[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-10713":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":19,"rankGlobal":10,"rankLanguage":10,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":21,"hasPages":21,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":32,"readmeContent":33,"aiSummary":34,"trendingCount":16,"starSnapshotCount":16,"syncStatus":17,"lastSyncTime":35,"discoverSource":36},10713,"autoflow","pingcap\u002Fautoflow","pingcap","pingcap\u002Fautoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https:\u002F\u002Ftidb.ai","https:\u002F\u002Ftidb.ai",null,"TypeScript",2788,178,25,66,0,2,12,60.96,"Apache License 2.0",false,"main",[24,25,26,27,28,29,30,31],"chatbot","cot","graphrag","knowledge-graph","mysql","rag","serverless","vector-database","2026-06-12 04:00:52","\u003C!-- markdownlint-disable MD033 MD041 -->\n\n\u003Cdiv align=\"center\">\n\u003Ch1>AutoFlow\u003C\u002Fh1>\n  \u003Ca href='https:\u002F\u002Fwww.pingcap.com\u002Ftidb-cloud-serverless\u002F?utm_source=tidb.ai&utm_medium=community'>\n    \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fpingcap\u002Fautoflow\u002Frefs\u002Fheads\u002Fmain\u002Fdocs\u002Fpublic\u002Ficon-dark.svg\" alt=\"AutoFlow\" width =100 height=100>\u003C\u002Fimg>\n  \u003C\u002Fa>\n\n  \u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F12294\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Ftrendshift.io\u002Fapi\u002Fbadge\u002Frepositories\u002F12294\" alt=\"pingcap%2Fautoflow | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"\u002F>\u003C\u002Fa>\n\n  [![Backend Docker Image Version](https:\u002F\u002Fimg.shields.io\u002Fdocker\u002Fv\u002Ftidbai\u002Fbackend?sort=semver&arch=amd64&label=tidbai%2Fbackend&color=blue&logo=fastapi)](https:\u002F\u002Fhub.docker.com\u002Fr\u002Ftidbai\u002Fbackend)\n  [![Frontend Docker Image Version](https:\u002F\u002Fimg.shields.io\u002Fdocker\u002Fv\u002Ftidbai\u002Ffrontend?sort=semver&arch=amd64&label=tidbai%2Ffrontend&&color=blue&logo=next.js)](https:\u002F\u002Fhub.docker.com\u002Fr\u002Ftidbai\u002Ffrontend)\n  [![E2E Status](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcheck-runs\u002Fpingcap\u002Ftidb.ai\u002Fmain?nameFilter=E2E%20Test&label=e2e)](https:\u002F\u002Ftidb-ai-playwright.vercel.app\u002F)\n\u003C\u002Fdiv>\n\n> [!WARNING]\n> Autoflow is still in the early stages of development. And we are actively working on it, the next move is to make it to a python package and make it a RAG solution e.g. `pip install autoflow-ai`. If you have any questions or suggestions, please feel free to contact us on [Discussion](https:\u002F\u002Fgithub.com\u002Fpingcap\u002Fautoflow\u002Fdiscussions).\n\n## Introduction\n\nAutoFlow is an open source graph rag (graphrag: knowledge graph rag) based knowledge base tool built on top of [TiDB Vector](https:\u002F\u002Fwww.pingcap.com\u002Fai?utm_source=tidb.ai&utm_medium=community) and [LlamaIndex](https:\u002F\u002Fgithub.com\u002Frun-llama\u002Fllama_index) and [DSPy](https:\u002F\u002Fgithub.com\u002Fstanfordnlp\u002Fdspy).\n\n- **Live Demo**: [https:\u002F\u002Ftidb.ai](https:\u002F\u002Ftidb.ai?utm_source=tidb.ai&utm_medium=community)\n- **Deployment Docs**: [Deployment Docs](https:\u002F\u002Fautoflow.tidb.ai\u002F?utm_source=github&utm_medium=tidb.ai)\n\n## Features\n\n1. **Perplexity-style Conversational Search page**: Our platform features an advanced built-in website crawler, designed to elevate your browsing experience. This crawler effortlessly navigates official and documentation sites, ensuring comprehensive coverage and streamlined search processes through sitemap URL scraping.\n\n![Image](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F50a4e5ce-8b93-446a-8ce7-11ed7844bd1e)\n\n2. **Embeddable JavaScript Snippet**: Integrate our conversational search window effortlessly into your website by copying and embedding a simple JavaScript code snippet. This widget, typically placed at the bottom right corner of your site, facilitates instant responses to product-related queries.\n\n![Image](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Ff0dc82db-c14d-4863-a242-c7da3a719568)\n\n## Deploy\n\n- [Deploy with Docker Compose](https:\u002F\u002Fautoflow.tidb.ai\u002Fdeploy-with-docker) (with: 4 CPU cores and 8GB RAM)\n\n## Tech Stack\n\n- [TiDB](https:\u002F\u002Fwww.pingcap.com\u002Fai?utm_source=tidb.ai&utm_medium=community) – Database to store chat history, vector, json, and analytic\n- [LlamaIndex](https:\u002F\u002Fwww.llamaindex.ai\u002F) - RAG framework\n- [DSPy](https:\u002F\u002Fgithub.com\u002Fstanfordnlp\u002Fdspy) - The framework for programming—not prompting—foundation models\n- [Next.js](https:\u002F\u002Fnextjs.org\u002F) – Framework\n- [Tailwind CSS](https:\u002F\u002Ftailwindcss.com\u002F) – CSS framework\n- [shadcn\u002Fui](https:\u002F\u002Fui.shadcn.com\u002F) - Design\n\n## Contributing\n\nWe welcome contributions from the community. If you are interested in contributing to the project, please read the [Contributing Guidelines](\u002FCONTRIBUTING.md).\n\n\u003Ca href=\"https:\u002F\u002Fnext.ossinsight.io\u002Fwidgets\u002Fofficial\u002Fcompose-last-28-days-stats?repo_id=752946440\" target=\"_blank\" style=\"display: block\" align=\"center\">\n  \u003Cpicture>\n    \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fnext.ossinsight.io\u002Fwidgets\u002Fofficial\u002Fcompose-last-28-days-stats\u002Fthumbnail.png?repo_id=752946440&image_size=auto&color_scheme=dark\" width=\"655\" height=\"auto\">\n    \u003Cimg alt=\"Performance Stats of pingcap\u002Fautoflow - Last 28 days\" src=\"https:\u002F\u002Fnext.ossinsight.io\u002Fwidgets\u002Fofficial\u002Fcompose-last-28-days-stats\u002Fthumbnail.png?repo_id=752946440&image_size=auto&color_scheme=light\" width=\"655\" height=\"auto\">\n  \u003C\u002Fpicture>\n\u003C\u002Fa>\n\u003C!-- Made with [OSS Insight](https:\u002F\u002Fossinsight.io\u002F) -->\n\n## License\n\nAutoFlow is open-source under the Apache License, Version 2.0. You can [find it here](https:\u002F\u002Fgithub.com\u002Fpingcap\u002Fautoflow\u002Fblob\u002Fmain\u002FLICENSE.txt).\n\n## Contact\n\nYou can reach out to us on [Discord](https:\u002F\u002Fdiscord.gg\u002FXzSW23Jg9p).\n","AutoFlow 是一个基于图RAG和对话式知识库工具，构建于TiDB Serverless Vector Storage之上。其核心功能包括通过高级网站爬虫实现的困惑度风格对话搜索页面，以及可通过简单JavaScript代码片段嵌入到任何网站中的对话搜索窗口。技术特点上，AutoFlow利用了TiDB Vector、LlamaIndex和DSPy等先进技术来提供高效的知识管理和查询服务。该工具适用于需要快速集成智能问答系统的企业官网或文档站点，帮助用户更便捷地获取信息和支持。","2026-06-11 03:29:50","top_topic"]