Extracts data fields from a document and outputs recommendations whether a field should be reviewed for validation. Use a prebuilt model or define custom fields for an Extraction.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
The name of the model that will be used for the extraction. A model name without a date is an alias to the latest version of that model, i.e. rre-de always points to the latest version of rre-de.
rre-de-2025-02-14, rre-de-2025-03-31, rre-de-2025-04-07, rre-de "rre-de-2025-04-07"
Base64-encoded contents of a document (PDF, JPG or PNG)
"JVBERi0xLjUNCiW1tbW1DQox..."
If set to true, the extraction will expand abbreviations in the extracted fields.
false
OK
The extracted data fields and review recommendations. Each key represents a field name, and the value conforms to the ExtractionField schema.
{
"referral_diagnosis": {
"content": "C61 - Castration-resistant prostate cancer in progress, N28.1 - Right renal cyst, F52.2 - Erectile dysfunction",
"review": {
"reasoning": "The referral diagnosis is clearly stated with multiple diagnoses. The referral is complete and no review is needed.",
"recommended": false
}
},
"ordered_procedure": {
"content": "MRI of the prostate, CT of the abdomen, PSA test",
"review": {
"reasoning": "The ordered procedures are clearly stated. No review is needed.",
"recommended": false
}
}
}