Skip to content

Split

Create Split Job
SplitCreateResponse Beta.Split.Create(SplitCreateParamsparameters, CancellationTokencancellationToken = default)
POST/api/v1/beta/split/jobs
List Split Jobs
SplitListPageResponse Beta.Split.List(SplitListParams?parameters, CancellationTokencancellationToken = default)
GET/api/v1/beta/split/jobs
Get Split Job
SplitGetResponse Beta.Split.Get(SplitGetParamsparameters, CancellationTokencancellationToken = default)
GET/api/v1/beta/split/jobs/{split_job_id}
ModelsExpand Collapse
class SplitCategory:

Category definition for document splitting.

required string Name

Name of the category.

maxLength200
minLength1
string? Description

Optional description of what content belongs in this category.

maxLength2000
minLength1
class SplitDocumentInput:

Document input specification for beta API.

required string Type

Type of document input. Valid values are: file_id

required string Value

Document identifier.

class SplitResultResponse:

Result of a completed split job.

required IReadOnlyList<SplitSegmentResponse> Segments

List of document segments.

required string Category

Category name this split belongs to.

required string ConfidenceCategory

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

required IReadOnlyList<Long> Pages

1-indexed page numbers in this split.

class SplitSegmentResponse:

A segment of the split document.

required string Category

Category name this split belongs to.

required string ConfidenceCategory

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

required IReadOnlyList<Long> Pages

1-indexed page numbers in this split.

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/