Structured Outputs permet au modèle de générer des réponses qui respectent le JSON Schema que vous avez fourni.
Modèles pris en charge
Les modèles suivants prennent en chargeStructured Outputs :
Guide de démarrage rapide
Ce guide montre comment utiliser la capacitéStructured Outputs pour générer la réponse JSON via le format de réponse json_schema. Nous allons parcourir un exemple complet de code Python.
1. Initialiser le client
Tout d’abord, vous devez initialiser le client avec votre clé API Novita.from openai import OpenAI
client = OpenAI(
base_url="https://api.novita.ai/openai",
# Get the Novita AI API Key from: https://novita.ai/settings/key-management.
api_key="<YOUR Novita AI API Key>",
)
# Go to the [Models](https://novita.ai/models) page to see the models that support `Structured Outputs`.
model = "mistralai/mistral-7b-instruct"
2. Définir le schéma JSON
Cet exemple crée un schéma pour extraire les informations de dépenses à partir de l’entrée de l’utilisateur.
# Define system prompt for expense tracking.
system_prompt = """You are an expense tracking assistant.
Extract expense information from the user's input and format it according to the provided schema."""
# Define JSON schema for structured response.
response_format = {
"type": "json_schema",
"json_schema": {
"name": "expense_tracking_schema",
"schema": {
"type": "object",
"properties": {
"expenses": {
"type": "array",
"items": {
"type": "object",
"properties": {
"description": {
"type": "string",
"description": "Description of the expense"
},
"amount": {
"type": "number",
"description": "Amount spent in dollars"
},
"date": {
"type": "string",
"description": "When the expense occurred"
},
"category": {
"type": "string",
"description": "Category of expense (e.g., food, office, travel)"
}
},
"required": [
"description",
"amount"
]
}
},
"total": {
"type": "number",
"description": "Total amount of all expenses"
}
},
"required": [
"expenses",
"total"
],
},
},
}
3. Demander l’API de complétion de chat
Maintenant, effectuez la requête de complétion de chat vers le endpoint Novita. Cette requête inclut le paramètreresponse_format, qui définit le schéma JSON que nous avons défini à l’étape précédente.
chat_completion = client.chat.completions.create(
model=model,
messages=[
{
"role": "system",
"content": system_prompt,
},
{
"role": "user",
"content": """I spent $120 on dinner at an Italian restaurant last Friday with my colleagues.
Also bought office supplies for $45 on Monday.""",
},
],
max_tokens=1024,
temperature=0.8,
stream=False,
response_format=response_format,
)
response_content = chat_completion.choices[0].message.content
# Parse and prettify the JSON
try:
json_response = json.loads(response_content)
prettified_json = json.dumps(json_response, indent=2)
print(prettified_json)
except json.JSONDecodeError:
print("Could not parse response as JSON. Raw response:")
print(response_content)
{
"expenses": [
{
"date": "2023-03-17",
"description": "Dinner at Italian restaurant",
"amount": 120,
"category": "Food & Dining"
},
{
"date": "2023-03-13",
"description": "Office supplies",
"amount": 45,
"category": "Office Supplies"
}
],
"total": 165
}
Le code complet
from openai import OpenAI
import json
client = OpenAI(
base_url="https://api.novita.ai/openai",
# Get the Novita AI API Key from: https://novita.ai/settings/key-management.
api_key="<YOUR Novita AI API Key>",
)
# Go to the [Models](https://novita.ai/models) page to see the models that support `Structured Outputs`.
model = "mistralai/mistral-7b-instruct"
# Example of using JSON Schema for structured output
# This example creates a schema for extracting expense information
# Define system prompt for expense tracking
system_prompt = """You are an expense tracking assistant.
Extract expense information from the user's input and format it according to the provided schema."""
# Define JSON schema for structured response
response_format = {
"type": "json_schema",
"json_schema": {
"name": "expense_tracking_schema",
"schema": {
"type": "object",
"properties": {
"expenses": {
"type": "array",
"items": {
"type": "object",
"properties": {
"description": {
"type": "string",
"description": "Description of the expense"
},
"amount": {
"type": "number",
"description": "Amount spent in dollars"
},
"date": {
"type": "string",
"description": "When the expense occurred"
},
"category": {
"type": "string",
"description": "Category of expense (e.g., food, office, travel)"
}
},
"required": [
"description",
"amount"
]
}
},
"total": {
"type": "number",
"description": "Total amount of all expenses"
}
},
"required": [
"expenses",
"total"
],
},
},
}
chat_completion = client.chat.completions.create(
model=model,
messages=[
{
"role": "system",
"content": system_prompt,
},
{
"role": "user",
"content": """I spent $120 on dinner at an Italian restaurant last Friday with my colleagues.
Also bought office supplies for $45 on Monday.""",
},
],
max_tokens=1024,
temperature=0.8,
stream=False,
response_format=response_format,
)
response_content = chat_completion.choices[0].message.content
# Parse and prettify the JSON
try:
json_response = json.loads(response_content)
prettified_json = json.dumps(json_response, indent=2)
print(prettified_json)
except json.JSONDecodeError:
print("Could not parse response as JSON. Raw response:")
print(response_content)