1.6 KiB
1.6 KiB
InferencePutGooglevertexaiRequest [interface-InferencePutGooglevertexaiRequest]
| Name | Type | Description |
|---|---|---|
body |
string | ({ [key: string]: any; } & { task_type?: never; googlevertexai_inference_id?: never; chunking_settings?: never; service?: never; service_settings?: never; task_settings?: never; }) |
chunking_settings |
InferenceInferenceChunkingSettings | The chunking configuration object. |
googlevertexai_inference_id |
Id | The unique identifier of the inference endpoint. |
querystring |
{ [key: string]: any; } & { task_type?: never; googlevertexai_inference_id?: never; chunking_settings?: never; service?: never; service_settings?: never; task_settings?: never; } | All values in querystring will be added to the request querystring. |
service_settings |
InferenceGoogleVertexAIServiceSettings | Settings used to install the inference model. These settings are specific to the googlevertexai service. |
service |
InferenceGoogleVertexAIServiceType | The type of service supported for the specified task type. In this case, googlevertexai. |
task_settings |
InferenceGoogleVertexAITaskSettings | Settings to configure the inference task. These settings are specific to the task type you specified. |
task_type |
InferenceGoogleVertexAITaskType | The type of the inference task that the model will perform. |