Should I Be Using Structured Outputs?¶

import openai
from pydantic import BaseModel, field_validator


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

    @field_validator("name")
    def ensure_uppercase(cls, v: str) -> str:
        if not v.isupper():
            raise ValueError("All letters must be uppercase. Got: " + v)
        return v


client = openai.OpenAI()
try:
    resp = client.beta.chat.completions.parse(
        response_format=User,
        messages=[
            {
                "role": "user",
                "content": "Extract the following user: Jason is 25 years old.",
            },
        ],
        model="gpt-4o-mini",
    )
except Exception as e:
    print(e)
    """
    1 validation error for User
    name
      Value error, All letters must be uppercase. Got: Jason [type=value_error, input_value='Jason', input_type=str]
        For further information visit https://errors.pydantic.dev/2.8/v/value_error
    """

import openai
from pydantic import BaseModel


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


client = openai.OpenAI()
with client.beta.chat.completions.stream(
    response_format=User,
    messages=[
        {
            "role": "user",
            "content": "Extract the following user: Jason is 25 years old.",
        },
    ],
    model="gpt-4o-mini",
) as stream:
    for event in stream:
        if event.type == "content.delta":
            print(event.snapshot, flush=True, end="\n")
            #>
            #> {"
            #> {"name
            #> {"name":"
            #> {"name":"Jason
            #> {"name":"Jason","
            #> {"name":"Jason","age
            #> {"name":"Jason","age":
            #> {"name":"Jason","age":25
            #> {"name":"Jason","age":25}

import instructor
import openai
from pydantic import BaseModel, field_validator


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

    @field_validator("name")
    def ensure_uppercase(cls, v: str) -> str:
        if not v.isupper():
            raise ValueError("All letters must be uppercase. Got: " + v)
        return v


client = instructor.from_openai(openai.OpenAI(), mode=instructor.Mode.TOOLS_STRICT)

resp = client.chat.completions.create(
    response_model=User,
    messages=[
        {
            "role": "user",
            "content": "Extract the following user: Jason is 25 years old.",
        }
    ],
    model="gpt-4o-mini",
)

print(resp)
#> name='JASON' age=25

import instructor
import openai
from pydantic import BaseModel

client = instructor.from_openai(openai.OpenAI(), mode=instructor.Mode.TOOLS_STRICT)


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


users = client.chat.completions.create_iterable(
    model="gpt-4o-mini",
    response_model=User,
    messages=[
        {
            "role": "system",
            "content": "You are a perfect entity extraction system",
        },
        {
            "role": "user",
            "content": (f"Extract `Jason is 10 and John is 10`"),
        },
    ],
)

for user in users:
    print(user)
    #> name='Jason' age=10
    #> name='John' age=10

import instructor
from openai import OpenAI
from pydantic import BaseModel
from rich.console import Console

client = instructor.from_openai(OpenAI(), mode=instructor.Mode.TOOLS_STRICT)

text_block = """
In our recent online meeting, participants from various backgrounds joined to discuss the upcoming tech conference. The names and contact details of the participants were as follows:

- Name: John Doe, Email: [email protected], Twitter: @TechGuru44
- Name: Jane Smith, Email: [email protected], Twitter: @DigitalDiva88
- Name: Alex Johnson, Email: [email protected], Twitter: @CodeMaster2023

During the meeting, we agreed on several key points. The conference will be held on March 15th, 2024, at the Grand Tech Arena located at 4521 Innovation Drive. Dr. Emily Johnson, a renowned AI researcher, will be our keynote speaker.

The budget for the event is set at $50,000, covering venue costs, speaker fees, and promotional activities. Each participant is expected to contribute an article to the conference blog by February 20th.

A follow-up meeting is scheduled for January 25th at 3 PM GMT to finalize the agenda and confirm the list of speakers.
"""


class User(BaseModel):
    name: str
    email: str
    twitter: str


class MeetingInfo(BaseModel):
    users: list[User]
    date: str
    location: str
    budget: int
    deadline: str


extraction_stream = client.chat.completions.create_partial(
    model="gpt-4o-mini",
    response_model=MeetingInfo,
    messages=[
        {
            "role": "user",
            "content": f"Get the information about the meeting and the users {text_block}",
        },
    ],
    stream=True,
)


console = Console()

for extraction in extraction_stream:
    obj = extraction.model_dump()
    console.clear()
    console.print(obj)

import instructor
from openai import OpenAI
from pydantic import BaseModel

client = instructor.from_openai(OpenAI())


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


resp = client.chat.completions.create(
    model="gpt-4o-mini",
    response_model=User,
    messages=[
        {
            "role": "user",
            "content": "Extract the user from the string belo - Chris is a 27 year old engineer in San Francisco",
        }
    ],
    max_tokens=100,
)

print(resp)
#> name='Chris' age=27

import instructor
from anthropic import Anthropic  # (1)!
from pydantic import BaseModel

client = instructor.from_anthropic(Anthropic())  # (2)!


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


resp = client.chat.completions.create(
    model="claude-3-5-sonnet-20240620",  # (3)!
    response_model=User,
    messages=[
        {
            "role": "user",
            "content": "Extract the user from the string belo - Chris is a 27 year old engineer in San Francisco",
        }
    ],
    max_tokens=100,
)

print(resp)
#> name='Chris' age=27