Generowanie tekstu
Interfejs Gemini API może generować tekst na podstawie tekstu, obrazów, filmów i dźwięku.
Oto podstawowy przykład:
Python
# This will only work for SDK newer than 2.0.0
from google import genai
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3-flash-preview",
input="How does AI work?"
)
print(interaction.steps[-1].content[0].text)
JavaScript
// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
async function main() {
const interaction = await ai.interactions.create({
model: "gemini-3-flash-preview",
input: "How does AI work?",
});
console.log(interaction.steps.at(-1).content[0].text);
}
await main();
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": "How does AI work?"
}'
Myślenie z Gemini
Modele Gemini mają często domyślnie włączoną funkcję „myślenia” , która umożliwia modelowi przeprowadzenie rozumowania przed udzieleniem odpowiedzi na żądanie.
Każdy model obsługuje różne konfiguracje myślenia, co daje Ci kontrolę nad kosztami, opóźnieniami i inteligencją. Więcej informacji znajdziesz w przewodniku po myśleniu.
Python
# This will only work for SDK newer than 2.0.0
from google import genai
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3-flash-preview",
input="How does AI work?",
generation_config={
"thinking_level": "low"
}
)
print(interaction.steps[-1].content[0].text)
JavaScript
// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
async function main() {
const interaction = await ai.interactions.create({
model: "gemini-3-flash-preview",
input: "How does AI work?",
generation_config: {
thinking_level: "low",
},
});
console.log(interaction.steps.at(-1).content[0].text);
}
await main();
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": "How does AI work?",
"generation_config": {
"thinking_level": "low"
}
}'
Instrukcje systemowe i inne konfiguracje
Zachowanie modeli Gemini możesz określać za pomocą instrukcji systemowych. Aby skonfigurować zachowanie modelu, przekaż parametr system_instruction.
Python
# This will only work for SDK newer than 2.0.0
from google import genai
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3-flash-preview",
system_instruction="You are a cat. Your name is Neko.",
input="Hello there"
)
print(interaction.steps[-1].content[0].text)
JavaScript
// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
async function main() {
const interaction = await ai.interactions.create({
model: "gemini-3-flash-preview",
input: "Hello there",
system_instruction: "You are a cat. Your name is Neko.",
});
console.log(interaction.steps.at(-1).content[0].text);
}
await main();
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",
"system_instruction": "You are a cat. Your name is Neko.",
"input": "Hello there"
}'
Możesz też zastąpić domyślne parametry generowania, takie jak temperatura, za pomocą parametru generation_config.
Python
# This will only work for SDK newer than 2.0.0
from google import genai
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3-flash-preview",
input="Explain how AI works",
generation_config={
"temperature": 1.0
}
)
print(interaction.steps[-1].content[0].text)
JavaScript
// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
async function main() {
const interaction = await ai.interactions.create({
model: "gemini-3-flash-preview",
input: "Explain how AI works",
generation_config: {
temperature: 1.0,
},
});
console.log(interaction.steps.at(-1).content[0].text);
}
await main();
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": "Explain how AI works",
"generation_config": {
"temperature": 1.0
}
}'
Pełną listę konfigurowalnych parametrów i ich opisów znajdziesz w dokumentacji interfejsu Interactions API.
Dane wejściowe multimodalne
Interfejs Gemini API obsługuje dane wejściowe multimodalne, co pozwala łączyć tekst z plikami multimedialnymi. Poniższy przykład pokazuje, jak podać obraz:
Python
# This will only work for SDK newer than 2.0.0
from google import genai
client = genai.Client()
uploaded_file = client.files.upload(file="path/to/organ.jpg")
interaction = client.interactions.create(
model="gemini-3-flash-preview",
input=[
{"type": "text", "text": "Tell me about this instrument"},
{
"type": "image",
"uri": uploaded_file.uri,
"mime_type": uploaded_file.mime_type
}
]
)
print(interaction.steps[-1].content[0].text)
JavaScript
// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
async function main() {
const uploadedFile = await ai.files.upload({
file: "path/to/organ.jpg",
config: { mimeType: "image/jpeg" }
});
const interaction = await ai.interactions.create({
model: "gemini-3-flash-preview",
input: [
{type: "text", text: "Tell me about this instrument"},
{
type: "image",
uri: uploadedFile.uri,
mime_type: uploadedFile.mimeType
}
],
});
console.log(interaction.steps.at(-1).content[0].text);
}
await main();
REST
# First upload the file using the Files API, then use the URI:
# 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": [
{"type": "text", "text": "Tell me about this instrument"},
{
"type": "image",
"uri": "YOUR_FILE_URI",
"mime_type": "image/jpeg"
}
]
}'
Więcej informacji o alternatywnych metodach udostępniania obrazów i bardziej zaawansowanym przetwarzaniu obrazów, znajdziesz w naszym przewodniku po rozpoznawaniu obrazów. Interfejs API obsługuje też dane wejściowe i rozpoznawanie dokumentów, filmów i dźwięku.
Strumieniowanie odpowiedzi
Domyślnie model zwraca odpowiedź dopiero po zakończeniu całego procesu generowania.
Aby interakcje były bardziej płynne, użyj strumieniowania do obsługi fragmentów odpowiedzi w miarę ich generowania.
Python
# This will only work for SDK newer than 2.0.0
from google import genai
client = genai.Client()
stream = client.interactions.create(
model="gemini-3-flash-preview",
input="Explain how AI works",
stream=True
)
for event in stream:
if event.event_type == "step.delta":
if event.delta.type == "text":
print(event.delta.text, end="")
JavaScript
// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
async function main() {
const stream = await ai.interactions.create({
model: "gemini-3-flash-preview",
input: "Explain how AI works",
stream: true,
});
for await (const event of stream) {
if (event.event_type === "step.delta") {
if (event.delta.type === "text") {
process.stdout.write(event.delta.text);
}
}
}
}
await main();
REST
# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?alt=sse" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-H "Api-Revision: 2026-05-20" \
--no-buffer \
-d '{
"model": "gemini-3-flash-preview",
"input": "Explain how AI works",
"stream": true
}'
Rozmowy wieloetapowe
Interfejs Interactions API obsługuje rozmowy wieloetapowe przez łączenie interakcji za pomocą parametru previous_interaction_id. Każda tura to osobna interakcja, a interfejs API automatycznie zarządza historią rozmowy.
Python
# This will only work for SDK newer than 2.0.0
from google import genai
client = genai.Client()
interaction1 = client.interactions.create(
model="gemini-3-flash-preview",
input="I have 2 dogs in my house.",
)
print(interaction1.steps[-1].content[0].text)
interaction2 = client.interactions.create(
model="gemini-3-flash-preview",
input="How many paws are in my house?",
previous_interaction_id=interaction1.id,
)
print(interaction2.steps[-1].content[0].text)
JavaScript
// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
async function main() {
const interaction1 = await ai.interactions.create({
model: "gemini-3-flash-preview",
input: "I have 2 dogs in my house.",
});
console.log("Response 1:", interaction1.steps.at(-1).content[0].text);
const interaction2 = await ai.interactions.create({
model: "gemini-3-flash-preview",
input: "How many paws are in my house?",
previous_interaction_id: interaction1.id,
});
console.log("Response 2:", interaction2.steps.at(-1).content[0].text);
}
await main();
REST
# Specifies the API revision to avoid breaking changes when they become default
RESPONSE1=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-H "Api-Revision: 2026-05-20" \
-d '{
"model": "gemini-3-flash-preview",
"input": "I have 2 dogs in my house."
}')
INTERACTION_ID=$(echo "$RESPONSE1" | jq -r '.id')
# 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: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-H "Api-Revision: 2026-05-20" \
-d '{
"model": "gemini-3-flash-preview",
"input": "I have two dogs in my house. How many paws are in my house?",
"previous_interaction_id": "'$INTERACTION_ID'"
}'
Strumieniowanie można też wykorzystać w rozmowach wieloetapowych, łącząc parametr previous_interaction_id z metodami strumieniowania.
Python
# This will only work for SDK newer than 2.0.0
from google import genai
client = genai.Client()
interaction1 = client.interactions.create(
model="gemini-3-flash-preview",
input="I have 2 dogs in my house.",
)
print(interaction1.steps[-1].content[0].text)
stream = client.interactions.create(
model="gemini-3-flash-preview",
input="How many paws are in my house?",
previous_interaction_id=interaction1.id,
stream=True
)
for event in stream:
if event.event_type == "step.delta":
if event.delta.type == "text":
print(event.delta.text, end="")
JavaScript
// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
async function main() {
const interaction1 = await ai.interactions.create({
model: "gemini-3-flash-preview",
input: "I have 2 dogs in my house.",
});
console.log("Response 1:", interaction1.steps.at(-1).content[0].text);
const stream = await ai.interactions.create({
model: "gemini-3-flash-preview",
input: "How many paws are in my house?",
previous_interaction_id: interaction1.id,
stream: true,
});
for await (const event of stream) {
if (event.event_type === "step.delta") {
if (event.delta.type === "text") {
process.stdout.write(event.delta.text);
}
}
}
}
await main();
REST
# Specifies the API revision to avoid breaking changes when they become default
RESPONSE1=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-H "Api-Revision: 2026-05-20" \
-d '{
"model": "gemini-3-flash-preview",
"input": "I have 2 dogs in my house."
}')
INTERACTION_ID=$(echo "$RESPONSE1" | jq -r '.id')
# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?alt=sse" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-H "Api-Revision: 2026-05-20" \
--no-buffer \
-d '{
"model": "gemini-3-flash-preview",
"input": "How many paws are in my house?",
"previous_interaction_id": "'$INTERACTION_ID'",
"stream": true
}'
Rozmowy bezstanowe
Domyślnie interfejs Interactions API zarządza stanem rozmowy po stronie serwera, gdy używasz parametru previous_interaction_id. Możesz jednak działać w trybie bezstanowym, samodzielnie zarządzając historią rozmowy po stronie klienta.
Aby użyć trybu bezstanowego: W żądaniu ustaw store=false, aby zrezygnować z przechowywania po stronie serwera.
2. Zachowaj historię rozmowy jako tablicę kroków po stronie klienta.
3. W kolejnych żądaniach przekaż zgromadzone kroki w polu input i dołącz nową turę jako krok user_input.
Python
# This will only work for SDK newer than 2.0.0
from google import genai
client = genai.Client()
# Initialize history with the first user turn
history = [
{
"type": "user_input",
"content": [{"type": "text", "text": "I have 2 dogs in my house."}]
}
]
# Turn 1: Send request with store=False
interaction1 = client.interactions.create(
model="gemini-3-flash-preview",
store=False,
input=history
)
print("Response 1:", interaction1.steps[-1].content[0].text)
# Append the model's response steps to history
for step in interaction1.steps:
# Convert the SDK Step object to a dictionary
history.append(step.model_dump())
# Append the next user turn as a user_input step
history.append({
"type": "user_input",
"content": [{"type": "text", "text": "How many paws are in my house?"}]
})
# Turn 2: Send full history with store=False
interaction2 = client.interactions.create(
model="gemini-3-flash-preview",
store=False,
input=history
)
print("Response 2:", interaction2.steps[-1].content[0].text)
JavaScript
// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
async function main() {
// Initialize history with the first user turn
const history = [
{
type: "user_input",
content: [{ type: "text", text: "I have 2 dogs in my house." }]
}
];
// Turn 1: Send request with store: false
const interaction1 = await ai.interactions.create({
model: "gemini-3-flash-preview",
store: false,
input: history
});
console.log("Response 1:", interaction1.steps.at(-1).content[0].text);
// Append model response steps to history
history.push(...interaction1.steps);
// Append the next user turn
history.push({
type: "user_input",
content: [{ type: "text", text: "How many paws are in my house?" }]
});
// Turn 2: Send full history with store: false
const interaction2 = await ai.interactions.create({
model: "gemini-3-flash-preview",
store: false,
input: history
});
console.log("Response 2:", interaction2.steps.at(-1).content[0].text);
}
await main();
REST
# Turn 1: Send request with store: false
# Specifies the API revision to avoid breaking changes when they become default
RESPONSE1=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-H "Api-Revision: 2026-05-20" \
-d '{
"model": "gemini-3-flash-preview",
"store": false,
"input": [
{
"type": "user_input",
"content": [{"type": "text", "text": "I have 2 dogs in my house."}]
}
]
}')
# Extract the steps from response
MODEL_STEPS=$(echo "$RESPONSE1" | jq '.steps')
# Reconstruct the full history for Turn 2 by combining:
# 1. First user input
# 2. Model response steps
# 3. Second user input
HISTORY=$(jq -n \
--argjson first_input '[{"type": "user_input", "content": [{"type": "text", "text": "I have 2 dogs in my house."}]}]' \
--argjson model_steps "$MODEL_STEPS" \
--argjson second_input '[{"type": "user_input", "content": [{"type": "text", "text": "How many paws are in my house?"}]}]' \
"'"'"'$first_input + $model_steps + $second_input'"'"'")
# Turn 2: Send the full history
# 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\",
\"store\": false,
\"input\": $HISTORY
}"
Wskazówki dotyczące tworzenia promptów
Wskazówki dotyczące optymalnego wykorzystania Gemini znajdziesz w naszym przewodniku po inżynierii promptów.
Co dalej?
- Wypróbuj Gemini w Google AI Studio.
- Eksperymentuj z strukturalnymi danymi wyjściowymi w przypadku odpowiedzi w formacie JSON.
- Poznaj możliwości Gemini w zakresie rozpoznawania obrazów, filmów, dźwięku i dokumentów.
- Dowiedz się więcej o strategiach tworzenia promptów dotyczących plików multimodalnych .