Create a DeepSeek inference endpoint Generally available; Added in 8.19.0
Path parameters
-
The type of the inference task that the model will perform.
Values are
completion
orchat_completion
. -
The unique identifier of the inference endpoint.
Query parameters
-
Specifies the amount of time to wait for the inference endpoint to be created.
External documentation
PUT /_inference/{task_type}/{deepseek_inference_id}
curl \ --request PUT 'http://api.example.com/_inference/{task_type}/{deepseek_inference_id}' \ --header "Authorization: $API_KEY" \ --header "Content-Type: application/json" \ --data '{"chunking_settings":{"max_chunk_size":250,"overlap":100,"sentence_overlap":1,"strategy":"sentence"},"service":"deepseek","service_settings":{"api_key":"string","model_id":"string","url":"string"}}'