Databricks is a platform that lets you build, deploy, and manage AI and machine learning applications. When you integrate Databricks, you integrate the metadata of your ML models, AI agents, and Genie spaces from Databricks AI to Collibra Platform. The resulting assets represent your Databricks AI models, AI agents, and the data they use. You can integrate Databricks AI only via Edge.
Ingested Databricks AI agents include Knowledge Assistants, Supervisor Agents, Genie Agents, and Agent Bricks tiles such as Information Extraction and Text Classification. For AI agents in Databricks, the Databricks AI integration also collects operational trust metrics from agent interaction data.
For information about Databricks AI, go to the Databricks AI documentation.
You can configure Edge connections and capabilities without an active AI Governance license. However, AI Governance must be enabled to harvest AI model and agent metadata, ingest corresponding AI assets in Data Catalog, and access the dashboards and features necessary to visualize and govern your AI landscape.
- Tip
-
- If you're looking for information on how to create technical lineage for Databricks Unity Catalog via Edge, go to the technical lineage for Databricks Unity Catalog documentation.