Create an Azure AI studio inference endpoint

PUT /_inference/{task_type}/{azureaistudio_inference_id}

Create an inference endpoint to perform an inference task with the azureaistudio service.

Query Parameters

timeout string Duration · default: 30s: Specifies the amount of time to wait for the inference endpoint to be created.

Run PUT _inference/text_embedding/azure_ai_studio_embeddings to create an inference endpoint that performs a text_embedding task. Note that you do not specify a model here, as it is defined already in the Azure AI Studio deployment.

Request Console 1 / 8 languages

Console Kibana Dev Tools

PUT _inference/text_embedding/azure_ai_studio_embeddings
{
    "service": "azureaistudio",
    "service_settings": {
        "api_key": "Azure-AI-Studio-API-key",
        "target": "Target-Uri",
        "provider": "openai",
        "endpoint_type": "token"
    }
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.put({
  task_type: "text_embedding",
  inference_id: "azure_ai_studio_embeddings",
  inference_config: {
    service: "azureaistudio",
    service_settings: {
      api_key: "Azure-AI-Studio-API-key",
      target: "Target-Uri",
      provider: "openai",
      endpoint_type: "token",
    },
  },
});

Python Elasticsearch Python Client

resp = client.inference.put(
    task_type="text_embedding",
    inference_id="azure_ai_studio_embeddings",
    inference_config={
        "service": "azureaistudio",
        "service_settings": {
            "api_key": "Azure-AI-Studio-API-key",
            "target": "Target-Uri",
            "provider": "openai",
            "endpoint_type": "token"
        }
    },
)

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/text_embedding/azure_ai_studio_embeddings" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "azureaistudio",
    "service_settings": {
      "api_key": "Azure-AI-Studio-API-key",
      "target": "Target-Uri",
      "provider": "openai",
      "endpoint_type": "token"
    }
  }'

Java Elasticsearch Java Client

client.inference().put(p -> p
    .inferenceId("azure_ai_studio_embeddings")
    .taskType(TaskType.TextEmbedding)
    .inferenceConfig(i -> i
        .service("azureaistudio")
        .serviceSettings(JsonData.fromJson("{\"api_key\":\"Azure-AI-Studio-API-key\",\"target\":\"Target-Uri\",\"provider\":\"openai\",\"endpoint_type\":\"token\"}"))
    )
);

C# Elasticsearch .NET Client

var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "azure_ai_studio_embeddings",
        TaskType = TaskType.TextEmbedding,
        InferenceConfig = new()
        {
            Service = "azureaistudio",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "api_key": "Azure-AI-Studio-API-key",
              "target": "Target-Uri",
              "provider": "openai",
              "endpoint_type": "token"
            }
            """)
        }
    });

PHP Elasticsearch PHP Client

$resp = $client->inference()->put([
    "task_type" => "text_embedding",
    "inference_id" => "azure_ai_studio_embeddings",
    "body" => [
        "service" => "azureaistudio",
        "service_settings" => [
            "api_key" => "Azure-AI-Studio-API-key",
            "target" => "Target-Uri",
            "provider" => "openai",
            "endpoint_type" => "token",
        ],
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.put(
  task_type: "text_embedding",
  inference_id: "azure_ai_studio_embeddings",
  body: {
    "service": "azureaistudio",
    "service_settings": {
      "api_key": "Azure-AI-Studio-API-key",
      "target": "Target-Uri",
      "provider": "openai",
      "endpoint_type": "token"
    }
  }
)

Response

No example

Run PUT _inference/completion/azure_ai_studio_completion to create an inference endpoint that performs a completion task.

Request Console 1 / 2 languages

Console Kibana Dev Tools

PUT _inference/completion/azure_ai_studio_completion
{
    "service": "azureaistudio",
    "service_settings": {
        "api_key": "Azure-AI-Studio-API-key",
        "target": "Target-URI",
        "provider": "databricks",
        "endpoint_type": "realtime"
    }
}

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/completion/azure_ai_studio_completion" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "azureaistudio",
    "service_settings": {
        "api_key": "Azure-AI-Studio-API-key",
        "target": "Target-URI",
        "provider": "databricks",
        "endpoint_type": "realtime"
    }
}'

Response

No example

Create an Azure AI studio inference endpoint

Required authorization

Path Parameters

Query Parameters

Request

Response

Required authorization

Path Parameters { task_type , azureaistudio_inference_id , }

Query Parameters

Request { chunking_settings , service , service_settings , task_settings , }

Response

Path Parameters

Request