Split a multi-page document into labeled subdocuments and return the canonical split resource. This endpoint is split-only: key-based grouping belongs toDocumentation Index
Fetch the complete documentation index at: https://docs.retab.com/llms.txt
Use this file to discover all available pages before exploring further.
/v1/partitions.
name, optional description, and allow_multiple_instances.8.true, bypass the cache and force a fresh split run.id, filename, mime_type.Canonical split request — subdocuments must be CreateSplitSubdocument (extra='forbid').
The subdocuments field below intentionally narrows the parent's list[Subdocument]
to list[CreateSplitSubdocument] so that legacy-only fields (e.g. partition_key)
are rejected. The override is annotated with the parent type to keep pyright happy
while a field_validator enforces the stricter shape at runtime.
The document to split
The subdocuments to split the document into
1The model to use to split the document
Free-form instructions appended to the system prompt to steer the split.
Number of consensus split runs to perform. Uses deterministic single-pass when set to 1.
1 <= x <= 8If true, skip the LLM cache and force a fresh completion
Successful Response
Backend-internal split with organization scoping.
Information about the split file
Model used for the split operation
Subdocuments used for the split operation
The list of document splits with their assigned pages
Unique identifier of the split
Number of consensus votes used
Free-form instructions supplied with the split request.
Consensus metadata for multi-vote split runs
Origin of the split request
Usage information for the split operation