Create an OpenAI inference endpoint | Elasticsearch API documentation (v8)

Create an OpenAI inference endpoint Generally available; Added in 8.12.0

PUT /_inference/{task_type}/{openai_inference_id}

Api key auth Basic auth Bearer auth

Create an inference endpoint to perform an inference task with the openai service or openai compatible APIs.

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 chat_completion, completion, or text_embedding.
openai_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 higher than 300 or lower than 20 (for sentence strategy) or 10 (for word strategy).
  
  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.
- strategy string
  
  The chunking strategy: sentence or word.
  
  Default value is sentence.
service string Required

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

Value is openai.
service_settings object Required

Settings used to install the inference model. These settings are specific to the openai service.
Hide service_settings attributes Show service_settings attributes object
- api_key string Required
  
  A valid API key of your OpenAI account. You can find your OpenAI API keys in your OpenAI account under the API keys section.
  
  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.
  
  External documentation
- dimensions number
  
  The number of dimensions the resulting output embeddings should have. It is supported only in text-embedding-3 and later models. If it is not set, the OpenAI defined default for the model is used.
- model_id string Required
  
  The name of the model to use for the inference task. Refer to the OpenAI documentation for the list of available text embedding models.
  
  External documentation
- organization_id string
  
  The unique identifier for your organization. You can find the Organization ID in your OpenAI account under Settings > Organizations.
- rate_limit object
  
  This setting helps to minimize the number of rate limit errors returned from OpenAI. The openai service sets a default number of requests allowed per minute depending on the task type. For text_embedding, it is set to 3000. For completion, it is set to 500.
  Hide rate_limit attribute Show rate_limit attribute object
  
  requests_per_minute number
  
  The number of requests allowed per minute.
- similarity string
  
  For a text_embedding task, the similarity measure. One of cosine, dot_product, l2_norm. Defaults to dot_product.
  
  Values are cosine, dot_product, or l2_norm.
- url string
  
  The URL endpoint to use for the requests. It can be changed for testing purposes.
  
  Default value is https://api.openai.com/v1/embeddings..
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
  
  Chunking configuration object
  
  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 higher than 300 or lower than 20 (for sentence strategy) or 10 (for word strategy).
  
  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.
  
  strategy string
  
  The chunking strategy: sentence or word.
  
  Default value is sentence.
- 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, chat_completion, or completion.

PUT /_inference/{task_type}/{openai_inference_id}

PUT _inference/text_embedding/openai-embeddings
{
    "service": "openai",
    "service_settings": {
        "api_key": "OpenAI-API-Key",
        "model_id": "text-embedding-3-small",
        "dimensions": 128
    }
}

resp = client.inference.put(
    task_type="text_embedding",
    inference_id="openai-embeddings",
    inference_config={
        "service": "openai",
        "service_settings": {
            "api_key": "OpenAI-API-Key",
            "model_id": "text-embedding-3-small",
            "dimensions": 128
        }
    },
)

const response = await client.inference.put({
  task_type: "text_embedding",
  inference_id: "openai-embeddings",
  inference_config: {
    service: "openai",
    service_settings: {
      api_key: "OpenAI-API-Key",
      model_id: "text-embedding-3-small",
      dimensions: 128,
    },
  },
});

response = client.inference.put(
  task_type: "text_embedding",
  inference_id: "openai-embeddings",
  body: {
    "service": "openai",
    "service_settings": {
      "api_key": "OpenAI-API-Key",
      "model_id": "text-embedding-3-small",
      "dimensions": 128
    }
  }
)

$resp = $client->inference()->put([
    "task_type" => "text_embedding",
    "inference_id" => "openai-embeddings",
    "body" => [
        "service" => "openai",
        "service_settings" => [
            "api_key" => "OpenAI-API-Key",
            "model_id" => "text-embedding-3-small",
            "dimensions" => 128,
        ],
    ],
]);

curl -X PUT -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"service":"openai","service_settings":{"api_key":"OpenAI-API-Key","model_id":"text-embedding-3-small","dimensions":128}}' "$ELASTICSEARCH_URL/_inference/text_embedding/openai-embeddings"

client.inference().put(p -> p
    .inferenceId("openai-embeddings")
    .taskType(TaskType.TextEmbedding)
    .inferenceConfig(i -> i
        .service("openai")
        .serviceSettings(JsonData.fromJson("{\"api_key\":\"OpenAI-API-Key\",\"model_id\":\"text-embedding-3-small\",\"dimensions\":128}"))
    )
);

Request examples

Run `PUT _inference/text_embedding/openai-embeddings` to create an inference endpoint that performs a `text_embedding` task. The embeddings created by requests to this endpoint will have 128 dimensions.

{
    "service": "openai",
    "service_settings": {
        "api_key": "OpenAI-API-Key",
        "model_id": "text-embedding-3-small",
        "dimensions": 128
    }
}

Run `PUT _inference/completion/openai-completion` to create an inference endpoint to perform a `completion` task type.

{
    "service": "openai",
    "service_settings": {
        "api_key": "OpenAI-API-Key",
        "model_id": "gpt-3.5-turbo"
    }
}