API Reference

Extract

Review

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Reject Extract Review

client.extract.review.reject(stringjobID, ReviewRejectParams { reason, revision, organization_id, project_id } params, RequestOptionsoptions?): ExtractReview { id, confidence_threshold, created_at, 16 more }

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

Beta: answers 403 until extract review is enabled for the caller and their organization.

Reject the result, with a reason. A job that failed or was cancelled can be rejected, which closes a review turned on while it ran. A job still queued or running answers 409 with code: job_not_reviewable. A revision other than the review’s latest answers 409 with code: stale_revision and the latest revision.

ParametersExpand Collapse

jobID: string

params: ReviewRejectParams { reason, revision, organization_id, project_id }

reason: string

Body param: Why the result was rejected.

minLength1

revision: number

Body param: The review’s revision as the caller last read it.

minimum0

organization_id?: string | null

Query param

formatuuid

project_id?: string | null

Query param

formatuuid

ReturnsExpand Collapse

ExtractReview { id, confidence_threshold, created_at, 16 more }

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

id: string

Unique identifier of the review.

confidence_threshold: number

Fields read below this confidence are flagged.

created_at: string

When review was turned on.

formatdate-time

decided_at: string | null

When it was approved or rejected.

formatdate-time

decided_by: string | null

ID of the user who approved or rejected it.

decided_reason: string | null

Why it was rejected.

field_actions: Record<string, FieldActions>

The latest action per field, keyed by JSON Pointer.

action: "clear" | "confirm" | "correct"

confirm, correct or clear.

One of the following:

"clear"

"confirm"

"correct"

actor_id: string

ID of the user who acted.

at: string

When they acted.

formatdate-time

value?: unknown

The corrected value, for correct.

fields_in_scope: Array<string>

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

flags: Array<Flag>

Fields the review asks a person to check.

handled: boolean

Whether someone confirmed, corrected or cleared it.

path: string

JSON Pointer of the field.

reason: "below_threshold" | "required_empty"

below_threshold, or required_empty for a required field left empty.

One of the following:

"below_threshold"

"required_empty"

cell?: Cell | null

Where in a list the least confident value is.

row: number

Index of the row, from 0.

column?: string | null

Property of the row, when rows are objects.

confidence?: number | null

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

job_id: string

The extract job reviewed.

open_flags: Array<string>

JSON Pointers of flagged fields nobody checked.

original_result: Record<string, unknown> | null

The result as the model read it.

required_fields: Array<string>

JSON Pointers of fields flagged when empty.

retain_until: string

When the job and its document may be deleted.

formatdate-time

reviewed_result: Record<string, unknown>

The result with the field actions.

revision: number

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

source_file_id: string | null

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

status: "approved" | "pending" | "rejected"

pending until approved or rejected.

One of the following:

"approved"

"pending"

"rejected"

updated_at: string

When the review last changed.

formatdate-time

Reject Extract Review

TypeScript

HTTP

TypeScript

Python

Go

Java

C#

CLI Tool

import LlamaCloud from '@llamaindex/llama-cloud';

const client = new LlamaCloud({
  apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted
});

const extractReview = await client.extract.review.reject('job_id', {
  reason: 'The invoice total does not match the line items.',
  revision: 0,
});

console.log(extractReview.id);

200 example

{
  "id": "id",
  "confidence_threshold": 0,
  "created_at": "2019-12-27T18:11:19.117Z",
  "decided_at": "2019-12-27T18:11:19.117Z",
  "decided_by": "decided_by",
  "decided_reason": "decided_reason",
  "field_actions": {
    "foo": {
      "action": "clear",
      "actor_id": "actor_id",
      "at": "2019-12-27T18:11:19.117Z",
      "value": {}
    }
  },
  "fields_in_scope": [
    "string"
  ],
  "flags": [
    {
      "handled": true,
      "path": "path",
      "reason": "below_threshold",
      "cell": {
        "row": 0,
        "column": "column"
      },
      "confidence": 0
    }
  ],
  "job_id": "job_id",
  "open_flags": [
    "string"
  ],
  "original_result": {
    "foo": "bar"
  },
  "required_fields": [
    "string"
  ],
  "retain_until": "2019-12-27T18:11:19.117Z",
  "reviewed_result": {
    "foo": "bar"
  },
  "revision": 0,
  "source_file_id": "source_file_id",
  "status": "approved",
  "updated_at": "2019-12-27T18:11:19.117Z"
}

Returns Examples

200 example

{
  "id": "id",
  "confidence_threshold": 0,
  "created_at": "2019-12-27T18:11:19.117Z",
  "decided_at": "2019-12-27T18:11:19.117Z",
  "decided_by": "decided_by",
  "decided_reason": "decided_reason",
  "field_actions": {
    "foo": {
      "action": "clear",
      "actor_id": "actor_id",
      "at": "2019-12-27T18:11:19.117Z",
      "value": {}
    }
  },
  "fields_in_scope": [
    "string"
  ],
  "flags": [
    {
      "handled": true,
      "path": "path",
      "reason": "below_threshold",
      "cell": {
        "row": 0,
        "column": "column"
      },
      "confidence": 0
    }
  ],
  "job_id": "job_id",
  "open_flags": [
    "string"
  ],
  "original_result": {
    "foo": "bar"
  },
  "required_fields": [
    "string"
  ],
  "retain_until": "2019-12-27T18:11:19.117Z",
  "reviewed_result": {
    "foo": "bar"
  },
  "revision": 0,
  "source_file_id": "source_file_id",
  "status": "approved",
  "updated_at": "2019-12-27T18:11:19.117Z"
}