model-serving

Deploy MLflow models to Databricks Model Serving by logging the model with MLflow autolog or pyfunc, then using the Databricks API or UI to create scalable endpoints for querying predictions.

Yes, you can deploy GenAI agents to Databricks endpoints. The skill supports deploying ResponsesAgent and LangGraph-based agents with tool-calling capabilities to scalable serving endpoints.

Databricks Model Serving supports Unity Catalog integration, allowing you to manage permissions and govern access to deployed ML models and GenAI agents through Unity Catalog.

Check Databricks model serving endpoint status using the built-in query and monitoring functions to verify deployment progress across development, staging, and production environments.

Yes, creating and querying Databricks serving endpoints requires explicit permissions. You need authorization to create endpoints and send requests to retrieve predictions from deployed MLflow models and agents.

Required packages include mlflow, databricks-langchain, langgraph, databricks-agents, and pydantic, along with Databricks authentication setup to deploy and query serving endpoints.