# Review ## Create Extract Review `ExtractReview extract().review().create(ReviewCreateParamsparams = ReviewCreateParams.none(), RequestOptionsrequestOptions = RequestOptions.none())` **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 - `ReviewCreateParams params` - `Optional jobId` - `Optional organizationId` - `Optional projectId` - `Optional confidenceThreshold` Fields read below this confidence are flagged. - `Optional> fieldsInScope` JSON Pointers of the fields the threshold applies to; empty means all. - `Optional> requiredFields` JSON Pointers of fields flagged when empty; defaults to the schema's required. ### Returns - `class ExtractReview:` An extract job's review: its settings, flags, field actions and decision, with the result as read and as reviewed. - `String id` Unique identifier of the review. - `double confidenceThreshold` Fields read below this confidence are flagged. - `LocalDateTime createdAt` When review was turned on. - `Optional decidedAt` When it was approved or rejected. - `Optional decidedBy` ID of the user who approved or rejected it. - `Optional decidedReason` Why it was rejected. - `FieldActions fieldActions` The latest action per field, keyed by JSON Pointer. - `Action action` confirm, correct or clear. - `CLEAR("clear")` - `CONFIRM("confirm")` - `CORRECT("correct")` - `String actorId` ID of the user who acted. - `LocalDateTime at` When they acted. - `Optional value` The corrected value, for `correct`. - `List fieldsInScope` JSON Pointers of the fields the threshold applies to; empty means all. - `List flags` Fields the review asks a person to check. - `boolean handled` Whether someone confirmed, corrected or cleared it. - `String path` JSON Pointer of the field. - `Reason reason` below_threshold, or required_empty for a required field left empty. - `BELOW_THRESHOLD("below_threshold")` - `REQUIRED_EMPTY("required_empty")` - `Optional cell` Where in a list the least confident value is. - `long row` Index of the row, from 0. - `Optional column` Property of the row, when rows are objects. - `Optional confidence` The field's confidence; for a list, its least confident value. - `String jobId` The extract job reviewed. - `List openFlags` JSON Pointers of flagged fields nobody checked. - `Optional originalResult` The result as the model read it. - `List requiredFields` JSON Pointers of fields flagged when empty. - `LocalDateTime retainUntil` When the job and its document may be deleted. - `ReviewedResult reviewedResult` The result with the field actions. - `long revision` Bumped by every change; actions name the one they saw. - `Optional sourceFileId` The file the job read, or the file behind the parse job it read; null for a URL. - `Status status` pending until approved or rejected. - `APPROVED("approved")` - `PENDING("pending")` - `REJECTED("rejected")` - `LocalDateTime updatedAt` When the review last changed. ### Example ```java package ai.llamaindex.llamacloud.example; import ai.llamaindex.llamacloud.client.LlamaCloudClient; import ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient; import ai.llamaindex.llamacloud.models.extract.review.ExtractReview; import ai.llamaindex.llamacloud.models.extract.review.ReviewCreateParams; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); ExtractReview extractReview = client.extract().review().create("job_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 `ExtractReview extract().review().get(ReviewGetParamsparams = ReviewGetParams.none(), RequestOptionsrequestOptions = RequestOptions.none())` **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 - `ReviewGetParams params` - `Optional jobId` - `Optional organizationId` - `Optional projectId` ### Returns - `class ExtractReview:` An extract job's review: its settings, flags, field actions and decision, with the result as read and as reviewed. - `String id` Unique identifier of the review. - `double confidenceThreshold` Fields read below this confidence are flagged. - `LocalDateTime createdAt` When review was turned on. - `Optional decidedAt` When it was approved or rejected. - `Optional decidedBy` ID of the user who approved or rejected it. - `Optional decidedReason` Why it was rejected. - `FieldActions fieldActions` The latest action per field, keyed by JSON Pointer. - `Action action` confirm, correct or clear. - `CLEAR("clear")` - `CONFIRM("confirm")` - `CORRECT("correct")` - `String actorId` ID of the user who acted. - `LocalDateTime at` When they acted. - `Optional value` The corrected value, for `correct`. - `List fieldsInScope` JSON Pointers of the fields the threshold applies to; empty means all. - `List flags` Fields the review asks a person to check. - `boolean handled` Whether someone confirmed, corrected or cleared it. - `String path` JSON Pointer of the field. - `Reason reason` below_threshold, or required_empty for a required field left empty. - `BELOW_THRESHOLD("below_threshold")` - `REQUIRED_EMPTY("required_empty")` - `Optional cell` Where in a list the least confident value is. - `long row` Index of the row, from 0. - `Optional column` Property of the row, when rows are objects. - `Optional confidence` The field's confidence; for a list, its least confident value. - `String jobId` The extract job reviewed. - `List openFlags` JSON Pointers of flagged fields nobody checked. - `Optional originalResult` The result as the model read it. - `List requiredFields` JSON Pointers of fields flagged when empty. - `LocalDateTime retainUntil` When the job and its document may be deleted. - `ReviewedResult reviewedResult` The result with the field actions. - `long revision` Bumped by every change; actions name the one they saw. - `Optional sourceFileId` The file the job read, or the file behind the parse job it read; null for a URL. - `Status status` pending until approved or rejected. - `APPROVED("approved")` - `PENDING("pending")` - `REJECTED("rejected")` - `LocalDateTime updatedAt` When the review last changed. ### Example ```java package ai.llamaindex.llamacloud.example; import ai.llamaindex.llamacloud.client.LlamaCloudClient; import ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient; import ai.llamaindex.llamacloud.models.extract.review.ExtractReview; import ai.llamaindex.llamacloud.models.extract.review.ReviewGetParams; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); ExtractReview extractReview = client.extract().review().get("job_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 `ExtractReview extract().review().changeFields(ReviewChangeFieldsParamsparams, RequestOptionsrequestOptions = RequestOptions.none())` **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 - `ReviewChangeFieldsParams params` - `Optional jobId` - `Optional organizationId` - `Optional projectId` - `List changes` Changes to apply, in order. - `InnerChange change` confirm, correct to `value`, clear, restore the model's value, or undo. - `CLEAR("clear")` - `CONFIRM("confirm")` - `CORRECT("correct")` - `RESTORE("restore")` - `UNDO("undo")` - `String path` JSON Pointer of the field. - `Optional value` The corrected value, for `correct`. - `long revision` The review's revision as the caller last read it. ### Returns - `class ExtractReview:` An extract job's review: its settings, flags, field actions and decision, with the result as read and as reviewed. - `String id` Unique identifier of the review. - `double confidenceThreshold` Fields read below this confidence are flagged. - `LocalDateTime createdAt` When review was turned on. - `Optional decidedAt` When it was approved or rejected. - `Optional decidedBy` ID of the user who approved or rejected it. - `Optional decidedReason` Why it was rejected. - `FieldActions fieldActions` The latest action per field, keyed by JSON Pointer. - `Action action` confirm, correct or clear. - `CLEAR("clear")` - `CONFIRM("confirm")` - `CORRECT("correct")` - `String actorId` ID of the user who acted. - `LocalDateTime at` When they acted. - `Optional value` The corrected value, for `correct`. - `List fieldsInScope` JSON Pointers of the fields the threshold applies to; empty means all. - `List flags` Fields the review asks a person to check. - `boolean handled` Whether someone confirmed, corrected or cleared it. - `String path` JSON Pointer of the field. - `Reason reason` below_threshold, or required_empty for a required field left empty. - `BELOW_THRESHOLD("below_threshold")` - `REQUIRED_EMPTY("required_empty")` - `Optional cell` Where in a list the least confident value is. - `long row` Index of the row, from 0. - `Optional column` Property of the row, when rows are objects. - `Optional confidence` The field's confidence; for a list, its least confident value. - `String jobId` The extract job reviewed. - `List openFlags` JSON Pointers of flagged fields nobody checked. - `Optional originalResult` The result as the model read it. - `List requiredFields` JSON Pointers of fields flagged when empty. - `LocalDateTime retainUntil` When the job and its document may be deleted. - `ReviewedResult reviewedResult` The result with the field actions. - `long revision` Bumped by every change; actions name the one they saw. - `Optional sourceFileId` The file the job read, or the file behind the parse job it read; null for a URL. - `Status status` pending until approved or rejected. - `APPROVED("approved")` - `PENDING("pending")` - `REJECTED("rejected")` - `LocalDateTime updatedAt` When the review last changed. ### Example ```java package ai.llamaindex.llamacloud.example; import ai.llamaindex.llamacloud.client.LlamaCloudClient; import ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient; import ai.llamaindex.llamacloud.models.extract.review.ExtractReview; import ai.llamaindex.llamacloud.models.extract.review.ReviewChangeFieldsParams; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); ReviewChangeFieldsParams params = ReviewChangeFieldsParams.builder() .jobId("job_id") .addChange(ReviewChangeFieldsParams.Change.builder() .change(ReviewChangeFieldsParams.Change.InnerChange.CORRECT) .path("/total") .build()) .revision(0L) .build(); ExtractReview extractReview = client.extract().review().changeFields(params); } } ``` #### 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 `ExtractReview extract().review().approve(ReviewApproveParamsparams, RequestOptionsrequestOptions = RequestOptions.none())` **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 - `ReviewApproveParams params` - `Optional jobId` - `Optional organizationId` - `Optional projectId` - `long revision` The review's revision as the caller last read it. - `Optional signOff` Confirm the flagged fields nobody checked as part of approving. ### Returns - `class ExtractReview:` An extract job's review: its settings, flags, field actions and decision, with the result as read and as reviewed. - `String id` Unique identifier of the review. - `double confidenceThreshold` Fields read below this confidence are flagged. - `LocalDateTime createdAt` When review was turned on. - `Optional decidedAt` When it was approved or rejected. - `Optional decidedBy` ID of the user who approved or rejected it. - `Optional decidedReason` Why it was rejected. - `FieldActions fieldActions` The latest action per field, keyed by JSON Pointer. - `Action action` confirm, correct or clear. - `CLEAR("clear")` - `CONFIRM("confirm")` - `CORRECT("correct")` - `String actorId` ID of the user who acted. - `LocalDateTime at` When they acted. - `Optional value` The corrected value, for `correct`. - `List fieldsInScope` JSON Pointers of the fields the threshold applies to; empty means all. - `List flags` Fields the review asks a person to check. - `boolean handled` Whether someone confirmed, corrected or cleared it. - `String path` JSON Pointer of the field. - `Reason reason` below_threshold, or required_empty for a required field left empty. - `BELOW_THRESHOLD("below_threshold")` - `REQUIRED_EMPTY("required_empty")` - `Optional cell` Where in a list the least confident value is. - `long row` Index of the row, from 0. - `Optional column` Property of the row, when rows are objects. - `Optional confidence` The field's confidence; for a list, its least confident value. - `String jobId` The extract job reviewed. - `List openFlags` JSON Pointers of flagged fields nobody checked. - `Optional originalResult` The result as the model read it. - `List requiredFields` JSON Pointers of fields flagged when empty. - `LocalDateTime retainUntil` When the job and its document may be deleted. - `ReviewedResult reviewedResult` The result with the field actions. - `long revision` Bumped by every change; actions name the one they saw. - `Optional sourceFileId` The file the job read, or the file behind the parse job it read; null for a URL. - `Status status` pending until approved or rejected. - `APPROVED("approved")` - `PENDING("pending")` - `REJECTED("rejected")` - `LocalDateTime updatedAt` When the review last changed. ### Example ```java package ai.llamaindex.llamacloud.example; import ai.llamaindex.llamacloud.client.LlamaCloudClient; import ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient; import ai.llamaindex.llamacloud.models.extract.review.ExtractReview; import ai.llamaindex.llamacloud.models.extract.review.ReviewApproveParams; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); ReviewApproveParams params = ReviewApproveParams.builder() .jobId("job_id") .revision(0L) .build(); ExtractReview extractReview = client.extract().review().approve(params); } } ``` #### 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 `ExtractReview extract().review().reject(ReviewRejectParamsparams, RequestOptionsrequestOptions = RequestOptions.none())` **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 - `ReviewRejectParams params` - `Optional jobId` - `Optional organizationId` - `Optional projectId` - `String reason` Why the result was rejected. - `long revision` The review's revision as the caller last read it. ### Returns - `class ExtractReview:` An extract job's review: its settings, flags, field actions and decision, with the result as read and as reviewed. - `String id` Unique identifier of the review. - `double confidenceThreshold` Fields read below this confidence are flagged. - `LocalDateTime createdAt` When review was turned on. - `Optional decidedAt` When it was approved or rejected. - `Optional decidedBy` ID of the user who approved or rejected it. - `Optional decidedReason` Why it was rejected. - `FieldActions fieldActions` The latest action per field, keyed by JSON Pointer. - `Action action` confirm, correct or clear. - `CLEAR("clear")` - `CONFIRM("confirm")` - `CORRECT("correct")` - `String actorId` ID of the user who acted. - `LocalDateTime at` When they acted. - `Optional value` The corrected value, for `correct`. - `List fieldsInScope` JSON Pointers of the fields the threshold applies to; empty means all. - `List flags` Fields the review asks a person to check. - `boolean handled` Whether someone confirmed, corrected or cleared it. - `String path` JSON Pointer of the field. - `Reason reason` below_threshold, or required_empty for a required field left empty. - `BELOW_THRESHOLD("below_threshold")` - `REQUIRED_EMPTY("required_empty")` - `Optional cell` Where in a list the least confident value is. - `long row` Index of the row, from 0. - `Optional column` Property of the row, when rows are objects. - `Optional confidence` The field's confidence; for a list, its least confident value. - `String jobId` The extract job reviewed. - `List openFlags` JSON Pointers of flagged fields nobody checked. - `Optional originalResult` The result as the model read it. - `List requiredFields` JSON Pointers of fields flagged when empty. - `LocalDateTime retainUntil` When the job and its document may be deleted. - `ReviewedResult reviewedResult` The result with the field actions. - `long revision` Bumped by every change; actions name the one they saw. - `Optional sourceFileId` The file the job read, or the file behind the parse job it read; null for a URL. - `Status status` pending until approved or rejected. - `APPROVED("approved")` - `PENDING("pending")` - `REJECTED("rejected")` - `LocalDateTime updatedAt` When the review last changed. ### Example ```java package ai.llamaindex.llamacloud.example; import ai.llamaindex.llamacloud.client.LlamaCloudClient; import ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient; import ai.llamaindex.llamacloud.models.extract.review.ExtractReview; import ai.llamaindex.llamacloud.models.extract.review.ReviewRejectParams; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); ReviewRejectParams params = ReviewRejectParams.builder() .jobId("job_id") .reason("The invoice total does not match the line items.") .revision(0L) .build(); ExtractReview extractReview = client.extract().review().reject(params); } } ``` #### 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 `ExtractReview extract().review().reopen(ReviewReopenParamsparams, RequestOptionsrequestOptions = RequestOptions.none())` **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 - `ReviewReopenParams params` - `Optional jobId` - `Optional organizationId` - `Optional projectId` - `long revision` The review's revision as the caller last read it. ### Returns - `class ExtractReview:` An extract job's review: its settings, flags, field actions and decision, with the result as read and as reviewed. - `String id` Unique identifier of the review. - `double confidenceThreshold` Fields read below this confidence are flagged. - `LocalDateTime createdAt` When review was turned on. - `Optional decidedAt` When it was approved or rejected. - `Optional decidedBy` ID of the user who approved or rejected it. - `Optional decidedReason` Why it was rejected. - `FieldActions fieldActions` The latest action per field, keyed by JSON Pointer. - `Action action` confirm, correct or clear. - `CLEAR("clear")` - `CONFIRM("confirm")` - `CORRECT("correct")` - `String actorId` ID of the user who acted. - `LocalDateTime at` When they acted. - `Optional value` The corrected value, for `correct`. - `List fieldsInScope` JSON Pointers of the fields the threshold applies to; empty means all. - `List flags` Fields the review asks a person to check. - `boolean handled` Whether someone confirmed, corrected or cleared it. - `String path` JSON Pointer of the field. - `Reason reason` below_threshold, or required_empty for a required field left empty. - `BELOW_THRESHOLD("below_threshold")` - `REQUIRED_EMPTY("required_empty")` - `Optional cell` Where in a list the least confident value is. - `long row` Index of the row, from 0. - `Optional column` Property of the row, when rows are objects. - `Optional confidence` The field's confidence; for a list, its least confident value. - `String jobId` The extract job reviewed. - `List openFlags` JSON Pointers of flagged fields nobody checked. - `Optional originalResult` The result as the model read it. - `List requiredFields` JSON Pointers of fields flagged when empty. - `LocalDateTime retainUntil` When the job and its document may be deleted. - `ReviewedResult reviewedResult` The result with the field actions. - `long revision` Bumped by every change; actions name the one they saw. - `Optional sourceFileId` The file the job read, or the file behind the parse job it read; null for a URL. - `Status status` pending until approved or rejected. - `APPROVED("approved")` - `PENDING("pending")` - `REJECTED("rejected")` - `LocalDateTime updatedAt` When the review last changed. ### Example ```java package ai.llamaindex.llamacloud.example; import ai.llamaindex.llamacloud.client.LlamaCloudClient; import ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient; import ai.llamaindex.llamacloud.models.extract.review.ExtractReview; import ai.llamaindex.llamacloud.models.extract.review.ReviewReopenParams; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); ReviewReopenParams params = ReviewReopenParams.builder() .jobId("job_id") .revision(0L) .build(); ExtractReview extractReview = client.extract().review().reopen(params); } } ``` #### 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 `ReviewListEventsPage extract().review().listEvents(ReviewListEventsParamsparams = ReviewListEventsParams.none(), RequestOptionsrequestOptions = RequestOptions.none())` **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 - `ReviewListEventsParams params` - `Optional jobId` - `Optional organizationId` - `Optional pageSize` Events per page. - `Optional pageToken` Token from the previous page. - `Optional projectId` ### Returns - `class ExtractReviewEvent:` One entry in a review's history. - `String id` Unique identifier of the entry. - `String actorId` ID of the user who acted. - `LocalDateTime createdAt` When it happened. - `Kind kind` What happened. - `APPROVED("approved")` - `CREATED("created")` - `FIELD_CLEARED("field_cleared")` - `FIELD_CONFIRMED("field_confirmed")` - `FIELD_CORRECTED("field_corrected")` - `FIELD_RESTORED("field_restored")` - `FIELD_UNDONE("field_undone")` - `FLAGS_SIGNED_OFF("flags_signed_off")` - `REJECTED("rejected")` - `REOPENED("reopened")` - `Optional detail` The settings for `created`, the reason for `rejected`, and the fields for `flags_signed_off`; null for the rest. - `class ExtractReviewCreatedDetail:` What a `created` entry records: where review was turned on, and its settings. - `double confidenceThreshold` Fields read below this confidence are flagged. - `List fieldsInScope` JSON Pointers of the fields the threshold applies to; empty means all. - `Origin origin` Turned on as the job ran, from History, by a first edit, or by the API. - `API("api")` - `EDIT("edit")` - `HISTORY("history")` - `RUN("run")` - `List requiredFields` JSON Pointers of fields flagged when empty. - `class ExtractReviewRejectedDetail:` What a `rejected` entry records. - `String reason` Why the result was rejected. - `class ExtractReviewSignedOffDetail:` What a `flags_signed_off` entry records. - `List paths` JSON Pointers of the flagged fields confirmed as part of approving. - `Optional path` JSON Pointer of the field it changed. - `Optional valueAfter` The field's value after the change. - `Optional valueBefore` The field's value before the change. ### Example ```java package ai.llamaindex.llamacloud.example; import ai.llamaindex.llamacloud.client.LlamaCloudClient; import ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient; import ai.llamaindex.llamacloud.models.extract.review.ReviewListEventsPage; import ai.llamaindex.llamacloud.models.extract.review.ReviewListEventsParams; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); ReviewListEventsPage page = client.extract().review().listEvents("job_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 - `class ExtractReview:` An extract job's review: its settings, flags, field actions and decision, with the result as read and as reviewed. - `String id` Unique identifier of the review. - `double confidenceThreshold` Fields read below this confidence are flagged. - `LocalDateTime createdAt` When review was turned on. - `Optional decidedAt` When it was approved or rejected. - `Optional decidedBy` ID of the user who approved or rejected it. - `Optional decidedReason` Why it was rejected. - `FieldActions fieldActions` The latest action per field, keyed by JSON Pointer. - `Action action` confirm, correct or clear. - `CLEAR("clear")` - `CONFIRM("confirm")` - `CORRECT("correct")` - `String actorId` ID of the user who acted. - `LocalDateTime at` When they acted. - `Optional value` The corrected value, for `correct`. - `List fieldsInScope` JSON Pointers of the fields the threshold applies to; empty means all. - `List flags` Fields the review asks a person to check. - `boolean handled` Whether someone confirmed, corrected or cleared it. - `String path` JSON Pointer of the field. - `Reason reason` below_threshold, or required_empty for a required field left empty. - `BELOW_THRESHOLD("below_threshold")` - `REQUIRED_EMPTY("required_empty")` - `Optional cell` Where in a list the least confident value is. - `long row` Index of the row, from 0. - `Optional column` Property of the row, when rows are objects. - `Optional confidence` The field's confidence; for a list, its least confident value. - `String jobId` The extract job reviewed. - `List openFlags` JSON Pointers of flagged fields nobody checked. - `Optional originalResult` The result as the model read it. - `List requiredFields` JSON Pointers of fields flagged when empty. - `LocalDateTime retainUntil` When the job and its document may be deleted. - `ReviewedResult reviewedResult` The result with the field actions. - `long revision` Bumped by every change; actions name the one they saw. - `Optional sourceFileId` The file the job read, or the file behind the parse job it read; null for a URL. - `Status status` pending until approved or rejected. - `APPROVED("approved")` - `PENDING("pending")` - `REJECTED("rejected")` - `LocalDateTime updatedAt` When the review last changed. ### Extract Review Event - `class ExtractReviewEvent:` One entry in a review's history. - `String id` Unique identifier of the entry. - `String actorId` ID of the user who acted. - `LocalDateTime createdAt` When it happened. - `Kind kind` What happened. - `APPROVED("approved")` - `CREATED("created")` - `FIELD_CLEARED("field_cleared")` - `FIELD_CONFIRMED("field_confirmed")` - `FIELD_CORRECTED("field_corrected")` - `FIELD_RESTORED("field_restored")` - `FIELD_UNDONE("field_undone")` - `FLAGS_SIGNED_OFF("flags_signed_off")` - `REJECTED("rejected")` - `REOPENED("reopened")` - `Optional detail` The settings for `created`, the reason for `rejected`, and the fields for `flags_signed_off`; null for the rest. - `class ExtractReviewCreatedDetail:` What a `created` entry records: where review was turned on, and its settings. - `double confidenceThreshold` Fields read below this confidence are flagged. - `List fieldsInScope` JSON Pointers of the fields the threshold applies to; empty means all. - `Origin origin` Turned on as the job ran, from History, by a first edit, or by the API. - `API("api")` - `EDIT("edit")` - `HISTORY("history")` - `RUN("run")` - `List requiredFields` JSON Pointers of fields flagged when empty. - `class ExtractReviewRejectedDetail:` What a `rejected` entry records. - `String reason` Why the result was rejected. - `class ExtractReviewSignedOffDetail:` What a `flags_signed_off` entry records. - `List paths` JSON Pointers of the flagged fields confirmed as part of approving. - `Optional path` JSON Pointer of the field it changed. - `Optional valueAfter` The field's value after the change. - `Optional valueBefore` The field's value before the change.