{"id":18183689,"url":"https://github.com/qredence/graphfleet","last_synced_at":"2025-04-01T21:31:11.033Z","repository":{"id":249380229,"uuid":"830779691","full_name":"Qredence/GraphFleet","owner":"Qredence","description":"An open-source integration of GraphRAG for Agentic System with NoCode","archived":false,"fork":false,"pushed_at":"2024-12-25T22:46:34.000Z","size":1060123,"stargazers_count":12,"open_issues_count":0,"forks_count":3,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-28T17:11:23.403Z","etag":null,"topics":["ai-agent","graph","graphrag","knowledge-graph","llm","llms","nocode","rag","streamlit","ui"],"latest_commit_sha":null,"homepage":"https://www.qredence.ai","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Qredence.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null},"funding":{"github":"qredence","patreon":null,"open_collective":null,"buy_me_a_coffee":null,"custom":null}},"created_at":"2024-07-19T01:40:51.000Z","updated_at":"2025-02-13T18:22:04.000Z","dependencies_parsed_at":"2024-08-18T17:58:01.570Z","dependency_job_id":"5c1509ba-1d2a-4fa1-b1b1-cc8c071ed0bb","html_url":"https://github.com/Qredence/GraphFleet","commit_stats":null,"previous_names":["qredence/graphfleet"],"tags_count":13,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Qredence%2FGraphFleet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Qredence%2FGraphFleet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Qredence%2FGraphFleet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Qredence%2FGraphFleet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Qredence","download_url":"https://codeload.github.com/Qredence/GraphFleet/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246713030,"owners_count":20821834,"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":["ai-agent","graph","graphrag","knowledge-graph","llm","llms","nocode","rag","streamlit","ui"],"created_at":"2024-11-02T20:03:55.520Z","updated_at":"2025-04-01T21:31:06.024Z","avatar_url":"https://github.com/Qredence.png","language":"Jupyter Notebook","funding_links":["https://github.com/sponsors/qredence"],"categories":[],"sub_categories":[],"readme":"# Overview\n\n\u003cdiv align=\"left\"\u003e\n\u003ca href=\"https://pypi.org/project/graphfleet/\"\u003e\n   \u003cimg alt=\"Pepy Total Downlods\" src=\"https://img.shields.io/pepy/dt/graphfleet\"\u003e\n   \u003c/a\u003e\n   \u003cimg alt=\"GitHub License\" src=\"https://img.shields.io/github/license/qredence/graphfleet\"\u003e\n   \u003cimg alt=\"GitHub forks\" src=\"https://img.shields.io/github/forks/qredence/graphfleet\"\u003e\n   \u003cimg alt=\"GitHub Repo stars\" src=\"https://img.shields.io/github/stars/qredence/graphfleet\"\u003e\n\n\u003c/div\u003e\n\n\nhttps://github.com/user-attachments/assets/ac3271fa-cab5-412f-a441-bbedfe4a009f\n\n# ** /!\\ DEPRECATED NEW FULL REVAMP COMING SOON /!\\**\n\nGraphFleet is an advanced implementation of [GraphRAG from Microsoft](https://github.com/microsoft/graphrag), designed to enhance large language models' ability to reason about complex information and private datasets. It builds upon GraphRAG (Retrieval Augmented Generation using Graph structures) and will gradually adopt its own path to fulfill our roadmap at Qredence.\n\n## GraphFleet\n\nGraphFleet uses knowledge graphs to provide substantial improvements in question-and-answer performance when reasoning about complex information. It addresses limitations of traditional RAG approaches:\n\n## Roadmap\n\n- [ ] Provide a FleetUI Design Kit and a quicker way of starting GraphFleet locally.\n- [ ] Provide a Toddle interface ready to use for GraphFleet\n- [ ] Add integrations of Composio\n- [ ] Add integrations of LangSmith\n- [ ] Add few selfhosting  one click deploy solutions.\n- [ ] Access GraphFleet through a secure and enterprise-ready Azure Cloud hosting version.\n- [ ] And way more... 👀\n\n## Key Features\n\n- Structured, hierarchical approach to Retrieval Augmented Generation.\n- Knowledge graph extraction from raw text.\n- Community hierarchy building.\n- Hierarchical summarization.\n- Enhanced reasoning capabilities for LLMs on private datasets.\n\nOur current API Endpoints : https://agenticfleet.apidocumentation.com/reference#tag/search/POST/search/global\n\n## Contribute\n\n- Leave us a star ♥\n- Fork and contribute to the project\n- \u003ca href=\"https://discord.gg/BD8MPgzEJc\"\u003e\n    \u003cimg alt=\"Discord\" src=\"https://img.shields.io/discord/1053300403149733969?style=for-the-badge\u0026logo=discord\"\u003e\n   \u003c/a\u003e\n   \u003cimg alt=\"X (formerly Twitter) Follow\" src=\"https://img.shields.io/twitter/follow/agenticfleet?style=for-the-badge\u0026logo=x\u0026logoColor=white\u0026labelColor=blue\u0026link=https%3A%2F%2Fx.com%2Fagenticfleet\"\u003e\n\n## Getting Started\n\n### Prerequisites\n\n- Python 3.11\n\n- Poetry\n- Make sure to have a virtual environment manager such as `virtualenv` installed\n\n### Installation\n\n1. Clone the repository:\n\n   ```bash\n   git clone https://github.com/Qredence/GraphFleet.git\n   cd GraphFleet\n   ```\n\n2. Install the dependencies:\n\n   ```bash\n   poetry shell\n   poetry install\n   ```\n\n### Usage\n\n1. Configuration:\nEnvironment Variables: Set up your environment variables in a .env file (refer to the .env.example file for available options). Key variables include:\n\nFill in the .env file in the root folder and the one in the graphfleet folder.\n\n ```sh\nexport GRAPHRAG_API_KEY=\"your_api_key_here\"\nexport GRAPHRAG_API_BASE=\"\u003chttps://your-azure-openai-resource.openai.azure.com/\u003e\"\nexport GRAPHRAG_API_VERSION=\"\"\nexport GRAPHRAG_DEPLOYMENT_NAME=\"your_deployment_name\"\nexport GRAPHRAG_API_TYPE=\"azure_openai\"\nexport GRAPHRAG_EMBEDDING_MODEL=\"text-embedding-ada-002\"\nexport GRAPHRAG_LLM_MODEL=\"gpt-4\"\nexport GRAPHRAG_DATA_PATH=\"./your_data_directory\"\nexport GRAPHRAG_EMBEDDING_TYPE=\"azure_openai_embedding\"\nexport GRAPHRAG_EMBEDDING_KEY=\"your_embedding_key_here\"\nexport GRAPHRAG_EMBEDDING_ENDPOINT=\"\u003chttps://your-azure-openai-embedding-resource.openai.azure.com/\u003e\"\nexport GRAPHRAG_EMBEDDING_DEPLOYMENT_NAME=\"your_embedding_deployment_name\"\n```\n\n\nsettings.yaml: Customize GraphFleet's behavior further by modifying the settings.yaml file within the graphfleet directory.\n\n\n\n1. Interacting with GraphFleet:\n   settings.yaml: Customize GraphFleet's behavior further by modifying the settings.yaml file within the graphfleet directory.\n   Jupyter Notebooks: Explore GraphFleet's capabilities with the provided notebooks:\n   get-started-graphfleet.ipynb: A comprehensive guide to indexing your data and running basic queries.\n   Local Search Notebook.ipynb: Demonstrates local search techniques.\n   app.py (FastAPI Application): Run a Streamlit-powered web interface to interact with GraphFleet using a user-friendly chat-like interface.\n\n### Add your text files in ./graphfleet/input/ and run the auto_prompt function\n\n``` bash\n!python -m graphrag.prompt_tune \\\n    --config ./graphfleet/settings.yaml \\\n    --root ./graphfleet \\\n    --no-entity-types \\\n    --output ./graphfleet/prompts\n```\n\n### Data Indexing\n\nJupyter Notebook Guide: Follow the instructions provided in the get-started-graphfleet.ipynb notebook to learn how to index your data with GraphFleet. This notebook provides a hands-on experience for setting up your knowledge base.\n\n``` bash\n! python -m graphrag.index \\\n    --verbose \\\n    --root ./graphfleet \\\n    --config ./graphfleet/settings.yaml\n```\n\n### Recommended Run these notebook to get started  with GraphFleet\n\nJupyter Notebooks: Explore GraphFleet's capabilities with the provided notebooks:\n\n([Get Started Quickly.ipynb](https://github.com/Qredence/GraphFleet/blob/a67eaeb295d99dd2ef48bcdd8f8a719b830ffb7d/notebook/Get%20Started%20Quickly.ipynb)): A comprehensive guide to indexing your data and running basic queries.\n([Local Search Notebook.ipynb:](https://github.com/Qredence/GraphFleet/blob/a67eaeb295d99dd2ef48bcdd8f8a719b830ffb7d/notebook/Local%20Search%20Notebook.ipynb)) Demonstrates local search techniques.\n\n([Global Search Notebook](https://github.com/Qredence/GraphFleet/blob/a67eaeb295d99dd2ef48bcdd8f8a719b830ffb7d/notebook/Global%20Search%20Notebook.ipynb))\n\n\n### Running the API only (or run CLI commands for local search or global search)\n\nTo run the API, save the code in a file named api.py and execute the following command in your terminal:\n\n``` bash\nuvicorn app:main --reload --port 8001 \n```\n\n### Running Streamlit\n\nTo run the API, save the code in a file named api.py and execute the following command in your terminal:\n\n``` bash\nstreamlit run app/streamlit_app.py\n```\n\n\n\n## Security\n\nFor details about our security policy, please see [Security](SECURITY.md)\n\n## License\n\nThis project is licensed under the Apache License 2.0. For the full license text, please see [License](LICENSE) \n\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=Qredence/GraphFleet\u0026type=Date)](https://star-history.com/#Qredence/GraphFleet\u0026Date) \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqredence%2Fgraphfleet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fqredence%2Fgraphfleet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqredence%2Fgraphfleet/lists"}