├── .gitignore ├── LICENSE ├── README.md ├── assets ├── knowledge_base_screenshot.png └── logo.png ├── data ├── 2wikimultihopqa │ ├── corpus.json │ └── samples.json ├── dataset_info.json ├── hotpotqa │ ├── corpus.json │ └── samples.json ├── multimodal_test_samples │ ├── documents.json │ ├── images │ │ ├── 1*2wrx2joD1PaAsC27pshn3A.png │ │ ├── 1*6pALyl4xZ2 G9LnGlMR18g.png │ │ ├── 1*93ZK9-74dYv4eXY-Oe bkA.png │ │ ├── 1*CTF2gfNwx4v7V-0qM4s6uw.png │ │ ├── 1*DbWfNKMRWJcomb9N5QIhOQ.png │ │ ├── 1*GFJ9 TnLk2oDnVGtXAwARw.png │ │ ├── 1*H7FLmJdZvGarmGGs81SIRA.png │ │ ├── 1*Jp-QxrEj IYlOga84KTyBw.png │ │ ├── 1*LM6CuPZiogendK21 UHwPA.png │ │ ├── 1*OB43zXlHa4fcnL3n44JxcQ.png │ │ ├── 1*OCjG5oY6DyOnLuo1 N4OlA.png │ │ ├── 1*PHsfndcMjOMoAdUAx8IJrw.png │ │ ├── 1*RYCIqV1Gfp18VkXfY411Xg.png │ │ ├── 1*VVWecqvibBb2vVXuyKU5rw.png │ │ ├── 1*b8pT6KIERk3ZPd-729TmXA.png │ │ ├── 1*chHcyzoxurmTuzVsYgrdLA.png │ │ ├── 1*k9jUdnEB8sR5g0fZzqSiNA.png │ │ ├── 1*mEipkYmePMYvX4t5tU8u2w.png │ │ ├── 1*oY5JoNIikQZj3RsXyMrb3w.png │ │ └── 1*yscMghSQVAQvQeHV6pZ4PQ.png │ ├── images_metadata.json │ ├── samples.json │ └── source_html_files │ │ ├── 2023-10-18_Using-a-Knowledge-Graph-to-implement-a-DevOps-RAG-application-b6ba24831b16.html │ │ ├── 2023-10-20_Constructing-knowledge-graphs-from-text-using-OpenAI-functions-096a6d010c17.html │ │ └── 2023-10-30_How-to-implement-Weaviate-RAG-applications-with-Local-LLMs-and-Embedding-models-24a9128eaf84.html ├── musique │ ├── corpus.json │ └── samples.json └── test_samples │ ├── corpus.json │ └── samples.json ├── docs ├── README.md ├── _navbar.md ├── _sidebar.md ├── api_reference.md ├── configuration.md ├── deployment.md ├── examples │ └── graph_rag.md ├── index.html ├── modules │ ├── graph_rag.md │ ├── mm_rag.md │ └── naive_rag.md └── quickstart.md ├── examples ├── TCL_rag │ ├── config.yaml │ ├── rag_flow.py │ └── test.py ├── bm25 │ ├── config.yaml │ └── main.py ├── faiss_construct │ ├── config.yaml │ └── faiss_constructor.py ├── graphrag │ └── config.yaml ├── multimodal_rag │ └── config.yaml └── rag │ └── config.yaml ├── main.py ├── mkdocs.yml ├── rag_factory ├── Embed │ ├── Embedding_Base.py │ ├── Embedding_Huggingface.py │ ├── __init__.py │ └── registry.py ├── Retrieval │ ├── Retriever │ │ ├── Retriever_BM25.py │ │ ├── Retriever_MultiPath.py │ │ ├── Retriever_VectorStore.py │ │ ├── registry.py │ │ └── test_bm25_retriever.py │ ├── RetrieverBase.py │ ├── __init__.py │ └── utils │ │ └── Fusion.py ├── Store │ ├── VectorStore │ │ ├── VectorStoreBase.py │ │ ├── VectorStore_Faiss.py │ │ ├── registry.py │ │ └── test.py │ └── __init__.py ├── agents │ ├── __init__.py │ └── agent_prompts.py ├── args.py ├── caches │ ├── __init__.py │ └── cache.py ├── documents │ ├── __init__.py │ └── kg_triples_parse.py ├── embeddings │ ├── __init__.py │ ├── clip.py │ └── openai_compatible.py ├── evaluations │ └── __init__.py ├── graph_constructor │ ├── __init__.py │ └── graphrag_constructor.py ├── indexer │ ├── graph_indexer │ │ └── __init__.py │ ├── multimodal_indexer │ │ └── __init__.py │ └── vector_indexer │ │ └── __init__.py ├── llms │ ├── __init__.py │ ├── dashscope │ │ ├── base.py │ │ └── utils.py │ ├── llm_base.py │ ├── openai_compatible.py │ ├── openai_llm.py │ ├── registry.py │ └── test.py ├── multi_modal_llms │ ├── __init__.py │ ├── dashscope │ │ ├── base.py │ │ └── utils.py │ └── openai_compatible.py ├── parser │ ├── Parser_Dotsocr │ │ ├── dots_ocr │ │ │ ├── model │ │ │ │ ├── download_model.py │ │ │ │ └── inference.py │ │ │ └── utils │ │ │ │ ├── consts.py │ │ │ │ ├── doc_utils.py │ │ │ │ ├── format_transformer.py │ │ │ │ ├── image_utils.py │ │ │ │ ├── layout_utils.py │ │ │ │ ├── output_cleaner.py │ │ │ │ └── prompts.py │ │ ├── fig_recognize.py │ │ ├── parser.py │ │ ├── readme.md │ │ └── vllm_launch.py │ ├── Parser_MinerU.py │ ├── __init__.py │ └── equation_detect.py ├── prompts │ ├── __init__.py │ ├── kg_triples_prompt.py │ └── multimodal_qa_prompt.py ├── rerankers │ ├── Reranker_Base.py │ ├── Reranker_Qwen3.py │ ├── __init__.py │ └── registry.py ├── retrivers │ ├── __init__.py │ └── graphrag_query_engine.py ├── storages │ ├── __init__.py │ ├── graph_storages │ │ ├── __init__.py │ │ └── graphrag_store.py │ ├── multimodal_storages │ │ ├── __init__.py │ │ └── neo4j_vector_store.py │ └── vector_storages │ │ ├── __init__.py │ │ └── qdrant_vector_store.py └── utils │ ├── __init__.py │ ├── kg_utils │ ├── __init__.py │ ├── coreference_resolution.py │ └── entity_disambiguation.py │ └── query_rewrite.py ├── requirements.txt ├── run.sh ├── scripts ├── convert_documents_format.py ├── download_mixed_wiki.py └── process_multimodal_html.py ├── setup.py └── tests └── test_llms.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/README.md -------------------------------------------------------------------------------- /assets/knowledge_base_screenshot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/assets/knowledge_base_screenshot.png -------------------------------------------------------------------------------- /assets/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/assets/logo.png -------------------------------------------------------------------------------- /data/2wikimultihopqa/corpus.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/2wikimultihopqa/corpus.json -------------------------------------------------------------------------------- /data/2wikimultihopqa/samples.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/2wikimultihopqa/samples.json -------------------------------------------------------------------------------- /data/dataset_info.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/dataset_info.json -------------------------------------------------------------------------------- /data/hotpotqa/corpus.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/hotpotqa/corpus.json -------------------------------------------------------------------------------- /data/hotpotqa/samples.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/hotpotqa/samples.json -------------------------------------------------------------------------------- /data/multimodal_test_samples/documents.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/documents.json -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*2wrx2joD1PaAsC27pshn3A.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*2wrx2joD1PaAsC27pshn3A.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*6pALyl4xZ2 G9LnGlMR18g.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*6pALyl4xZ2 G9LnGlMR18g.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*93ZK9-74dYv4eXY-Oe bkA.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*93ZK9-74dYv4eXY-Oe bkA.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*CTF2gfNwx4v7V-0qM4s6uw.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*CTF2gfNwx4v7V-0qM4s6uw.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*DbWfNKMRWJcomb9N5QIhOQ.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*DbWfNKMRWJcomb9N5QIhOQ.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*GFJ9 TnLk2oDnVGtXAwARw.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*GFJ9 TnLk2oDnVGtXAwARw.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*H7FLmJdZvGarmGGs81SIRA.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*H7FLmJdZvGarmGGs81SIRA.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*Jp-QxrEj IYlOga84KTyBw.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*Jp-QxrEj IYlOga84KTyBw.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*LM6CuPZiogendK21 UHwPA.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*LM6CuPZiogendK21 UHwPA.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*OB43zXlHa4fcnL3n44JxcQ.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*OB43zXlHa4fcnL3n44JxcQ.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*OCjG5oY6DyOnLuo1 N4OlA.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*OCjG5oY6DyOnLuo1 N4OlA.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*PHsfndcMjOMoAdUAx8IJrw.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*PHsfndcMjOMoAdUAx8IJrw.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*RYCIqV1Gfp18VkXfY411Xg.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*RYCIqV1Gfp18VkXfY411Xg.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*VVWecqvibBb2vVXuyKU5rw.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*VVWecqvibBb2vVXuyKU5rw.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*b8pT6KIERk3ZPd-729TmXA.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*b8pT6KIERk3ZPd-729TmXA.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*chHcyzoxurmTuzVsYgrdLA.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*chHcyzoxurmTuzVsYgrdLA.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*k9jUdnEB8sR5g0fZzqSiNA.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*k9jUdnEB8sR5g0fZzqSiNA.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*mEipkYmePMYvX4t5tU8u2w.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*mEipkYmePMYvX4t5tU8u2w.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*oY5JoNIikQZj3RsXyMrb3w.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*oY5JoNIikQZj3RsXyMrb3w.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images/1*yscMghSQVAQvQeHV6pZ4PQ.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images/1*yscMghSQVAQvQeHV6pZ4PQ.png -------------------------------------------------------------------------------- /data/multimodal_test_samples/images_metadata.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/images_metadata.json -------------------------------------------------------------------------------- /data/multimodal_test_samples/samples.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/samples.json -------------------------------------------------------------------------------- /data/multimodal_test_samples/source_html_files/2023-10-18_Using-a-Knowledge-Graph-to-implement-a-DevOps-RAG-application-b6ba24831b16.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/source_html_files/2023-10-18_Using-a-Knowledge-Graph-to-implement-a-DevOps-RAG-application-b6ba24831b16.html -------------------------------------------------------------------------------- /data/multimodal_test_samples/source_html_files/2023-10-20_Constructing-knowledge-graphs-from-text-using-OpenAI-functions-096a6d010c17.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/source_html_files/2023-10-20_Constructing-knowledge-graphs-from-text-using-OpenAI-functions-096a6d010c17.html -------------------------------------------------------------------------------- /data/multimodal_test_samples/source_html_files/2023-10-30_How-to-implement-Weaviate-RAG-applications-with-Local-LLMs-and-Embedding-models-24a9128eaf84.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/multimodal_test_samples/source_html_files/2023-10-30_How-to-implement-Weaviate-RAG-applications-with-Local-LLMs-and-Embedding-models-24a9128eaf84.html -------------------------------------------------------------------------------- /data/musique/corpus.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/musique/corpus.json -------------------------------------------------------------------------------- /data/musique/samples.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/musique/samples.json -------------------------------------------------------------------------------- /data/test_samples/corpus.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/test_samples/corpus.json -------------------------------------------------------------------------------- /data/test_samples/samples.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/data/test_samples/samples.json -------------------------------------------------------------------------------- /docs/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/docs/README.md -------------------------------------------------------------------------------- /docs/_navbar.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/docs/_navbar.md -------------------------------------------------------------------------------- /docs/_sidebar.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/docs/_sidebar.md -------------------------------------------------------------------------------- /docs/api_reference.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/docs/api_reference.md -------------------------------------------------------------------------------- /docs/configuration.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/docs/configuration.md -------------------------------------------------------------------------------- /docs/deployment.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/docs/deployment.md -------------------------------------------------------------------------------- /docs/examples/graph_rag.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/docs/examples/graph_rag.md -------------------------------------------------------------------------------- /docs/index.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/docs/index.html -------------------------------------------------------------------------------- /docs/modules/graph_rag.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/docs/modules/graph_rag.md -------------------------------------------------------------------------------- /docs/modules/mm_rag.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/docs/modules/mm_rag.md -------------------------------------------------------------------------------- /docs/modules/naive_rag.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/docs/modules/naive_rag.md -------------------------------------------------------------------------------- /docs/quickstart.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/docs/quickstart.md -------------------------------------------------------------------------------- /examples/TCL_rag/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/examples/TCL_rag/config.yaml -------------------------------------------------------------------------------- /examples/TCL_rag/rag_flow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/examples/TCL_rag/rag_flow.py -------------------------------------------------------------------------------- /examples/TCL_rag/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/examples/TCL_rag/test.py -------------------------------------------------------------------------------- /examples/bm25/config.yaml: -------------------------------------------------------------------------------- 1 | retriever: 2 | name: bm25 3 | k: 8 -------------------------------------------------------------------------------- /examples/bm25/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/examples/bm25/main.py -------------------------------------------------------------------------------- /examples/faiss_construct/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/examples/faiss_construct/config.yaml -------------------------------------------------------------------------------- /examples/faiss_construct/faiss_constructor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/examples/faiss_construct/faiss_constructor.py -------------------------------------------------------------------------------- /examples/graphrag/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/examples/graphrag/config.yaml -------------------------------------------------------------------------------- /examples/multimodal_rag/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/examples/multimodal_rag/config.yaml -------------------------------------------------------------------------------- /examples/rag/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/examples/rag/config.yaml -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/main.py -------------------------------------------------------------------------------- /mkdocs.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/mkdocs.yml -------------------------------------------------------------------------------- /rag_factory/Embed/Embedding_Base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Embed/Embedding_Base.py -------------------------------------------------------------------------------- /rag_factory/Embed/Embedding_Huggingface.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Embed/Embedding_Huggingface.py -------------------------------------------------------------------------------- /rag_factory/Embed/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Embed/__init__.py -------------------------------------------------------------------------------- /rag_factory/Embed/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Embed/registry.py -------------------------------------------------------------------------------- /rag_factory/Retrieval/Retriever/Retriever_BM25.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Retrieval/Retriever/Retriever_BM25.py -------------------------------------------------------------------------------- /rag_factory/Retrieval/Retriever/Retriever_MultiPath.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Retrieval/Retriever/Retriever_MultiPath.py -------------------------------------------------------------------------------- /rag_factory/Retrieval/Retriever/Retriever_VectorStore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Retrieval/Retriever/Retriever_VectorStore.py -------------------------------------------------------------------------------- /rag_factory/Retrieval/Retriever/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Retrieval/Retriever/registry.py -------------------------------------------------------------------------------- /rag_factory/Retrieval/Retriever/test_bm25_retriever.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Retrieval/Retriever/test_bm25_retriever.py -------------------------------------------------------------------------------- /rag_factory/Retrieval/RetrieverBase.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Retrieval/RetrieverBase.py -------------------------------------------------------------------------------- /rag_factory/Retrieval/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Retrieval/__init__.py -------------------------------------------------------------------------------- /rag_factory/Retrieval/utils/Fusion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Retrieval/utils/Fusion.py -------------------------------------------------------------------------------- /rag_factory/Store/VectorStore/VectorStoreBase.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Store/VectorStore/VectorStoreBase.py -------------------------------------------------------------------------------- /rag_factory/Store/VectorStore/VectorStore_Faiss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Store/VectorStore/VectorStore_Faiss.py -------------------------------------------------------------------------------- /rag_factory/Store/VectorStore/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Store/VectorStore/registry.py -------------------------------------------------------------------------------- /rag_factory/Store/VectorStore/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Store/VectorStore/test.py -------------------------------------------------------------------------------- /rag_factory/Store/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/Store/__init__.py -------------------------------------------------------------------------------- /rag_factory/agents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/agents/__init__.py -------------------------------------------------------------------------------- /rag_factory/agents/agent_prompts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/agents/agent_prompts.py -------------------------------------------------------------------------------- /rag_factory/args.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/args.py -------------------------------------------------------------------------------- /rag_factory/caches/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/caches/__init__.py -------------------------------------------------------------------------------- /rag_factory/caches/cache.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/caches/cache.py -------------------------------------------------------------------------------- /rag_factory/documents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/documents/__init__.py -------------------------------------------------------------------------------- /rag_factory/documents/kg_triples_parse.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/documents/kg_triples_parse.py -------------------------------------------------------------------------------- /rag_factory/embeddings/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/embeddings/__init__.py -------------------------------------------------------------------------------- /rag_factory/embeddings/clip.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/embeddings/clip.py -------------------------------------------------------------------------------- /rag_factory/embeddings/openai_compatible.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/embeddings/openai_compatible.py -------------------------------------------------------------------------------- /rag_factory/evaluations/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/evaluations/__init__.py -------------------------------------------------------------------------------- /rag_factory/graph_constructor/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/graph_constructor/__init__.py -------------------------------------------------------------------------------- /rag_factory/graph_constructor/graphrag_constructor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/graph_constructor/graphrag_constructor.py -------------------------------------------------------------------------------- /rag_factory/indexer/graph_indexer/__init__.py: -------------------------------------------------------------------------------- 1 | from llama_index.core import PropertyGraphIndex -------------------------------------------------------------------------------- /rag_factory/indexer/multimodal_indexer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rag_factory/indexer/vector_indexer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rag_factory/llms/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/llms/__init__.py -------------------------------------------------------------------------------- /rag_factory/llms/dashscope/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/llms/dashscope/base.py -------------------------------------------------------------------------------- /rag_factory/llms/dashscope/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/llms/dashscope/utils.py -------------------------------------------------------------------------------- /rag_factory/llms/llm_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/llms/llm_base.py -------------------------------------------------------------------------------- /rag_factory/llms/openai_compatible.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/llms/openai_compatible.py -------------------------------------------------------------------------------- /rag_factory/llms/openai_llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/llms/openai_llm.py -------------------------------------------------------------------------------- /rag_factory/llms/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/llms/registry.py -------------------------------------------------------------------------------- /rag_factory/llms/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/llms/test.py -------------------------------------------------------------------------------- /rag_factory/multi_modal_llms/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/multi_modal_llms/__init__.py -------------------------------------------------------------------------------- /rag_factory/multi_modal_llms/dashscope/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/multi_modal_llms/dashscope/base.py -------------------------------------------------------------------------------- /rag_factory/multi_modal_llms/dashscope/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/multi_modal_llms/dashscope/utils.py -------------------------------------------------------------------------------- /rag_factory/multi_modal_llms/openai_compatible.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/multi_modal_llms/openai_compatible.py -------------------------------------------------------------------------------- /rag_factory/parser/Parser_Dotsocr/dots_ocr/model/download_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/Parser_Dotsocr/dots_ocr/model/download_model.py -------------------------------------------------------------------------------- /rag_factory/parser/Parser_Dotsocr/dots_ocr/model/inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/Parser_Dotsocr/dots_ocr/model/inference.py -------------------------------------------------------------------------------- /rag_factory/parser/Parser_Dotsocr/dots_ocr/utils/consts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/Parser_Dotsocr/dots_ocr/utils/consts.py -------------------------------------------------------------------------------- /rag_factory/parser/Parser_Dotsocr/dots_ocr/utils/doc_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/Parser_Dotsocr/dots_ocr/utils/doc_utils.py -------------------------------------------------------------------------------- /rag_factory/parser/Parser_Dotsocr/dots_ocr/utils/format_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/Parser_Dotsocr/dots_ocr/utils/format_transformer.py -------------------------------------------------------------------------------- /rag_factory/parser/Parser_Dotsocr/dots_ocr/utils/image_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/Parser_Dotsocr/dots_ocr/utils/image_utils.py -------------------------------------------------------------------------------- /rag_factory/parser/Parser_Dotsocr/dots_ocr/utils/layout_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/Parser_Dotsocr/dots_ocr/utils/layout_utils.py -------------------------------------------------------------------------------- /rag_factory/parser/Parser_Dotsocr/dots_ocr/utils/output_cleaner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/Parser_Dotsocr/dots_ocr/utils/output_cleaner.py -------------------------------------------------------------------------------- /rag_factory/parser/Parser_Dotsocr/dots_ocr/utils/prompts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/Parser_Dotsocr/dots_ocr/utils/prompts.py -------------------------------------------------------------------------------- /rag_factory/parser/Parser_Dotsocr/fig_recognize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/Parser_Dotsocr/fig_recognize.py -------------------------------------------------------------------------------- /rag_factory/parser/Parser_Dotsocr/parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/Parser_Dotsocr/parser.py -------------------------------------------------------------------------------- /rag_factory/parser/Parser_Dotsocr/readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/Parser_Dotsocr/readme.md -------------------------------------------------------------------------------- /rag_factory/parser/Parser_Dotsocr/vllm_launch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/Parser_Dotsocr/vllm_launch.py -------------------------------------------------------------------------------- /rag_factory/parser/Parser_MinerU.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/Parser_MinerU.py -------------------------------------------------------------------------------- /rag_factory/parser/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/__init__.py -------------------------------------------------------------------------------- /rag_factory/parser/equation_detect.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/parser/equation_detect.py -------------------------------------------------------------------------------- /rag_factory/prompts/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/prompts/__init__.py -------------------------------------------------------------------------------- /rag_factory/prompts/kg_triples_prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/prompts/kg_triples_prompt.py -------------------------------------------------------------------------------- /rag_factory/prompts/multimodal_qa_prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/prompts/multimodal_qa_prompt.py -------------------------------------------------------------------------------- /rag_factory/rerankers/Reranker_Base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/rerankers/Reranker_Base.py -------------------------------------------------------------------------------- /rag_factory/rerankers/Reranker_Qwen3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/rerankers/Reranker_Qwen3.py -------------------------------------------------------------------------------- /rag_factory/rerankers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/rerankers/__init__.py -------------------------------------------------------------------------------- /rag_factory/rerankers/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/rerankers/registry.py -------------------------------------------------------------------------------- /rag_factory/retrivers/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rag_factory/retrivers/graphrag_query_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/retrivers/graphrag_query_engine.py -------------------------------------------------------------------------------- /rag_factory/storages/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rag_factory/storages/graph_storages/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/storages/graph_storages/__init__.py -------------------------------------------------------------------------------- /rag_factory/storages/graph_storages/graphrag_store.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/storages/graph_storages/graphrag_store.py -------------------------------------------------------------------------------- /rag_factory/storages/multimodal_storages/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/storages/multimodal_storages/__init__.py -------------------------------------------------------------------------------- /rag_factory/storages/multimodal_storages/neo4j_vector_store.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/storages/multimodal_storages/neo4j_vector_store.py -------------------------------------------------------------------------------- /rag_factory/storages/vector_storages/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/storages/vector_storages/__init__.py -------------------------------------------------------------------------------- /rag_factory/storages/vector_storages/qdrant_vector_store.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/storages/vector_storages/qdrant_vector_store.py -------------------------------------------------------------------------------- /rag_factory/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/utils/__init__.py -------------------------------------------------------------------------------- /rag_factory/utils/kg_utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rag_factory/utils/kg_utils/coreference_resolution.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/utils/kg_utils/coreference_resolution.py -------------------------------------------------------------------------------- /rag_factory/utils/kg_utils/entity_disambiguation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/utils/kg_utils/entity_disambiguation.py -------------------------------------------------------------------------------- /rag_factory/utils/query_rewrite.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/rag_factory/utils/query_rewrite.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/requirements.txt -------------------------------------------------------------------------------- /run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/run.sh -------------------------------------------------------------------------------- /scripts/convert_documents_format.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/scripts/convert_documents_format.py -------------------------------------------------------------------------------- /scripts/download_mixed_wiki.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/scripts/download_mixed_wiki.py -------------------------------------------------------------------------------- /scripts/process_multimodal_html.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/scripts/process_multimodal_html.py -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/DataArcTech/RAG-Factory/HEAD/setup.py -------------------------------------------------------------------------------- /tests/test_llms.py: -------------------------------------------------------------------------------- 1 | --------------------------------------------------------------------------------