Local Document Chatbot with Groq & Cohere RAG

This powerful n8n workflow demonstrates how to build an intelligent Q&A system for your unstructured data using a Retrieval Augmented Generation (RAG) architecture. It automates the process of ingesting local text files, splitting them into manageable chunks, and embedding them into an in-memory vector store using Cohere. When a user asks a question via the integrated chat trigger, the workflow dynamically retrieves the most relevant document segments (after embedding the query with Cohere) from the same in-memory store and passes them, along with the user's query, to a high-performance Groq Llama-3 chat model. This ensures that the AI's responses are grounded in your specific data, providing factual and up-to-date answers without hallucinations, all within a self-contained n8n environment for rapid prototyping and local knowledge retrieval.