Explanation
Deep dives into Struktur's architecture, strategies, and design decisions.
The Extraction Pipeline
How data flows through Struktur from input to output
Models and Providers
Supported LLM providers and how to add new ones
Artifact Format
The artifact JSON structure
Document Parsing
How files are converted to artifacts
Extraction Strategies
Built-in strategies overview and how to choose
Chunking & Token Budgets
Token-aware document splitting
Validation & Retries
Schema validation and retry logic