{"full_name":"infiniflow/ragflow","owner":"infiniflow","name":"ragflow","shard":"1","url":"https://github.com/infiniflow/ragflow","description":"RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.","homepage":"https://ragflow.io","topics":["ai","ai-agents","rag","retrieval-augmented-generation","agentic-ai","agentic-retrieval","agentic-search","context-management","knowledge-compilation","agent-harness","context-engineering","harness-engineering","search-harness","agent-native-database","context-engine"],"tag_pages":["agent-harness","agentic-ai","ai","ai-agents","context-engineering","harness-engineering","rag","retrieval-augmented-generation"],"language":"Go","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/69962740?v=4","created_at":"2023-12-12T06:13:13Z","pushed_at":"2026-11-13T13:08:52Z","metrics":{"stars":94193,"forks":11326,"watchers":361,"issues":8125,"prs":13407,"releases":60,"issues_open":827,"issues_closed":7298,"prs_open":467,"prs_closed":1816,"prs_merged":11124,"discussions":624},"growth":{"day":{"stars":39,"forks":5,"base_day":"2026-11-15"},"week":{"stars":372,"forks":56,"base_day":"2026-11-09"},"month":{"stars":2123,"forks":363,"base_day":"2026-10-17"}},"history":{"dates":["2026-09-06","2026-09-07","2026-09-08","2026-09-09","2026-09-10","2026-09-11","2026-09-12","2026-09-13","2026-09-14","2026-09-15","2026-09-16","2026-09-17","2026-09-18","2026-09-19","2026-09-20","2026-09-21","2026-09-22","2026-09-23","2026-09-24","2026-09-25","2026-09-26","2026-09-27","2026-09-28","2026-09-29","2026-09-30","2026-10-01","2026-10-02","2026-10-03","2026-10-04","2026-10-05","2026-10-06","2026-10-07","2026-10-08","2026-10-09","2026-10-10","2026-10-11","2026-10-12","2026-10-13","2026-10-14","2026-10-15","2026-10-16","2026-10-17","2026-10-18","2026-10-19","2026-10-20","2026-10-21","2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04","2026-11-09","2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[89158,89231,89318,89399,89448,89519,89589,89837,89915,89993,90053,90100,90214,90303,90386,90457,90528,90578,90685,90752,90825,90886,90958,90999,91105,91170,91228,91273,91300,91332,91436,91507,91584,91606,91626,91699,91730,91772,91847,91912,91958,92070,92152,92217,92283,92333,92376,92480,92544,92605,92663,92748,92809,92912,92968,93022,93092,93208,93365,93440,93821,93944,94032,94084,94093,94126,94154,94193],"forks":[10482,10494,10511,10520,10531,10543,10560,10591,10602,10610,10622,10626,10646,10655,10670,10683,10698,10708,10732,10743,10751,10758,10770,10774,10805,10808,10814,10824,10825,10830,10849,10863,10874,10876,10881,10890,10899,10905,10918,10933,10948,10963,10979,10986,10997,11008,11018,11037,11049,11061,11073,11091,11100,11120,11128,11142,11162,11183,11207,11220,11270,11289,11304,11311,11313,11317,11321,11326],"watchers":[361,360,359,359,360,360,360,364,364,364,364,365,365,365,365,363,363,364,364,365,365,365,365,365,364,363,362,362,362,362,360,361,359,360,361,361,361,361,362,362,362,362,362,362,362,362,362,362,362,362,362,362,358,359,359,360,359,358,359,359,360,360,361,361,361,362,361,361],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,824,825,826,825,827,827],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,443,456,455,448,458,467]},"boards":{"total":168},"same_owner":[],"issues":[{"number":4214,"title":"ROADMAP 2025","comments":64,"created_at":"2024-12-24T11:00:53Z"},{"number":5598,"title":"[Question]: What type of GPU and how many GPUs are recommended to fasten the speed of parsing files?","comments":27,"created_at":"2025-03-04T07:58:29Z"},{"number":7881,"title":"[Question]:when conducting a knowledge base search in the chat interface, it was found that ollama has a high cpu usage rate?","comments":26,"created_at":"2025-05-27T05:57:12Z"},{"number":8619,"title":"[Bug]: Nothing found for the query in Chat Assisntand but the retreival testing displays several chunking including the correct chunk in the 1st position.","comments":23,"created_at":"2025-07-01T17:00:45Z"},{"number":21310,"title":"[Question]: problems ./entrypoint.sh: line 226: python3: command not found  .","comments":19,"created_at":"2026-10-22T01:06:46Z"},{"number":13517,"title":"[Question]: can i generate keywords and questions in the same ingestion pipeline?","comments":18,"created_at":"2026-03-11T01:20:05Z"},{"number":7959,"title":"[Feature Request]: The construction of the knowledge graph is extremely slow. How can I check its progress?","comments":18,"created_at":"2025-05-29T12:55:06Z"},{"number":19983,"title":"[Feature Request]: add Vastbase  as document engine and metadata database","comments":16,"created_at":"2026-09-21T08:35:53Z"}],"discussions":[{"number":22309,"title":"Chopper: a small open model that cuts only the needed sentences out of retrieved text","comments":0,"category":"Show and tell","created_at":"2026-11-12T19:45:29Z"},{"number":22288,"title":"mcp-slim: Zero-dependency MCP stdio proxy for RAGFlow Agents (-50% to -98% tool schema tokens & SecretGuard)","comments":2,"category":"Show and tell","created_at":"2026-11-12T05:35:52Z"},{"number":22244,"title":"Request: a written Community/Enterprise boundary policy, edition matrix, and removal notices for v1.0","comments":1,"category":"General","created_at":"2026-11-11T11:58:59Z"},{"number":22240,"title":"I can't set up the integration with Langfuse correctly with v1.0.0","comments":2,"category":"Q&A","created_at":"2026-11-11T11:05:22Z"},{"number":22167,"title":"Cloud Alter Ego: a remote MCP connector that gives your agents your own context","comments":1,"category":"Show and tell","created_at":"2026-11-09T08:22:06Z"},{"number":22141,"title":"Title: [Bug] Hardcoded 8192 max_tokens limit overrides model's 32K context window, causing \"no completion capacity\" error","comments":2,"category":"Q&A","created_at":"2026-11-09T02:37:40Z"},{"number":21895,"title":"Title: [Bug]: Chat and Agent modes fail with ERROR: no such method when using local Ollama (v1.0.0-rc3)","comments":4,"category":"Q&A","created_at":"2026-11-03T04:40:13Z"},{"number":21848,"title":"RAGFlow 切片踩坑笔记（中文入门整理）","comments":2,"category":"Show and tell","created_at":"2026-11-02T05:42:14Z"}],"latest_release":{"name":"v1.0.0","tag":"v1.0.0","published_at":"2026-11-06T12:31:31Z","body":"After three release candidates, we are pleased to announce the official release of RAGFlow 1.0, now ready for production. Built on a complete rewrite in Go, this release significantly reduces deployment and runtime overhead and introduces an all-new Agentic Chat experience. We encourage all users to upgrade for improved stability, performance, and question answering.\r\n\r\n### Highlights\r\n- Rewritten in Go for lighter deployment: Docker images are approximately 10× smaller, and startup is approximately 10× faster.\r\n- Approximately 100× greater concurrency, with substantial improvements in query latency, memory usage, and document parsing speed.\r\n- All-new Agentic Chat: Enables multi-step reasoning and answers to complex questions through iterative retrieval, tool calls, and evidence sufficiency assessment.\r\n\r\n### Chat and Agents\r\n- Added Agentic Chat mode, replacing the previous Low, Medium, High, and Ultra thinking levels.\r\n- Introduced the Jev decision model into the agent tool-calling loop to determine whether the available evidence is sufficient to answer a question.\r\n- Added support for the Jev decision model in the Categorize agent component.\r\n- Added storage and display of prompts, token usage, and execution time in chat history.\r\n\r\n### Document Ingestion and Retrieval\r\n- Unified the 12 built-in document parsers with the pipeline parsers.\r\n- Added support for multiple ingestion pipeline DSL versions.\r\n\r\n### Architecture and Deployment\r\n- Migrated the message queue from Redis to NATS.\r\n- Adopted Kvrocks for cache and checkpoint storage.\r\n- Added Docker images for the arm64 architecture.\r\n- Reimplemented the RAGFlow CLI in Go.\r\n\r\n### Stability\r\n- Fixed multiple critical bugs reported by the community and issues identified during the release candidate phase, further improving runtime stability.\r\n\r\n### Benchmarks\r\n- Achieved 91% accuracy on the FRAMES multi-hop question-answering benchmark using RAGFlow Agentic Chat with MiniMax M3.\r\n\r\n### Upgrading\r\n- From v1.0.0-rc1, rc2, or rc3: Existing data is fully compatible. You can upgrade directly.\r\n- From v0.27.2: You can upgrade directly to v1.0.0. Data migration runs automatically when the RAGFlow Docker container starts.\r\n- From versions earlier than v0.27.2: Follow the migration guide to complete the required intermediate upgrades before upgrading to v1.0.0.\r\n- Back up all data before upgrading. Data migration from v0.27.2 to v1.0.0 is irreversible. If migration fails, restore the complete pre-upgrade backup before trying again.\r\n\r\n### Compatibility and Limitations\r\n- Deprecated API aliases are no longer supported.\r\n- The Python SDK is unaffected.\r\n- DeepDoc currently supports CPU environments only.\r\n\r\n### Relative references\r\n- Backup and upgrade guide: https://ragflow.io/docs/migration_overview\r\n- Removed APIs: https://ragflow.io/docs/http_api_reference#removed-api-aliases\r\n\r\n\r\n### What's Changed\r\n* fix(parser): keep recovered PDF TOC leader lines out of the body guard by @jay77721 in https://github.com/infiniflow/ragflow/pull/21768\r\n* CI: Fix log tee failure by @myf-bee in https://github.com/infiniflow/ragflow/pull/21791\r\n* Update release notes of 1.0.0.rc3 by @yingfeng in https://github.com/infiniflow/ragflow/pull/21793\r\n* feat: add Wally as a model provider by @adityabatra072 in https://github.com/infiniflow/ragflow/pull/21719\r\n* add audit hooks to file APIs by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/21807\r\n* add log hooks by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/21822\r\n* i18n: translate pipeline version and parser settings strings in tr-TR by @bakiburakogun in https://github.com/infiniflow/ragflow/pull/21819\r\n* fix(models): honour context cancellation in driver HTTP requests by @ccclucky in https://github.com/infiniflow/ragflow/pull/21643\r\n* feat(vastbase): support Vastbase G100 as the metadata database in Go by @FengYikai710 in https://github.com/infiniflow/ragflow/pull/20913\r\n* fix: README.md by @eridan-ltu in https://github.com/infini","is_prerelease":false},"readme":true,"readme_zh":true,"news":[{"title":"RAGFlow is an open-source RAG engine based on OCR and document parsing","url":"https://github.com/infiniflow/ragflow","hn":"https://news.ycombinator.com/item?id=39896923","source":"Hacker News","lang":"en","date":"2024-04-01","points":230,"comments":53},{"title":"DeepSeek-V2 integrated, RAGFlow v0.5.0 is released","url":"https://github.com/infiniflow/ragflow/releases/tag/v0.5.0","hn":"https://news.ycombinator.com/item?id=40294775","source":"Hacker News","lang":"en","date":"2024-05-08","points":7,"comments":0},{"title":"RAGFlow 0.9 is released to support GraphRAG end-to-end","url":"https://github.com/infiniflow/ragflow/releases/tag/v0.9.0","hn":"https://news.ycombinator.com/item?id=41170397","source":"Hacker News","lang":"en","date":"2024-08-06","points":3,"comments":0},{"title":"Ragflow: fuses RAG with Agent capabilities to create context layer for LLMs","url":"https://github.com/infiniflow/ragflow","hn":"https://news.ycombinator.com/item?id=47313655","source":"Hacker News","lang":"en","date":"2026-03-09","points":2,"comments":0},{"title":"Integrated Rerankers, implemented RAPTOR, RAGFlow 0.7 released","url":"https://github.com/infiniflow/ragflow/releases/tag/v0.7.0","hn":"https://news.ycombinator.com/item?id=40522767","source":"Hacker News","lang":"en","date":"2024-05-30","points":2,"comments":0},{"title":"MinerU 集成 RAGFlow 实战指南：为 RAG 知识库启用 MinerU 高级 PDF 解析器","url":"https://blog.csdn.net/gitblog_00242/article/details/155741448","source":"blog.csdn","lang":"zh","date":"2026-09-04"},{"title":"RAGFlow v0.24.0 首次部署默认登录账号说明","url":"https://www.sohu.com/a/986653726_122632418","source":"搜狐","lang":"zh","date":"2026-02-12"},{"title":"主流 RAG 框架解读：从 RAGFlow 到 GraphRAG（企业级智能应用构建必读）","url":"https://finance.sina.com.cn/roll/2025-11-11/doc-infwyqem4671800.shtml","source":"新浪网","lang":"zh","date":"2025-11-10"},{"title":"【GitHub项目推荐--RAGFlow：开源检索增强生成引擎】","url":"https://blog.csdn.net/j8267643/article/details/153259224","source":"blog.csdn","lang":"zh","date":"2025-10-14"},{"title":"Github上的十大RAG(信息检索增强生成)框架","url":"https://news.qq.com/rain/a/20241031A021QI00","source":"腾讯网","lang":"zh","date":"2024-10-31"},{"title":"RAGFlow开源Star量破万，是时候思考下RAG的未来是什么了","url":"https://finance.sina.com.cn/tech/roll/2024-07-06/doc-inccemmn5863127.shtml","source":"新浪网","lang":"zh","date":"2024-07-06"},{"title":"由近期 RAGFlow 的火爆看 RAG 的现状与未来","url":"https://news.qq.com/rain/a/20240409A01DO500","source":"腾讯网","lang":"zh","date":"2024-04-09"},{"title":"RAGFlow 1.0 正式发布：超越 RAG，迈向 Agent Native Database","url":"https://news.google.com/rss/articles/CBMiXEFVX3lxTFBzUlI5NWFqUTVVVzBjM1NmbjF4aTVXRVJ2X1NmT2JOV21kdGRQdldBSmZEUGlIWDV0WGhmUFBRNkNoT3FxelRSZVJSY3pmNDJnV1JMUWFWbWoxdUx4?oc=5","source":"53AI","lang":"zh","date":"2026-11-09"},{"title":"10 Open-Source No-Code AI Platforms for Building LLM Apps, RAG Systems, and AI Agents","url":"https://news.google.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?oc=5","source":"MarkTechPost","lang":"en","date":"2026-07-18"},{"title":"Top 6 No-Code Tools for AI Engineers/Developers","url":"https://news.google.com/rss/articles/CBMikgFBVV95cUxNNU9xRnhWc2o3NTRMbzBYdzhMM0psMzJTYmk5OXdYVmFBVFBDTzVmMXpEaXJPT1c4SVlHaUlVNjRKSlB1NXBEdU5HTUptVC1nQmV2WVZIMXN0TWxhMDhreXlERGFEMzE1SUxCNUV3NjhnRmdibGNwa2pKaFlUaVo5ZGhQVTc3dmlmeEtPc21GUnZJZ9IBkgFBVV95cUxNNU9xRnhWc2o3NTRMbzBYdzhMM0psMzJTYmk5OXdYVmFBVFBDTzVmMXpEaXJPT1c4SVlHaUlVNjRKSlB1NXBEdU5HTUptVC1nQmV2WVZIMXN0TWxhMDhreXlERGFEMzE1SUxCNUV3NjhnRmdibGNwa2pKaFlUaVo5ZGhQVTc3dmlmeEtPc21GUnZJZw?oc=5","source":"MarkTechPost","lang":"en","date":"2026-06-28"},{"title":"Top 100 OSS AI Tools That Matter — Mapping the Contemporary High-Leverage Open-Source AI Tooling","url":"https://news.google.com/rss/articles/CBMi1gFBVV95cUxPZWFnelZuYnN0ei15Vk1Nc3lwRFZVajEwTkpTeVI5Z0pSSkdBY3FMb3dwcl8tbF9sS2lpcDlWak9RU1dqQnp1WWliUUNXeUxMUzdaRUJ5S05iMV9jc3o0Mzh0R0JDUTc4X2FhUE5EdkRLZzI3cGR1Y3Q0X3ptcFgzSWF5X1hOLWdIS00wV1hkQTRxNkhnR1RTdGpLUVpwT2djZzdtWUNqeG1uZkVxb1Qyb0dtMm1vcXNwVHc1dTBNUEpucGVWT0ozMmFPRTNfQ2x0TDBvOWFn?oc=5","source":"Medium","lang":"en","date":"2026-03-05"},{"title":"掌握RAG系统的七个优秀GitHub存储库","url":"https://news.google.com/rss/articles/CBMiU0FVX3lxTE5DbUswTVdkaXYxak9sYTFVUE5ILTRwRXI0TU16cGtZbXMtYzJoUmhXeXUtZGZXdWpVZ1ZaZFdnbEszcWVVakZ2TEo2Rlo1MGNIUFJv?oc=5","source":"51CTO","lang":"zh","date":"2025-10-29"},{"title":"DeepSeek+ragflow构建企业知识库：高级应用篇，越折腾越觉得ragflow好玩","url":"https://news.google.com/rss/articles/CBMiV0FVX3lxTE5uRk1CTmpLWTk1TUpEa0FRX3JFZ1E3MlFtV181aGhVcnBmbVRRUzhvYjlhNGg0VlJPaXBuVHdpeFBySnVRQmY1LXc5YmJyUUhCTTF5WFJURQ?oc=5","source":"我来 wolai","lang":"zh","date":"2025-09-23"},{"title":"The Sequence Engineering #661: Create Your Own Deep Research Agent with DeerFlow","url":"https://news.google.com/rss/articles/CBMiekFVX3lxTFB0aE5UVXRDSkdzSjB1M3REZGtESThTcjNfMUNuWU9XT0VuOUV1WmVQM05mYmhNdjB2aERfYlVTMlVkN0lFdUZlTXRsZGVHX2tNbHNSeVRnNllvdXVidWxoTlgxNnpEcXBzdDhHT2dtYTlUcURrX2xpajRB?oc=5","source":"TheSequence | Jesus Rodriguez","lang":"en","date":"2025-06-11"},{"title":"DeepSeek接入个人知识库，保姆级教程来了！","url":"https://news.google.com/rss/articles/CBMiSEFVX3lxTE9tS0lvc08xQnMzaDZkMTZ0N1lEQm56ZHc3YTdwbExtUHlSSF9RSzhLa0lPUkVjRk02U3p6b1EwOVJSN0RBU3VGcg?oc=5","source":"智源社区","lang":"zh","date":"2025-02-26"},{"title":"Open Source LLM Tool Sniffs Out Python Zero-Days","url":"https://news.google.com/rss/articles/CBMilwFBVV95cUxNdTZDVFdUVnRjZEQzR0llX2VmbHZTMWdaQmthb0dzLTNaN29xQWF1bTE4ZGpUTW9Ed2NRRHExTndhMWl0aTIxVkZmeHBJakhXYm1mRTY3Wm5HOHN4LUFzdmk0MUxGY0ZiV2VWM3FQclFxcjRWYUFKd2Q1UWZHdHc0ajZPUVJmaFJBaFR5c0l4OVM5azVwMWdv?oc=5","source":"Dark Reading","lang":"en","date":"2024-10-24"},{"title":"RAGFlow：基于OCR和文档解析的下一代 RAG 引擎","url":"https://news.google.com/rss/articles/CBMiUEFVX3lxTE1oYTJDTDdVSVI5V2dPSzZYX3NuOHNyUTBMTVdXREtaNkdqTDFpbUlQaTUzM3RJVGx3WmV4UlZ3V19RS1hDRk1rbWdYVWdYY3Q4?oc=5","source":"53AI","lang":"zh","date":"2024-05-05"}],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}