Real-time Email RAG Assistant: Gmail, OpenAI & PGVector

This workflow creates a powerful real-time Retrieval-Augmented Generation (RAG) assistant for Gmail users. It continuously watches for new emails, extracts key content like subject, body, sender, and date, then generates vector embeddings using OpenAI's models. These embeddings are stored in a PostgreSQL database enhanced with the PGVector extension, enabling efficient semantic search across your email history.

When you query the system with natural language, the AI agent performs vector similarity searches to retrieve relevant emails, augments the context, and generates intelligent, time-sensitive responses using OpenAI's Chat model. This setup is perfect for professionals, project managers, sales, and support teams handling high email volumes, turning chaotic inboxes into searchable knowledge bases.

Benefits include lightning-fast searches without manual digging, context-aware answers that consider dates and senders, and scalability for enterprise use. Customize filtering by labels/senders, text chunking, or search depth to fit your needs. Requires n8n, Gmail API, OpenAI key, and PGVector-enabled Postgres.