Salidas estructuradas
Puedes configurar los modelos de Gemini para generar respuestas que cumplan con un esquema JSON proporcionado. Esto garantiza resultados predecibles y con seguridad de tipos, y simplifica la extracción de datos estructurados de texto no estructurado.
El uso de salidas estructuradas es ideal para lo siguiente:
- Extracción de datos: Extrae información específica, como nombres y fechas, del texto.
- Clasificación estructurada: Clasifica el texto en categorías predefinidas.
- Flujos de trabajo de agentes: Genera entradas estructuradas para herramientas o APIs.
Además de admitir el esquema JSON en la API de REST, los SDKs de GenAI de Google permiten definir esquemas con Pydantic (Python) y Zod (JavaScript).
En este ejemplo, se muestra cómo extraer datos estructurados del texto con tipos básicos de esquema JSON, como object, array, string y integer.
Python
# This will only work for SDK newer than 2.0.0
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-flash-preview",
input=prompt,
response_format={
"type": "text",
"mime_type": "application/json",
"schema": Recipe.model_json_schema()
},
)
recipe = Recipe.model_validate_json(interaction.steps[-1].content[0].text)
print(recipe)
JavaScript
// This will only work for SDK newer than 2.0.0
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"]
}
},
instructions: {
type: "array",
items: { type: "string" }
}
},
required: ["recipe_name", "ingredients", "instructions"]
};
const recipeSchema = z.fromJSONSchema(recipeJsonSchema);
const client = new GoogleGenAI({});
const 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.
`;
const interaction = await client.interactions.create({
model: "gemini-3-flash-preview",
input: prompt,
response_format: {
type: 'text',
mime_type: 'application/json',
schema: recipeJsonSchema
},
});
const recipe = recipeSchema.parse(JSON.parse(interaction.steps.at(-1).content[0].text));
console.log(recipe);
REST
# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-H "Api-Revision: 2026-05-20" \
-d '{
"model": "gemini-3-flash-preview",
"input": "Please extract the recipe from the following text.\nThe user wants to make delicious chocolate chip cookies.\nThey need 2 and 1/4 cups of all-purpose flour, 1 teaspoon of baking soda,\n1 teaspoon of salt, 1 cup of unsalted butter (softened), 3/4 cup of granulated sugar,\n3/4 cup of packed brown sugar, 1 teaspoon of vanilla extract, and 2 large eggs.\nFor the best part, they will need 2 cups of semisweet chocolate chips.\nFirst, preheat the oven to 375°F (190°C). Then, in a small bowl, whisk together the flour,\nbaking soda, and salt. In a large bowl, cream together the butter, granulated sugar, and brown sugar\nuntil light and fluffy. Beat in the vanilla and eggs, one at a time. Gradually beat in the dry\ningredients until just combined. Finally, stir in the chocolate chips. Drop by rounded tablespoons\nonto ungreased baking sheets and bake for 9 to 11 minutes.",
"response_format": {
"type": "text",
"mime_type": "application/json",
"schema": {
"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"]
}
},
"instructions": {
"type": "array",
"items": { "type": "string" }
}
},
"required": ["recipe_name", "ingredients", "instructions"]
}
}
}
}'
Respuesta de ejemplo:
{
"recipe_name": "Delicious Chocolate Chip Cookies",
"ingredients": [
{ "name": "all-purpose flour", "quantity": "2 and 1/4 cups" },
{ "name": "baking soda", "quantity": "1 teaspoon" },
{ "name": "salt", "quantity": "1 teaspoon" },
{ "name": "unsalted butter (softened)", "quantity": "1 cup" },
{ "name": "granulated sugar", "quantity": "3/4 cup" },
{ "name": "packed brown sugar", "quantity": "3/4 cup" },
{ "name": "vanilla extract", "quantity": "1 teaspoon" },
{ "name": "large eggs", "quantity": "2" },
{ "name": "semisweet chocolate chips", "quantity": "2 cups" }
],
"instructions": [
"Preheat the oven to 375°F (190°C).",
"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.",
"Stir in the chocolate chips.",
"Drop by rounded tablespoons onto ungreased baking sheets and bake for 9 to 11 minutes."
]
}
Transmisión de resultados
Puedes transmitir salidas estructuradas, lo que te permite comenzar a procesar la respuesta a medida que se genera. Los fragmentos transmitidos son cadenas JSON parciales válidas que se pueden concatenar para formar el objeto JSON final.
Python
# This will only work for SDK newer than 2.0.0
from google import genai
from pydantic import BaseModel
from typing import Literal
class Feedback(BaseModel):
sentiment: Literal["positive", "neutral", "negative"]
summary: str
client = genai.Client()
prompt = "The new UI is incredibly intuitive. Add a very long summary to test streaming!"
stream = client.interactions.create(
model="gemini-3-flash-preview",
input=prompt,
response_format={
"type": "text",
"mime_type": "application/json",
"schema": Feedback.model_json_schema()
},
stream=True
)
for event in stream:
if event.event_type == "step.delta" and event.delta.text:
print(event.delta.text, end="")
JavaScript
// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";
import * as z from "zod";
const feedbackJsonSchema = {
type: "object",
properties: {
sentiment: { type: "string", enum: ["positive", "neutral", "negative"] },
summary: { type: "string" }
},
required: ["sentiment", "summary"]
};
const feedbackSchema = z.fromJSONSchema(feedbackJsonSchema);
const client = new GoogleGenAI({});
const stream = await client.interactions.create({
model: "gemini-3-flash-preview",
input: "The new UI is incredibly intuitive. Add a very long summary!",
response_format: {
type: 'text',
mime_type: 'application/json',
schema: feedbackJsonSchema
},
stream: true,
});
for await (const event of stream) {
if (event.type === "step.delta" && event.delta?.text) {
process.stdout.write(event.delta.text);
}
}
Salidas estructuradas con herramientas
Gemini 3 te permite combinar salidas estructuradas con herramientas integradas, como Fundamentación con la Búsqueda de Google, contexto de URL, ejecución de código, búsqueda de archivos, y llamada a función.
Python
# This will only work for SDK newer than 2.0.0
from google import genai
from pydantic import BaseModel, Field
from typing import List
class MatchResult(BaseModel):
winner: str = Field(description="The name of the winner.")
final_match_score: str = Field(description="The final match score.")
scorers: List[str] = Field(description="The name of the scorer.")
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-pro-preview",
input="Search for all details for the latest Euro.",
tools=[{"type": "google_search"}, {"type": "url_context"}],
response_format={
"type": "text",
"mime_type": "application/json",
"schema": MatchResult.model_json_schema()
},
)
result = MatchResult.model_validate_json(interaction.steps[-1].content[0].text)
print(result)
JavaScript
// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";
import * as z from "zod";
const matchJsonSchema = {
type: "object",
properties: {
winner: { type: "string" },
final_match_score: { type: "string" },
scorers: { type: "array", items: { type: "string" } }
},
required: ["winner", "final_match_score", "scorers"]
};
const matchSchema = z.fromJSONSchema(matchJsonSchema);
const client = new GoogleGenAI({});
const interaction = await client.interactions.create({
model: "gemini-3.1-pro-preview",
input: "Search for all details for the latest Euro.",
tools: [{type: "google_search"}, {type: "url_context"}],
response_format: {
type: 'text',
mime_type: 'application/json',
schema: matchJsonSchema
},
});
const match = matchSchema.parse(JSON.parse(interaction.steps.at(-1).content[0].text));
console.log(match);
REST
# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-H "Api-Revision: 2026-05-20" \
-d '{
"model": "gemini-3.1-pro-preview",
"input": "Search for all details for the latest Euro.",
"tools": [{"type": "google_search"}, {"type": "url_context"}],
"response_format": {
"type": "text",
"mime_type": "application/json",
"schema": {
"type": "object",
"properties": {
"winner": {"type": "string"},
"final_match_score": {"type": "string"},
"scorers": {"type": "array", "items": {"type": "string"}}
},
"required": ["winner", "final_match_score", "scorers"]
}
}
}'
Compatibilidad con el esquema JSON
Para generar un objeto JSON, configura response_format con un objeto (o un array que contenga un objeto) de tipo text y establece su mime_type en application/json. El esquema debe proporcionarse en el campo schema.
El modo de salida estructurada de Gemini admite un subconjunto de la especificación del esquema JSON.
Se admiten los siguientes valores de type:
string: Para textonumber: Para números de punto flotanteinteger: Para números enterosboolean: Para valores verdaderos o falsosobject: Para datos estructurados con pares clave-valorarray: Para listas de elementosnull: Para permitir que una propiedad sea nula, incluye"null"en el array de tipos (p.ej.,{"type": ["string", "null"]}).
Estas propiedades descriptivas ayudan a guiar el modelo:
title: Una breve descripción de una propiedaddescription: Una descripción más larga y detallada de una propiedad
Propiedades específicas de los tipos
Para valores:object
properties: Un objeto en el que cada clave es un nombre de propiedad y cada valor es un esquema para esa propiedadrequired: Un array de cadenas que indica qué propiedades son obligatoriasadditionalProperties: Controla si se permiten las propiedades que no aparecen enpropertiesPuede ser un valor booleano o un esquema.
Para valores string:
enum: Muestra un conjunto específico de cadenas posibles para tareas de clasificaciónformat: Especifica una sintaxis para la cadena, comodate-time,dateytime.
Para valores number y integer:
enum: Muestra un conjunto específico de valores numéricos posiblesminimum: El valor inclusivo mínimomaximum: El valor inclusivo máximo
Para array valores:
items: Define el esquema para todos los elementos del arrayprefixItems: Define una lista de esquemas para los primeros N elementos, lo que permite estructuras similares a tuplasminItems: La cantidad mínima de elementos en el arraymaxItems: La cantidad máxima de elementos en el array
Salidas estructuradas en comparación con la llamada a función
| Función | Caso de uso principal |
|---|---|
| Salidas estructuradas | Dar formato a la respuesta final (se usa cuando deseas que la respuesta del modelo tenga un formato específico) |
| Llamada a función | Realizar acciones durante la conversación (se usa cuando el modelo necesita pedirte que realices una tarea antes de proporcionar una respuesta final) |
Prácticas recomendadas
- Descripciones claras: Usa el campo
descriptionpara guiar el modelo. - Tipos sólidos: Usa tipos específicos (
integer,string,enum). - Ingeniería de instrucciones: Indica claramente lo que quieres que haga el modelo.
- Validación: Si bien el resultado es un objeto JSON sintácticamente correcto, siempre valida los valores en tu aplicación.
- Manejo de errores: Implementa un manejo de errores sólido para las salidas que cumplen con el esquema, pero que son semánticamente incorrectas.
Limitaciones
- Subconjunto de esquemas: No se admiten todas las funciones del esquema JSON.
- Complejidad del esquema: Es posible que se rechacen los esquemas muy grandes o anidados.