{"id":14959380,"url":"https://github.com/blacksmithop/llm-graph-builder","last_synced_at":"2025-08-18T10:10:31.514Z","repository":{"id":247584790,"uuid":"823566040","full_name":"blacksmithop/LLM-Graph-Builder","owner":"blacksmithop","description":"Build Neo4J Knowledge Graphs from Excel files","archived":false,"fork":false,"pushed_at":"2024-11-18T13:18:27.000Z","size":2786,"stargazers_count":16,"open_issues_count":0,"forks_count":2,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-01-31T03:25:33.645Z","etag":null,"topics":["knowledge-graph","llm","neo4j","python"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/blacksmithop.png","metadata":{"files":{"readme":"Readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-07-03T09:19:31.000Z","updated_at":"2025-01-16T07:07:53.000Z","dependencies_parsed_at":"2024-07-17T08:56:42.017Z","dependency_job_id":null,"html_url":"https://github.com/blacksmithop/LLM-Graph-Builder","commit_stats":{"total_commits":109,"total_committers":2,"mean_commits":54.5,"dds":"0.13761467889908252","last_synced_commit":"e527734de333dc88e2656aaa5356fbc613263bdf"},"previous_names":["blacksmithop/llm-graph-builder"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blacksmithop%2FLLM-Graph-Builder","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blacksmithop%2FLLM-Graph-Builder/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blacksmithop%2FLLM-Graph-Builder/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blacksmithop%2FLLM-Graph-Builder/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/blacksmithop","download_url":"https://codeload.github.com/blacksmithop/LLM-Graph-Builder/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":238008473,"owners_count":19401260,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["knowledge-graph","llm","neo4j","python"],"created_at":"2024-09-24T13:19:35.144Z","updated_at":"2025-02-09T19:31:15.608Z","avatar_url":"https://github.com/blacksmithop.png","language":"Python","readme":"# Knowledge Graph Builder\n\n![Python](https://skillicons.dev/icons?i=python,docker)\n\n## Graph Creation\n```mermaid\nflowchart TD\n    A[File Upload] --\u003e B[Identify File Type]\n    B --\u003e C[Create Documents]\n    C --\u003e D[Extract Entity from Document]\n    D --\u003e E[Get Entity Relationships]\n    E --\u003e F[Create Vector Index]\n```\n\n### Installation\n\n\nFirst, install the dependenices\n```bash\npip install -r requirements.txt\n```\n\n### Configure Neo4J (Dozerdb)\n\nNext, install Neo4j. I recommend doing this [Dozerb](https://dozerdb.org/) as it offers enterprise features in the community edition. You can use this [script](./install_dozerdb.sh) to get a docker container running.\n\n### Configure LLM, Embeddings\n\nYou can use Azure OpenAI, Ollama or your custom provider. You just need to define your LLM and Embeddings model in [llm_core.py](./utils/common/llm_core.py)\n\n### Usage\n\nOnce complete you can set your `FILE_PATH` in [knowledge_graph_creator.py](./knowledge_graph_creator.py) and run the python script. It should you populate you Neo4J database.\n\n\nThe Builder supports different modes of operation when creating the nodes. This can be toggled by changing `prompt_version` in [Neo4JKnowledgeGraph](/utils/custom/knowledge_graph.py#L40). Defaults to `2`.\n\n\n\n## Question Answering\n\n```mermaid\ngraph TD\n  A[Query] --\u003e B[Construct Cypher from Schema]\n  B --\u003e C[Retrieve related Nodes]\n  C --\u003e D{Can Answer Question}\n  D --\u003e|Yes| E[Response]\n  D --\u003e|No| F[Process result]\n  F --\u003e E\n```\n\nYou can perform QA on your knowledge graph using the streamlit application at [graph_qa_chatbot.py](./graph_qa_chatbot.py)\n\n```bash\nstreamlit run graph_qa_chatbot.py\n```\n\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=blacksmithop/LLM-Graph-Builder\u0026type=Date)](https://star-history.com/#blacksmithop/LLM-Graph-Builder\u0026Date)\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fblacksmithop%2Fllm-graph-builder","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fblacksmithop%2Fllm-graph-builder","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fblacksmithop%2Fllm-graph-builder/lists"}