Create part of a trained model definition

PUT /_ml/trained_models/{model_id}/definition/{part}

Auth

Required privileges

Cluster privileges manage_ml

Path parameters

model_id string required: The unique identifier of the trained model.
part number required: The definition part number. When the definition is loaded for inference the definition parts are streamed in the order of their part number. The first part must be 0 and the final part must be total_parts - 1.

Request body

definition string required: The definition part for the model. Must be a base64 encoded string.
total_definition_length number required: The total uncompressed definition length in bytes. Not base64 encoded.
total_parts number required: The total number of parts that will be uploaded. Must be greater than 0.

Response

application/json

acknowledged boolean required: For a successful response, this value is always true. On failure, an exception is returned instead.

View as Markdown

Examples

Request Console 1 / 8 languages

An example body for a PUT _ml/trained_models/elastic__distilbert-base-uncased-finetuned-conll03-english/definition/0 request.

Console Kibana Dev Tools

PUT _ml/trained_models/elastic__distilbert-base-uncased-finetuned-conll03-english/definition/0
{
    "definition": "...",
    "total_definition_length": 265632637,
    "total_parts": 64
}

JavaScript Elasticsearch JavaScript Client

const response = await client.ml.putTrainedModelDefinitionPart({
  model_id: "elastic__distilbert-base-uncased-finetuned-conll03-english",
  part: 0,
  definition: "...",
  total_definition_length: 265632637,
  total_parts: 64,
});

Python Elasticsearch Python Client

resp = client.ml.put_trained_model_definition_part(
    model_id="elastic__distilbert-base-uncased-finetuned-conll03-english",
    part="0",
    definition="...",
    total_definition_length=265632637,
    total_parts=64,
)

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_ml/trained_models/elastic__distilbert-base-uncased-finetuned-conll03-english/definition/0" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "definition": "...",
    "total_definition_length": 265632637,
    "total_parts": 64
  }'

Java Elasticsearch Java Client

client.ml().putTrainedModelDefinitionPart(p -> p
    .definition("...")
    .modelId("elastic__distilbert-base-uncased-finetuned-conll03-english")
    .part(0)
    .totalDefinitionLength(265632637L)
    .totalParts(64)
);

C# Elasticsearch .NET Client

var response = await client.MachineLearning
    .PutTrainedModelDefinitionPartAsync(modelId: "elastic__distilbert-base-uncased-finetuned-conll03-english", part: 0, d1 => d1
        .Definition("...")
        .TotalDefinitionLength(265632637L)
        .TotalParts(64)
    );

PHP Elasticsearch PHP Client

$resp = $client->ml()->putTrainedModelDefinitionPart([
    "model_id" => "elastic__distilbert-base-uncased-finetuned-conll03-english",
    "part" => "0",
    "body" => [
        "definition" => "...",
        "total_definition_length" => 265632637,
        "total_parts" => 64,
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.ml.put_trained_model_definition_part(
  model_id: "elastic__distilbert-base-uncased-finetuned-conll03-english",
  part: "0",
  body: {
    "definition": "...",
    "total_definition_length": 265632637,
    "total_parts": 64
  }
)

Response

{
  "acknowledged": false
}

Generated from the API spec