Document Extraction
Extraction schema CRUD, plus queued schema generation and extraction runs (202, poll GET /v1/operations/{operationId}).
Generate and save reusable extraction schema
Requires a parsed file and debits exactly 1 credit. Queued, not synchronous: responds 202 with { operation_id, status } and generates a reusable organization extraction schema asynchronously — poll GET /v1/operations/{operationId}. A re-attach to an already-completed operation returns 200 with the schema inline.
Generate and save reusable extraction schema › Request Body
file_idmodel_idreasoning_levelidempotency_keysegment_idstitleGenerate and save reusable extraction schema › Responses
Generated schema (idempotent replay of an already-completed run)
operation_idoperation_typestatusPopulated only once status is completed.
errorcreated_atcompleted_atSave reusable extraction schema
Saves a user-provided schema. This is CRUD and does not debit credits.
Save reusable extraction schema › Request Body
file_idknowledge_base_idSave reusable extraction schema › Responses
Saved schema
Enqueue a product extraction run
Requires a parsed file and schema_id or inline schema. Debits exactly 1 credit after validation and before model work. Queued, not synchronous: responds 202 with { operation_id, status } and the extraction runs asynchronously — poll GET /v1/operations/{operationId} for progress and output. A request that re-attaches to an already-completed operation (same idempotency key) returns 200 with the result inline instead.
Enqueue a product extraction run › Request Body
file_idmodel_idreasoning_levelidempotency_keyschema_idsegment_idsEnqueue a product extraction run › Responses
Extraction result (idempotent replay of an already-completed run)
operation_idoperation_typestatusPopulated only once status is completed.
errorcreated_atcompleted_at