Structured Outputs by Example Star on GitHub
Stay updated when new content is added and get tips from the Instructor team
Getting Started

Your First Extraction

Edit

Extract structured data from text using Instructor and a Pydantic model.
from pydantic import BaseModel

class Person(BaseModel):
    name: str
    age: int

import instructor
from openai import OpenAI

Patch the client
client = instructor.from_openai(OpenAI())

Extract structured data
person = client.chat.completions.create(
    model="gpt-3.5-turbo",
    response_model=Person,
    messages=[
        {"role": "user", "content": "John Doe is 30 years old"}
    ]
)

print(f"Name: {person.name}, Age: {person.age}")

Running the Example

First, install Instructor and any dependencies
$ pip install instructor pydantic
Run the Python script
$ python first-extraction.py

Further Information