Skip to main content

Text embedding

Nomic Atlas natively supports the following text embeddings models:

ModelDescriptionContext LengthDimensionMTEB
nomic-embed-text-v1Nomic Embed specialized for retrieval, similarity, clustering and classification.819276862.39
nomic-embed-text-v1.5Nomic Embed with support for variable embedding size and specialized for retrieval, similarity, clustering and classification. Recommended output sizes are 768, 512, 256, 128 and 64.819276862.28

Visit the API Reference for use details.

*Model quality degrades with decreased output dimensionality. Learn more.

Embedding task types

There are four task types for Nomic Embed:

  • search_query: A query for retrieval.
  • search_document: A document for retrieval, or a query for similarity search.
  • classification: Used for classification tasks.
  • clustering: Results in very high linear separability.