I Built a RAG Agent in n8n Using Gemini File Search API (No Vector DB)
This weekend I experimented with a different way to build RAG. Instead of the typical setup: - Generate embeddings - Store in Pinecone / Supabase - Manage vector DB infra - Handle indexing + costs I tested Gemini File Search API directly inside n8n. And honestlyโฆ it simplified the entire pipeline. ๐ง What I Actually Built Inside n8n, I used just 4 HTTP requests: 1. Create a file store 2. Upload a document 3. Move the file into the store 4. Query Gemini Thatโs it. Gemini handled: - Chunking - Embeddings - Indexing - Retrieval No external vector database.No embedding model setup. ๐ฐ Why This Is Interesting - Storage is free - No hourly DB cost - Indexing is $0.15 per 1M tokens For small projects, internal tools, or MVPs โ this is extremely cost-efficient. โ ๏ธ Important Limitations I Noticed This is not magic. - No automatic version control (re-upload = duplicate data) - Chunk-based retrieval struggles with full-document reasoning - OCR works, but messy documents still need preprocessing - Data is processed on Google servers (privacy considerations apply) So architecture thinking still matters. My Take For: - Internal AI assistants - Automation workflows - Startup prototypes - Personal tools This is a powerful alternative to traditional vector DB setups. I wouldnโt blindly replace enterprise-grade systems yet โ but for builders, this is very interesting. If anyone here is experimenting with Gemini File Search or building RAG in n8n, Iโd love to compare notes ๐ Happy to share the workflow structure if thereโs interest.