OpenAI API 结构化输出手把手实践

# List of hotel reviews
reviews = [
   "The room was clean and the staff was friendly.",
   "The location was terrible and the service was slow.",
   "The food was amazing but the room was too small.",
]
# Classify sentiment for each review and print the results
for review in reviews:
   sentiment = classify_sentiment(review)
   print(f"Review: {review}\nSentiment: {sentiment}\n")

output：
Review: The room was clean and the staff was friendly.
Sentiment: Positive
Review: The location was terrible and the service was slow.
Sentiment: Negative
Review: The food was amazing but the room was too small.
Sentiment: The sentiment of the review is neutral.

def classify_sentiment_with_structured_outputs(review):
   """Sentiment classifier with Structured Outputs"""
   ...
# Classify sentiment for each review with Structured Outputs
for review in reviews:
   sentiment = classify_sentiment_with_structured_outputs(review)
   print(f"Review: {review}\nSentiment: {sentiment}\n")

output:
Review: The room was clean and the staff was friendly.
Sentiment: {"sentiment":"positive"}
Review: The location was terrible and the service was slow.
Sentiment: {"sentiment":"negative"}
Review: The food was amazing but the room was too small.
Sentiment: {"sentiment":"neutral"}

from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
   model="gpt-4o-mini",
   messages=[
       {"role": "system", "content": "You are a helpful assistant."},
       {"role": "user", "content": "Say hello!"}
   ],
   max_tokens=5
)
>>> print(response.choices[0].message.content.strip())
Hello! How can I

from pydantic import BaseModel
from typing import Literal
class SentimentResponse(BaseModel):
   sentiment: Literal["positive", "negative", "neutral"]

response = client.beta.chat.completions.parse(
   model=MODEL,
   messages=[...],
   response_format=SentimentResponse
)

from openai import OpenAI
from pydantic import BaseModel
from typing import Literal
class SentimentResponse(BaseModel):
   sentiment: Literal["positive", "negative", "neutral"]
client = OpenAI()
MODEL = "gpt-4o-mini"
SYSTEM_PROMPT = "You are a sentiment classifier assistant."
PROMPT_TEMPLATE = """
   Classify the sentiment of the following hotel review as positive, negative, or neutral:\n\n{review}
"""

# Function to classify sentiment using OpenAI's chat completions API with structured outputs
def classify_sentiment_with_structured_outputs(review):
   response = client.beta.chat.completions.parse(
       model=MODEL,
       messages=[
           {"role": "system", "content": SYSTEM_PROMPT},
           {"role": "user", "content": PROMPT_TEMPLATE.format(review=review)},
       ],
       response_format=SentimentResponse
   )
   return response.choices[0].message

# List of hotel reviews
reviews = [
   "The room was clean and the staff was friendly.",
   "The location was terrible and the service was slow.",
   "The food was amazing but the room was too small.",
]
result = classify_sentiment_with_structured_outputs(reviews[0])
>>> print(result.content)
{"sentiment":"positive"}

这result是一个消息对象：

>>> type(result)
openai.types.chat.parsed_chat_completion.ParsedChatCompletionMessage[SentimentResponse]

from pydantic import BaseModel
from typing import List
# Define the Pydantic model for an address
class Address(BaseModel):
   street: str
   city: str
   state: str
   zip_code: str
# Define the Pydantic model for user information
class UserInfo(BaseModel):
   name: str
   email: str
   phone: str
   addresses: List[Address]

SYSTEM_PROMPT = "You are a user information extraction assistant."
PROMPT_TEMPLATE = """ Extract the user information from the following text:\n\n{text}"""
# Function to extract user information using OpenAI's chat completions API with structured outputs
def extract_user_info(text):
   response = client.beta.chat.completions.parse(
       model=MODEL,
       messages=[
           {"role": "system", "content": SYSTEM_PROMPT},
           {"role": "user", "content": PROMPT_TEMPLATE.format(text=text)},
       ],
       response_format=UserInfo
   )
   return response.choices[0].message
# Example text containing user information
text = """John DoeEmail: john.doe@example.comPhone: 123-456-7890Addresses:- 123 Main St, Springfield, IL, 62701- 456 Elm St, Shelbyville, IL, 62702"""
# Extract user information and print the results
user_info = extract_user_info(text)

import json
data = json.loads(user_info.content)
pretty_response = json.dumps(data, indent=2)
print(pretty_response)
{
 "name": "John Doe",
 "email": "john.doe@example.com",
 "phone": "123-456-7890",
 "addresses": [
   {
     "street": "123 Main St",
     "city": "Springfield",
     "state": "IL",
     "zip_code": "62701"
   },
   {
     "street": "456 Elm St",
     "city": "Shelbyville",
     "state": "IL",
     "zip_code": "62702"
   }
 ]
}

{
   "type": "function",
   "function": {
       "name": "get_current_weather",
       "description": "Get the current weather",
       "parameters": {
           "type": "object",
           "properties": {
               "location": {
                   "type": "string",
                   "description": "The city and state, e.g. San Francisco, CA",
               },
               "format": {
                   "type": "string",
                   "enum": ["celsius", "fahrenheit"],
                   "description": "The temperature unit to use. Infer this from the users location.",
               },
           },
           "required": ["location", "format"],
       },
   }
}

from pydantic import BaseModel
from typing import Literal
def get_weather(location: str, unit: str, condition: str):
   # Implementation details...
   pass
class WeatherData(BaseModel):
   location: str
   unit: Literal["celsius", "fahrenheit"]
   condition: Literal["sunny", "cloudy", "rainy", "snowy"]

>>> import openai
>>> openai.pydantic_function_tool(WeatherData)
{'type': 'function',
'function': {'name': 'WeatherData',
 'strict': True,
 'parameters': {'properties': {'location': {'title': 'Location',
    'type': 'string'},
   'unit': {'enum': ['celsius', 'fahrenheit'],
    'title': 'Unit',
    'type': 'string'},
   'condition': {'enum': ['sunny', 'cloudy', 'rainy', 'snowy'],
    'title': 'Condition',
    'type': 'string'}},
  'required': ['location', 'unit', 'condition'],
  'title': 'WeatherData',
  'type': 'object',
  'additionalProperties': False}}}

import openai
client = OpenAI()
tools = [openai.pydantic_function_tool(WeatherData)]
messages = [
   {
       "role": "system",
       "content": "You are a helpful customer support assistant. Use the supplied tools to assist the user.",
   },
   {
       "role": "user",
       "content": "What is the weather in Tokyo?",
   }
]
response = client.chat.completions.create(
   model=MODEL, messages=messages, tools=tools
)
tool_call = response.choices[0].message.tool_calls[0]
>>> tool_call
ChatCompletionMessageToolCall(id='call_QnZZ0DmNN2cxw3bN433JQNIC', function=Function(arguments='{"location":"Tokyo","unit":"celsius","condition":"sunny"}', name='WeatherData'), type='function')

arguments = json.loads(tool_call.function.arguments)
>>> arguments
{'location': 'Tokyo', 'unit': 'celsius', 'condition': 'sunny'}

text = """John DoeEmail: john.doe@example.comPhone: 123-456-7890Addresses:- 123 Main St, Springfield, IL, 62701- 456 Elm St, Shelbyville, IL, 62702"""
user_info = extract_user_info(text)
if user_info.refusal:
   print(user_info.refusal)
else:
   print(user_info.content)

输出：

{"name":"John Doe","email":"john.doe@example.com","phone":"123-456-7890","addresses":[{"street":"123 Main St","city":"Springfield","state":"IL","zip_code":"62701"},{"street":"456 Elm St","city":"Shelbyville","state":"IL","zip_code":"62702"}]}

from pydantic import BaseModel, Field
class Person(BaseModel):
   name: str = Field(..., description="The person's full name")
   age: int = Field(..., description="The person's age in years")
   occupation: str = Field(..., description="The person's current job or profession")