Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
id | str | "meta-llama/llama-3-1-70b-instruct" | The id of the IBM WatsonX model to use |
name | str | "IBMWatsonx" | The name of the model |
provider | str | "IBM" | The provider of the model |
api_key | Optional[str] | None | The API key for IBM WatsonX (defaults to WATSONX_API_KEY env var) |
base_url | str | "https://us-south.ml.cloud.ibm.com/ml/v1/text/chat" | The base URL for the IBM WatsonX API |
project_id | Optional[str] | None | The project ID for IBM WatsonX (defaults to WATSONX_PROJECT_ID env var) |
retries | int | 0 | Number of retries to attempt before raising a ModelProviderError |
| delay_between_retries | int | 1 | Delay between retries, in seconds |
| exponential_backoff | bool | False | If True, the delay between retries is doubled each time |
IBM WatsonX extends the OpenAI-compatible interface and supports most parameters from OpenAI.