Resultados estructurados
Puedes configurar los modelos de Gemini para que generen respuestas que se ajusten a un esquema JSON proporcionado. Esto garantiza resultados predecibles y con seguridad de tipos, y simplifica la extracción de datos estructurados a partir de texto no estructurado.
El uso de resultados estructurados 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 basados en agentes: Generan entradas estructuradas para herramientas o APIs.
Además de admitir el esquema JSON en la API de REST, los SDKs de IA generativa 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
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
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
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-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"]
}
}
}
}'
Ejemplo de respuesta:
{
"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."
]
}
Resultados de transmisión
Puedes transmitir resultados estructurados, 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
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
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);
}
}
Resultados estructurados 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 funciones.
Python
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
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
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-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 de esquema JSON.
Se admiten los siguientes valores de type:
string: Para textonumber: Para números de punto flotante.integer: Para números enterosboolean: Para valores verdaderos o falsos.object: Para datos estructurados con pares clave-valor.array: Para listas de elementos.null: 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: Es una descripción breve de una propiedad.description: Es una descripción más larga y detallada de una propiedad.
Propiedades específicas del tipo
Para los valores de object:
properties: Es un objeto en el que cada clave es un nombre de propiedad y cada valor es un esquema para esa propiedad.required: Es un array de cadenas que indica qué propiedades son obligatorias.additionalProperties: Controla si se permiten las propiedades que no se incluyen enproperties. Puede ser un valor booleano o un esquema.
Para los valores de string:
enum: Enumera un conjunto específico de cadenas posibles para las tareas de clasificación.format: Especifica una sintaxis para la cadena, comodate-time,dateotime.
Para los valores de number y integer:
enum: Enumera un conjunto específico de valores numéricos posibles.minimum: Es el valor mínimo inclusivo.maximum: Es el valor máximo inclusivo.
Para los valores de array:
items: Define el esquema para todos los elementos del array.prefixItems: Define una lista de esquemas para los primeros N elementos, lo que permite estructuras similares a tuplas.minItems: Es la cantidad mínima de elementos en el array.maxItems: Es la cantidad máxima de elementos en el array.
Compatibilidad con modelos
| Modelo | Resultados estructurados |
|---|---|
| Versión preliminar de Gemini 3.1 Pro | ✔️ |
| Versión preliminar de Gemini 3 Flash | ✔️ |
| Gemini 2.5 Pro | ✔️ |
| Gemini 2.5 Flash | ✔️ |
| Gemini 2.5 Flash-Lite | ✔️ |
| Gemini 2.0 Flash | ✔️* |
| Gemini 2.0 Flash-Lite | ✔️* |
* Gemini 2.0 requiere una lista de propertyOrdering explícita.
Comparación entre los resultados estructurados y las llamadas a funciones
| Función | Caso de uso principal |
|---|---|
| Salidas estructuradas | Dar formato a la respuesta final Úsalo cuando quieras 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 al modelo. - Escritura sólida: 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 esquema: No se admiten todas las funciones del esquema JSON.
- Complejidad del esquema: Es posible que se rechacen los esquemas muy grandes o anidados de forma profunda.