Running open-Jev in SQL on Databricks

Summary

System One decision models such as Jev produce well-calibrated decisions from discrete options and are fast and cheap for large-scale applications, with potential use cases ranging from analyzing customer support transcripts to applying complex decisions at scale. Open-weight versions like SemIf-OpenJev are available, and Databricks enables serving them on governed data using serverless GPUs via AI Runtime, which provides on-demand GPU compute without managing infrastructure. The workflow is packaged in an importable notebook that downloads the model files, logs and registers the model using Express Deployments, and creates a GPU Model Serving endpoint automatically. The endpoint can be called from SQL via ai_query, which supports arbitrary custom model APIs, allowing structured request formats directly from SQL to return selected classifications and option probabilities as structured columns. The example classifies hotel reviews as good or bad, and users can import the notebook, select Serverless GPU, and run all to get started.

Takeaways

1. 1

   “System One” decision models like Jev are fast, cheap, and produce well-calibrated decisions from discrete options, suitable for large-scale data applications.

2. 2

   Databricks AI Runtime provides serverless, on-demand GPU compute without requiring users to manage GPU infrastructure.

3. 3

   The ai_query function in Databricks supports arbitrary custom model APIs, allowing structured request formats directly from SQL to return classifications and probabilities as structured columns.

FAQ