Split Then Extract
A 6-step recipe with Mindee. We can help you get access.
Recipe · 6 steps
Split Then Extract
with Mindee
Split a multi-document file, then extract fields from it.
- Send the multi-document file to the asynchronous split queue to discover its document ranges.
- Poll the shared jobs endpoint until the split job reports Processed or Failed.
- Read the identified document ranges from the completed split inference.
- Send the same file to the extraction queue against the chosen extraction model to read the contents of the documents.
- Poll the shared jobs endpoint until the extraction job reports Processed or Failed.
- Retrieve the completed extraction inference and read the structured fields parsed from the documents.
What you'll need to have ready
- authorization: Mindee API key sent in the Authorization header.
- splitModelId: UUID of the split utility model.
- extractionModelId: UUID of the extraction model to apply after splitting.
- file: The multi-document file to upload as binary form data.
- filename: Optional filename to associate with the uploaded file.
For your developer
Arazzo workflow mindee:split-then-extract, 6 operations: Enqueue_Split_Product_Inference_v2_products_split_enqueue_post → Get_Job_Status_v2_jobs__job_id__get → Get_Split_Product_Result_v2_products_split_results__inference_id__get → Enqueue_Extraction_Product_Inference_v2_products_extraction_enqueue_post → Get_Job_Status_v2_jobs__job_id__get → Get_Extraction_Product_Result_v2_products_extraction_results__inference_id__get. Specs on APIs.io.