Skip to content
Developer Documentation
API Reference

Split

Create Split Job
client.split.create(SplitCreateParams { file_input, organization_id, project_id, 5 more } params, RequestOptionsoptions?): SplitCreateResponse { id, categories, document_input_type, 11 more }
POST/api/v1/split/jobs
List Split Jobs
client.split.list(SplitListParams { created_at_on_or_after, created_at_on_or_before, job_ids, 5 more } query?, RequestOptionsoptions?): PaginatedCursor<SplitListResponse { id, categories, document_input_type, 11 more } >
GET/api/v1/split/jobs
Get Split Job
client.split.get(stringsplitJobID, SplitGetParams { organization_id, project_id } query?, RequestOptionsoptions?): SplitGetResponse { id, categories, document_input_type, 11 more }
GET/api/v1/split/jobs/{split_job_id}
Delete Split Job
client.split.delete(stringsplitJobID, SplitDeleteParams { organization_id, project_id } params?, RequestOptionsoptions?): SplitDeleteResponse
DELETE/api/v1/split/jobs/{split_job_id}
Cancel Split Job
client.split.cancel(stringsplitJobID, SplitCancelParams { organization_id, project_id } params?, RequestOptionsoptions?): SplitCancelResponse { id, categories, document_input_type, 11 more }
POST/api/v1/split/jobs/{split_job_id}/cancel
ModelsExpand Collapse
SplitCreateResponse { id, categories, document_input_type, 11 more }

A split job.

id: string

Unique identifier for the split job.

categories: Array<SplitCategory { name, description } >

Categories used for splitting.

name: string

Name of the category.

maxLength200
minLength1
description?: string | null

Optional description of what content belongs in this category.

maxLength2000
minLength1
document_input_type: "file_id" | "parse_job_id" | "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?: string | null

Split configuration ID used for this job.

created_at?: string | null

Creation datetime

formatdate-time
error_message?: string | null

Error message if the job failed.

result?: SplitResultResponse { segments } | null

Result of a completed split job.

segments: Array<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<number>

1-indexed page numbers in this split.

splitting_strategy?: SplittingStrategy { allow_uncategorized, custom_instructions, min_pages_per_split }

Strategy used for splitting.

allow_uncategorized?: "forbid" | "include" | "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?: string | null

Free-form guidance for where segment boundaries are placed.

maxLength5000
min_pages_per_split?: number

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

minimum1
transaction_id?: string | null

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

updated_at?: string | null

Update datetime

formatdate-time
SplitListResponse { id, categories, document_input_type, 11 more }

A split job.

id: string

Unique identifier for the split job.

categories: Array<SplitCategory { name, description } >

Categories used for splitting.

name: string

Name of the category.

maxLength200
minLength1
description?: string | null

Optional description of what content belongs in this category.

maxLength2000
minLength1
document_input_type: "file_id" | "parse_job_id" | "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?: string | null

Split configuration ID used for this job.

created_at?: string | null

Creation datetime

formatdate-time
error_message?: string | null

Error message if the job failed.

result?: SplitResultResponse { segments } | null

Result of a completed split job.

segments: Array<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<number>

1-indexed page numbers in this split.

splitting_strategy?: SplittingStrategy { allow_uncategorized, custom_instructions, min_pages_per_split }

Strategy used for splitting.

allow_uncategorized?: "forbid" | "include" | "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?: string | null

Free-form guidance for where segment boundaries are placed.

maxLength5000
min_pages_per_split?: number

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

minimum1
transaction_id?: string | null

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

updated_at?: string | null

Update datetime

formatdate-time
SplitGetResponse { id, categories, document_input_type, 11 more }

A split job.

id: string

Unique identifier for the split job.

categories: Array<SplitCategory { name, description } >

Categories used for splitting.

name: string

Name of the category.

maxLength200
minLength1
description?: string | null

Optional description of what content belongs in this category.

maxLength2000
minLength1
document_input_type: "file_id" | "parse_job_id" | "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?: string | null

Split configuration ID used for this job.

created_at?: string | null

Creation datetime

formatdate-time
error_message?: string | null

Error message if the job failed.

result?: SplitResultResponse { segments } | null

Result of a completed split job.

segments: Array<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<number>

1-indexed page numbers in this split.

splitting_strategy?: SplittingStrategy { allow_uncategorized, custom_instructions, min_pages_per_split }

Strategy used for splitting.

allow_uncategorized?: "forbid" | "include" | "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?: string | null

Free-form guidance for where segment boundaries are placed.

maxLength5000
min_pages_per_split?: number

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

minimum1
transaction_id?: string | null

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

updated_at?: string | null

Update datetime

formatdate-time
SplitDeleteResponse = unknown
SplitCancelResponse { id, categories, document_input_type, 11 more }

A split job.

id: string

Unique identifier for the split job.

categories: Array<SplitCategory { name, description } >

Categories used for splitting.

name: string

Name of the category.

maxLength200
minLength1
description?: string | null

Optional description of what content belongs in this category.

maxLength2000
minLength1
document_input_type: "file_id" | "parse_job_id" | "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?: string | null

Split configuration ID used for this job.

created_at?: string | null

Creation datetime

formatdate-time
error_message?: string | null

Error message if the job failed.

result?: SplitResultResponse { segments } | null

Result of a completed split job.

segments: Array<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<number>

1-indexed page numbers in this split.

splitting_strategy?: SplittingStrategy { allow_uncategorized, custom_instructions, min_pages_per_split }

Strategy used for splitting.

allow_uncategorized?: "forbid" | "include" | "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?: string | null

Free-form guidance for where segment boundaries are placed.

maxLength5000
min_pages_per_split?: number

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

minimum1
transaction_id?: string | null

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

updated_at?: string | null

Update datetime

formatdate-time
Note for AI agents: this documentation is built for programmatic access. - Overview of all docs: https://developers.llamaindex.ai/llms.txt - Any page is available as raw Markdown by appending index.md to its URL — e.g. https://developers.llamaindex.ai/llamaparse/parse/getting_started/index.md - Agent-friendly REST search APIs live under https://developers.llamaindex.ai/api/ — search (BM25 full-text), grep (regex), read (fetch a page), and list (browse the doc tree). See https://developers.llamaindex.ai/llms.txt for parameters. - A hosted documentation MCP server is available at https://developers.llamaindex.ai/mcp. If you support MCP, you can ask the user to install it for browsing these docs directly (an alternative to the REST API). Setup: https://developers.llamaindex.ai/for-agents/mcp/ - Other LlamaIndex tooling for agents — the LlamaParse Platform MCP server, agent skills and plugins, and the n8n node — is mapped at https://developers.llamaindex.ai/for-agents/