jk-shah opened a new issue, #41308: URL: https://github.com/apache/beam/issues/41308
### What would you like to happen? Expose Beam existing `RunInference` model handlers and `Enrichment` / RAG vector search integrations directly in Beam SQL (`SqlTransform`) via standard Table-Valued Functions `ML_PREDICT(...)` and `VECTOR_SEARCH(...)` (and corresponding `VectorSearch` YAML transform). ### Motivation Beam already provides `RunInference`, `apache_beam.ml.rag`, and `Enrichment`, whereas Flink 2.1/2.2 (`ML_PREDICT`, `VECTOR_SEARCH`) and Databricks (`ai_query()`) let users invoke real-time AI inference and vector similarity lookups inline inside SQL queries. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
