AnnouncementPinecone serverless on AWS is now generally availableLearn more


Good performance text embedding model that outputs compressed vectors. Closed source model behind API.
Dimension:Size of a single vector
supported by this model.
Distance Metric:Used to measure similarity
between vectors.
cosine or dot product
Max Seq. Length:Number of tokens the model
can process at once.


Ideal for easy to use text embeddings where short queries are expected to return medium-length passages of text (1-2 paragraphs). Performance is close to full size Cohere-embed-english-v3.0 model while outputting lower-dimensional embeddings for vector storage savings.

Must add input_type=\"search_document\" to requests when embedding passages/documents, and input_type=\"search_query\" when embedding queries. See here for an example.

Using the Model


Creating Embeddings:

Learn more about Cohere-embed-english-light-v3.0