In this episode, Ankur and David discuss how RAG (retrieval augmented generation) technology works and why it matters. They build up a testbed example dataset and environment where they show code for how RAG works under the hood, how to evaluate the quality of results, why this technique matters, and where it can be applied.

You can browse a public version of the BrainTrust eval on the Coda help center content here: https://www.braintrustdata.com/app/braintrustdata.com/p/coda-help-desk

Here is the Open Source repository for the evaluation code and simple Next.js playground: https://github.com/braintrustdata/braintrust-examples/tree/main/help-docs/js

Check out more about the show at www.bitsandbots.ai