Perform completion inference on the service

POST /_inference/completion/{inference_id}

Get responses for completion tasks. This API works only with the completion 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.

This API requires the monitor_inference cluster privilege (the built-in inference_admin and inference_user roles grant this privilege).

Path Parameters

inference_id string Id required: The inference Id

Query Parameters

timeout string Duration · default: 120s: Specifies the amount of time to wait for the inference request to complete.

Request

Response

application/json

Examples

Run POST _inference/completion/openai_completions to perform a completion on the example question.

Request Console 1 / 8 languages

Console Kibana Dev Tools

POST _inference/completion/openai_completions
{
  "input": "What is Elastic?"
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.completion({
  inference_id: "openai_completions",
  input: "What is Elastic?",
});

Python Elasticsearch Python Client

resp = client.inference.completion(
    inference_id="openai_completions",
    input="What is Elastic?",
)

curl Shell

curl -X POST "$ELASTICSEARCH_URL/_inference/completion/openai_completions" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "What is Elastic?"
  }'

Java Elasticsearch Java Client

client.inference().completion(c -> c
    .inferenceId("openai_completions")
    .input("What is Elastic?")
);

C# Elasticsearch .NET Client

var response = await client.Inference
    .CompletionAsync(inferenceId: "openai_completions", d1 => d1
        .Input("What is Elastic?")
    );

PHP Elasticsearch PHP Client

$resp = $client->inference()->completion([
    "inference_id" => "openai_completions",
    "body" => [
        "input" => "What is Elastic?",
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.completion(
  inference_id: "openai_completions",
  body: {
    "input": "What is Elastic?"
  }
)

Response

{
  "completion": [
    {
      "result": "Elastic is a company that provides a range of software solutions for search, logging, security, and analytics. Their flagship product is Elasticsearch, an open-source, distributed search engine that allows users to search, analyze, and visualize large volumes of data in real-time. Elastic also offers products such as Kibana, a data visualization tool, and Logstash, a log management and pipeline tool, as well as various other tools and solutions for data analysis and management."
    }
  ]
}

Path Parameters

Query Parameters

Request { input , task_settings , }

Response

Request