Create a VoyageAI inference endpoint

PUT /_inference/{task_type}/{voyageai_inference_id}

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

Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.

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/voyageai-embeddings to create an inference endpoint that performs a text_embedding task. The embeddings created by requests to this endpoint will have 512 dimensions.

Request Console 1 / 8 languages

Console Kibana Dev Tools

PUT _inference/text_embedding/openai-embeddings
{
    "service": "voyageai",
    "service_settings": {
        "model_id": "voyage-3-large",
        "dimensions": 512
    }
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.put({
  task_type: "text_embedding",
  inference_id: "openai-embeddings",
  inference_config: {
    service: "voyageai",
    service_settings: {
      model_id: "voyage-3-large",
      dimensions: 512,
    },
  },
});

Python Elasticsearch Python Client

resp = client.inference.put(
    task_type="text_embedding",
    inference_id="openai-embeddings",
    inference_config={
        "service": "voyageai",
        "service_settings": {
            "model_id": "voyage-3-large",
            "dimensions": 512
        }
    },
)

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": "voyageai",
    "service_settings": {
      "model_id": "voyage-3-large",
      "dimensions": 512
    }
  }'

Java Elasticsearch Java Client

client.inference().put(p -> p
    .inferenceId("openai-embeddings")
    .taskType(TaskType.TextEmbedding)
    .inferenceConfig(i -> i
        .service("voyageai")
        .serviceSettings(JsonData.fromJson("{\"model_id\":\"voyage-3-large\",\"dimensions\":512}"))
    )
);

C# Elasticsearch .NET Client

var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "openai-embeddings",
        TaskType = TaskType.TextEmbedding,
        InferenceConfig = new()
        {
            Service = "voyageai",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "model_id": "voyage-3-large",
              "dimensions": 512
            }
            """)
        }
    });

PHP Elasticsearch PHP Client

$resp = $client->inference()->put([
    "task_type" => "text_embedding",
    "inference_id" => "openai-embeddings",
    "body" => [
        "service" => "voyageai",
        "service_settings" => [
            "model_id" => "voyage-3-large",
            "dimensions" => 512,
        ],
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.put(
  task_type: "text_embedding",
  inference_id: "openai-embeddings",
  body: {
    "service": "voyageai",
    "service_settings": {
      "model_id": "voyage-3-large",
      "dimensions": 512
    }
  }
)

Response

No example

Run PUT _inference/rerank/voyageai-rerank to create an inference endpoint that performs a rerank task.

Request Console 1 / 2 languages

Console Kibana Dev Tools

PUT _inference/rerank/voyageai-rerank
{
    "service": "voyageai",
    "service_settings": {
        "model_id": "rerank-2"
    }
}

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/rerank/voyageai-rerank" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "voyageai",
    "service_settings": {
        "model_id": "rerank-2"
    }
}'

Response

No example

Create a VoyageAI inference endpoint

Required authorization

Path Parameters

Query Parameters

Request

Response

Required authorization

Path Parameters { task_type , voyageai_inference_id , }

Query Parameters

Request { chunking_settings , service , service_settings , task_settings , }

Response

Path Parameters

Request