This is the second part of a series of blog find out on using a local RAG (Retrieval Augmented Generation) system for your team’s codebase without leaking any code or data to third parties.

In this part, we find out how the LLM (Large Language Model) can read and understand Elixir code and start a conversation about the codebase with the LLM 🤖.

https://bitcrowd.dev/a-rag-for-elixir