# Review ## Create Extract Review `client.extract.review.create(stringjobID, ReviewCreateParamsparams?, RequestOptionsoptions?): ExtractReview` **post** `/api/v2/extract/{job_id}/review` Beta: answers 403 until extract review is enabled for the caller and their organization. Turn review on for an extract job. Fields read below `confidence_threshold`, and required fields left empty, are flagged for a person to check. Every setting has a default, so the body can be left out. A job still running can be named: it waits for review once it completes. A job that failed or was cancelled without a review, or that cannot be reviewed, answers 409 with `code: job_not_reviewable`; a field in `fields_in_scope` the job's schema does not have answers 400. Answers 201 with the new review, or 200 with the job's existing review, whose settings stay as they are. ### Parameters - `jobID: string` - `params: ReviewCreateParams` - `organization_id?: string | null` Query param - `project_id?: string | null` Query param - `confidence_threshold?: number` Body param: Fields read below this confidence are flagged. - `fields_in_scope?: Array` Body param: JSON Pointers of the fields the threshold applies to; empty means all. - `required_fields?: Array | null` Body param: JSON Pointers of fields flagged when empty; defaults to the schema's required. ### Returns - `ExtractReview` 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. - `decided_at: string | null` When it was approved or rejected. - `decided_by: string | null` ID of the user who approved or rejected it. - `decided_reason: string | null` Why it was rejected. - `field_actions: Record` The latest action per field, keyed by JSON Pointer. - `action: "clear" | "confirm" | "correct"` confirm, correct or clear. - `"clear"` - `"confirm"` - `"correct"` - `actor_id: string` ID of the user who acted. - `at: string` When they acted. - `value?: unknown` The corrected value, for `correct`. - `fields_in_scope: Array` JSON Pointers of the fields the threshold applies to; empty means all. - `flags: Array` 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. - `"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` JSON Pointers of flagged fields nobody checked. - `original_result: Record | null` The result as the model read it. - `required_fields: Array` JSON Pointers of fields flagged when empty. - `retain_until: string` When the job and its document may be deleted. - `reviewed_result: Record` 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. - `"approved"` - `"pending"` - `"rejected"` - `updated_at: string` When the review last changed. ### Example ```typescript 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.create('job_id'); console.log(extractReview.id); ``` #### Response ```json { "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" } ``` ## Get Extract Review `client.extract.review.get(stringjobID, ReviewGetParamsquery?, RequestOptionsoptions?): ExtractReview` **get** `/api/v2/extract/{job_id}/review` Beta: answers 403 until extract review is enabled for the caller and their organization. Get an extract job's review: its flags, field actions and decision, with the result as the model read it and as reviewed. A job without a review answers 404. ### Parameters - `jobID: string` - `query: ReviewGetParams` - `organization_id?: string | null` - `project_id?: string | null` ### Returns - `ExtractReview` 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. - `decided_at: string | null` When it was approved or rejected. - `decided_by: string | null` ID of the user who approved or rejected it. - `decided_reason: string | null` Why it was rejected. - `field_actions: Record` The latest action per field, keyed by JSON Pointer. - `action: "clear" | "confirm" | "correct"` confirm, correct or clear. - `"clear"` - `"confirm"` - `"correct"` - `actor_id: string` ID of the user who acted. - `at: string` When they acted. - `value?: unknown` The corrected value, for `correct`. - `fields_in_scope: Array` JSON Pointers of the fields the threshold applies to; empty means all. - `flags: Array` 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. - `"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` JSON Pointers of flagged fields nobody checked. - `original_result: Record | null` The result as the model read it. - `required_fields: Array` JSON Pointers of fields flagged when empty. - `retain_until: string` When the job and its document may be deleted. - `reviewed_result: Record` 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. - `"approved"` - `"pending"` - `"rejected"` - `updated_at: string` When the review last changed. ### Example ```typescript 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.get('job_id'); console.log(extractReview.id); ``` #### Response ```json { "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" } ``` ## Change Extract Review Fields `client.extract.review.changeFields(stringjobID, ReviewChangeFieldsParamsparams, RequestOptionsoptions?): ExtractReview` **post** `/api/v2/extract/{job_id}/review/fields` Beta: answers 403 until extract review is enabled for the caller and their organization. Confirm, correct, clear, restore or undo fields of a completed job. The changes apply in order, in one write. A job without a review gets one with the default settings, at revision 0. A path that is not a field of the job, or a value the field's schema refuses, answers 400 and changes nothing. A job that has not completed 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`. ### Parameters - `jobID: string` - `params: ReviewChangeFieldsParams` - `changes: Array` Body param: Changes to apply, in order. - `change: "clear" | "confirm" | "correct" | 2 more` confirm, correct to `value`, clear, restore the model's value, or undo. - `"clear"` - `"confirm"` - `"correct"` - `"restore"` - `"undo"` - `path: string` JSON Pointer of the field. - `value?: unknown` The corrected value, for `correct`. - `revision: number` Body param: The review's revision as the caller last read it. - `organization_id?: string | null` Query param - `project_id?: string | null` Query param ### Returns - `ExtractReview` 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. - `decided_at: string | null` When it was approved or rejected. - `decided_by: string | null` ID of the user who approved or rejected it. - `decided_reason: string | null` Why it was rejected. - `field_actions: Record` The latest action per field, keyed by JSON Pointer. - `action: "clear" | "confirm" | "correct"` confirm, correct or clear. - `"clear"` - `"confirm"` - `"correct"` - `actor_id: string` ID of the user who acted. - `at: string` When they acted. - `value?: unknown` The corrected value, for `correct`. - `fields_in_scope: Array` JSON Pointers of the fields the threshold applies to; empty means all. - `flags: Array` 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. - `"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` JSON Pointers of flagged fields nobody checked. - `original_result: Record | null` The result as the model read it. - `required_fields: Array` JSON Pointers of fields flagged when empty. - `retain_until: string` When the job and its document may be deleted. - `reviewed_result: Record` 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. - `"approved"` - `"pending"` - `"rejected"` - `updated_at: string` When the review last changed. ### Example ```typescript 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.changeFields('job_id', { changes: [{ change: 'correct', path: '/total' }], revision: 0, }); console.log(extractReview.id); ``` #### Response ```json { "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" } ``` ## Approve Extract Review `client.extract.review.approve(stringjobID, ReviewApproveParamsparams, RequestOptionsoptions?): ExtractReview` **post** `/api/v2/extract/{job_id}/review/approve` Beta: answers 403 until extract review is enabled for the caller and their organization. Approve the reviewed result. While flagged fields nobody checked remain, answers 409 with `code: open_flags` and their `paths`, unless `sign_off` confirms them as part of approving. A job that has not completed 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`. ### Parameters - `jobID: string` - `params: ReviewApproveParams` - `revision: number` Body param: The review's revision as the caller last read it. - `organization_id?: string | null` Query param - `project_id?: string | null` Query param - `sign_off?: boolean` Body param: Confirm the flagged fields nobody checked as part of approving. ### Returns - `ExtractReview` 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. - `decided_at: string | null` When it was approved or rejected. - `decided_by: string | null` ID of the user who approved or rejected it. - `decided_reason: string | null` Why it was rejected. - `field_actions: Record` The latest action per field, keyed by JSON Pointer. - `action: "clear" | "confirm" | "correct"` confirm, correct or clear. - `"clear"` - `"confirm"` - `"correct"` - `actor_id: string` ID of the user who acted. - `at: string` When they acted. - `value?: unknown` The corrected value, for `correct`. - `fields_in_scope: Array` JSON Pointers of the fields the threshold applies to; empty means all. - `flags: Array` 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. - `"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` JSON Pointers of flagged fields nobody checked. - `original_result: Record | null` The result as the model read it. - `required_fields: Array` JSON Pointers of fields flagged when empty. - `retain_until: string` When the job and its document may be deleted. - `reviewed_result: Record` 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. - `"approved"` - `"pending"` - `"rejected"` - `updated_at: string` When the review last changed. ### Example ```typescript 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.approve('job_id', { revision: 0 }); console.log(extractReview.id); ``` #### Response ```json { "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" } ``` ## Reject Extract Review `client.extract.review.reject(stringjobID, ReviewRejectParamsparams, RequestOptionsoptions?): ExtractReview` **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`. ### Parameters - `jobID: string` - `params: ReviewRejectParams` - `reason: string` Body param: Why the result was rejected. - `revision: number` Body param: The review's revision as the caller last read it. - `organization_id?: string | null` Query param - `project_id?: string | null` Query param ### Returns - `ExtractReview` 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. - `decided_at: string | null` When it was approved or rejected. - `decided_by: string | null` ID of the user who approved or rejected it. - `decided_reason: string | null` Why it was rejected. - `field_actions: Record` The latest action per field, keyed by JSON Pointer. - `action: "clear" | "confirm" | "correct"` confirm, correct or clear. - `"clear"` - `"confirm"` - `"correct"` - `actor_id: string` ID of the user who acted. - `at: string` When they acted. - `value?: unknown` The corrected value, for `correct`. - `fields_in_scope: Array` JSON Pointers of the fields the threshold applies to; empty means all. - `flags: Array` 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. - `"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` JSON Pointers of flagged fields nobody checked. - `original_result: Record | null` The result as the model read it. - `required_fields: Array` JSON Pointers of fields flagged when empty. - `retain_until: string` When the job and its document may be deleted. - `reviewed_result: Record` 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. - `"approved"` - `"pending"` - `"rejected"` - `updated_at: string` When the review last changed. ### Example ```typescript 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); ``` #### Response ```json { "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" } ``` ## Reopen Extract Review `client.extract.review.reopen(stringjobID, ReviewReopenParamsparams, RequestOptionsoptions?): ExtractReview` **post** `/api/v2/extract/{job_id}/review/reopen` Beta: answers 403 until extract review is enabled for the caller and their organization. Put an approved or rejected review back to pending. Its field actions stay. A `revision` other than the review's latest answers 409 with `code: stale_revision` and the latest `revision`. ### Parameters - `jobID: string` - `params: ReviewReopenParams` - `revision: number` Body param: The review's revision as the caller last read it. - `organization_id?: string | null` Query param - `project_id?: string | null` Query param ### Returns - `ExtractReview` 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. - `decided_at: string | null` When it was approved or rejected. - `decided_by: string | null` ID of the user who approved or rejected it. - `decided_reason: string | null` Why it was rejected. - `field_actions: Record` The latest action per field, keyed by JSON Pointer. - `action: "clear" | "confirm" | "correct"` confirm, correct or clear. - `"clear"` - `"confirm"` - `"correct"` - `actor_id: string` ID of the user who acted. - `at: string` When they acted. - `value?: unknown` The corrected value, for `correct`. - `fields_in_scope: Array` JSON Pointers of the fields the threshold applies to; empty means all. - `flags: Array` 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. - `"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` JSON Pointers of flagged fields nobody checked. - `original_result: Record | null` The result as the model read it. - `required_fields: Array` JSON Pointers of fields flagged when empty. - `retain_until: string` When the job and its document may be deleted. - `reviewed_result: Record` 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. - `"approved"` - `"pending"` - `"rejected"` - `updated_at: string` When the review last changed. ### Example ```typescript 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.reopen('job_id', { revision: 0 }); console.log(extractReview.id); ``` #### Response ```json { "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" } ``` ## List Extract Review Events `client.extract.review.listEvents(stringjobID, ReviewListEventsParamsquery?, RequestOptionsoptions?): PaginatedCursor` **get** `/api/v2/extract/{job_id}/review/events` Beta: answers 403 until extract review is enabled for the caller and their organization. List a review's history, newest first. ### Parameters - `jobID: string` - `query: ReviewListEventsParams` - `organization_id?: string | null` - `page_size?: number` Events per page. - `page_token?: string | null` Token from the previous page. - `project_id?: string | null` ### Returns - `ExtractReviewEvent` One entry in a review's history. - `id: string` Unique identifier of the entry. - `actor_id: string` ID of the user who acted. - `created_at: string` When it happened. - `kind: "approved" | "created" | "field_cleared" | 7 more` What happened. - `"approved"` - `"created"` - `"field_cleared"` - `"field_confirmed"` - `"field_corrected"` - `"field_restored"` - `"field_undone"` - `"flags_signed_off"` - `"rejected"` - `"reopened"` - `detail?: ExtractReviewCreatedDetail | ExtractReviewRejectedDetail | ExtractReviewSignedOffDetail | null` The settings for `created`, the reason for `rejected`, and the fields for `flags_signed_off`; null for the rest. - `ExtractReviewCreatedDetail` What a `created` entry records: where review was turned on, and its settings. - `confidence_threshold: number` Fields read below this confidence are flagged. - `fields_in_scope: Array` JSON Pointers of the fields the threshold applies to; empty means all. - `origin: "api" | "edit" | "history" | "run"` Turned on as the job ran, from History, by a first edit, or by the API. - `"api"` - `"edit"` - `"history"` - `"run"` - `required_fields: Array` JSON Pointers of fields flagged when empty. - `ExtractReviewRejectedDetail` What a `rejected` entry records. - `reason: string` Why the result was rejected. - `ExtractReviewSignedOffDetail` What a `flags_signed_off` entry records. - `paths: Array` JSON Pointers of the flagged fields confirmed as part of approving. - `path?: string | null` JSON Pointer of the field it changed. - `value_after?: unknown` The field's value after the change. - `value_before?: unknown` The field's value before the change. ### Example ```typescript 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 }); // Automatically fetches more pages as needed. for await (const extractReviewEvent of client.extract.review.listEvents('job_id')) { console.log(extractReviewEvent.id); } ``` #### Response ```json { "items": [ { "id": "id", "actor_id": "actor_id", "created_at": "2019-12-27T18:11:19.117Z", "kind": "approved", "detail": { "confidence_threshold": 0, "fields_in_scope": [ "string" ], "origin": "api", "required_fields": [ "string" ] }, "path": "path", "value_after": {}, "value_before": {} } ], "next_page_token": "next_page_token", "total_size": 0 } ``` ## Domain Types ### Extract Review - `ExtractReview` 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. - `decided_at: string | null` When it was approved or rejected. - `decided_by: string | null` ID of the user who approved or rejected it. - `decided_reason: string | null` Why it was rejected. - `field_actions: Record` The latest action per field, keyed by JSON Pointer. - `action: "clear" | "confirm" | "correct"` confirm, correct or clear. - `"clear"` - `"confirm"` - `"correct"` - `actor_id: string` ID of the user who acted. - `at: string` When they acted. - `value?: unknown` The corrected value, for `correct`. - `fields_in_scope: Array` JSON Pointers of the fields the threshold applies to; empty means all. - `flags: Array` 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. - `"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` JSON Pointers of flagged fields nobody checked. - `original_result: Record | null` The result as the model read it. - `required_fields: Array` JSON Pointers of fields flagged when empty. - `retain_until: string` When the job and its document may be deleted. - `reviewed_result: Record` 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. - `"approved"` - `"pending"` - `"rejected"` - `updated_at: string` When the review last changed. ### Extract Review Event - `ExtractReviewEvent` One entry in a review's history. - `id: string` Unique identifier of the entry. - `actor_id: string` ID of the user who acted. - `created_at: string` When it happened. - `kind: "approved" | "created" | "field_cleared" | 7 more` What happened. - `"approved"` - `"created"` - `"field_cleared"` - `"field_confirmed"` - `"field_corrected"` - `"field_restored"` - `"field_undone"` - `"flags_signed_off"` - `"rejected"` - `"reopened"` - `detail?: ExtractReviewCreatedDetail | ExtractReviewRejectedDetail | ExtractReviewSignedOffDetail | null` The settings for `created`, the reason for `rejected`, and the fields for `flags_signed_off`; null for the rest. - `ExtractReviewCreatedDetail` What a `created` entry records: where review was turned on, and its settings. - `confidence_threshold: number` Fields read below this confidence are flagged. - `fields_in_scope: Array` JSON Pointers of the fields the threshold applies to; empty means all. - `origin: "api" | "edit" | "history" | "run"` Turned on as the job ran, from History, by a first edit, or by the API. - `"api"` - `"edit"` - `"history"` - `"run"` - `required_fields: Array` JSON Pointers of fields flagged when empty. - `ExtractReviewRejectedDetail` What a `rejected` entry records. - `reason: string` Why the result was rejected. - `ExtractReviewSignedOffDetail` What a `flags_signed_off` entry records. - `paths: Array` JSON Pointers of the flagged fields confirmed as part of approving. - `path?: string | null` JSON Pointer of the field it changed. - `value_after?: unknown` The field's value after the change. - `value_before?: unknown` The field's value before the change.