You're looking at a specific version of this model. Jump to the model overview.

zsxkib /embedding-gemma-300m:d753bd5a

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
text
string
Text to embed. Automatically truncated to 2048 tokens if longer.
task
None
retrieval_document
Task type - affects the internal prompt used for embedding
embedding_dim
None
768
Output embedding dimensions using Matryoshka truncation
output_format
None
base64
Output format: base64 (efficient) or array (list of floats)
normalize
boolean
True
Whether to L2-normalize the embedding to unit length

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'anyOf': [{'type': 'string'}, {'items': {'type': 'number'}, 'type': 'array'}],
 'title': 'Output'}