Create an OpenAI inference endpoint

PUT /_inference/{task_type}/{openai_inference_id}

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

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/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.

Request Console 1 / 8 languages

Console Kibana Dev Tools

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

JavaScript Elasticsearch JavaScript Client

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,
    },
  },
});

Python Elasticsearch Python Client

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
        }
    },
)

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/text_embedding/openai-embeddings" \
  -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
    }
  }'

Java Elasticsearch Java Client

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}"))
    )
);

C# Elasticsearch .NET Client

var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "openai-embeddings",
        TaskType = TaskType.TextEmbedding,
        InferenceConfig = new()
        {
            Service = "openai",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "api_key": "OpenAI-API-Key",
              "model_id": "text-embedding-3-small",
              "dimensions": 128
            }
            """)
        }
    });

PHP Elasticsearch PHP Client

$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,
        ],
    ],
]);

Ruby Elasticsearch Ruby Client

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
    }
  }
)

Response

No example

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

Request Console 1 / 2 languages

Console Kibana Dev Tools

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

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/completion/openai-completion" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "openai",
    "service_settings": {
        "api_key": "OpenAI-API-Key",
        "model_id": "gpt-3.5-turbo"
    }
}'

Response

No example

Create an OpenAI inference endpoint

Required authorization

Path Parameters

Query Parameters

Request

Response

Required authorization

Path Parameters { task_type , openai_inference_id , }

Query Parameters

Request { chunking_settings , service , service_settings , task_settings , }

Response

Path Parameters

Request