DOC: advanced RAG Retrieval (Reranking, Hierarchical, etc) in Databricks

[Kushagra0409]

URL

No response

Checklist

• I added a very descriptive title to this issue.
• I included a link to the documentation page I am referring to (if applicable).

Issue with current documentation:

I wish to perform advanced RAG using langchain, in Databricks. In the documentation, they tell how to use the vector endpoint url, and index stored in catalogs. But I could not find any advanced RAG algos that are easily implemented in Databricks. Can you please advise me on a step-wise documentation on how I can proceed with this task?

I would appreciate if we can implement advanced RAG with minimum reliance on catalogs and endpoints, but rather langchain-exclusive tools that make stuff easier to do

Idea or request for content:

Seperate sections- each with a advanced rag technique, and how to use that in Databricks with minimum reliance on catalogs and endpoints, but rather langchain-exclusive tools that make stuff easier to do.