Running open-Jev in SQL on Databricks
Summary
Run models like SemIf-OpenJev directly on governed Databricks data using serverless GPUs and managed Model Serving. Query custom endpoints from SQL or Lakeflow jobs using ai_query to return structured decisions and probability scores at scale, with an importable notebook to deploy and adapt the workflow.
Summary generated by brickster.ai. For the full article, follow the source link above.
More from Databricks Blog
From Data to Dialogue: How S&P Global Energy Made Its Structured Data Estate Conversational with Databricks Genie Agents and MCP
S&P Global Energy made its structured data estate conversational by composing Databricks Genie Agents as managed MCP servers through a FastMCP proxy for cross-domain queries. This approach enables domain experts to curate code-free semantic layers, accelerating time-to-market for conversational data products while preserving Unity Catalog governance.
Deploy and manage coding agents at scale with the Unity Gateway CLI
The new Unity Gateway CLI enables organizations to centrally deploy, configure, and govern coding agents and frontier models at scale. Developers can launch approved agents with a single command, while admins manage models, shared MCP tools, spending policies, and lakehouse trace exports from a unified interface.
How I built agent-based security reviews on Databricks
An agent-based security review layer on Databricks automates predictable evaluations while routing ambiguous or high-risk cases to human reviewers. Built using Unity Catalog, Lakeflow Jobs, Databricks Apps, and hosted foundation models, this governed architecture improves review cycle times and consistency without removing human authority.
How Concurrence governs clinical AI at a trillion-token scale with Unity Gateway
Concurrence scaled its clinical AI agent platform to an annualized 1.2 trillion tokens by consolidating its data and AI architecture on Databricks. The system pairs an immutable patient world model built on Delta tables and Lakebase with Unity Catalog and Unity Gateway to enforce compliance-gated model routing and continuous agent evaluation.
Top 5 System Table Queries for Understanding Your Databricks Costs
Five targeted system table queries deliver near-real-time visibility into your Databricks spend broken down by product, SQL warehouse, and team. Deploy them to flag cost spikes against a rolling 14-day baseline with DBSQL alerts and project 30-day expenditures in a single query using AI_FORECAST.
The Genie One MCP is now Generally Available
The Genie One MCP server is now generally available, bringing trusted insights across structured and unstructured data into any AI agent workflow. Grounded in Genie Ontology, it provides agents with governed access to unified business context across tables, documents, and tools to reduce conflicting answers and support queries, visualizations, and citations.