Databricks 发布教程：用 ai_query 在治理数据上运行 Jev 决策模型
Databricks 出了个可直接导入的 notebook，教你把 Jev 决策模型跑在自家 Serverless GPU 上，SQL 里调 ai_query 就能拿分类和概率分数，换上自己数据就能用。
Databricks 分享了一套可直接导入的 notebook，演示如何运行 Jev 风格的决策模型。流程是把 SemIf-OpenJev 这类开放权重模型部署到 Serverless GPU 上，配合 AI Runtime 和 Model Serving。
随后通过 ai_query 在 SQL 或 Lakeflow 作业里直接调用模型，返回结构化分类结果和概率分数。整个流程只需选模型、选 Serverless GPU、点 Run All 三步，用户可替换成自己的数据和决策标准。
Here's how to run Jev-style decision models directly on governed data with Databricks 👇
Serve open-weight models like SemIf-OpenJev on serverless GPUs with AI Runtime + Model Serving, then call them directly from SQL or Lakeflow jobs using ai_query to return structured classifications and probability scores.
↳ Pick your model ↳ Select Serverless GPU ↳ Click Run All
One importable notebook. Swap in your own data and decision criteria from there.
https://t.co/UD9DujSuFw
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Databricks, SemIf-OpenJev, ai_query, Lakeflow.
Source attribution: curated from Databricks (@databricks).
