--- title: OpenRAG: An open-source stack for RAG — Phil Nash description: OpenRAG is an open-source RAG stack built at IBM that combines three projects: Docling for document processing, OpenSearch for hybrid vector and keyword... canonical: https://daily.dev/posts/openrag-an-open-source-stack-for-rag-phil-nash-h18yzzsiz twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: OpenRAG: An open-source stack for RAG — Phil Nash | daily.dev og:description: OpenRAG is an open-source RAG stack built at IBM that combines three projects: Docling for document processing, OpenSearch for hybrid vector and keyword... og:url: https://daily.dev/posts/openrag-an-open-source-stack-for-rag-phil-nash-h18yzzsiz og:image: https://api.daily.dev/og/posts/H18YZzsIZ.png og:image:alt: OpenRAG: An open-source stack for RAG — Phil Nash og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # OpenRAG: An open-source stack for RAG — Phil Nash **[AI Engineer](https://daily.dev/sources/aidotengineer)** · 15 min read · 0 upvotes · 0 comments ## Summary OpenRAG is an open-source RAG stack built at IBM that combines three projects: Docling for document processing, OpenSearch for hybrid vector and keyword search, and LangFlow for visual orchestration and agentic retrieval. It supports multiple document types including PDFs, uses hierarchical chunking, supports multiple embedding providers (including local Ollama models), and can run fully offline. The stack features agentic retrieval where an LLM agent decides what searches to perform, cloud connector integrations (Google Drive, SharePoint, OneDrive), configurable chunking and OCR settings, an MCP server, and an API for integration. Currently at v0.4.0, the frontend is Next.js and the backend is Python. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [From Zero to Agentic Search in 15 Minutes with OpenRAG](https://daily.dev/posts/from-zero-to-agentic-search-in-15-minutes-with-openrag-3idvmzuvp) · Niklas Heidloff · 48 upvotes · 2 comments - [The Open-source RAG Stack](https://daily.dev/posts/the-open-source-rag-stack-u5yz786h6) · Daily Dose of Data Science \| Avi Chawla \| Substack · 136 upvotes · 0 comments - [Building Agentic RAG with LangGraph and OpenSearch](https://daily.dev/posts/building-agentic-rag-with-langgraph-and-opensearch-9inxh7ahs) · BigData Boutique blog · 4 upvotes · 0 comments --- Tags: [#rag](https://daily.dev/tags/rag), [#vector-search](https://daily.dev/tags/vector-search), [#opensearch](https://daily.dev/tags/opensearch) [View this post on daily.dev](https://daily.dev/posts/openrag-an-open-source-stack-for-rag-phil-nash-h18yzzsiz) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"OpenRAG: An open-source stack for RAG — Phil Nash","url":"https://daily.dev/posts/openrag-an-open-source-stack-for-rag-phil-nash-h18yzzsiz","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/openrag-an-open-source-stack-for-rag-phil-nash-h18yzzsiz"},"datePublished":"2026-04-08T11:10:05.377Z","dateModified":"2026-04-08T11:10:23.589Z","description":"OpenRAG is an open-source RAG stack built at IBM that combines three projects: Docling for document processing, OpenSearch for hybrid vector and keyword...","image":"https://i.ytimg.com/vi/4TxOBhDRRCM/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/4TxOBhDRRCM/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AI Engineer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AI Engineer","logo":"https://media.daily.dev/image/upload/s--u5PucxNT--/f_auto/v1724338940/logos/aidotengineer","url":"https://daily.dev/sources/aidotengineer"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/openrag-an-open-source-stack-for-rag-phil-nash-h18yzzsiz","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"rag,vector-search,opensearch","timeRequired":"PT15M","video":{"@type":"VideoObject","name":"OpenRAG: An open-source stack for RAG — Phil Nash","description":"OpenRAG is an open-source RAG stack built at IBM that combines three projects: Docling for document processing, OpenSearch for hybrid vector and keyword...","thumbnailUrl":"https://i.ytimg.com/vi/4TxOBhDRRCM/sddefault.jpg","uploadDate":"2026-04-08T11:10:05.377Z","duration":"PT15M","url":"https://api.daily.dev/r/H18YZzsIZ","embedUrl":"https://www.youtube.com/embed/4TxOBhDRRCM"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Engineer","item":"https://daily.dev/sources/aidotengineer"},{"@type":"ListItem","position":3,"name":"OpenRAG: An open-source stack for RAG — Phil Nash"}]} ```