get_uncertainties

The job retrieves the uncertainty of the representations for specified contents within an archive. This allows you to prioritize high uncertainty content for labeling and ensure safer interpretation of search results and automatic propagations. Uncertainty is only computed for archives vectorized with a custom fine tuned vectorizer.

Required Account Privileges: "read"

Request JSON ["inputs"]:

    "archive":
       string (3 <= len <= 30) unique in account 
       null NOT allowed
       A unique string identifier for the archive within your account.
    
    "archive_content_ids_subset": 
       list of ints
       null allowed
       Optional. A list of integers representing the IDs of the specific contents to consider for filtering. If not provided, all contents in the archive will be considered.

Response JSON ["results"]

   "id_to_uncertainty":
      dict
      {"id"(int): float}