Instructor: Extract Structured Data From Any LLM With Pydantic

pip install instructor

import instructor
from openai import OpenAI
from pydantic import BaseModel

client = instructor.from_openai(OpenAI())

class Person(BaseModel):
    name: str
    age: int
    email: str | None = None

person = client.chat.completions.create(
    model="gpt-4o-mini",
    response_model=Person,
    messages=[{"role": "user", "content": "John Doe is 34 and works at john@acme.com"}],
)
print(person)  # Person(name='John Doe', age=34, email='john@acme.com')

from pydantic import field_validator

class CVData(BaseModel):
    name: str
    years_experience: int
    skills: list[str]

    @field_validator("years_experience")
    @classmethod
    def must_be_positive(cls, v: int) -> int:
        if v < 0:
            raise ValueError("years_experience must be non-negative")
        return v

cv = client.chat.completions.create(
    model="gpt-4o-mini",
    response_model=CVData,
    messages=[{"role": "user", "content": "Jane has 5 years exp in Python, SQL, and ML."}],
    max_retries=3,
)

pip install instructor anthropic

import anthropic
import instructor

client = instructor.from_anthropic(anthropic.Anthropic())
# Same API  -  response_model works identically

for partial_person in client.chat.completions.create_partial(
    model="gpt-4o-mini",
    response_model=Person,
    messages=[{"role": "user", "content": "Alice is 28, alice@example.com"}],
):
    print(partial_person)  # name='Alice' age=None email=None → ... → fully populated

class SearchQuery(BaseModel):
    intent: str
    keywords: list[str]
    date_range: str | None = None
    max_results: int = 10

query = client.chat.completions.create(
    model="gpt-4o-mini",
    response_model=SearchQuery,
    messages=[{"role": "user", "content": "Find Python ML papers from last year, top 5"}],
)
# SearchQuery(intent='research', keywords=['Python', 'ML'], date_range='last year', max_results=5)