Skip to main content

Instructor

Structured LLM outputs with Pydantic — type-safe data extraction from any language model

LLM FrameworksFree

Instructor is a Python library that makes it trivially easy to get structured, validated data from LLMs using Pydantic models. Define a Pydantic class, pass it to `instructor.patch(client)`, and your LLM calls return typed Python objects — not raw strings. Supports OpenAI, Anthropic, Google, Cohere, Mistral, and local models. 9K+ GitHub stars.

Key specs
9,000 GitHub stars source
as of 2026-03-27
Loading…

FAQ

Alternatives

Integrations

None listed.

Built on

None listed.