Create a Mistral inference endpoint

PUT /_inference/{task_type}/{mistral_inference_id}

Auth

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

Required authorization

Cluster privileges manage_inference

Path parameters

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

Query parameters

timeout string · default: 30s: Specifies the amount of time to wait for the inference endpoint to be created.

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, mistral.; Values: mistral
service_settings object required: Settings used to install the inference model. These settings are specific to the mistral service.

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

Examples

Request Console 1 / 8 languages

Run PUT _inference/text_embedding/mistral-embeddings-test to create a Mistral inference endpoint that performs a text embedding task.

Console Kibana Dev Tools

PUT _inference/text_embedding/mistral-embeddings-test
{
  "service": "mistral",
  "service_settings": {
    "api_key": "Mistral-API-Key",
    "model": "mistral-embed" 
  }
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.put({
  task_type: "text_embedding",
  inference_id: "mistral-embeddings-test",
  inference_config: {
    service: "mistral",
    service_settings: {
      api_key: "Mistral-API-Key",
      model: "mistral-embed",
    },
  },
});

Python Elasticsearch Python Client

resp = client.inference.put(
    task_type="text_embedding",
    inference_id="mistral-embeddings-test",
    inference_config={
        "service": "mistral",
        "service_settings": {
            "api_key": "Mistral-API-Key",
            "model": "mistral-embed"
        }
    },
)

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/text_embedding/mistral-embeddings-test" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "mistral",
    "service_settings": {
      "api_key": "Mistral-API-Key",
      "model": "mistral-embed"
    }
  }'

Java Elasticsearch Java Client

client.inference().put(p -> p
    .inferenceId("mistral-embeddings-test")
    .taskType(TaskType.TextEmbedding)
    .inferenceConfig(i -> i
        .service("mistral")
        .serviceSettings(JsonData.fromJson("{\"api_key\":\"Mistral-API-Key\",\"model\":\"mistral-embed\"}"))
    )
);

C# Elasticsearch .NET Client

var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "mistral-embeddings-test",
        TaskType = TaskType.TextEmbedding,
        InferenceConfig = new()
        {
            Service = "mistral",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "api_key": "Mistral-API-Key",
              "model": "mistral-embed"
            }
            """)
        }
    });

PHP Elasticsearch PHP Client

$resp = $client->inference()->put([
    "task_type" => "text_embedding",
    "inference_id" => "mistral-embeddings-test",
    "body" => [
        "service" => "mistral",
        "service_settings" => [
            "api_key" => "Mistral-API-Key",
            "model" => "mistral-embed",
        ],
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.put(
  task_type: "text_embedding",
  inference_id: "mistral-embeddings-test",
  body: {
    "service": "mistral",
    "service_settings": {
      "api_key": "Mistral-API-Key",
      "model": "mistral-embed"
    }
  }
)

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