Overview of Split
Introduction to the Split API, a tool for automatically segmenting concatenated PDFs into logical document sections based on content categories.
Overview
Section titled “Overview”The Split API provides a simple way to automatically segment concatenated PDFs into logical document sections based on content categories. Using AI-powered classification, it analyzes each page’s content, classifies pages into user-defined categories, and detects where one document ends and the next begins—so adjacent segments may share a category.
Split is currently in beta and is subject to breaking changes.
Is Split right for me?
Section titled “Is Split right for me?”Split is a great fit when you need:
- Document separation: Automatically separate bundled documents (e.g., a collection of reports, research papers, or contracts) before further processing
- Content organization: Categorize and organize mixed document collections by type
- Pre-processing for extraction: Identify different document types within a single file before running targeted extraction with LlamaExtract
- Flexible categorization: Define any categories relevant to your use case with natural-language descriptions
Key Features
Section titled “Key Features”- AI-powered classification: Uses LLMs to understand page content and assign categories
- Flexible categories: Define any categories relevant to your use case
- Confidence scoring: Each segment includes a confidence level (high, medium, low)
- Page-level granularity: Results include exact page numbers for each segment
- Uncategorized handling: Optionally capture pages that don’t match any defined category
- Custom instructions: Steer boundary and classification decisions with free-form guidance
Quick Start
Section titled “Quick Start”Get an API key
Section titled “Get an API key”First, get an API key to use the Split API.
API/SDK Usage
Section titled “API/SDK Usage”Check out the Getting Started guide for a complete walkthrough.
Typical Flow
Section titled “Typical Flow”- Upload your PDF to LlamaCloud using the Files API
- Define categories with names and natural-language descriptions
- Create a split job with your file and categories
- Poll for completion until the job finishes
- Retrieve results with segments, page ranges, and confidence scores
Pricing
Section titled “Pricing”See Pricing for credit rates and billing details.
API Reference
Section titled “API Reference”- Create Split Job:
POST /api/v1/beta/split/jobs - Get Split Job:
GET /api/v1/beta/split/jobs/{job_id} - List Split Jobs:
GET /api/v1/beta/split/jobs
For the complete API reference, see our API documentation.