| Name | Type | Description |
|---|---|---|
model | Optional[str] | Default: NoneThe model to use for embedding. |
nvidia_api_key | Optional[str] | Default: NoneThe API key to use for connecting to the hosted NIM. |
api_key | Optional[str] | Default: None |
base_url | Optional[str] | Default: None |
trucate | Optional[Literal['NONE', 'START', 'END']] | Default: None |
dimensions | Optional[int] | Default: None |
usage_telemetry_enabled* | unknown | |
**kwargs | Any | Default: {} |
Client to NVIDIA embeddings models.
Alternative to nvidia_api_key.
The base URL of the NIM to connect to. Format for base URL is http://host:port
'NONE', 'START', 'END', truncate input text if it
exceeds the model's context length. Default is 'NONE', which raises
an error if an input is too long.
The number of dimensions for the embeddings. This parameter is not supported by all models.
Enable content-free hourly usage aggregates for NVIDIA-hosted NIMs. Enabled by default unless disabled.
Additional parameters passed to the underlying client.