# Regenerate All Captions

Regenerate captions for all images in dataset. This action is crucial after the user updates the visual schema or caption_prefix, and then it's recommended to regenerate all the captions of all images, to have full compatibility with the new visual schema or caption_prefix.

This is an asynchronous operation. Once this endpoint is called, Get Dataset by ID should be sampled until the captions_update_status changes to 'completed'.

Endpoint: PUT /tailored-gen/datasets/{dataset_id}/images

## Path parameters:

  - `dataset_id` (integer, required)
    Dataset ID

## Header parameters:

  - `api_token` (string, required)

## Response 202 fields (application/json):

  - `id` (integer)
    Unique identifier for the dataset

  - `project_id` (integer)
    Associated project ID

  - `name` (string)
    Dataset name

  - `training_version` (string)
    The foundation model version this dataset targets (e.g., 'fibo', 'max').
    Enum: "max", "light", "3.2", "2.3", "fibo"

  - `caption_prefix` (string,null)
    Text prepended to captions. 
* For training_version = max/light/3.2/2.3: Required string.
* For training_version = fibo: Null.

  - `status` (string)
    Status of the dataset
    Enum: "draft", "completed"

  - `captions_update_status` (string)
    Status of captions update process
    Enum: "empty", "in_progress", "completed"

  - `created_at` (string)
    Timestamp when the dataset was created

  - `updated_at` (string)
    Timestamp when the dataset was last updated


## Response 401 fields

## Response 404 fields

## Response 429 fields

## Response 500 fields