{"id":"f68932b3-746d-4c92-bb82-c7b4708c46b5","slug":"n8n-5148-local-chatbot-with-retrieval-augmented-generation-rag","name":"Local Chatbot with Retrieval Augmented Generation (RAG)","description":"Build a 100% local RAG with n8n, Ollama and Qdrant. This agent uses a semantic database (Qdrant) to answer questions about PDF files.\n\nTutorial\n\nClick here to view the YouTube Tutorial\n\nHow it works\nBuild a chatbot that answers based on documents you provide it (Retrieval Augmented Generation). You can upload as many PDF files as you want to the Qdrant database. The chatbot will use its retrieval tool to fetch the chunks and use them to answer questions.\n\nInstallation\nInstall n8n + Ollama + Qdrant using the Self-hosted AI starter kit\nMake sure to install Llama 3.2 and mxbai-embed-large as embeddings model.\n\nHow to use it\nFirst run the \"Data Ingestion\" part and upload as many PDF files as you want\nRun the Chatbot and start asking questions about the documents you uploaded\n","capabilities":["workflow","automation","ai agent","chatbot","documents","agent","AI","Langchain","Ollama Chat Model","lmChatOllama","Simple Memory","memoryBufferWindow","Recursive Character Text Splitter","textSplitterRecursiveCharacterTextSplitter","Default Data Loader","documentDefaultDataLoader","Qdrant Vector Store","vectorStoreQdrant","Embeddings Ollama"],"protocols":[],"safetyScore":80,"overallRank":84,"trustScore":null,"trust":null,"source":"N8N_TEMPLATES","updatedAt":"2026-05-22T06:53:57.851Z"}