{"product_id":"n8n-rag-chat-agent-gemini-embeddings-supabase-vector-store","title":"n8n RAG Chat Agent: Gemini Embeddings + Supabase Vector Store","description":"\u003ch3\u003eBuild a Gemini-powered RAG chatbot in n8n—powered by Supabase vector search\u003c\/h3\u003e\n\u003cp\u003eThis \u003cstrong\u003en8n RAG Chat Agent\u003c\/strong\u003e workflow ingests a \u003cstrong\u003eREADME.md from GitHub\u003c\/strong\u003e, generates \u003cstrong\u003eGoogle Gemini embeddings\u003c\/strong\u003e, stores them in a \u003cstrong\u003eSupabase Vector Store\u003c\/strong\u003e, and then answers questions in an \u003cstrong\u003en8n Chat\u003c\/strong\u003e interface using retrieved, grounded context.\u003c\/p\u003e\n\n\u003ch3\u003eWhat this workflow does\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eIngest content from GitHub:\u003c\/strong\u003e Runs manually to fetch a \u003cem\u003eREADME.md\u003c\/em\u003e file from a GitHub \u003cstrong\u003eraw URL\u003c\/strong\u003e using an \u003cstrong\u003eHTTP Request\u003c\/strong\u003e node.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eChunk and enrich documents:\u003c\/strong\u003e Splits the fetched Markdown into document chunks and adds metadata for each chunk.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eCreate embeddings with Google Gemini:\u003c\/strong\u003e Uses Gemini for embeddings, then inserts embedded documents into a \u003cstrong\u003eSupabase vector-enabled table\u003c\/strong\u003e via the Supabase vector store.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eEnable chat with retrieval-augmented answers:\u003c\/strong\u003e Triggers when a chat message is received in \u003cstrong\u003en8n Chat\u003c\/strong\u003e, uses a \u003cstrong\u003eGoogle Gemini chat model\u003c\/strong\u003e with buffer memory, and a \u003cstrong\u003eSupabase retrieval tool\u003c\/strong\u003e to pull relevant chunks.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eGrounded responses:\u003c\/strong\u003e Returns answers grounded in the retrieved Supabase documents.\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eUse cases\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eSaaS operator support:\u003c\/strong\u003e Answer internal questions using docs stored in a Supabase vector table.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003en8n workflow onboarding:\u003c\/strong\u003e Build a chat agent that explains how your GitHub-hosted README works.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eKnowledge base Q\u0026amp;A:\u003c\/strong\u003e Retrieve the most relevant document chunks from Supabase for accurate, source-based responses.\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eTechnical details\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eIntegrations:\u003c\/strong\u003e GitHub (raw README via HTTP Request), \u003cstrong\u003eGoogle Gemini\u003c\/strong\u003e (embeddings + chat), \u003cstrong\u003eSupabase Vector Store\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eWorkflow triggers:\u003c\/strong\u003e Manual trigger for ingestion; \u003cstrong\u003en8nnodes-langchainchat\u003c\/strong\u003e for chat messages in n8n Chat.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eKey nodes\/tools:\u003c\/strong\u003e \u003cstrong\u003en8nnodes-langchainagent\u003c\/strong\u003e, \u003cstrong\u003en8nnodes-langchainchat trigger\u003c\/strong\u003e, \u003cstrong\u003en8nnodes-langchainlm (Google Gemini)\u003c\/strong\u003e, plus vector store retrieval.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cstrong\u003eSetup note:\u003c\/strong\u003e Create a Supabase vector table (e.g., \u003ccode\u003edocuments\u003c\/code\u003e) and ensure the vector size matches the embedding model; then add \u003cstrong\u003eSupabase\u003c\/strong\u003e credentials and \u003cstrong\u003eGoogle Gemini (PaLM)\u003c\/strong\u003e API credentials for both embeddings and the chat model.\u003c\/p\u003e","brand":"N8N Commerce","offers":[{"title":"Default Title","offer_id":45862253002931,"sku":"N8N-18057","price":35.99,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0749\/6279\/6723\/files\/ni-BLsuWyIWnTbDVO7-Rd_xPb9gJze.png?v=1786958204","url":"https:\/\/buyflowscripts.com\/products\/n8n-rag-chat-agent-gemini-embeddings-supabase-vector-store","provider":"N8N Commerce","version":"1.0","type":"link"}