Databricks Community

dkushari

Unified governance and interoperability for unstructured data Summary Access unstructured data in Unity Catalog Volumes from any external tool or application using a new credential vending API that issues temporary, scoped credentials for volumes bas...

dkushari

Summary External engines — Apache Spark™ (batch and Structured Streaming), DuckDB, Apache Flink, Starburst, and StreamNative Kafka Service — can now create, read, and write Unity Catalog-managed Delta tables from outside Databricks, with every commit...

dkushari · 02-10-2025

Databricks Unity Catalog (UC) is the industry’s only unified and open governance solution for data and AI, built into the Databricks Data Intelligence Platform. Unity Catalog provides a single source of truth for your organization’s data and AI asset...

dkushari · 11-04-2024

Databricks Unity Catalog (UC) is the industry’s only unified and open governance solution for data and AI, built into the Databricks Data Intelligence Platform. Unity Catalog provides a single source of truth for your organization’s data and AI asset...

dkushari · 05-16-2024

Keeping your Databricks Direct Vector Access Index fresh in near real time Databricks Vector Search is a vector database that is built into the Databricks Data Intelligence Platform and integrated with its governance and productivity tools. A vector ...

dkushari · 10-28-2025

Hi @Mahsa, can you use the local disk as a cache instead of a volume? It should work. Please see below %pip install -U "transformers==4.44.2" "huggingface_hub>=0.20.0" accelerate datasets evaluate torch safetensors dbutils.library.restartPython() f...

dkushari · 10-25-2025

Hi @Tito, you can use the standard cluster (formerly known as the shared cluster) from VSCode using DBConnect. Here is an example, from databricks.connect import DatabricksSession # Option 1: Use cluster_id from .databrickscfg automatically # Since ...

dkushari · 10-25-2025

Hi @hammad, you can use AgentBricks - Multi Agent Supervisor to achieve the same result. You also use Genie as a Databricks-managed MCP tool. Depending on your situation, you can choose the option that suits you best.

dkushari · 10-25-2025

Hi @wind2025, since you posted this question, progress has been made quite a bit. You can now use Agent Bricks to construct a multi-agent supervisor tailored to your specific use case. Take a look at this. If you prefer to use code, consider this exa...

dkushari · 10-25-2025

Hi @xiinex - You are right. This demo is now deprecated. Please use the ai-agent demo.

Databricks Community

User Stats

User Activity

Processing Unstructured Data in Volumes with Unity Catalog Open APIs

Performing DML Operations on Unity Catalog Managed Tables from External Engines

How to Read Unity Catalog Tables from Trino via Open APIs

Integrating Apache Spark™ with Databricks Unity Catalog Assets via Open APIs

Keeping Your Databricks Direct Vector Access Index Fresh in Near Real Time

Re: Load the HF pipeline in databricks

Re: VS Code Databricks Connect Cluster Configuration

Re: How can we serve Genie as an endpoint model like RAG?

Re: I am struggling on complicated RAG code for Mosaic evaluation deployment

Re: Exception: The demo llm-rag-chatbot doesn't exist.