You're looking at a specific version of this model. Jump to the model overview.
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 |
|---|---|---|---|
| texts |
array
|
Array of texts to embed. Returned vectors follow the input order.
|
|
| instruction |
string
|
|
None
|
| embedding_dim |
None
|
896
|
Output embedding dimension supported by Matryoshka representation learning.
|
| batch_size |
integer
|
32
Min: 1 |
Number of texts processed together in each inference batch.
|
| max_length |
integer
|
512
Min: 1 Max: 32768 |
Maximum number of tokens per formatted text, including the optional instruction. Longer inputs are truncated.
|
| normalize |
boolean
|
True
|
Whether to L2-normalize each embedding to unit length.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'items': {'properties': {'embedding': {'items': {'type': 'number'},
'title': 'Embedding',
'type': 'array'},
'index': {'title': 'Index', 'type': 'integer'}},
'required': ['index', 'embedding'],
'type': 'object'},
'title': 'Output',
'type': 'array'}