A completed classification job returns the overall document classification, a confidence score, and per-page results. The example below is a real response from classifying an invoice against four candidate categories.Documentation Index
Fetch the complete documentation index at: https://docs.unsiloed.ai/llms.txt
Use this file to discover all available pages before exploring further.
Top-Level Fields
job_id: unique identifier for the classification jobstatus: job state (completed,failed, or an in-progress value such asprocessing)progress: human-readable progress messageerror: error message if the job failed, otherwisenullresult: the classification result object (described below)
Result Object
success: whether the classification operation succeededclassification: the overall predicted category for the documentconfidence: confidence score for the overall classification (0–1)total_pages: total number of pages in the documentprocessed_pages: number of pages successfully processedpage_results: per-page classifications (described below)
Page Result Object
Each item inpage_results describes the classification of one page:
page: page number, 1-indexedsuccess: whether classification succeeded for that pageclassification: the predicted category for the pageraw_result: the model’s raw output before normalization to a category name; usually identical toclassificationconfidence: confidence score for the page’s classification (0–1)
Other Job States
The submit response (before polling kicks in) returns a smaller body:result:
error message:

