This page shows you how to create a serverless index. For guidance on pod-based indexes, see Using pods.

You can create an index using the Pinecone console.

Vector embedding

You can create a serverless index designed for integrated or standalone embedding:

  • Integrated embedding: In this case, you upsert and search with your source text, and Pinecone uses a hosted embedding model to convert the text to vectors automatically.

  • Standalone embedding: In this case, you use a standalone embedding model to convert your data to vectors, and then you upsert and search with those vectors directly. The standalone embedding model can be hosted on Pinecone or external.

Create a serverless index

This feature is in public preview.

To create a serverless index with integrated embedding, use the create_for_model operation as follows:

  • Provide a name for the index.
  • Set embed.model to one of Pinecone’s hosted embedding models.
  • Set spec.cloud and spec.region to the cloud and region where the index should be deployed.
  • Set embed.field_map to the name of the field in your source document that contains the data for embedding.

Other parameters are optional. See the API reference for details.

The response will look like this:

Create a serverless index from a backup

You can create a serverless index from a backup. For more details, see Restore an index.

Migrate a pod-based index to serverless

You can migrate a pod-based index to serverless by creating a new serverless index from a collection. For more information, see Migrate a pod-based index to serverless.