Skip to content
LlamaIndex API Docs
Get started
API Reference
Beta
Split

Create Split Job

beta.split.create(SplitCreateParams**kwargs) -> SplitCreateResponse
POST/api/v1/beta/split/jobs

Create a document split job. Experimental: This endpoint is not yet ready for production use and is subject to change at any time.

ParametersExpand Collapse

Categories to split the document into.

name: str

Name of the category.

maxLength200
minLength1
description: Optional[str]

Optional description of what content belongs in this category.

maxLength2000
minLength1
document_input: SplitDocumentInputParam

Document to be split.

type: str

Type of document input. Valid values are: file_id

value: str

Document identifier.

organization_id: Optional[str]
project_id: Optional[str]
splitting_strategy: Optional[SplittingStrategy]

Strategy for splitting the document.

allow_uncategorized: Optional[bool]

Whether to allow pages that don't match any category to be grouped as 'uncategorized'. If False, all pages must be assigned to a defined category.

ReturnsExpand Collapse
class SplitCreateResponse: …

A document split job.

id: str

Unique identifier for the split job.

categories: List[SplitCategory]

Categories used for splitting.

name: str

Name of the category.

maxLength200
minLength1
description: Optional[str]

Optional description of what content belongs in this category.

maxLength2000
minLength1
document_input: SplitDocumentInput

Document that was split.

type: str

Type of document input. Valid values are: file_id

value: str

Document identifier.

project_id: str

Project ID this job belongs to.

status: str

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

user_id: str

User ID who created this job.

created_at: Optional[datetime]

Creation datetime

formatdate-time
error_message: Optional[str]

Error message if the job failed.

result: Optional[SplitResultResponse]

Result of a completed split job.

segments: List[SplitSegmentResponse]

List of document segments.

category: str

Category name this split belongs to.

confidence_category: str

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

pages: List[int]

1-indexed page numbers in this split.

updated_at: Optional[datetime]

Update datetime

formatdate-time

Create Split Job

import os
from llama_cloud import LlamaCloud

client = LlamaCloud(
    api_key=os.environ.get("LLAMA_CLOUD_API_KEY"),  # This is the default and can be omitted
)
split = client.beta.split.create(
    categories=[{
        "name": "x"
    }],
    document_input={
        "type": "type",
        "value": "value",
    },
)
print(split.id)
{
  "id": "id",
  "categories": [
    {
      "name": "x",
      "description": "x"
    }
  ],
  "document_input": {
    "type": "type",
    "value": "value"
  },
  "project_id": "project_id",
  "status": "status",
  "user_id": "user_id",
  "created_at": "2019-12-27T18:11:19.117Z",
  "error_message": "error_message",
  "result": {
    "segments": [
      {
        "category": "category",
        "confidence_category": "confidence_category",
        "pages": [
          0
        ]
      }
    ]
  },
  "updated_at": "2019-12-27T18:11:19.117Z"
}
Returns Examples
{
  "id": "id",
  "categories": [
    {
      "name": "x",
      "description": "x"
    }
  ],
  "document_input": {
    "type": "type",
    "value": "value"
  },
  "project_id": "project_id",
  "status": "status",
  "user_id": "user_id",
  "created_at": "2019-12-27T18:11:19.117Z",
  "error_message": "error_message",
  "result": {
    "segments": [
      {
        "category": "category",
        "confidence_category": "confidence_category",
        "pages": [
          0
        ]
      }
    ]
  },
  "updated_at": "2019-12-27T18:11:19.117Z"
}