resp = client.inference.put(
task_type="text_embedding",
inference_id="my-e5-model",
inference_config={
"service": "elasticsearch",
"service_settings": {
"adaptive_allocations": {
"enabled": True,
"min_number_of_allocations": 3,
"max_number_of_allocations": 10
},
"num_threads": 1,
"model_id": ".multilingual-e5-small"
}
},
)
print(resp)