instructor - Generate validated structured LLM outputs
Extracts, validates, retries, and streams structured LLM outputs using Pydantic response models.
Tags
Updated: 2026-10-02Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Extract structured data
- Validate outputs with Pydantic
- Retry validation failures
- Parse typed JSON
- Stream partial results
- Support multiple LLM providers
Inputs
- Source text or prompt
- Pydantic response model
- Provider credentials
- Model configuration
Outputs
- Validated structured data
- Validation error feedback
- Retried extraction results
- Partial streamed results
Requirements
- instructor package
- pydantic package
- openai package
- anthropic package
- Linux, macOS, or Windows
- Provider access credentials