ToG-3
Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval
File Explorer
Download Latest Version (.zip)- knowledge_base_screenshot.png
- logo.png
- corpus.json
- samples.json
- corpus.json
- samples.json
- 1*2wrx2joD1PaAsC27pshn3A.png
- 1*6pALyl4xZ2 G9LnGlMR18g.png
- 1*93ZK9-74dYv4eXY-Oe bkA.png
- 1*b8pT6KIERk3ZPd-729TmXA.png
- 1*chHcyzoxurmTuzVsYgrdLA.png
- 1*CTF2gfNwx4v7V-0qM4s6uw.png
- 1*DbWfNKMRWJcomb9N5QIhOQ.png
- 1*GFJ9 TnLk2oDnVGtXAwARw.png
- 1*H7FLmJdZvGarmGGs81SIRA.png
- 1*Jp-QxrEj IYlOga84KTyBw.png
- 1*k9jUdnEB8sR5g0fZzqSiNA.png
- 1*LM6CuPZiogendK21 UHwPA.png
- 1*mEipkYmePMYvX4t5tU8u2w.png
- 1*OB43zXlHa4fcnL3n44JxcQ.png
- 1*OCjG5oY6DyOnLuo1 N4OlA.png
- 1*oY5JoNIikQZj3RsXyMrb3w.png
- 1*PHsfndcMjOMoAdUAx8IJrw.png
- 1*RYCIqV1Gfp18VkXfY411Xg.png
- 1*VVWecqvibBb2vVXuyKU5rw.png
- 1*yscMghSQVAQvQeHV6pZ4PQ.png
- 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
- documents.json
- images_metadata.json
- samples.json
- corpus.json
- samples.json
- corpus.json
- samples.json
- dataset_info.json
- graph_rag.md
- graph_rag.md
- mm_rag.md
- naive_rag.md
- _navbar.md
- _sidebar.md
- api_reference.md
- configuration.md
- deployment.md
- index.html
- quickstart.md
- README.md
- config.yaml
- main.py
- config.yaml
- faiss_constructor.py
- config.yaml
- config.yaml
- config.yaml
- config.yaml
- rag_flow.py
- test.py
- __init__.py
- agent_prompts.py
- __init__.py
- cache.py
- __init__.py
- kg_triples_parse.py
- __init__.py
- Embedding_Base.py
- Embedding_Huggingface.py
- registry.py
- __init__.py
- clip.py
- openai_compatible.py
- __init__.py
- __init__.py
- graphrag_constructor.py
- __init__.py
- __init__.py
- __init__.py
- base.py
- utils.py
- __init__.py
- llm_base.py
- openai_compatible.py
- openai_llm.py
- registry.py
- test.py
- base.py
- utils.py
- __init__.py
- openai_compatible.py
- download_model.py
- inference.py
- 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
- __init__.py
- equation_detect.py
- Parser_MinerU.py
- __init__.py
- kg_triples_prompt.py
- multimodal_qa_prompt.py
- __init__.py
- registry.py
- Reranker_Base.py
- Reranker_Qwen3.py
- registry.py
- Retriever_BM25.py
- Retriever_MultiPath.py
- Retriever_VectorStore.py
- test_bm25_retriever.py
- Fusion.py
- __init__.py
- RetrieverBase.py
- __init__.py
- graphrag_query_engine.py
- __init__.py
- graphrag_store.py
- __init__.py
- neo4j_vector_store.py
- __init__.py
- qdrant_vector_store.py
- __init__.py
- registry.py
- test.py
- VectorStore_Faiss.py
- VectorStoreBase.py
- __init__.py
- __init__.py
- coreference_resolution.py
- entity_disambiguation.py
- __init__.py
- query_rewrite.py
- args.py
- convert_documents_format.py
- download_mixed_wiki.py
- process_multimodal_html.py
- test_llms.py
- .gitignore
- LICENSE
- main.py
- mkdocs.yml
- README.md
- requirements.txt
- run.sh
- setup.py
# Installation Guide
1. Get the code
git clone https://github.com/DataArcTech/ToG-3
Downloads the entire project code from GitHub to your computer.
cd ToG-3
Moves into the project folder you just downloaded.
2. Python
Easy RecommendedPrerequisites
pip install -e .
Installs the Python libraries listed in requirements.txt (or similar).
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)