[ML] no error when updating num_threads in inference endpoint #137129
Description
Version:
9.2.0
Step to reproduce:
Right now, it is not allowed to update num_threads in inference API. ( code reference). However, the update request still returns a successful 200 response, we should throw an error instead.
Requests:
PUT _inference/rerank/mytest
{
"service": "elasticsearch",
"service_settings": {
"num_threads": 1,
"model_id": ".rerank-v1",
"adaptive_allocations": {
"enabled": true,
"min_number_of_allocations": 0,
"max_number_of_allocations": 32
}
},
"task_settings": {
"return_documents": true
}
}
PUT _inference/mytest/_update
{
"task_type": "rerank",
"service_settings": {
"num_threads": 4,
"model_id": ".rerank-v1",
"adaptive_allocations": {
"enabled": true,
"min_number_of_allocations": 0,
"max_number_of_allocations": 32
}
}
}
It returns:
{
"inference_id": "mytesta",
"task_type": "rerank",
"service": "elasticsearch",
"service_settings": {
"num_threads": 1,
"model_id": ".rerank-v1",
"adaptive_allocations": {
"enabled": true,
"min_number_of_allocations": 0,
"max_number_of_allocations": 32
}
},
"task_settings": {
"return_documents": true
}
}
you can see it still has "num_threads": 1,. it should throw an error instead.