> ## Documentation Index
> Fetch the complete documentation index at: https://docs.reducto.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Split
> Understanding Reducto's Split endpoint
## Overview
Split is an endpoint designed for long documents with multiple sections that require different treatments or extraction schemas. It uses a natural language prompt to intelligently divide a document into meaningful page ranges. This step is typically used before extraction or after parsing to make the process more targeted and effective.
**Example Use Cases**
1. Financial 10-K Report with sections like "Business Overview," "Financial Data," and "Corporate Governance".
2. Multi-page medical record book with intake packets of several patients.
3. Employee onboarding packet with sections like policies, benefits, tax forms, and more.
## Key features
Under the hood, split runs a parsing call followed by LLM calls to determine which pages match your inputted description.
**Key Inputs:**
1. split\_description
* name: Name of the category of pages you’re trying to extract
* description: Details describing the characteristics of the pages you want
* partition\_key (optional): Identifier for splitting sections by. In the output the partition\_key will be filled in with values from the content and appended after the split\_description name
* Examples: account number, index, name, holding type. If your partition key is `account number` and the split description name is `account holdings`, then the output mappings will be `account holdings 111`, `account holdings 112`, etc.
2. split\_rules
* Optional field for changing the default rules
* Example: Each page can only be classified into a single category
**Output:**
1. splits
* List of objects with `name`, `pages`, `conf`, and `partitions` fields
* `name`: Comes from the names that are filled into for split\_description
* `pages`: Pages for this category
* `conf`: Confidence for the categorization, either "low" or "high"
* `partitions`: Either a list of objects with `name`, `conf`, and `pages` or null if `partition_key` is not defined
* `name`: The value filled in from the content
* `pages`: List of pages for this partition
* `conf`: Confidence for the categorization of this partition, either "low" or "high"
```json theme={null}
{
"result": {
"splits": [
{
"name": "account holdings", // Category name from split_descriptions
"pages": [1, 2, 3, 7, 8, 9, 10, 11], // All the pages that this category is on (1-indexed)
"conf": "high", // "low" or "high" confidence
"partitions": [
{
"name": "1111", // partition value that was filled in
"conf": "high", // "low" or "high" confidence
"pages": [1, 2, 3] // pages of this specific partition
},
{
"name": "2222",
"conf": "high",
"pages": [7, 8, 9, 10, 11]
}
]
}
]
}
}
```
The default split\_rules only allows overlap for sections at the first and last pages.
## Pipelining with Split
Split is powerful when used in conjunction with other endpoints, specifically extraction. When you have a long document with each subsection needing a different schema, splitting helps you break up the document into logically grouped subsets. This process is known as pipelining.
### Sample scenarios
### Scenario 1:
#### You have a long document and the information that you plan to Extract is only on some subset of the pages.
1. Run /parse on the file and get the parse job id.
2. Run /split on the parse output (feed in the parse job id).
Example config:
```json theme={null}
{
"document_url": "jobid://{parse_job_id}",
"split_description": [
{
"name": "Clinical Scenarios",
"description": "Pages of the Clinical Scenarios"
},
{
"name": "Recommendation",
"description": "Page that includes the recommendation at the top of the page"
}
]
}
```
Example response:
```json theme={null}
{
"usage": {
"num_pages": 20
},
"result": {
"splits": [
{
"name": "Clinical Scenarios",
"pages": [
1,
2,
3
],
"conf": "high",
"partitions": null
},
{
"name": "Recommendation",
"pages": [
1
],
"conf": "high",
"partitions": null
}
]
}
}
```
```json theme={null}
{
"usage": {
"num_pages": 20
},
"result": {
"section_mapping": {
"Clinical Scenarios": [
1,
2,
3
],
"Recommendation": [
1
]
},
"splits": [
{
"name": "Clinical Scenarios",
"pages": [
1,
2,
3
],
"conf": "high",
"partitions": null
},
{
"name": "Recommendation",
"pages": [
1
],
"conf": "high",
"partitions": null
}
]
}
}
```
3. Run /extract on the parse output using the same document\_url you sent into split. Set the page range as the pages returned from split:
```json theme={null}
{
"document_url": "jobid://{parse_job_id}",
"advanced_options":
{ "page_range": [
{
"start": 1,
"end": 2
}
] },
"schema": extract_schema
}
```
### Scenario 2:
#### You have a long document with information that can be clearly broken down into subsections.
An example of this would be a financial statement with multiple accounts. Each account will have a unique account number. Consider the following schema:
```json theme={null}
{
"type": "object",
"properties": {
"acct_holdings": {
"type": "array",
"items": {
"type": "object",
"properties": {
"price": {
"type": "number",
"description": "The price of the holding per unit."
},
"quantity": {
"type": "number",
"description": "The quantity of the holding"
},
"ticker": {
"type": "string",
"description": "The ticker of the holding."
},
"category": {
"type": "string",
"description": "The category of the holding, such as equity, fixed income, or cash."
},
"acct_number": {
"type": "string",
"description": "The unique number for the account."
}
}
},
"description": "A list of holdings across all the accounts."
}
}
}
```
The schema is extracting the holdings. So we can make a split request to get the holdings for each account. From the schema description, it’s clear that the acct\_number is a unique field. By setting the account number as the partition key, we will get the account holdings returned in multiple sections where each section has a different account number. If the partition key is not set in this case, all of the account holdings would be returned in a single array.
Example config:
```json theme={null}
"split_description": [
{
"name": "account holdings",
"description": "Pages for each separate account holdings",
"partition_key": "account number"
}
],
"split_rules": "Split the document into the applicable sections"
```
Example response:
```json theme={null}
{
"usage": {
"num_pages": 58
},
"result": {
"splits": [
{
"name": "account holdings",
"pages": [1, 2, 3, 7, 8, 9, 10, 11, 12, 19, 20, 21, 22, 23, 24],
"conf": "high",
"partitions": [
{
"name": "1111",
"conf": "high",
"pages": [1, 2, 3]
},
{
"name": "2222",
"conf": "high",
"pages": [7, 8, 9, 10, 11, 12]
},
{
"name": "3333",
"conf": "high",
"pages": [19, 20, 21, 22, 23, 24]
}
]
}
]
}
}
```
```json theme={null}
{
"usage": {
"num_pages": 58
},
"result": {
"section_mapping": {
"account holdings 1111": [
1,
2,
3
],
"account holdings 2222": [
7,
8,
9,
10,
11,
12
],
"account holdings 3333": [
19,
20,
21,
22,
23,
24
]
},
"splits": [
{
"name": "account holdings",
"pages": [1, 2, 3, 7, 8, 9, 10, 11, 12, 19, 20, 21, 22, 23, 24],
"conf": "high",
"partitions": [
{
"name": "1111",
"conf": "high",
"pages": [1, 2, 3]
},
{
"name": "2222",
"conf": "high",
"pages": [7, 8, 9, 10, 11, 12]
},
{
"name": "3333",
"conf": "high",
"pages": [19, 20, 21, 22, 23, 24]
}
]
}
]
}
}
```
You can then run extract on each subset of the pages. The “acct\_holdings” can be concatenated across the extract calls since its an array.