Building search-based RAG using Claude, Datasette and Val.Town

Retrieval Augmented Generation (RAG) is a technique for adding extra "knowledge" to systems built on LLMs, allowing them to answer questions against custom information not included in their training data. A common way to implement this is to take a question from a user, translate that into a set of search queries, run those against a search engine and then feed the results back into the LLM to generate an answer.

I built a basic version of this pattern against …

ai annotatedtalks anthropic building claude data datasette extra generativeai information knowledge llms projects promptengineering queries question questions rag retrieval retrieval augmented generation search set systems them training training data translate valtown