# Documentation

- [config](/docs/cli/config): Manage providers, models, and parsers.
- [extract](/docs/cli/extract): Main extraction command for Struktur CLI.
- [Fields Shorthand](/docs/cli/fields): Build schemas on the fly from the CLI using a concise field definition string.
- [CLI](/docs/cli): undefined
- [Installation & Setup](/docs/cli/installation): Install and configure Struktur.
- [parse](/docs/cli/parse): Convert files to Artifact JSON for inspection or pre-processing.
- [utils](/docs/cli/utils): Utility commands for working with artifacts.
- [verify](/docs/cli/verify): Validate artifact JSON format.
- [Enrich Records from URLs](/docs/examples/enrich-records): Fetch URLs and extract structured data to enrich existing records.
- [Extract Invoice Data](/docs/examples/extract-invoice): Extract structured invoice data from PDF or text files.
- [Extract Real Estate Listings](/docs/examples/extract-realestate): Extract property data from PDF real estate exposés.
- [Examples](/docs/examples): undefined
- [Shell Pipelines & Patterns](/docs/examples/pipelines): Practical patterns for using Struktur in shell workflows.
- [Process a Directory of Files](/docs/examples/process-directory): Batch processing with shell pipelines or scripts.
- [Watch a Folder for New Files](/docs/examples/watch-folder): Process files as they arrive in a folder.
- [Artifact Format](/docs/explanation/artifact-format): The artifact abstraction and complete specification.
- [Chunking & Token Budgets](/docs/explanation/chunking): How large documents are split and merged to fit within context windows.
- [Document Parsing](/docs/explanation/document-parsing): How Struktur converts files into Artifacts before extraction.
- [Explanation](/docs/explanation): undefined
- [Models and Providers](/docs/explanation/models-and-providers): How Struktur integrates with LLM providers through the Vercel AI SDK.
- [Extraction Lifecycle](/docs/explanation/pipeline): How data flows through Struktur from input to output.
- [Extraction Strategies](/docs/explanation/strategies): The Agent strategy uses autonomous exploration. Other strategies are available for specific use cases.
- [Validation & Retries](/docs/explanation/validation): How the schema validation loop works and why it matters.
- [What is Struktur?](/docs): All-in-one tool for structured data extraction using an autonomous agent that turns documents into validated JSON.
- [Quickstart](/docs/quickstart): Get started with Struktur in under 5 minutes. Extract structured data from any file.
- [Events & Observability](/docs/sdk/events): Event handlers for progress tracking and observability.
- [extract()](/docs/sdk/extract): Main extraction function for the TypeScript SDK.
- [SDK](/docs/sdk): undefined
- [Installation](/docs/sdk/installation): Install the Struktur TypeScript SDK.
- [parse()](/docs/sdk/parse): Load files and text into artifacts for extraction.
- [Struktur Agent Skill](/docs/skill): Install the Struktur agent skill to teach AI coding assistants how to use Struktur.
- [Installation](/docs/skill/installation): Install the Struktur agent skill for your preferred AI coding tool.
- [Usage](/docs/skill/usage): How to use the Struktur agent skill with your AI coding assistant.
- [What is an Extraction Agent?](/docs/what-is-an-extraction-agent): An extraction agent is an autonomous LLM that explores documents and decides how to extract data, rather than following a fixed extraction strategy.
- [What is Structured Data Extraction?](/docs/what-is-structured-data-extraction): Structured data extraction is the process of converting unstructured documents into validated, typed data using AI and schema validation.