[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72225":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":16,"stars30d":17,"stars90d":15,"forks30d":15,"starsTrendScore":18,"compositeScore":19,"rankGlobal":9,"rankLanguage":9,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":23,"hasPages":21,"topics":24,"createdAt":9,"pushedAt":9,"updatedAt":25,"readmeContent":26,"aiSummary":27,"trendingCount":15,"starSnapshotCount":15,"syncStatus":16,"lastSyncTime":28,"discoverSource":29},72225,"fast-graphrag","circlemind-ai\u002Ffast-graphrag","circlemind-ai","RAG that intelligently adapts to your use case, data, and queries",null,"Python",3799,246,19,31,0,2,17,6,65.88,"MIT License",false,"main",true,[],"2026-06-12 04:01:04","\u003Ch1 align=\"center\">\n  \u003Cimg width=\"800\" src=\"banner.png\" alt=\"circlemind fast-graphrag\">\n\u003C\u002Fh1>\n\u003Ch4 align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fcirclemind-ai\u002Ffast-graphrag\u002Fblob\u002Fmain\u002FLICENSE\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-blue.svg\" alt=\"fast-graphrag is released under the MIT license.\" alt=\"Fast GraphRAG by Circlemind\"\u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fcirclemind-ai\u002Ffast-graphrag\u002Fblob\u002Fmain\u002FCONTRIBUTING.md\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-Welcome-brightgreen\" alt=\"PRs welcome!\" \u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fcirclemind.co\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FProject-Page-Green\" alt=\"Circlemind Page\" \u002F>\n  \u003C\u002Fa>\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython->=3.10.1-blue\">\n\u003C\u002Fh4>\n\u003Cp align=\"center\">\n  \u003Cp align=\"center\">\u003Cb>Streamlined and promptable Fast GraphRAG framework designed for interpretable, high-precision, agent-driven retrieval workflows. \u003C\u002Fb> \u003C\u002Fp>\n\u003C\u002Fp>\n\n\u003Ch4 align=\"center\">\n  \u003Ca href=\"#install\">Install\u003C\u002Fa> |\n  \u003Ca href=\"#quickstart\">Quickstart\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FDvY2B8u4sA\">Community\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fcirclemind-ai\u002Ffast-graphrag\u002Fissues\u002Fnew?assignees=&labels=&projects=&template=%F0%9F%90%9E-bug-report.md&title=\">Report Bug\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fcirclemind-ai\u002Ffast-graphrag\u002Fissues\u002Fnew?assignees=&labels=&projects=&template=%F0%9F%92%A1-feature-request.md&title=\">Request Feature\u003C\u002Fa>\n\u003C\u002Fh4>\n\n> [!NOTE]\n> Using *The Wizard of Oz*, `fast-graphrag` costs $0.08 vs. `graphrag` $0.48 — **a 6x costs saving** that further improves with data size and number of insertions.\n\n## Features\n\n- **Interpretable and Debuggable Knowledge:** Graphs offer a human-navigable view of knowledge that can be queried, visualized, and updated.\n- **Fast, Low-cost, and Efficient:** Designed to run at scale without heavy resource or cost requirements.\n- **Dynamic Data:** Automatically generate and refine graphs to best fit your domain and ontology needs.\n- **Incremental Updates:** Supports real-time updates as your data evolves.\n- **Intelligent Exploration:** Leverages PageRank-based graph exploration for enhanced accuracy and dependability.\n- **Asynchronous & Typed:** Fully asynchronous, with complete type support for robust and predictable workflows.\n\nFast GraphRAG is built to fit seamlessly into your retrieval pipeline, giving you the power of advanced RAG, without the overhead of building and designing agentic workflows.\n\n## Install\n\n**Install from source (recommended for best performance)**\n\n```bash\n# clone this repo first\ncd fast_graphrag\npoetry install\n```\n\n**Install from PyPi (recommended for stability)**\n\n```bash\npip install fast-graphrag\n```\n\n## Quickstart\n\nSet the OpenAI API key in the environment:\n\n```bash\nexport OPENAI_API_KEY=\"sk-...\"\n```\n\nDownload a copy of *A Christmas Carol* by Charles Dickens:\n\n```bash\ncurl https:\u002F\u002Fraw.githubusercontent.com\u002Fcirclemind-ai\u002Ffast-graphrag\u002Frefs\u002Fheads\u002Fmain\u002Fmock_data.txt > .\u002Fbook.txt\n```\n\nOptional: Set the limit for concurrent requests to the LLM (i.e., to control the number of tasks processed simultaneously by the LLM, this is helpful when running local models)\n```bash\nexport CONCURRENT_TASK_LIMIT=8\n```\n\nUse the Python snippet below:\n\n```python\nfrom fast_graphrag import GraphRAG\n\nDOMAIN = \"Analyze this story and identify the characters. Focus on how they interact with each other, the locations they explore, and their relationships.\"\n\nEXAMPLE_QUERIES = [\n    \"What is the significance of Christmas Eve in A Christmas Carol?\",\n    \"How does the setting of Victorian London contribute to the story's themes?\",\n    \"Describe the chain of events that leads to Scrooge's transformation.\",\n    \"How does Dickens use the different spirits (Past, Present, and Future) to guide Scrooge?\",\n    \"Why does Dickens choose to divide the story into \\\"staves\\\" rather than chapters?\"\n]\n\nENTITY_TYPES = [\"Character\", \"Animal\", \"Place\", \"Object\", \"Activity\", \"Event\"]\n\ngrag = GraphRAG(\n    working_dir=\".\u002Fbook_example\",\n    domain=DOMAIN,\n    example_queries=\"\\n\".join(EXAMPLE_QUERIES),\n    entity_types=ENTITY_TYPES\n)\n\nwith open(\".\u002Fbook.txt\") as f:\n    grag.insert(f.read())\n\nprint(grag.query(\"Who is Scrooge?\").response)\n```\n\nThe next time you initialize fast-graphrag from the same working directory, it will retain all the knowledge automatically.\n\n## Examples\nPlease refer to the `examples` folder for a list of tutorials on common use cases of the library:\n- `custom_llm.py`: a brief example on how to configure fast-graphrag to run with different OpenAI API compatible language models and embedders;\n- `checkpointing.ipynb`: a tutorial on how to use checkpoints to avoid irreversible data corruption;\n- `query_parameters.ipynb`: a tutorial on how to use the different query parameters. In particular, it shows how to include references to the used information in the provided answer (using the `with_references=True` parameter). \n\n## Contributing\n\nWhether it's big or small, we love contributions. Contributions are what make the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated. Check out our [guide](https:\u002F\u002Fgithub.com\u002Fcirclemind-ai\u002Ffast-graphrag\u002Fblob\u002Fmain\u002FCONTRIBUTING.md) to see how to get started.\n\nNot sure where to get started? You can join our [Discord](https:\u002F\u002Fdiscord.gg\u002FDvY2B8u4sA) and ask us any questions there.\n\n## Philosophy\n\nOur mission is to increase the number of successful GenAI applications in the world. To do that, we build memory and data tools that enable LLM apps to leverage highly specialized retrieval pipelines without the complexity of setting up and maintaining agentic workflows.\n\nFast GraphRAG currently exploit the personalized pagerank algorithm to explore the graph and find the most relevant pieces of information to answer your query. For an overview on why this works, you can check out the HippoRAG paper [here](https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.14831).\n\n## Open-source or Managed Service\n\nThis repo is under the MIT License. See [LICENSE.txt](https:\u002F\u002Fgithub.com\u002Fcirclemind-ai\u002Ffast-graphrag\u002Fblob\u002Fmain\u002FLICENSE) for more information.\n\nThe fastest and most reliable way to get started with Fast GraphRAG is using our managed service. Your first 100 requests are free every month, after which you pay based on usage.\n\n\u003Ch1 align=\"center\">\n  \u003Cimg width=\"800\" src=\"demo.gif\" alt=\"circlemind fast-graphrag demo\">\n\u003C\u002Fh1>\n\nTo learn more about our managed service, [book a demo](https:\u002F\u002Fcirclemind.co\u002Fdemo) or see our [docs](https:\u002F\u002Fdocs.circlemind.co\u002Fquickstart).\n","Fast GraphRAG 是一个智能适应用户案例、数据和查询的检索增强生成框架。它通过构建可解释和调试的知识图谱，提供高效、低成本的数据处理方案，并支持动态数据更新与增量式知识图谱优化。项目利用PageRank算法进行智能探索，确保了高精度和可靠性；同时，其全异步设计及类型支持特性保证了工作流的健壮性和可预测性。适用于需要高效检索和理解复杂信息结构的应用场景，如大规模文档分析、知识管理和问答系统等。","2026-06-11 03:40:57","high_star"]