DeepMind’s RAG System with Animesh Chatterji and Ivan Solovyev

Retrieval Augmented Generation, or RAG, has become a foundational approach to building production AI systems. However, deploying RAG in practice can be complex and costly. Developers typically have to manage vector databases, chunking strategies, embedding models, and indexing infrastructure. Designing effective RAG systems is also a moving target, as techniques and best practices evolve in step with rapidly advancing language models. Google DeepMind recently released the FileSearch tool, a fully managed RAG system built directly into the Gemini API. FileSearch abstracts away the retrieval pipeline, allowing developers to upload documents, code, and other text data, automatically generate embeddings, and query their knowledge base. We wanted to understand how the DeepMind team designed a general purpose reg system that maintains high retrieval quality. Animesh Chatterjee is a software engineer at Google DeepMind, and Ivan Solavyev is a product manager at DeepMind, and they worked on the file search tool. They joined the podcast with Sean Falconer to discuss the evolution of RAG, why simplicity and pricing transparency matter, how embedding models have improved retrieval quality, the trade offs between configurability and ease of use, and what's next for multimodal retrieval across text, images, and beyond. This episode is hosted by Sean Falconer. Check the show notes for more information on Sean's work and where to find him. Yvonne and Animesh, welcome to the show. Thank you so much. Pleasure to be here. Awesome. Well, why don't we so there you know, we have two guests today just so everyone can kinda learn whose voice is who. Why don't we start off with Ivan, we'll start with you. You know, who are you and what do you do? Yeah. My name is Ivan. I'm product manager for file search on Gemini API. Great. And, Animesh, you? Hi. I'm Animesh. I'm the engineering lead on file search. Awesome. Well, thanks both for being here. So, you know, we're talking about this product, which you you mentioned to your file, the FHIR search tool for Gemini APIs. And before we get too deep into, I think, sort of some general things around with AI, RAG, agents, and so on, Can you talk a little bit about, you know, what the file search tool is and what problem it tries to address? Maybe, Yvonne, you can take that. Yeah. Absolutely. So file search tool, first of all, is a integrated rack solution that makes it super easy for you to take loads and loads of data, text, PDFs, codes, whatever you have uploaded into Gemini and start asking questions about your data. There are plenty of rack pipelines available on the market, like we have vertex rack engine, and there are other providers who do support this feature. So it's nothing you. And what we focused on in file search in particular is accessibility and simplicity of use. We made some opinionated decisions, we removed a lot of complexity in terms of configuration setup, you don't need to set up your database, you don't need …