prompt-engineering-instructor

Topics in the source

• Instructor: Structured LLM Outputs
• When to Use This Skill
• Installation
• Quick Start
• Basic Example: Extract User Data
• With OpenAI
• Core Concepts
• 1. Response Models (Pydantic)

Use Instructor when you need to: Extract structured data from LLM responses reliably Validate outputs against Pydantic schemas automatically Retry failed extractions with automatic error handling Parse complex JSON with type safety and validation Stream partial results for real-time processing Support multiple LLM providers with consistent API GitHub Stars: 15,000+ | Battle-tested: 100,000+ developers Response models define the structure and validation rules for LLM outputs. Benefits: Type safety with Python type hints Automatic validation (wordcount > 0) Self-documenting with Field descriptions IDE autocomplete support Pydantic validates LLM outputs automatically. If validation fails, Instructor retries. Instructor retries automatically when validation fails, providing error feedback to the LLM. How it works: 1. LLM generates output 2. Pydantic validates 3. If invalid: Error message sent back to LLM 4. LLM tries again with error feedback 5. Repeats up to maxretries Stream partial results for real-time processing. | Feature | Instructor | Manual JSON | LangChain | DSPy | |---------|------------|-------------|-----------|------| | Type Safety | ✅ Yes | ❌ No | ⚠️ Partial | ✅ Yes | |

This is an excerpt. Refer to the complete source and its current requirements.