Create an Azure OpenAI inference endpoint | Elasticsearch Serverless API documentation

Create an Azure OpenAI inference endpoint Generally available

PUT /_inference/{task_type}/{azureopenai_inference_id}

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

The list of chat completion models that you can choose from in your Azure OpenAI deployment include:

The list of embeddings models that you can choose from in your deployment can be found in the Azure models documentation.

Required authorization

Cluster privileges: manage_inference

Path parameters

task_type string

The type of the inference task that the model will perform. NOTE: The chat_completion task type only supports streaming and only through the _stream API.

Values are completion or text_embedding.
azureopenai_inference_id string Required

The unique identifier of the inference endpoint.

Query parameters

timeout string

Specifies the amount of time to wait for the inference endpoint to be created.

External documentation

application/json

Body Required

chunking_settings object

The chunking configuration object.

External documentation
Hide chunking_settings attributes Show chunking_settings attributes object
- max_chunk_size number
  
  The maximum size of a chunk in words. This value cannot be lower than 20 (for sentence strategy) or 10 (for word strategy). This value should not exceed the window size for the associated model.
  
  Default value is 250.
- overlap number
  
  The number of overlapping words for chunks. It is applicable only to a word chunking strategy. This value cannot be higher than half the max_chunk_size value.
  
  Default value is 100.
- sentence_overlap number
  
  The number of overlapping sentences for chunks. It is applicable only for a sentence chunking strategy. It can be either 1 or 0.
  
  Default value is 1.
- separator_group string
  
  Only applicable to the recursive strategy and required when using it.
  
  Sets a predefined list of separators in the saved chunking settings based on the selected text type. Values can be markdown or plaintext.
  
  Using this parameter is an alternative to manually specifying a custom separators list.
- separators array[string]
  
  Only applicable to the recursive strategy and required when using it.
  
  A list of strings used as possible split points when chunking text.
  
  Each string can be a plain string or a regular expression (regex) pattern. The system tries each separator in order to split the text, starting from the first item in the list.
  
  After splitting, it attempts to recombine smaller pieces into larger chunks that stay within the max_chunk_size limit, to reduce the total number of chunks generated.
- strategy string
  The chunking strategy: sentence, word, none or recursive.
  
  If strategy is set to recursive, you must also specify:
  
  max_chunk_size
  
  either separators orseparator_group
  
  Learn more about different chunking strategies in the linked documentation.
  Default value is sentence.
  
  External documentation
service string Required

The type of service supported for the specified task type. In this case, azureopenai.

Value is azureopenai.
service_settings object Required

Settings used to install the inference model. These settings are specific to the azureopenai service.
Hide service_settings attributes Show service_settings attributes object
- api_key string
  
  A valid API key for your Azure OpenAI account. You must specify either api_key or entra_id. If you do not provide either or you provide both, you will receive an error when you try to create your model.
  
  IMPORTANT: You need to provide the API key only once, during the inference model creation. The get inference endpoint API does not retrieve your API key. After creating the inference model, you cannot change the associated API key. If you want to use a different API key, delete the inference model and recreate it with the same name and the updated API key.
  
  External documentation
- api_version string Required
  
  The Azure API version ID to use. It is recommended to use the latest supported non-preview version.
- deployment_id string Required
  
  The deployment name of your deployed models. Your Azure OpenAI deployments can be found though the Azure OpenAI Studio portal that is linked to your subscription.
  
  External documentation
- entra_id string
  
  A valid Microsoft Entra token. You must specify either api_key or entra_id. If you do not provide either or you provide both, you will receive an error when you try to create your model.
  
  External documentation
- rate_limit object
  
  This setting helps to minimize the number of rate limit errors returned from Azure. The azureopenai service sets a default number of requests allowed per minute depending on the task type. For text_embedding, it is set to 1440. For completion, it is set to 120.
  
  External documentation
  Hide rate_limit attribute Show rate_limit attribute object
  
  requests_per_minute number
  
  The number of requests allowed per minute. By default, the number of requests allowed per minute is set by each service as follows:
  
  alibabacloud-ai-search service: 1000
  
  anthropic service: 50
  
  azureaistudio service: 240
  
  azureopenai service and task type text_embedding: 1440
  
  azureopenai service and task type completion: 120
  
  cohere service: 10000
  
  contextualai service: 1000
  
  elastic service and task type chat_completion: 240
  
  googleaistudio service: 360
  
  googlevertexai service: 30000
  
  hugging_face service: 3000
  
  jinaai service: 2000
  
  llama service: 3000
  
  mistral service: 240
  
  openai service and task type text_embedding: 3000
  
  openai service and task type completion: 500
  
  voyageai service: 2000
  
  watsonxai service: 120
- resource_name string Required
  
  The name of your Azure OpenAI resource. You can find this from the list of resources in the Azure Portal for your subscription.
  
  External documentation
task_settings object

Settings to configure the inference task. These settings are specific to the task type you specified.
Hide task_settings attribute Show task_settings attribute object
- user string
  
  For a completion or text_embedding task, specify the user issuing the request. This information can be used for abuse detection.

Responses

200 application/json
Hide response attributes Show response attributes object
- chunking_settings object
  
  The chunking configuration object. Applies only to the sparse_embedding and text_embedding task types. Not applicable to the rerank, completion, or chat_completion task types.
  
  Hide chunking_settings attributes Show chunking_settings attributes object
  
  max_chunk_size number
  
  The maximum size of a chunk in words. This value cannot be lower than 20 (for sentence strategy) or 10 (for word strategy). This value should not exceed the window size for the associated model.
  
  Default value is 250.
  
  overlap number
  
  The number of overlapping words for chunks. It is applicable only to a word chunking strategy. This value cannot be higher than half the max_chunk_size value.
  
  Default value is 100.
  
  sentence_overlap number
  
  The number of overlapping sentences for chunks. It is applicable only for a sentence chunking strategy. It can be either 1 or 0.
  
  Default value is 1.
  
  separator_group string
  
  Only applicable to the recursive strategy and required when using it.
  
  Sets a predefined list of separators in the saved chunking settings based on the selected text type. Values can be markdown or plaintext.
  
  Using this parameter is an alternative to manually specifying a custom separators list.
  
  separators array[string]
  
  Only applicable to the recursive strategy and required when using it.
  
  A list of strings used as possible split points when chunking text.
  
  Each string can be a plain string or a regular expression (regex) pattern. The system tries each separator in order to split the text, starting from the first item in the list.
  
  After splitting, it attempts to recombine smaller pieces into larger chunks that stay within the max_chunk_size limit, to reduce the total number of chunks generated.
  
  strategy string
  
  The chunking strategy: sentence, word, none or recursive.
  
  If strategy is set to recursive, you must also specify:
  
  max_chunk_size
  
  either separators orseparator_group
  
  Learn more about different chunking strategies in the linked documentation.
  
  Default value is sentence.
  
  External documentation
- service string Required
  
  The service type
- service_settings object Required
  
  Settings specific to the service
- task_settings object
  
  Task settings specific to the service and task type
- inference_id string Required
  
  The inference Id
- task_type string Required
  
  The task type
  
  Values are text_embedding or completion.

PUT /_inference/{task_type}/{azureopenai_inference_id}

PUT _inference/text_embedding/azure_openai_embeddings
{
    "service": "azureopenai",
    "service_settings": {
        "api_key": "Api-Key",
        "resource_name": "Resource-name",
        "deployment_id": "Deployment-id",
        "api_version": "2024-02-01"
    }
}

resp = client.inference.put(
    task_type="text_embedding",
    inference_id="azure_openai_embeddings",
    inference_config={
        "service": "azureopenai",
        "service_settings": {
            "api_key": "Api-Key",
            "resource_name": "Resource-name",
            "deployment_id": "Deployment-id",
            "api_version": "2024-02-01"
        }
    },
)

const response = await client.inference.put({
  task_type: "text_embedding",
  inference_id: "azure_openai_embeddings",
  inference_config: {
    service: "azureopenai",
    service_settings: {
      api_key: "Api-Key",
      resource_name: "Resource-name",
      deployment_id: "Deployment-id",
      api_version: "2024-02-01",
    },
  },
});

response = client.inference.put(
  task_type: "text_embedding",
  inference_id: "azure_openai_embeddings",
  body: {
    "service": "azureopenai",
    "service_settings": {
      "api_key": "Api-Key",
      "resource_name": "Resource-name",
      "deployment_id": "Deployment-id",
      "api_version": "2024-02-01"
    }
  }
)

$resp = $client->inference()->put([
    "task_type" => "text_embedding",
    "inference_id" => "azure_openai_embeddings",
    "body" => [
        "service" => "azureopenai",
        "service_settings" => [
            "api_key" => "Api-Key",
            "resource_name" => "Resource-name",
            "deployment_id" => "Deployment-id",
            "api_version" => "2024-02-01",
        ],
    ],
]);

curl -X PUT -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"service":"azureopenai","service_settings":{"api_key":"Api-Key","resource_name":"Resource-name","deployment_id":"Deployment-id","api_version":"2024-02-01"}}' "$ELASTICSEARCH_URL/_inference/text_embedding/azure_openai_embeddings"

client.inference().put(p -> p
    .inferenceId("azure_openai_embeddings")
    .taskType(TaskType.TextEmbedding)
    .inferenceConfig(i -> i
        .service("azureopenai")
        .serviceSettings(JsonData.fromJson("{\"api_key\":\"Api-Key\",\"resource_name\":\"Resource-name\",\"deployment_id\":\"Deployment-id\",\"api_version\":\"2024-02-01\"}"))
    )
);

Request examples

Run `PUT _inference/text_embedding/azure_openai_embeddings` to create an inference endpoint that performs a `text_embedding` task. You do not specify a model, as it is defined already in the Azure OpenAI deployment.

{
    "service": "azureopenai",
    "service_settings": {
        "api_key": "Api-Key",
        "resource_name": "Resource-name",
        "deployment_id": "Deployment-id",
        "api_version": "2024-02-01"
    }
}

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

{
    "service": "azureopenai",
    "service_settings": {
        "api_key": "Api-Key",
        "resource_name": "Resource-name",
        "deployment_id": "Deployment-id",
        "api_version": "2024-02-01"
    }
}