# Refine Structured Prompt

Refines a Structured Prompt object (such as a Visual Schema or an Image Caption) based on user instructions.

Access Control & Validation:
* Dataset Ownership: Requires a valid dataset_id to verify that the API token belongs to the organization owning the dataset.
* Draft Status: The referenced dataset must be in draft mode. Refinement is disabled for completed datasets.

Use Cases:
1. Refine Visual Schema: Input the initial schema generated by Bria and instructions like "Make the style description more detailed".
2. Refine Image Caption: Input a specific image's caption and instructions like "Fix the description of the hair color".

The endpoint uses a VLM/LLM to process the input JSON and instructions, returning a valid, modified JSON structure that preserves the required format.

Endpoint: POST /tailored-gen/refine_structured_prompt

## Header parameters:

  - `api_token` (string, required)

## Request fields (application/json):

  - `dataset_id` (integer, required)
    The ID of the dataset associated with this refinement. Used to validate ownership and draft status.

  - `structured_prompt` (string, required)
    The current structured prompt string (Visual Schema or Caption) to be refined.

  - `instruction` (string, required)
    Natural language instruction describing how to modify the JSON (e.g., "Add a field for mood", "Correct the object color").

  - `context_images` (array)
    Optional. List of image URLs or Base64 strings to provide visual context for the refinement (useful when refining specific image captions).

## Response 200 fields (application/json):

  - `structured_prompt` (string)
    The refined Structured Prompt string.


## Response 400 fields

## Response 401 fields

## Response 403 fields

## Response 404 fields

## Response 429 fields

## Response 500 fields