Get an inference endpoint

GET /_inference/{task_type}/{inference_id}
GET /_inference/{task_type}/_all
GET /_inference/{inference_id}
GET /_inference

Auth

Path parameters

task_type enum optional

The task type of the endpoint to return

Leave it out to use /_inference.

Values: sparse_embedding text_embedding rerank completion chat_completion

inference_id string optional

The inference Id of the endpoint to return. Using _all or * will return all endpoints with the specified task_type if one is specified, or all endpoints for all task types if no task_type is specified

Leave it out to use /_inference.

Response

application/json

endpoints object[] required

View as Markdown

Examples

Request Console 1 / 8 languages

Console Kibana Dev Tools

GET _inference/sparse_embedding/my-elser-model

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.get({
  task_type: "sparse_embedding",
  inference_id: "my-elser-model",
});

Python Elasticsearch Python Client

resp = client.inference.get(
    task_type="sparse_embedding",
    inference_id="my-elser-model",
)

curl Shell

curl -X GET "$ELASTICSEARCH_URL/_inference/sparse_embedding/my-elser-model" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY"

Java Elasticsearch Java Client

client.inference().get(g -> g
    .inferenceId("my-elser-model")
    .taskType(TaskType.SparseEmbedding)
);

C# Elasticsearch .NET Client

var response = await client.Inference
    .GetAsync(d1 => d1
        .InferenceId("my-elser-model")
        .TaskType(TaskType.SparseEmbedding)
    );

PHP Elasticsearch PHP Client

$resp = $client->inference()->get([
    "task_type" => "sparse_embedding",
    "inference_id" => "my-elser-model",
]);

Ruby Elasticsearch Ruby Client

response = client.inference.get(
  task_type: "sparse_embedding",
  inference_id: "my-elser-model"
)

Response

{
  "endpoints": [
    {
      "chunking_settings": {
        "max_chunk_size": 250,
        "overlap": 100,
        "sentence_overlap": 1,
        "strategy": "sentence"
      },
      "service": "string",
      "service_settings": {},
      "task_settings": {},
      "inference_id": "string",
      "task_type": "sparse_embedding"
    }
  ]
}

Generated from the API spec