Great walkthrough, @BijuThottathil!
I really liked how you tied the full flow together: curated Delta table, Vector Search, MCP endpoint, and Claude Desktop via a local bridge. That end-to-end view is whatโs usually missing in most demos.
Two points that stood out to me:
1. Building the search_text column from structured attributes to create a richer embedding signal is a very practical pattern. It is often overlooked but makes a big difference for retrieval quality.
2. Using a local MCP bridge to authenticate and call the Databricks Vector Search tool cleanly separates concerns and keeps things flexible.
One question: have you tested how this behaves with incremental updates to the source Delta table? I am curious how you would approach re-embedding or managing latency as the table evolves. ๐
![Community [Industry BrickTalk #4] Transforming Commercial Real Estate Portfolio Management with AI](/t5/image/serverpage/image-id/25529iFB6AFAFAE433451D/image-size/large?v=v2&px=999)