API Reference

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Split

Create Split Job

POST/api/v1/split/jobs

List Split Jobs

GET/api/v1/split/jobs

Get Split Job

GET/api/v1/split/jobs/{split_job_id}

Delete Split Job

DELETE/api/v1/split/jobs/{split_job_id}

Cancel Split Job

POST/api/v1/split/jobs/{split_job_id}/cancel

ModelsExpand Collapse

SplitCreateResponse object { id, categories, document_input_type, 11 more }

A split job.

id: string

Unique identifier for the split job.

categories: array of SplitCategory { name, description }

Categories used for splitting.

name: string

Name of the category.

maxLength200

minLength1

description: optional string

Optional description of what content belongs in this category.

maxLength2000

minLength1

document_input_type: "file_id" or "parse_job_id" or "url"

Whether the input was a file or parse job

One of the following:

"file_id"

"parse_job_id"

"url"

file_input: string

File ID or parse job ID

project_id: string

Project this job belongs to.

status: string

Current job status. Valid values are: pending, processing, completed, failed, cancelled.

user_id: string

User who created this job.

configuration_id: optional string

Split configuration ID used for this job.

created_at: optional string

Creation datetime

formatdate-time

error_message: optional string

Error message if the job failed.

result: optional SplitResultResponse { segments }

Result of a completed split job.

segments: array of SplitSegmentResponse { category, confidence_category, pages }

List of document segments.

category: string

Category name this split belongs to.

confidence_category: string

Categorical confidence level. Valid values are: high, medium, low.

pages: array of number

1-indexed page numbers in this split.

splitting_strategy: optional object { allow_uncategorized, custom_instructions, min_pages_per_split }

Strategy used for splitting.

allow_uncategorized: optional "forbid" or "include" or "omit"

Controls handling of pages that don’t match any category. ‘include’: pages can be grouped as ‘uncategorized’ and included in results. ‘forbid’: all pages must be assigned to a defined category. ‘omit’: pages can be classified as ‘uncategorized’ but are excluded from results.

One of the following:

"forbid"

"include"

"omit"

custom_instructions: optional string

Free-form guidance for where segment boundaries are placed.

maxLength5000

min_pages_per_split: optional number

Minimum pages per segment. Shorter segments are merged into an adjacent segment; 1 disables merging.

minimum1

transaction_id: optional string

Idempotency key scoped to the project, if one was provided.

updated_at: optional string

Update datetime

formatdate-time

SplitListResponse object { id, categories, document_input_type, 11 more }

A split job.

id: string

Unique identifier for the split job.

categories: array of SplitCategory { name, description }

Categories used for splitting.

name: string

Name of the category.

maxLength200

minLength1

description: optional string

Optional description of what content belongs in this category.

maxLength2000

minLength1

document_input_type: "file_id" or "parse_job_id" or "url"

Whether the input was a file or parse job

One of the following:

"file_id"

"parse_job_id"

"url"

file_input: string

File ID or parse job ID

project_id: string

Project this job belongs to.

status: string

Current job status. Valid values are: pending, processing, completed, failed, cancelled.

user_id: string

User who created this job.

configuration_id: optional string

Split configuration ID used for this job.

created_at: optional string

Creation datetime

formatdate-time

error_message: optional string

Error message if the job failed.

result: optional SplitResultResponse { segments }

Result of a completed split job.

segments: array of SplitSegmentResponse { category, confidence_category, pages }

List of document segments.

category: string

Category name this split belongs to.

confidence_category: string

Categorical confidence level. Valid values are: high, medium, low.

pages: array of number

1-indexed page numbers in this split.

splitting_strategy: optional object { allow_uncategorized, custom_instructions, min_pages_per_split }

Strategy used for splitting.

allow_uncategorized: optional "forbid" or "include" or "omit"

Controls handling of pages that don’t match any category. ‘include’: pages can be grouped as ‘uncategorized’ and included in results. ‘forbid’: all pages must be assigned to a defined category. ‘omit’: pages can be classified as ‘uncategorized’ but are excluded from results.

One of the following:

"forbid"

"include"

"omit"

custom_instructions: optional string

Free-form guidance for where segment boundaries are placed.

maxLength5000

min_pages_per_split: optional number

Minimum pages per segment. Shorter segments are merged into an adjacent segment; 1 disables merging.

minimum1

transaction_id: optional string

Idempotency key scoped to the project, if one was provided.

updated_at: optional string

Update datetime

formatdate-time

SplitGetResponse object { id, categories, document_input_type, 11 more }

A split job.

id: string

Unique identifier for the split job.

categories: array of SplitCategory { name, description }

Categories used for splitting.

name: string

Name of the category.

maxLength200

minLength1

description: optional string

Optional description of what content belongs in this category.

maxLength2000

minLength1

document_input_type: "file_id" or "parse_job_id" or "url"

Whether the input was a file or parse job

One of the following:

"file_id"

"parse_job_id"

"url"

file_input: string

File ID or parse job ID

project_id: string

Project this job belongs to.

status: string

Current job status. Valid values are: pending, processing, completed, failed, cancelled.

user_id: string

User who created this job.

configuration_id: optional string

Split configuration ID used for this job.

created_at: optional string

Creation datetime

formatdate-time

error_message: optional string

Error message if the job failed.

result: optional SplitResultResponse { segments }

Result of a completed split job.

segments: array of SplitSegmentResponse { category, confidence_category, pages }

List of document segments.

category: string

Category name this split belongs to.

confidence_category: string

Categorical confidence level. Valid values are: high, medium, low.

pages: array of number

1-indexed page numbers in this split.

splitting_strategy: optional object { allow_uncategorized, custom_instructions, min_pages_per_split }

Strategy used for splitting.

allow_uncategorized: optional "forbid" or "include" or "omit"

Controls handling of pages that don’t match any category. ‘include’: pages can be grouped as ‘uncategorized’ and included in results. ‘forbid’: all pages must be assigned to a defined category. ‘omit’: pages can be classified as ‘uncategorized’ but are excluded from results.

One of the following:

"forbid"

"include"

"omit"

custom_instructions: optional string

Free-form guidance for where segment boundaries are placed.

maxLength5000

min_pages_per_split: optional number

Minimum pages per segment. Shorter segments are merged into an adjacent segment; 1 disables merging.

minimum1

transaction_id: optional string

Idempotency key scoped to the project, if one was provided.

updated_at: optional string

Update datetime

formatdate-time

SplitDeleteResponse = unknown

SplitCancelResponse object { id, categories, document_input_type, 11 more }

A split job.

id: string

Unique identifier for the split job.

categories: array of SplitCategory { name, description }

Categories used for splitting.

name: string

Name of the category.

maxLength200

minLength1

description: optional string

Optional description of what content belongs in this category.

maxLength2000

minLength1

document_input_type: "file_id" or "parse_job_id" or "url"

Whether the input was a file or parse job

One of the following:

"file_id"

"parse_job_id"

"url"

file_input: string

File ID or parse job ID

project_id: string

Project this job belongs to.

status: string

Current job status. Valid values are: pending, processing, completed, failed, cancelled.

user_id: string

User who created this job.

configuration_id: optional string

Split configuration ID used for this job.

created_at: optional string

Creation datetime

formatdate-time

error_message: optional string

Error message if the job failed.

result: optional SplitResultResponse { segments }

Result of a completed split job.

segments: array of SplitSegmentResponse { category, confidence_category, pages }

List of document segments.

category: string

Category name this split belongs to.

confidence_category: string

Categorical confidence level. Valid values are: high, medium, low.

pages: array of number

1-indexed page numbers in this split.

splitting_strategy: optional object { allow_uncategorized, custom_instructions, min_pages_per_split }

Strategy used for splitting.

allow_uncategorized: optional "forbid" or "include" or "omit"

Controls handling of pages that don’t match any category. ‘include’: pages can be grouped as ‘uncategorized’ and included in results. ‘forbid’: all pages must be assigned to a defined category. ‘omit’: pages can be classified as ‘uncategorized’ but are excluded from results.

One of the following:

"forbid"

"include"

"omit"

custom_instructions: optional string

Free-form guidance for where segment boundaries are placed.

maxLength5000

min_pages_per_split: optional number

Minimum pages per segment. Shorter segments are merged into an adjacent segment; 1 disables merging.

minimum1

transaction_id: optional string

Idempotency key scoped to the project, if one was provided.

updated_at: optional string

Update datetime

formatdate-time