Vous pouvez configurer les modèles Gemini pour générer des réponses conformes à un schéma JSON fourni. Cela garantit des résultats prévisibles et de type sécurisé, et simplifie l'extraction de données structurées à partir de texte non structuré.
L'utilisation de sorties structurées est idéale pour :
- Extraction de données : extraire des informations spécifiques, comme des noms et des dates, à partir d'un texte.
- Classification structurée : classer le texte dans des catégories prédéfinies.
- Workflows agentiques : générer des entrées structurées pour des outils ou des API.
En plus de la prise en charge du schéma JSON dans l'API REST, les SDK GenAI de Google permettent de définir des schémas à l'aide de Pydantic (Python) et Zod (JavaScript).
Exemples de sorties structurées
Extracteur de recettes
Cet exemple montre comment extraire des données structurées à partir de texte à l'aide de types de schéma JSON de base tels que object, array, string et integer.
Python
from google import genai
from pydantic import BaseModel, Field
from typing import List, Optional
class Ingredient(BaseModel):
name: str = Field(description="Name of the ingredient.")
quantity: str = Field(description="Quantity of the ingredient, including units.")
class Recipe(BaseModel):
recipe_name: str = Field(description="The name of the recipe.")
prep_time_minutes: Optional[int] = Field(description="Optional time in minutes to prepare the recipe.")
ingredients: List[Ingredient]
instructions: List[str]
client = genai.Client()
prompt = """
Please extract the recipe from the following text.
The user wants to make delicious chocolate chip cookies.
They need 2 and 1/4 cups of all-purpose flour, 1 teaspoon of baking soda,
1 teaspoon of salt, 1 cup of unsalted butter (softened), 3/4 cup of granulated sugar,
3/4 cup of packed brown sugar, 1 teaspoon of vanilla extract, and 2 large eggs.
For the best part, they'll need 2 cups of semisweet chocolate chips.
First, preheat the oven to 375°F (190°C). Then, in a small bowl, whisk together the flour,
baking soda, and salt. In a large bowl, cream together the butter, granulated sugar, and brown sugar
until light and fluffy. Beat in the vanilla and eggs, one at a time. Gradually beat in the dry
ingredients until just combined. Finally, stir in the chocolate chips. Drop by rounded tablespoons
onto ungreased baking sheets and bake for 9 to 11 minutes.
"""
interaction = client.interactions.create(
model="gemini-3.6-flash",
input=prompt,
response_format={
"type": "text",
"mime_type": "application/json",
"schema": Recipe.model_json_schema()
},
)
recipe = Recipe.model_validate_json(interaction.output_text)
print(recipe)
JavaScript
// Note: Ensure zod is installed (npm install zod)
import { GoogleGenAI } from "@google/genai";
import * as z from "zod";
const recipeJsonSchema = {
type: "object",
properties: {
recipe_name: {
type: "string",
description: "The name of the recipe."
},
prep_time_minutes: {
type: "integer",
description: "Optional time in minutes to prepare the recipe."
},
ingredients: {
type: "array",
items: {
type: "object",
properties: {
name: { type: "string", description: "Name of the ingredient."},
quantity: { type: "string", description: "Quantity of the ingredient, including units."}
},
required: ["name", "quantity"]
}