Unstructured home page

Contact Us
Unstructured-IO/unstructured
Unstructured-IO/unstructured

Getting Started

Unstructured Open Source Library
Installation
Quick Start

Core Functionality

Overview
Partitioning
Cleaning
Extracting
Staging
Chunking
Embedding

Ingest

Overview
Source Connectors
Destination Connectors
Ingest Configuration

Examples

Overview
Data Processing into Vector Database
Delta Table Source Connector
Multi-files API Processing

Integrations

Overview

Concepts

Document elements and metadata
Partitioning strategies
Glossary

Best Practices

Overview
Models
Table Extraction from PDF

Best Practices

Best Practices

Unstructured offers a few strategies and models to extract document information. These best practices are intended to provide guidelines to configure the strategy and model configurations to optimize document information extraction.

High-level overview of available strategies and models in Unstructured library: strategy

strategy

Was this page helpful?

Glossary Models

twitter linkedin

Powered by Mintlify

Assistant

Responses are generated using AI and may contain mistakes.