For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
GuidesAPI ReferenceChangelogModel Versioning
GuidesAPI ReferenceChangelogModel Versioning
    • Getting Started
        • Quick Start
        • Configuring an Extractor
          • Overview
          • Field Names and Prompt Crafting
          • Advanced Options
          • Latency Optimization
        • Schema
        • Output Types
        • Citations
        • Confidence Scores
        • Review Agent
      • Batch Processing
LogoLogo
On this page
  • Overview
  • Getting Started
  • Guide Structure
Core Document ProcessingExtractionBest Practices

Best Practices: Extractors

Was this page helpful?
Previous

Best Practices: Field Names and Prompt Crafting

Next
Built with

Overview

This guide provides comprehensive best practices for configuring extractors effectively in Extend. Whether you’re just getting started or optimizing advanced extraction workflows, these guidelines will help you build robust, efficient document processing solutions.

Getting Started

If you’re new to Extend, start with our Getting Started guide to understand the platform fundamentals before diving into these best practices.

Guide Structure

  1. Field Names and Prompt Crafting - Schema definition, field naming conventions, descriptions, and extraction rules
  2. Advanced Options - Extraction Light vs Performance, chunking & merging strategies
  3. Latency Optimization - Quick guide to reducing processing latency

Next: Field Names and Prompt Crafting