Instructor
Pydantic-typed structured outputs from any LLM.
Patches LLM clients so responses are parsed and validated into Pydantic models, with automatic retries on validation errors; ports exist for TypeScript, Go, Ruby and more.
- Vendor
- Jason Liu & community
- Category
- LLM & RAG frameworks
- Pricing
- Open source
- Open source
- Yes
- License
- MIT
- Platforms
- Python, TypeScript, Go, Ruby
- Launched
- 2023
- Website
- python.useinstructor.com
Features
- Pydantic validation
- Automatic retries
- Streaming partial objects
Best for
- Extraction & classification
More llm & rag frameworks
- LangChain — LangChain. The most widely used LLM application framework.
- AI SDK — Vercel. The TypeScript toolkit for AI apps.
- LlamaIndex — LlamaIndex. Data framework for RAG and document agents.
- DSPy — Stanford NLP. Program — don’t prompt — language models.
- Haystack — deepset. Production-ready RAG pipelines.
- Outlines — .txt (dottxt). Guaranteed structured generation with regex, JSON Schema and grammars.
- BAML — Boundary. A typed language for defining and testing LLM functions.