Modele Gemini możesz skonfigurować tak, aby generowały odpowiedzi zgodne z podanym schematem JSON. Zapewnia to przewidywalne i bezpieczne pod względem typów wyniki oraz upraszcza wyodrębnianie uporządkowanych danych z nieuporządkowanego tekstu.
Używanie uporządkowanych danych wyjściowych jest idealne w tych przypadkach:
- Wyodrębnianie danych: wyodrębnianie z tekstu konkretnych informacji, takich jak imiona i nazwiska oraz daty.
- Uporządkowana klasyfikacja: klasyfikowanie tekstu według wstępnie zdefiniowanych kategorii.
- Przepływy pracy agenta: generowanie uporządkowanych danych wejściowych dla narzędzi lub interfejsów API.
Oprócz obsługi schematu JSON w interfejsie REST API, pakiety SDK Google GenAI umożliwiają definiowanie schematów za pomocą Pydantic (Python) i Zod (JavaScript).
Przykłady uporządkowanych danych wyjściowych
Ekstraktor przepisów
Ten przykład pokazuje, jak wyodrębnić uporządkowane dane z tekstu za pomocą podstawowych typów schematu JSON, takich jak object, array, string i 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-3.5-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
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-3.5-flash",
input: prompt,
response_format: {
type: 'text',
mime_type: 'application/json',
schema: recipeJsonSchema
},
});
const recipe = recipeSchema.parse(JSON.parse(interaction.output_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-3.5-flash",
"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"]
}
}
}
}'
Przykładowa odpowiedź:
{
"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."
]
}
Moderacja treści
Ten przykład pokazuje, jak używać anyOf w przypadku schematów warunkowych i enum w przypadku klasyfikacji, co pozwala na zmianę struktury danych wyjściowych w zależności od treści.
Python
from google import genai
from pydantic import BaseModel, Field
from typing import Union, Literal
class SpamDetails(BaseModel):
reason: str = Field(description="The reason why the content is considered spam.")
spam_type: Literal["phishing", "scam", "unsolicited promotion", "other"] = Field(description="The type of spam.")
class NotSpamDetails(BaseModel):
summary: str = Field(description="A brief summary of the content.")
is_safe: bool = Field(description="Whether the content is safe for all audiences.")
class ModerationResult(BaseModel):
decision: Union[SpamDetails, NotSpamDetails]
client = genai.Client()
prompt = """
Please moderate the following content and provide a decision.
Content: 'Congratulations! You''ve won a free cruise to the Bahamas. Click here to claim your prize: www.definitely-not-a-scam.com'
"""
interaction = client.interactions.create(
model="gemini-3.5-flash",
input=prompt,
response_format={
"type": "text",
"mime_type": "application/json",
"schema": ModerationResult.model_json_schema()
},
)
result = ModerationResult.model_validate_json(interaction.output_text)
print(result)
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as z from "zod";
const moderationResultJsonSchema = {
type: "object",
properties: {
decision: {
anyOf: [
{
type: "object",
title: "SpamDetails",
description: "Details for content classified as spam.",
properties: {
reason: { type: "string", description: "The reason why the content is considered spam." },
spam_type: { type: "string", enum: ["phishing", "scam", "unsolicited promotion", "other"], description: "The type of spam." }
},
required: ["reason", "spam_type"]
},
{
type: "object",
title: "NotSpamDetails",
description: "Details for content classified as not spam.",
properties: {
summary: { type: "string", description: "A brief summary of the content." },
is_safe: { type: "boolean", description: "Whether the content is safe for all audiences." }
},
required: ["summary", "is_safe"]
}
]
}
},
required: ["decision"]
};
const moderationResultSchema = z.fromJSONSchema(moderationResultJsonSchema);
const client = new GoogleGenAI({});
const prompt = `
Please moderate the following content and provide a decision.
Content: 'Congratulations! You''ve won a free cruise to the Bahamas. Click here to claim your prize: www.definitely-not-a-scam.com'
`;
const interaction = await client.interactions.create({
model: "gemini-3.5-flash",
input: prompt,
response_format: {
type: 'text',
mime_type: 'application/json',
schema: moderationResultJsonSchema
},
});
const result = moderationResultSchema.parse(JSON.parse(interaction.output_text));
console.log(result);
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-3.5-flash",
"input": "Please moderate the following content and provide a decision.\nContent: '\''Congratulations! You have won a free cruise to the Bahamas. Click here to claim your prize: www.definitely-not-a-scam.com'\''",
"response_format": {
"type": "text",
"mime_type": "application/json",
"schema": {
"type": "object",
"properties": {
"decision": {
"anyOf": [
{
"type": "object",
"title": "SpamDetails",
"description": "Details for content classified as spam.",
"properties": {
"reason": { "type": "string", "description": "The reason why the content is considered spam." },
"spam_type": { "type": "string", "enum": ["phishing", "scam", "unsolicited promotion", "other"], "description": "The type of spam." }
},
"required": ["reason", "spam_type"]
},
{
"type": "object",
"title": "NotSpamDetails",
"description": "Details for content classified as not spam.",
"properties": {
"summary": { "type": "string", "description": "A brief summary of the content." },
"is_safe": { "type": "boolean", "description": "Whether the content is safe for all audiences." }
},
"required": ["summary", "is_safe"]
}
]
}
},
"required": ["decision"]
}
}
}
}'
Przykładowa odpowiedź:
{
"decision": {
"reason": "The content is an unsolicited prize notification attempting to trick the user into clicking a suspicious link.",
"spam_type": "scam"
}
}
Struktury rekurencyjne
Ten przykład pokazuje, jak zdefiniować schemat rekurencyjny, np. schemat organizacyjny.
Python
from google import genai
from pydantic import BaseModel, Field
from typing import List
class Employee(BaseModel):
"""Represents an employee in an organization."""
name: str
employee_id: int
reports: List["Employee"] = Field(
default_factory=list,
description="A list of employees reporting to this employee."
)
client = genai.Client()
prompt = """
Generate an organization chart for a small team.
The manager is Alice, who manages Bob and Charlie. Bob manages David.
"""
interaction = client.interactions.create(
model="gemini-3.5-flash",
input=prompt,
response_format={
"type": "text",
"mime_type": "application/json",
"schema": Employee.model_json_schema()
},
)
employee = Employee.model_validate_json(interaction.output_text)
print(employee)
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as z from "zod";
const employeeJsonSchema = {
type: "object",
properties: {
name: { type: "string" },
employee_id: { type: "integer" },
reports: {
type: "array",
description: "A list of employees reporting to this employee.",
items: {
"$ref": "#"
}
}
},
required: ["name", "employee_id", "reports"]
};
const employeeSchema = z.fromJSONSchema(employeeJsonSchema);
const client = new GoogleGenAI({});
const prompt = `
Generate an organization chart for a small team.
The manager is Alice, who manages Bob and Charlie. Bob manages David.
`;
const interaction = await client.interactions.create({
model: "gemini-3.5-flash",
input: prompt,
response_format: {
type: 'text',
mime_type: 'application/json',
schema: employeeJsonSchema
},
});
const employee = employeeSchema.parse(JSON.parse(interaction.output_text));
console.log(employee);
REST
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.5-flash",
"input": "Generate an organization chart for a small team.\nThe manager is Alice, who manages Bob and Charlie. Bob manages David.",
"response_format": {
"type": "text",
"mime_type": "application/json",
"schema": {
"type": "object",
"properties": {
"name": { "type": "string" },
"employee_id": { "type": "integer" },
"reports": {
"type": "array",
"description": "A list of employees reporting to this employee.",
"items": {
"$ref": "#"
}
}
},
"required": ["name", "employee_id", "reports"]
}
}
}
}'
Przykładowa odpowiedź:
{
"name": "Alice",
"employee_id": 101,
"reports": [
{
"name": "Bob",
"employee_id": 102,
"reports": [
{
"name": "David",
"employee_id": 104,
"reports": []
}
]
},
{
"name": "Charlie",
"employee_id": 103,
"reports": []
}
]
}
Strumieniowanie wyników
Możesz strumieniować uporządkowane dane wyjściowe, co pozwala na rozpoczęcie przetwarzania odpowiedzi w trakcie jej generowania. Strumieniowane fragmenty są prawidłowymi częściowymi ciągami JSON, które można połączyć, aby utworzyć ostateczny obiekt JSON.
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-3.5-flash",
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-3.5-flash",
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);
}
}
Uporządkowane dane wyjściowe z narzędziami
Gemini 3 umożliwia łączenie uporządkowanych danych wyjściowych z wbudowanymi narzędziami, takimi jak powiązanie ze źródłami informacji przy użyciu wyszukiwarki Google, kontekst adresu URL, wykonanie kodu, wyszukiwanie plików i wywoływanie funkcji.
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.output_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.output_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"]
}
}
}'
Obsługa schematu JSON
Aby wygenerować obiekt JSON, skonfiguruj response_format za pomocą obiektu (lub tablicy zawierającej obiekt) typu text i ustaw jego mime_type na application/json. Schemat należy podać w polu schema.
Tryb uporządkowanych danych wyjściowych Gemini obsługuje podzbiór specyfikacji schematu JSON.
Obsługiwane są te wartości type:
string: w przypadku tekstu.number: w przypadku liczb zmiennoprzecinkowych.integer: w przypadku liczb całkowitych.boolean: w przypadku wartości true lub false.object: w przypadku uporządkowanych danych z parami klucz-wartość.array: w przypadku list elementów.null: aby zezwolić na wartość null właściwości, dodaj"null"do tablicy typów (np.{"type": ["string", "null"]}).
Te właściwości opisowe pomagają modelowi:
title: krótki opis właściwości.description: dłuższy i bardziej szczegółowy opis właściwości.
Właściwości specyficzne dla typu
W przypadku wartości object:
properties: obiekt, w którym każdy klucz jest nazwą właściwości, a każda wartość jest schematem tej właściwości.required: tablica ciągów znaków, która zawiera listę właściwości obowiązkowych.additionalProperties: określa, czy właściwości nieuwzględnione wpropertiessą dozwolone. Może to być wartość logiczna lub schemat.
W przypadku wartości string:
enum: zawiera listę konkretnych możliwych ciągów znaków w przypadku zadań klasyfikacji.format: określa składnię ciągu znaków, np.date-time,date,time.
W przypadku wartości number i integer:
enum: zawiera listę konkretnych możliwych wartości liczbowych.minimum: minimalna wartość włącznie.maximum: maksymalna wartość włącznie.
W przypadku wartości array values:
items: określa schemat wszystkich elementów w tablicy.prefixItems: określa listę schematów dla pierwszych N elementów, co umożliwia tworzenie struktur podobnych do krotek.minItems: minimalna liczba elementów w tablicy.maxItems: maksymalna liczba elementów w tablicy.
Uporządkowane dane wyjściowe a wywoływanie funkcji
| Funkcja | Główny przypadek użycia |
|---|---|
| Uporządkowane dane wyjściowe | Formatowanie ostatecznej odpowiedzi. Używaj, gdy chcesz, aby odpowiedź modelu miała określony format. |
| Wywoływanie funkcji | Podejmowanie działań podczas rozmowy. Używaj, gdy model musi poprosić Cię o wykonanie zadania przed udzieleniem ostatecznej odpowiedzi. |
Sprawdzone metody
- Jasne opisy: używaj pola
description, aby prowadzić model. - Silne typowanie: używaj konkretnych typów (
integer,string,enum). - Inżynieria promptów: jasno określ, co ma zrobić model.
- Weryfikacja: chociaż dane wyjściowe są syntaktycznie poprawnym kodem JSON, zawsze sprawdzaj wartości w swojej aplikacji.
- Obsługa błędów: zaimplementuj niezawodną obsługę błędów w przypadku danych wyjściowych zgodnych ze schematem, ale niepoprawnych semantycznie.
Ograniczenia
- Podzbiór schematu: nie wszystkie funkcje schematu JSON są obsługiwane.
- Złożoność schematu: bardzo duże lub głęboko zagnieżdżone schematy mogą zostać odrzucone.