Google DeepMind just turned every self-hosted RAG stack into legacy code.
The new File Search Tool, available in the Gemini API, enables developers to upload any document, PDF, DOCX, Python script, or JSON file once and query it indefinitely with no cost for storage or runtime embeddings.
Pay a single $0.15 per million tokens to index, and then every search is free, citations are automatic, and the entire pipeline lives within the same generateContent call you already use.
No vector DB, no chunking headaches, no surprise bills.
Key Takeaways:
- File Search Tool is a fully managed RAG engine built directly into the Gemini API, no external vector DB required.
- Developers pay only for initial indexing ($0.15/M tokens); storage, query-time embeddings, and all searches are permanently free.
You may also want to check out some of our other recent updates.
Wanna know what’s trending online every day? Subscribe to Vavoza Insider to access the latest business and marketing insights, news, and trends daily with unmatched speed and conciseness! 🗞️
