Generate embeddings from third party API in Delta Live Tables

- - Certifications
- - Learning Paths
- - Databricks Product Tours
- - Get Started Guides
- - Product Platform Updates
- - What's New in Databricks

- - Get Started Resources
- - Events
- - Support FAQs
- - Technical Blog
- - Knowledge Sharing Hub
- - Announcements
- - DatabricksTV

- - Private Groups
- - Skills@Scale

- - Databricks Community Champions
- - Khoros Community Forums Support (Not for Databricks Product Questions)
- - Databricks Community Code of Conduct

Data Engineering

Join discussions on data engineering best practices, architectures, and optimization strategies within the Databricks Community. Exchange insights and solutions with fellow data engineers.

We currently have a Delta Live Tables flow through which textual data is flowing. As a final enrichment step we would also want to generate embeddings using a third party api provider (probably Voyage.AI). They support batch embedding which would greatly help speed this up (but we would still rate limits).

Is it best-practice to include this as a UDF in the DLT flow? Or should these be generated in another step?

Thanks