{"product_id":"n8n-rag-chatbot-ollama-qdrant-retrieval-qa-workflow","title":"n8n RAG Chatbot: Ollama + Qdrant Retrieval QA Workflow","description":"\u003ch3\u003eBuild a local RAG chatbot in n8n that answers from your own Qdrant knowledge base\u003c\/h3\u003e\n\u003cp\u003eThis n8n workflow lets you create a retrieval-augmented generation (RAG) chat experience on your machine: it pulls relevant passages from a Qdrant vector collection, then generates an answer with a local Ollama model—staying grounded in the retrieved context.\u003c\/p\u003e\n\n\u003ch3\u003eWhat this workflow does\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eReceives your question\u003c\/strong\u003e via an n8n chat trigger.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eRetrieves relevant document chunks\u003c\/strong\u003e from a \u003cstrong\u003eQdrant\u003c\/strong\u003e collection using an \u003cstrong\u003eOllama-powered embeddings model\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eInjects retrieved context\u003c\/strong\u003e into a \u003cstrong\u003eretrieval QA prompt\u003c\/strong\u003e that instructs the assistant to \u003cstrong\u003eanswer only from the provided passages\u003c\/strong\u003e and to \u003cstrong\u003edecline when information is missing\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eGenerates a concise response\u003c\/strong\u003e using the local Ollama chat model \u003cstrong\u003eqwen2.5:7b\u003c\/strong\u003e.\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eUse cases\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eInternal support chatbot\u003c\/strong\u003e for your handbook or SOPs, grounded in your own indexed documents.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eKnowledge Q\u0026amp;A for SaaS operations\u003c\/strong\u003e (policies, troubleshooting notes, release procedures) with transparent, context-only answers.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eRAG testing in automation projects\u003c\/strong\u003e—tune retrieval by increasing \u003cem\u003eTop K\u003c\/em\u003e when multi-fact questions need broader context.\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eTechnical details\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003en8n trigger:\u003c\/strong\u003e \u003ccode\u003en8nn8n-nodes-langchainchat\u003c\/code\u003e chat trigger\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eEmbeddings:\u003c\/strong\u003e \u003ccode\u003en8nn8n-nodes-langchainembeddings\u003c\/code\u003e with Ollama (e.g., \u003cstrong\u003enomic-embed-text:latest\u003c\/strong\u003e)\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eVector store:\u003c\/strong\u003e \u003ccode\u003en8nn8n-nodes-langchainvectorstore\u003c\/code\u003e connected to \u003cstrong\u003eQdrant\u003c\/strong\u003e\n\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eRetrieval QA:\u003c\/strong\u003e \u003ccode\u003en8nn8n-nodes-langchainchain\u003c\/code\u003e retrieval QA chain\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eLLM:\u003c\/strong\u003e \u003ccode\u003en8nn8n-nodes-langchainlm\u003c\/code\u003e Ollama chat model (\u003cstrong\u003eqwen2.5:7b\u003c\/strong\u003e)\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eSetup essentials\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003eRun the companion indexing workflow first: \u003cstrong\u003e“Index local documents for RAG using Ollama embeddings and Qdrant”\u003c\/strong\u003e (https:\/\/creators.n8n.io\/workflows\/17764).\u003c\/li\u003e\n  \u003cli\u003eStart \u003cstrong\u003eOllama locally\u003c\/strong\u003e and pull \u003cstrong\u003eqwen2.5:7b\u003c\/strong\u003e and \u003cstrong\u003enomic-embed-text:latest\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003eCreate n8n credentials for \u003cstrong\u003elocal Ollama\u003c\/strong\u003e and your \u003cstrong\u003eQdrant\u003c\/strong\u003e instance.\u003c\/li\u003e\n  \u003cli\u003eSet the \u003cstrong\u003eQdrant collection name\u003c\/strong\u003e to match the one used during indexing (e.g., \u003cstrong\u003e“handbook”\u003c\/strong\u003e).\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"N8N Commerce","offers":[{"title":"Default Title","offer_id":45758755668147,"sku":"N8N-17780","price":53.99,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0749\/6279\/6723\/files\/NOYz8I_MFFMOgnPofTtLO_20jilT2p.png?v=1785834645","url":"https:\/\/buyflowscripts.com\/products\/n8n-rag-chatbot-ollama-qdrant-retrieval-qa-workflow","provider":"N8N Commerce","version":"1.0","type":"link"}