This project is a Retrieval-Augmented Generation (RAG) AI Agent built using n8n to enable intelligent document understanding and contextual retrieval. The workflow automates the process of file ingestion, text extraction, embedding generation, and context retrieval for AI chat or analysis. It integrates tools such as OpenAI Embeddings for vector creation, PGVector (PostgreSQL) for semantic storage and retrieval, and n8n workflow automation to orchestrate the entire pipeline — from document upload to contextual response generation. This setup allows users to query documents intelligently using natural language while leveraging powerful vector search for precise, context-aware results.
Tools:
PGVector (PostgreSQL), n8n, Ollama, Docker
