Databricks Community

Hey @Iris12 ,Not sure if this will fix your issue, but I’ve seen similar errors caused by permission mismatches.Make sure that the user or service principal you’re using has the correct permissions both in the Models and Serving tab.Also, double-chec...

Hi all,I just came across this thread and wanted to jump in — I’m currently working on implementing a Genie Space that will be used by external customers, and we’re also looking into whether it can be accessed via API or embedded into a custom fronte...

Have you tried looking at lineage through the system tables: "system.access.table_lineage" and "system.access.column_lineage".  You would need to have entitlements on these objects but you should be able to reference them in Genie.  Give it a try and...

Hi @SandipCoder, About point 2, is it working intermittently or failing all the time?

Had the same question when I was trying to deploy my custom llm. How we did it was wrapping it inside a custom mlflow model and registering it.

very cool

Hi @Krthk, Thanks for your question. Have you thought about using Model serving endpoint for your use-case: https://docs.databricks.com/aws/en/machine-learning/model-serving/ Launching a Databricks job via the REST API and dbutils is a different para...

Hi SaiVihAIIn my opinion, Databricks utilizes Mosaic Vector Search, which is largely aided by the Hierarchial Navigable Small World (HNSW) algorithm for neighbor search and hybrid keyword similarity search.Ref   Mosaic AI Vector Search | Databricks D...

I think Teams/Slack channel as a chat bot will be more exciting use case. When we demoed the Genie to our executives we are in Retail Industry Client and we have lots of stores one of the thing they said is this would be awesome if this can be in Tea...

Hello @SaiVihAI, Yes, It uses in-query filtering. The algorithm takes a series of iterative steps to determine if the filtered set is small enough to execute brute-force search or if it proceeds with AN

Serving endpoints with external models will require creating Network Connectivity Configuration objects at the account level to connect to the Azure OpenAI resource. The feature is currently in private preview, please reach out to your Databricks acc...

Direct cloning of a vector index table may not be possible. However, if Databricks generates the embeddings, you can enable "Sync computed embeddings" to save them to a Unity Catalog table. Alternatively, you can set the parameter sync_computed_embed...

Hi MariuszK,I can confirm that the RAG architecture on Databricks works very well—we’ve taken it to production and are very satisfied with the results. As a first step, I'll try creating a Genie Room on the system table to see if it can help retrieve...