Create a Google Vertex AI inference endpoint

PUT /_inference/{task_type}/{googlevertexai_inference_id}

Auth

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

Required privileges

Cluster privileges manage_inference

Path parameters

task_type enum required: The type of the inference task that the model will perform.; Values: rerank text_embedding completion chat_completion
googlevertexai_inference_id string required: The unique identifier of the inference endpoint.

Query parameters

timeout union oneOf · default: 30s: Specifies the amount of time to wait for the inference endpoint to be created.; Values: -1 0

Request body

chunking_settings object: The chunking configuration object.; Reference
service enum required: The type of service supported for the specified task type. In this case, googlevertexai.; Values: googlevertexai
service_settings object required: Settings used to install the inference model. These settings are specific to the googlevertexai service.
task_settings object: Settings to configure the inference task. These settings are specific to the task type you specified.

Response

application/json

chunking_settings object: Chunking configuration object
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 enum required: The task type; Values: text_embedding rerank

Examples

Request Console 1 / 8 languages

Run PUT _inference/text_embedding/google_vertex_ai_embeddings to create an inference endpoint to perform a text_embedding task type.

Console Kibana Dev Tools

PUT _inference/text_embedding/google_vertex_ai_embeddingss
{
    "service": "googlevertexai",
    "service_settings": {
        "service_account_json": "service-account-json",
        "model_id": "model-id",
        "location": "location",
        "project_id": "project-id"
    }
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.put({
  task_type: "text_embedding",
  inference_id: "google_vertex_ai_embeddingss",
  inference_config: {
    service: "googlevertexai",
    service_settings: {
      service_account_json: "service-account-json",
      model_id: "model-id",
      location: "location",
      project_id: "project-id",
    },
  },
});

Python Elasticsearch Python Client

resp = client.inference.put(
    task_type="text_embedding",
    inference_id="google_vertex_ai_embeddingss",
    inference_config={
        "service": "googlevertexai",
        "service_settings": {
            "service_account_json": "service-account-json",
            "model_id": "model-id",
            "location": "location",
            "project_id": "project-id"
        }
    },
)

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/text_embedding/google_vertex_ai_embeddingss" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "googlevertexai",
    "service_settings": {
      "service_account_json": "service-account-json",
      "model_id": "model-id",
      "location": "location",
      "project_id": "project-id"
    }
  }'

Java Elasticsearch Java Client

client.inference().put(p -> p
    .inferenceId("google_vertex_ai_embeddingss")
    .taskType(TaskType.TextEmbedding)
    .inferenceConfig(i -> i
        .service("googlevertexai")
        .serviceSettings(JsonData.fromJson("{\"service_account_json\":\"service-account-json\",\"model_id\":\"model-id\",\"location\":\"location\",\"project_id\":\"project-id\"}"))
    )
);

C# Elasticsearch .NET Client

var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "google_vertex_ai_embeddingss",
        TaskType = TaskType.TextEmbedding,
        InferenceConfig = new()
        {
            Service = "googlevertexai",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "service_account_json": "service-account-json",
              "model_id": "model-id",
              "location": "location",
              "project_id": "project-id"
            }
            """)
        }
    });

PHP Elasticsearch PHP Client

$resp = $client->inference()->put([
    "task_type" => "text_embedding",
    "inference_id" => "google_vertex_ai_embeddingss",
    "body" => [
        "service" => "googlevertexai",
        "service_settings" => [
            "service_account_json" => "service-account-json",
            "model_id" => "model-id",
            "location" => "location",
            "project_id" => "project-id",
        ],
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.put(
  task_type: "text_embedding",
  inference_id: "google_vertex_ai_embeddingss",
  body: {
    "service": "googlevertexai",
    "service_settings": {
      "service_account_json": "service-account-json",
      "model_id": "model-id",
      "location": "location",
      "project_id": "project-id"
    }
  }
)

Response

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

Generated from the API spec

Request Console 1 / 8 languages

Run PUT _inference/rerank/google_vertex_ai_rerank to create an inference endpoint to perform a rerank task type.

Console Kibana Dev Tools

PUT _inference/rerank/google_vertex_ai_rerank
{
    "service": "googlevertexai",
    "service_settings": {
        "service_account_json": "service-account-json",
        "project_id": "project-id"
    }
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.put({
  task_type: "rerank",
  inference_id: "google_vertex_ai_rerank",
  inference_config: {
    service: "googlevertexai",
    service_settings: {
      service_account_json: "service-account-json",
      project_id: "project-id",
    },
  },
});

Python Elasticsearch Python Client

resp = client.inference.put(
    task_type="rerank",
    inference_id="google_vertex_ai_rerank",
    inference_config={
        "service": "googlevertexai",
        "service_settings": {
            "service_account_json": "service-account-json",
            "project_id": "project-id"
        }
    },
)

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/rerank/google_vertex_ai_rerank" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "googlevertexai",
    "service_settings": {
      "service_account_json": "service-account-json",
      "project_id": "project-id"
    }
  }'

Java Elasticsearch Java Client

client.inference().put(p -> p
    .inferenceId("google_vertex_ai_rerank")
    .taskType(TaskType.Rerank)
    .inferenceConfig(i -> i
        .service("googlevertexai")
        .serviceSettings(JsonData.fromJson("{\"service_account_json\":\"service-account-json\",\"project_id\":\"project-id\"}"))
    )
);

C# Elasticsearch .NET Client

var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "google_vertex_ai_rerank",
        TaskType = TaskType.Rerank,
        InferenceConfig = new()
        {
            Service = "googlevertexai",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "service_account_json": "service-account-json",
              "project_id": "project-id"
            }
            """)
        }
    });

PHP Elasticsearch PHP Client

$resp = $client->inference()->put([
    "task_type" => "rerank",
    "inference_id" => "google_vertex_ai_rerank",
    "body" => [
        "service" => "googlevertexai",
        "service_settings" => [
            "service_account_json" => "service-account-json",
            "project_id" => "project-id",
        ],
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.put(
  task_type: "rerank",
  inference_id: "google_vertex_ai_rerank",
  body: {
    "service": "googlevertexai",
    "service_settings": {
      "service_account_json": "service-account-json",
      "project_id": "project-id"
    }
  }
)

Response

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

Generated from the API spec