Large scale embeddings

Check your docs version

These docs are for the new Anyscale design. If you started using Anyscale before April 2024, use Version 1.0.0 of the docs. If you're transitioning to Anyscale Preview, see the guide for how to migrate.

tip

If you are looking for an endpoint for embeddings, see endpoints for the gte-large model and the bge-large-en-v1.5 model.

Large scale embedding generation is a critical step in retrieval augmented generation workflows and can help establish relationships between different text chunks.

Anyscale is piloting features for large scale embedding workloads, allowing users to scale embedding generation jobs for data up to terabyte-scale.

If you're interested in more details, fill out this form.