Create a trained model vocabulary Added in 8.0.0
This API is supported only for natural language processing (NLP) models.
The vocabulary is stored in the index as described in inference_config.*.vocabulary
of the trained model definition.
Path parameters
-
The unique identifier of the trained model.
Body Required
PUT /_ml/trained_models/{model_id}/vocabulary
curl \
-X PUT http://api.example.com/_ml/trained_models/{model_id}/vocabulary \
-H "Content-Type: application/json" \
-d '{"vocabulary":["string"],"merges":["string"],"scores":[42.0]}'
Request examples
{
"vocabulary": [
"string"
],
"merges": [
"string"
],
"scores": [
42.0
]
}
Response examples (200)
{
"acknowledged": true
}