The SDK default,
BAAI/bge-en-icl, is retired. Select an active embedding model with the Nebius List Models API, then override id and dimensions.Parameters
| Parameter | Type | Description | Default |
|---|---|---|---|
id | str | The model ID to use for embeddings | "BAAI/bge-en-icl" |
dimensions | int | Output dimensions requested from the selected model | 1024 |
encoding_format | Literal["float", "base64"] | Format of the embedding output | "float" |
user | Optional[str] | A unique identifier representing your end-user | None |
api_key | Optional[str] | Nebius API key | Environment variable NEBIUS_API_KEY |
organization | Optional[str] | Organization ID for API requests | None |
base_url | str | Base URL for API requests | "https://api.tokenfactory.nebius.com/v1/" |
request_params | Optional[Dict[str, Any]] | Additional parameters for embedding requests | None |
client_params | Optional[Dict[str, Any]] | Additional parameters for client initialization | None |
openai_client | Optional[OpenAIClient] | Pre-configured OpenAI client | None |
async_client | Optional[AsyncOpenAI] | Pre-configured async OpenAI client, used for async embedding calls | None |
enable_batch | bool | Enable batch processing to reduce API calls | False |
batch_size | int | Number of texts to process in each API call | 100 |