Langchain SQL Agent with local RAG

[dinonovak]

I would like to use SQL Agent to query database. But also I would like to use CromaDB to save embeddings with local knowledge of the database structure, columns content, ...
So this means thy I would like to create chain that would extend LLM with this local knowledge, and then pass this as LLM fro SQL queries.

Any ideas how to set up this architecture?

I know that rag_chain can be used to query expanded knowledge as described in: https://python.langchain.com/docs/use_cases/question_answering/
but how it can be combined with sql_agent ?