We're also working to have a RAG system on Jemini so you can talk to the files. many of the files have been embedded into vectors thru turbopuffer.
Will do a shameless plug here of Skald: https://www.useskald.com/
You'll get the whole RAG/context layer going in an hour. Can self-host too if you prefer.
This is really impressive btw!
RAG doesn't have to be vectors. You can also make a regular full text search and it's gonna be RAG.