAG技术找到最优方案
https://github.com/FareedKhan-dev/all-rag-techniques
------------------------
fareedkhan-dev-all-rag-techniques/ ├── README.md <- You are here! ├── 1_simple_rag.ipynb ├── 2_semantic_chunking.ipynb ├── 3_chunk_size_selector.ipynb ├── 4_context_enriched_rag.ipynb ├── 5_contextual_chunk_headers_rag.ipynb ├── 6_doc_augmentation_rag.ipynb ├── 7_query_transform.ipynb ├── 8_reranker.ipynb ├── 9_rse.ipynb ├── 10_contextual_compression.ipynb ├── 11_feedback_loop_rag.ipynb ├── 12_adaptive_rag.ipynb ├── 13_self_rag.ipynb ├── 14_proposition_chunking.ipynb ├── 15_multimodel_rag.ipynb ├── 16_fusion_rag.ipynb ├── 17_graph_rag.ipynb ├── 18_hierarchy_rag.ipynb ├── 19_HyDE_rag.ipynb ├── 20_crag.ipynb ├── 21_rag_with_rl.ipynb ├── requirements.txt <- Python dependencies └── data/└── val.json <- Sample validation data (queries and answers)└── AI_information.pdf <- A sample PDF document for testing.└── attention_is_all_you_need.pdf <- A sample PDF document for testing (for Multi-Modal RAG).