API Reference

Extract

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Review

Create Extract Review

extract.review.create(strjob_id, ReviewCreateParams**kwargs) -> ExtractReview

POST/api/v2/extract/{job_id}/review

Get Extract Review

extract.review.get(strjob_id, ReviewGetParams**kwargs) -> ExtractReview

GET/api/v2/extract/{job_id}/review

Change Extract Review Fields

extract.review.change_fields(strjob_id, ReviewChangeFieldsParams**kwargs) -> ExtractReview

POST/api/v2/extract/{job_id}/review/fields

Approve Extract Review

extract.review.approve(strjob_id, ReviewApproveParams**kwargs) -> ExtractReview

POST/api/v2/extract/{job_id}/review/approve

Reject Extract Review

extract.review.reject(strjob_id, ReviewRejectParams**kwargs) -> ExtractReview

POST/api/v2/extract/{job_id}/review/reject

Reopen Extract Review

extract.review.reopen(strjob_id, ReviewReopenParams**kwargs) -> ExtractReview

POST/api/v2/extract/{job_id}/review/reopen

List Extract Review Events

extract.review.list_events(strjob_id, ReviewListEventsParams**kwargs) -> SyncPaginatedCursor[ExtractReviewEvent]

GET/api/v2/extract/{job_id}/review/events

ModelsExpand Collapse

class ExtractReview: …

An extract job’s review: its settings, flags, field actions and decision, with the result as read and as reviewed.

id: str

Unique identifier of the review.

confidence_threshold: float

Fields read below this confidence are flagged.

created_at: datetime

When review was turned on.

formatdate-time

decided_at: Optional[datetime]

When it was approved or rejected.

formatdate-time

decided_by: Optional[str]

ID of the user who approved or rejected it.

decided_reason: Optional[str]

Why it was rejected.

field_actions: Dict[str, FieldActions]

The latest action per field, keyed by JSON Pointer.

action: Literal["clear", "confirm", "correct"]

confirm, correct or clear.

One of the following:

"clear"

"confirm"

"correct"

actor_id: str

ID of the user who acted.

at: datetime

When they acted.

formatdate-time

value: Optional[object]

The corrected value, for correct.

fields_in_scope: List[str]

JSON Pointers of the fields the threshold applies to; empty means all.

flags: List[Flag]

Fields the review asks a person to check.

handled: bool

Whether someone confirmed, corrected or cleared it.

path: str

JSON Pointer of the field.

reason: Literal["below_threshold", "required_empty"]

below_threshold, or required_empty for a required field left empty.

One of the following:

"below_threshold"

"required_empty"

cell: Optional[FlagCell]

Where in a list the least confident value is.

row: int

Index of the row, from 0.

column: Optional[str]

Property of the row, when rows are objects.

confidence: Optional[float]

The field’s confidence; for a list, its least confident value.

job_id: str

The extract job reviewed.

open_flags: List[str]

JSON Pointers of flagged fields nobody checked.

original_result: Optional[Dict[str, object]]

The result as the model read it.

required_fields: List[str]

JSON Pointers of fields flagged when empty.

retain_until: datetime

When the job and its document may be deleted.

formatdate-time

reviewed_result: Dict[str, object]

The result with the field actions.

revision: int

Bumped by every change; actions name the one they saw.

source_file_id: Optional[str]

The file the job read, or the file behind the parse job it read; null for a URL.

status: Literal["approved", "pending", "rejected"]

pending until approved or rejected.

One of the following:

"approved"

"pending"

"rejected"

updated_at: datetime

When the review last changed.

formatdate-time

class ExtractReviewEvent: …

One entry in a review’s history.

id: str

Unique identifier of the entry.

actor_id: str

ID of the user who acted.

created_at: datetime

When it happened.

formatdate-time

kind: Literal["approved", "created", "field_cleared", 7 more]

What happened.

One of the following:

"approved"

"created"

"field_cleared"

"field_confirmed"

"field_corrected"

"field_restored"

"field_undone"

"flags_signed_off"

"rejected"

"reopened"

detail: Optional[Detail]

The settings for created, the reason for rejected, and the fields for flags_signed_off; null for the rest.

One of the following:

class DetailExtractReviewCreatedDetail: …

What a created entry records: where review was turned on, and its settings.

confidence_threshold: float

Fields read below this confidence are flagged.

fields_in_scope: List[str]

JSON Pointers of the fields the threshold applies to; empty means all.

origin: Literal["api", "edit", "history", "run"]

Turned on as the job ran, from History, by a first edit, or by the API.

One of the following:

"api"

"edit"

"history"

"run"

required_fields: List[str]

JSON Pointers of fields flagged when empty.

class DetailExtractReviewRejectedDetail: …

What a rejected entry records.

reason: str

Why the result was rejected.

class DetailExtractReviewSignedOffDetail: …

What a flags_signed_off entry records.

paths: List[str]

JSON Pointers of the flagged fields confirmed as part of approving.

path: Optional[str]

JSON Pointer of the field it changed.

value_after: Optional[object]

The field’s value after the change.

value_before: Optional[object]

The field’s value before the change.