Update an inference endpoint

PUT /_inference/{task_type}/{inference_id}/_update
PUT /_inference/{inference_id}/_update

Modify task_settings, secrets (within service_settings), or num_allocations for an inference endpoint, depending on the specific endpoint service and task_type.

IMPORTANT: The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Azure, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face. For built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models. However, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.

Required authorization

Cluster privileges: manage_inference

Path Parameters

Query Parameters

timeout string Duration: Specifies the amount of time to wait for the inference endpoint to be updated. The default depends on the task type: 120s for completion and chat_completion, and 30s for all other task types.

Request

Response

application/json

Examples

An example body for a PUT _inference/my-inference-endpoint/_update request.

Request Console 1 / 8 languages

Console Kibana Dev Tools

PUT _inference/my-inference-endpoint/_update
{
 "service_settings": {
   "api_key": "<API_KEY>"
 },
"service": "example-service"
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.update({
  inference_id: "my-inference-endpoint",
  inference_config: {
    service_settings: {
      api_key: "<API_KEY>",
    },
    service: "example-service",
  },
});

Python Elasticsearch Python Client

resp = client.inference.update(
    inference_id="my-inference-endpoint",
    inference_config={
        "service_settings": {
            "api_key": "<API_KEY>"
        },
        "service": "example-service"
    },
)

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/my-inference-endpoint/_update" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service_settings": {
      "api_key": "\u003CAPI_KEY\u003E"
    },
    "service": "example-service"
  }'

Java Elasticsearch Java Client

client.inference().update(u -> u
    .inferenceId("my-inference-endpoint")
    .inferenceConfig(i -> i
        .service("example-service")
        .serviceSettings(JsonData.fromJson("""
{"api_key":"<API_KEY>"}
"""))
    )
);

C# Elasticsearch .NET Client

var response = await client.Inference
    .UpdateAsync(new UpdateInferenceRequest()
    {
        InferenceId = "my-inference-endpoint",
        InferenceConfig = new()
        {
            Service = "example-service",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "api_key": "\u003CAPI_KEY\u003E"
            }
            """)
        }
    });

PHP Elasticsearch PHP Client

$resp = $client->inference()->update([
    "inference_id" => "my-inference-endpoint",
    "body" => [
        "service_settings" => [
            "api_key" => "<API_KEY>",
        ],
        "service" => "example-service",
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.update(
  inference_id: "my-inference-endpoint",
  body: {
    "service_settings": {
      "api_key": "<API_KEY>"
    },
    "service": "example-service"
  }
)

Response

No example

Required authorization

Path Parameters { task_type , inference_id , }

Query Parameters

Request { chunking_settings , service , service_settings , task_settings , }

Response

Path Parameters

Request