--- schema: 1 type: video title: 'OpenRAG: An open-source stack for RAG — Phil Nash' description: >- There are many variables in building RAG applications, from document parsing to the language model you pick for generation and everything in between. Combining Docling for document parsing, OpenSearch for retrieval, and Langflow for orchestration, plus local and remote models, OpenRAG is an opinionated, agentic, open-source stack for building the RAG application of your dreams. Just because it has opinions doesn't make it inflexible though. In this talk we'll look at how OpenRAG gives you a great baseline for RAG and how you can tune it and evaluate the outcomes to create RAG applications that work well with your data. You'll learn how to get the best out of your documents with Docling, how OpenSearch provides more than just vector search, and how Langflow makes it easy to customise your pipeline to interact with your data the way you want to. You’ll leave with a playbook of options to improve your RAG app and a stack you can extend without reinventing everything. Phil Nash - Developer relations engineer, IBM Phil is a developer relations engineer for DataStax and Google Developer Expert living in Melbourne, Australia. He's been working in developer relations for a decade, speaking at conferences since 2012, and writing JavaScript since before jQuery. Away from the keyboard, Phil enjoys travel, live music, and hanging out with his mini sausage dog, Ruby. Socials: https://x.com/philnash https://linkedin.com/in/philnash https://philna.sh https://github.com/philnash --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/4TxOBhDRRCM-openrag-an-open-source-stack-for-rag-phil-nash Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- canonical: 'https://liquidgold.cc/watch/4TxOBhDRRCM' markdown: 'https://liquidgold.cc/watch/4TxOBhDRRCM.md' llms: 'https://liquidgold.cc/watch/4TxOBhDRRCM/llms.txt' parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T15:36:53.287Z' language: null children: [] videoId: 4TxOBhDRRCM durationSeconds: 952 publishedAt: '2026-04-08T11:00:16.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 14 endSeconds: 101 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=14' heldReason: rights - ordinal: 1 text: null startSeconds: 14 endSeconds: 101 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=14' heldReason: rights - ordinal: 2 text: null startSeconds: 14 endSeconds: 101 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=14' heldReason: rights - ordinal: 3 text: null startSeconds: 101 endSeconds: 112 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=101' heldReason: rights - ordinal: 4 text: null startSeconds: 112 endSeconds: 202 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=112' heldReason: rights - ordinal: 5 text: null startSeconds: 112 endSeconds: 202 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=112' heldReason: rights - ordinal: 6 text: null startSeconds: 213 endSeconds: 314 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=213' heldReason: rights - ordinal: 7 text: null startSeconds: 213 endSeconds: 314 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=213' heldReason: rights - ordinal: 8 text: null startSeconds: 213 endSeconds: 314 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=213' heldReason: rights - ordinal: 9 text: null startSeconds: 314 endSeconds: 326 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=314' heldReason: rights - ordinal: 10 text: null startSeconds: 326 endSeconds: 459 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=326' heldReason: rights - ordinal: 11 text: null startSeconds: 326 endSeconds: 459 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=326' heldReason: rights - ordinal: 12 text: null startSeconds: 326 endSeconds: 459 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=326' heldReason: rights - ordinal: 13 text: null startSeconds: 459 endSeconds: 470 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=459' heldReason: rights - ordinal: 14 text: null startSeconds: 579 endSeconds: 668 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=579' heldReason: rights - ordinal: 15 text: null startSeconds: 579 endSeconds: 668 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=579' heldReason: rights - ordinal: 16 text: null startSeconds: 679 endSeconds: 768 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=679' heldReason: rights - ordinal: 17 text: null startSeconds: 768 endSeconds: 780 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=768' heldReason: rights - ordinal: 18 text: null startSeconds: 780 endSeconds: 869 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=780' heldReason: rights - ordinal: 19 text: null startSeconds: 780 endSeconds: 869 watch: 'https://liquidgold.cc/watch/4TxOBhDRRCM?t=780' heldReason: rights --- # OpenRAG: An open-source stack for RAG — Phil Nash There are many variables in building RAG applications, from document parsing to the language model you pick for generation and everything in between. Combining Docling for document parsing, OpenSearch for retrieval, and Langflow for orchestration, plus local and remote models, OpenRAG is an opinionated, agentic, open-source stack for building the RAG application of your dreams. Just because it has opinions doesn't make it inflexible though. In this talk we'll look at how OpenRAG gives you a great baseline for RAG and how you can tune it and evaluate the outcomes to create RAG applications that work well with your data. You'll learn how to get the best out of your documents with Docling, how OpenSearch provides more than just vector search, and how Langflow makes it easy to customise your pipeline to interact with your data the way you want to. You’ll leave with a playbook of options to improve your RAG app and a stack you can extend without reinventing everything. Phil Nash - Developer relations engineer, IBM Phil is a developer relations engineer for DataStax and Google Developer Expert living in Melbourne, Australia. He's been working in developer relations for a decade, speaking at conferences since 2012, and writing JavaScript since before jQuery. Away from the keyboard, Phil enjoys travel, live music, and hanging out with his mini sausage dog, Ruby. Socials: https://x.com/philnash https://linkedin.com/in/philnash https://philna.sh https://github.com/philnash --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/4TxOBhDRRCM-openrag-an-open-source-stack-for-rag-phil-nash Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- Canonical: https://liquidgold.cc/watch/4TxOBhDRRCM · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks > Missing: no stored document chunks are available.