Panduan ini akan membantu Anda mulai menggunakan Gemini API dengan Interactions API. Anda akan melakukan panggilan API pertama dalam waktu kurang dari satu menit dan menjelajahi pembuatan teks, pemahaman multimodal, pembuatan gambar, output terstruktur, alat, panggilan fungsi, agen, dan eksekusi latar belakang.
Interactions API tersedia melalui SDK Python dan JavaScript, serta melalui REST.
1. Mendapatkan kunci API
Untuk menggunakan Gemini API, Anda memerlukan kunci API. Buat secara gratis untuk memulai:
Kemudian, tetapkan sebagai variabel lingkungan:
export GEMINI_API_KEY="YOUR_API_KEY"
2. Menginstal SDK dan melakukan panggilan pertama
Instal SDK dan buat teks dengan satu panggilan API.
Python
Instal SDK:
pip install -U google-genai
Lakukan inisialisasi klien dan ajukan permintaan:
from google import genai
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.5-flash",
input="Explain how AI works in a few words"
)
print(interaction.output_text)
JavaScript
Instal SDK:
npm install @google/genai
Lakukan inisialisasi klien dan ajukan permintaan:
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.5-flash",
input: "Explain how AI works in a few words",
});
console.log(interaction.output_text);
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": "Explain how AI works in a few words"
}'
Respons:
{
"id": "v1_ChdpQUFvYXI...",
"status": "completed",
"usage": {
"total_tokens": 197,
"total_input_tokens": 8,
"total_output_tokens": 12
},
"created": "2026-06-09T12:01:25Z",
"steps": [
{
"type": "thought",
"signature": "EvEFCu4FAQw..."
},
{
"type": "model_output",
"content": [
{
"type": "text",
"text": "AI learns patterns from data, then uses those patterns to make predictions or decisions on new data."
}
]
}
],
"object": "interaction",
"model": "gemini-3.5-flash",
}
Saat menggunakan REST, API akan menampilkan resource Interaction lengkap yang berisi metadata, statistik penggunaan, dan histori langkah demi langkah giliran.
Meskipun SDK mengekspos respons penuh, SDK juga menyediakan properti praktis seperti interaction.output_text dan interaction.output_image untuk mengakses output akhir secara langsung. Pelajari lebih lanjut struktur respons di Ringkasan interaksi atau baca panduan pembuatan teks untuk mengetahui detail tentang petunjuk sistem dan konfigurasi pembuatan.
3. Streaming respons
Untuk interaksi yang lebih lancar, streaming respons saat respons dibuat. Setiap peristiwa step.delta akan mengirimkan potongan teks yang dapat Anda tampilkan dengan segera.
Python
from google import genai
client = genai.Client()
stream = client.interactions.create(
model="gemini-3.5-flash",
input="Explain how AI works",
stream=True
)
for event in stream:
print(event)
JavaScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
const stream = await ai.interactions.create({
model: "gemini-3.5-flash",
input: "Explain how AI works",
stream: true,
});
for await (const event of stream) {
console.log(event);
}
REST
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?alt=sse" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
--no-buffer \
-d '{
"model": "gemini-3.5-flash",
"input": "Explain how AI works",
"stream": true
}'
Saat melakukan streaming, server merespons dengan aliran peristiwa yang dikirim server (SSE). Setiap peristiwa mencakup jenis dan data JSON.
Respons:
event: interaction.created
data: {"interaction":{"id":"v1_Chd...","status":"in_progress","model":"gemini-3.5-flash"},"event_type":"interaction.created"}
event: step.start
data: {"index":0,"step":{"type":"thought"},"event_type":"step.start"}
event: step.delta
data: {"index":0,"delta":{"signature":"EvEFCu4F...","type":"thought_signature"},"event_type":"step.delta"}
event: step.stop
data: {"index":0,"event_type":"step.stop"}
event: step.start
data: {"index":1,"step":{"type":"model_output"},"event_type":"step.start"}
event: step.delta
data: {"index":1,"delta":{"text":"AI ","type":"text"},"event_type":"step.delta"}
event: step.delta
data: {"index":1,"delta":{"text":"works ","type":"text"},"event_type":"step.delta"}
event: step.stop
data: {"index":1,"event_type":"step.stop"}
event: interaction.completed
data: {"interaction":{"id":"v1_Chd...","status":"completed","usage":{"total_tokens":197}},"event_type":"interaction.completed"}
Untuk melihat secara mendetail cara menangani peristiwa streaming dan jenis delta, lihat panduan interaksi streaming.
4. Percakapan multi-giliran
Interactions API mendukung percakapan multi-giliran dengan dua pendekatan:
- Stateful (direkomendasikan): Melanjutkan percakapan di server menggunakan
previous_interaction_id. Ideal untuk sebagian besar alur kerja chat dan agentic yang menginginkan server mengelola histori dan mengoptimalkan penyimpanan dalam cache. Stateless: Mengelola histori percakapan di klien dengan meneruskan semua giliran sebelumnya (termasuk langkah-langkah alat dan pemikiran model perantara) dalam setiap permintaan.
Stateful (direkomendasikan)
Rantai interaksi dengan meneruskan previous_interaction_id. Server mengelola histori percakapan lengkap untuk Anda.
Python
from google import genai
client = genai.Client()
# Server-side state (recommended)
interaction1 = client.interactions.create(
model="gemini-3.5-flash",
input="I have 2 dogs in my house.",
)
print("Response 1:", interaction1.output_text)
interaction2 = client.interactions.create(
model="gemini-3.5-flash",
input="How many paws are in my house?",
previous_interaction_id=interaction1.id,
)
print("Response 2:", interaction2.output_text)
JavaScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
// Server-side state (recommended)
const interaction1 = await ai.interactions.create({
model: "gemini-3.5-flash",
input: "I have 2 dogs in my house.",
});
console.log("Response 1:", interaction1.output_text);
const interaction2 = await ai.interactions.create({
model: "gemini-3.5-flash",
input: "How many paws are in my house?",
previous_interaction_id: interaction1.id,
});
console.log("Response 2:", interaction2.output_text);
REST
RESPONSE1=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.5-flash",
"input": "I have 2 dogs in my house."
}')
INTERACTION_ID=$(echo "$RESPONSE1" | jq -r '.id')
echo "Interaction 1 ID: $INTERACTION_ID"
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.5-flash",
"input": "How many paws are in my house?",
"previous_interaction_id": "'$INTERACTION_ID'"
}'
Stateless
Menyetel store=false dan mengelola histori percakapan di sisi klien. Anda harus mempertahankan dan mengirim ulang semua langkah yang dihasilkan model (termasuk langkah thought dan function_call) persis seperti yang diterima.
Python
from google import genai
client = genai.Client()
history = [
{
"type": "user_input",
"content": [{"type": "text", "text": "I have 2 dogs in my house."}]
}
]
interaction1 = client.interactions.create(
model="gemini-3.5-flash",
store=False,
input=history
)
print("Response 1:", interaction1.steps[-1].content[0].text)
for step in interaction1.steps:
history.append(step.model_dump())
history.append({
"type": "user_input",
"content": [{"type": "text", "text": "How many paws are in my house?"}]
})
interaction2 = client.interactions.create(
model="gemini-3.5-flash",
store=False,
input=history
)
print("Response 2:", interaction2.steps[-1].content[0].text)
JavaScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
const history = [
{
type: "user_input",
content: [{ type: "text", text: "I have 2 dogs in my house." }]
}
];
const interaction1 = await ai.interactions.create({
model: "gemini-3.5-flash",
store: false,
input: history
});
console.log("Response 1:", interaction1.steps.at(-1).content[0].text);
history.push(...interaction1.steps);
history.push({
type: "user_input",
content: [{ type: "text", text: "How many paws are in my house?" }]
});
const interaction2 = await ai.interactions.create({
model: "gemini-3.5-flash",
store: false,
input: history
});
console.log("Response 2:", interaction2.steps.at(-1).content[0].text);
REST
# Turn 1: Send with store: false
RESPONSE1=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.5-flash",
"store": false,
"input": [
{
"type": "user_input",
"content": "I have 2 dogs in my house."
}
]
}')
MODEL_STEPS=$(echo "$RESPONSE1" | jq '.steps')
# Turn 2: Build full history
HISTORY=$(jq -n \
--argjson first_input '[{"type": "user_input", "content": "I have 2 dogs in my house."}]' \
--argjson model_steps "$MODEL_STEPS" \
--argjson second_input '[{"type": "user_input", "content": "How many paws are in my house?"}]' \
'$first_input + $model_steps + $second_input')
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\",
\"store\": false,
\"input\": $HISTORY
}"
Respons:
{
"id": "v2_Chd...",
"status": "completed",
"usage": {
"total_tokens": 240,
"total_input_tokens": 60,
"total_output_tokens": 20
},
"steps": [
{
"type": "model_output",
"content": [
{
"type": "text",
"text": "There are 8 paws in your house. 2 dogs \u00d7 4 paws = 8 paws."
}
]
}
],
"object": "interaction",
"model": "gemini-3.5-flash"
}
Interaksi kedua menampilkan objek respons lengkap yang hanya menyertakan langkah-langkah baru, tetapi didasarkan pada konteks giliran sebelumnya. Pelajari lebih lanjut cara mempertahankan status dalam panduan percakapan multi-giliran, atau pelajari mode tanpa status untuk pengelolaan histori sisi klien.
5. Pemahaman multimodal
Model Gemini memahami gambar, audio, video, dan dokumen secara native. Teruskan media bersama teks dalam satu permintaan.
Python
import base64
from google import genai
client = genai.Client()
# Load a local image
with open("sample.jpg", "rb") as f:
image_bytes = f.read()
image_b64 = base64.b64encode(image_bytes).decode("utf-8")
interaction = client.interactions.create(
model="gemini-3.5-flash",
input=[
{"type": "text", "text": "Compare this local image and this remote audio file."},
{
"type": "image",
"data": image_b64,
"mime_type": "image/jpeg"
},
{
"type": "audio",
"uri": "https://storage.googleapis.com/generativeai-downloads/data/sample.mp3",
"mime_type": "audio/mp3"
}
]
)
print(interaction.output_text)
JavaScript
import fs from "fs";
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
// Load a local image
const imageBytes = fs.readFileSync("sample.jpg");
const imageB64 = imageBytes.toString("base64");
const interaction = await ai.interactions.create({
model: "gemini-3.5-flash",
input: [
{ type: "text", text: "Compare this local image and this remote audio file." },
{
type: "image",
data: imageB64,
mime_type: "image/jpeg"
},
{
type: "audio",
uri: "https://storage.googleapis.com/generativeai-downloads/data/sample.mp3",
mime_type: "audio/mp3"
}
],
});
console.log(interaction.output_text);
REST
# Base64-encode local image
BASE64_IMAGE=$(base64 -w 0 sample.jpg)
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" -H "x-goog-api-key: $GEMINI_API_KEY" -H 'Content-Type: application/json' -H "Api-Revision: 2026-05-20" -d '{
"model": "gemini-3.5-flash",
"input": [
{
"type": "text",
"text": "Compare this local image and this remote audio file."
},
{
"type": "image",
"data": "'$BASE64_IMAGE'",
"mime_type": "image/jpeg"
},
{
"type": "audio",
"uri": "https://storage.googleapis.com/generativeai-downloads/data/sample.mp3",
"mime_type": "audio/mp3"
}
]
}'
Respons:
{
"id": "v1_Chd...",
"status": "completed",
"usage": {
"total_tokens": 300
},
"steps": [
{
"type": "model_output",
"content": [
{
"type": "text",
"text": "The local image displays a pipe organ while the remote audio file is a sample MP3 clip..."
}
]
}
],
"object": "interaction",
"model": "gemini-3.5-flash",
}
Pelajari cara meneruskan gambar, video, dan file audio dalam panduan pemahaman gambar.
Pemahaman audio
Mentranskripsikan, meringkas, atau menjawab pertanyaan tentang file audio.
Pemahaman video
Menganalisis konten video, menemukan peristiwa, dan mendeskripsikan tindakan.
Pemrosesan dokumen
Mengekstrak informasi dari PDF dan format dokumen lainnya.
6. Pembuatan multimodal
Gemini dapat membuat gambar secara native menggunakan model gambar Nano Banana.
Python
import base64
from google import genai
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.1-flash-image",
input="Generate an image of a futuristic city skyline at sunset",
)
with open("generated_image.png", "wb") as f:
f.write(base64.b64decode(interaction.output_image.data))
JavaScript
import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.1-flash-image",
input: "Generate an image of a futuristic city skyline at sunset",
});
const generatedImage = interaction.output_image;
if (generatedImage) {
const buffer = Buffer.from(generatedImage.data, "base64");
fs.writeFileSync("generated_image.png", buffer);
}
REST
curl -s -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-flash-image",
"input": [
{"type": "text", "text": "Generate an image of a futuristic city skyline at sunset"}
]
}'
Respons:
{
"id": "v1_Chd...",
"status": "completed",
"steps": [
{
"type": "model_output",
"content": [
{
"type": "image",
"data": "BASE64_ENCODED_IMAGE",
"mime_type": "image/png"
}
]
}
],
"object": "interaction",
"model": "gemini-3.1-flash-image",
}
Saat menghasilkan gambar, model akan menampilkan data gambar berenkode base64 dalam langkah di dalam array steps, serta melalui properti praktis output_image. Lihat panduan pembuatan gambar untuk mempelajari rasio aspek, pengeditan gambar, dan referensi.
Pembuatan ucapan
Buat ucapan multi-penutur yang ekspresif dengan Gemini 3.1 Flash TTS.
Pembuatan musik
Buat klip dan lagu berdurasi penuh dengan Lyria 3.
7. Menggunakan output terstruktur
Konfigurasi model untuk menampilkan JSON yang sesuai dengan skema yang Anda tentukan. Output terstruktur berfungsi dengan Pydantic (Python) dan Zod (JavaScript).
Python
from google import genai
from pydantic import BaseModel, Field
from typing import List, Optional
class Recipe(BaseModel):
recipe_name: str = Field(description="Name of the recipe.")
ingredients: List[str] = Field(description="List of ingredients.")
prep_time_minutes: Optional[int] = Field(description="Prep time in minutes.")
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.5-flash",
input="Give me a recipe for banana bread",
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 ai = new GoogleGenAI({});
const recipeJsonSchema = {
type: "object",
properties: {
recipe_name: { type: "string", description: "Name of the recipe." },
ingredients: {
type: "array",
items: { type: "string" },
description: "List of ingredients."
},
prep_time_minutes: {
type: "integer",
description: "Prep time in minutes."
}
},
required: ["recipe_name", "ingredients"]
};
const recipeSchema = z.fromJSONSchema(recipeJsonSchema);
const interaction = await ai.interactions.create({
model: "gemini-3.5-flash",
input: "Give me a recipe for banana bread",
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": "Give me a recipe for banana bread",
"response_format": {
"type": "text",
"mime_type": "application/json",
"schema": {
"type": "object",
"properties": {
"recipe_name": { "type": "string", "description": "Name of the recipe." },
"ingredients": {
"type": "array",
"items": { "type": "string" },
"description": "List of ingredients."
},
"prep_time_minutes": {
"type": "integer",
"description": "Prep time in minutes."
}
},
"required": ["recipe_name", "ingredients"]
}
}
}'
Respons:
{
"id": "v1_Chd...",
"status": "completed",
"steps": [
{
"type": "model_output",
"content": [
{
"type": "text",
"text": "{\n \"recipe_name\": \"Classic Banana Bread\",\n \"ingredients\": [\n \"3 ripe bananas, mashed\",\n \"1/3 cup melted butter\",\n \"3/4 cup sugar\",\n \"1 egg, beaten\",\n \"1 teaspoon vanilla extract\",\n \"1 teaspoon baking soda\",\n \"Pinch of salt\",\n \"1.5 cups all-purpose flour\"\n ],\n \"prep_time_minutes\": 15\n}"
}
]
}
],
"object": "interaction",
"model": "gemini-3.5-flash",
}
Blok teks output berisi string JSON yang valid dan sesuai persis dengan skema yang diminta. Untuk mempelajari cara menentukan struktur yang lebih kompleks dan skema rekursif, lihat panduan output terstruktur.
8. Menggunakan alat
Melakukan grounding respons model dalam informasi real-time dengan Google Penelusuran. API secara otomatis menelusuri, memproses hasil, dan menampilkan kutipan.
Python
from google import genai
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.5-flash",
input="Who won the euro 2024?",
tools=[{"type": "google_search"}]
)
print(interaction.output_text)
# Print citations
for step in interaction.steps:
if step.type == "model_output":
for content_block in step.content:
if content_block.type == "text" and content_block.annotations:
print("\nCitations:")
for annotation in content_block.annotations:
if annotation.type == "url_citation":
print(f" [{annotation.title}]({annotation.url})")
JavaScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.5-flash",
input: "Who won the euro 2024?",
tools: [{ type: "google_search" }]
});
console.log(interaction.output_text);
// Print citations
for (const step of interaction.steps) {
if (step.type === "model_output") {
for (const contentBlock of step.content) {
if (contentBlock.type === "text" && contentBlock.annotations) {
console.log("\nCitations:");
for (const annotation of contentBlock.annotations) {
if (annotation.type === "url_citation") {
console.log(` [${annotation.title}](${annotation.url})`);
}
}
}
}
}
}
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": "Who won the euro 2024?",
"tools": [{"type": "google_search"}]
}'
Respons:
{
"id": "v1_Chd...",
"status": "completed",
"steps": [
{
"type": "thought",
"signature": "EvEFCu4F..."
},
{
"type": "google_search_call",
"arguments": {
"queries": ["UEFA Euro 2024 winner"]
}
},
{
"type": "google_search_result",
"call_id": "search_001",
"result": [
{
"search_suggestions": "<!-- HTML and CSS search widget -->"
}
]
},
{
"type": "model_output",
"content": [
{
"type": "text",
"text": "Spain won Euro 2024, defeating England 2-1 in the final.",
"annotations": [
{
"type": "url_citation",
"url": "https://www.uefa.com/euro2024",
"title": "uefa.com",
"start_index": 0,
"end_index": 56
}
]
}
]
}
],
"object": "interaction",
"model": "gemini-3.5-flash",
}
Langkah-langkah penelusuran dijelaskan dalam histori interaksi, dan output akhir mencakup kutipan inline yang mengarah ke sumber web.
Anda dapat mempelajari cara mengekstrak kutipan penelusuran di panduan perujukan Google Penelusuran, atau melihat cara menggabungkan beberapa alat di panduan kombinasi alat.
Eksekusi kode
Menjalankan kode Python di lingkungan Borg sandbox yang aman.
Konteks URL
Teruskan URL web publik secara langsung untuk mendasari respons dalam konten halaman web.
Penelusuran file
Mengindeks dan menelusuri dokumen dan file media yang diupload.
Google Maps
Melakukan grounding pada respons dalam data geospasial dan lokasi dunia nyata.
Penggunaan komputer
Otomatisasi browser dan interaksi layar.
9. Memanggil fungsi Anda sendiri
Pemanggilan fungsi memungkinkan Anda menghubungkan model ke kode Anda. Anda mendeklarasikan nama dan parameter fungsi, model memutuskan kapan harus memanggilnya dan menampilkan argumen terstruktur, lalu Anda mengeksekusinya secara lokal dan mengirimkan hasilnya kembali.
Stateful (direkomendasikan)
Python
import json
from google import genai
client = genai.Client()
weather_tool = {
"type": "function",
"name": "get_current_temperature",
"description": "Gets the current temperature for a given location.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. San Francisco",
},
},
"required": ["location"],
},
}
available_functions = {
"get_current_temperature": lambda location: {
"location": location, "temperature": "22", "unit": "celsius"
},
}
user_input = "What is the temperature in London?"
previous_id = None
while True:
interaction = client.interactions.create(
model="gemini-3.5-flash",
input=user_input,
tools=[weather_tool],
previous_interaction_id=previous_id,
)
function_results = []
for step in interaction.steps:
if step.type == "function_call":
result = available_functions[step.name](**step.arguments)
print(f"Called {step.name}({step.arguments}) → {result}")
function_results.append({
"type": "function_result",
"name": step.name,
"call_id": step.id,
"result": [{"type": "text", "text": json.dumps(result)}],
})
if not function_results:
break
user_input = function_results
previous_id = interaction.id
print(interaction.output_text)
JavaScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
const weatherTool = {
type: "function",
name: "get_current_temperature",
description: "Gets the current temperature for a given location.",
parameters: {
type: "object",
properties: {
location: {
type: "string",
description: "The city name, e.g. San Francisco",
},
},
required: ["location"],
},
};
const availableFunctions = {
get_current_temperature: ({ location }) => ({
location, temperature: "22", unit: "celsius"
}),
};
let input = "What is the temperature in London?";
let previousId = null;
let interaction;
while (true) {
interaction = await ai.interactions.create({
model: "gemini-3.5-flash",
input,
tools: [weatherTool],
previous_interaction_id: previousId,
});
const functionResults = [];
for (const step of interaction.steps) {
if (step.type === "function_call") {
const result = availableFunctions[step.name](step.arguments);
console.log(`Called ${step.name}(${JSON.stringify(step.arguments)}) →`, result);
functionResults.push({
type: "function_result",
name: step.name,
call_id: step.id,
result: [{ type: "text", text: JSON.stringify(result) }],
});
}
}
if (functionResults.length === 0) break;
input = functionResults;
previousId = interaction.id;
}
console.log(interaction.output_text);
REST
# Turn 1: Send prompt with function declaration
RESPONSE1=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.5-flash",
"input": "What is the temperature in London?",
"tools": [{
"type": "function",
"name": "get_current_temperature",
"description": "Gets the current temperature for a given location.",
"parameters": {
"type": "object",
"properties": {
"location": {"type": "string", "description": "The city name"}
},
"required": ["location"]
}
}]
}')
INTERACTION_ID=$(echo "$RESPONSE1" | jq -r '.id')
FC_NAME=$(echo "$RESPONSE1" | jq -r '.steps[] | select(.type=="function_call") | .name')
FC_ID=$(echo "$RESPONSE1" | jq -r '.steps[] | select(.type=="function_call") | .id')
echo "Function: $FC_NAME, Call ID: $FC_ID"
# Turn 2: Send function result back
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.5-flash",
"previous_interaction_id": "'$INTERACTION_ID'",
"input": [{
"type": "function_result",
"name": "'$FC_NAME'",
"call_id": "'$FC_ID'",
"result": [{"type": "text", "text": "{\"location\": \"London\", \"temperature\": \"22\", \"unit\": \"celsius\"}"}]
}],
"tools": [{
"type": "function",
"name": "get_current_temperature",
"description": "Gets the current temperature for a given location.",
"parameters": {
"type": "object",
"properties": {
"location": {"type": "string", "description": "The city name"}
},
"required": ["location"]
}
}]
}'
Stateless
Anda juga dapat menggunakan panggilan fungsi dalam mode tanpa status dengan mengelola histori percakapan di sisi klien dan menyetel store=false. Dalam mode tanpa status, Anda harus meneruskan histori lengkap percakapan di kolom input setiap permintaan berikutnya. Histori ini harus mencakup:
- Langkah
user_inputawal. - Semua langkah yang dihasilkan model ditampilkan di Turn 1 (termasuk langkah
thoughtdanfunction_call) persis seperti yang diterima. - Langkah
function_resultyang berisi output fungsi yang dijalankan.
Python
import json
from google import genai
client = genai.Client()
weather_tool = {
"type": "function",
"name": "get_current_temperature",
"description": "Gets the current temperature for a given location.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. San Francisco",
},
},
"required": ["location"],
},
}
available_functions = {
"get_current_temperature": lambda location: {
"location": location, "temperature": "22", "unit": "celsius"
},
}
history = [
{
"type": "user_input",
"content": [{"type": "text", "text": "What is the temperature in London?"}]
}
]
while True:
interaction = client.interactions.create(
model="gemini-3.5-flash",
store=False,
input=history,
tools=[weather_tool],
)
function_results = []
for step in interaction.steps:
history.append(step.model_dump())
if step.type == "function_call":
result = available_functions[step.name](**step.arguments)
print(f"Called {step.name}({step.arguments}) → {result}")
fn_result = {
"type": "function_result",
"name": step.name,
"call_id": step.id,
"result": [{"type": "text", "text": json.dumps(result)}],
}
function_results.append(fn_result)
history.append(fn_result)
if not function_results:
break
print(interaction.output_text)
JavaScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
const weatherTool = {
type: "function",
name: "get_current_temperature",
description: "Gets the current temperature for a given location.",
parameters: {
type: "object",
properties: {
location: {
type: "string",
description: "The city name, e.g. San Francisco",
},
},
required: ["location"],
},
};
const availableFunctions = {
get_current_temperature: ({ location }) => ({
location, temperature: "22", unit: "celsius"
}),
};
const history = [
{
type: "user_input",
content: [{ type: "text", text: "What is the temperature in London?" }]
}
];
let interaction;
while (true) {
interaction = await ai.interactions.create({
model: "gemini-3.5-flash",
store: false,
input: history,
tools: [weatherTool],
});
const functionResults = [];
for (const step of interaction.steps) {
history.push(step);
if (step.type === "function_call") {
const result = availableFunctions[step.name](step.arguments);
console.log(`Called ${step.name}(${JSON.stringify(step.arguments)}) →`, result);
const fnResult = {
type: "function_result",
name: step.name,
call_id: step.id,
result: [{ type: "text", text: JSON.stringify(result) }],
};
functionResults.push(fnResult);
history.push(fnResult);
}
}
if (functionResults.length === 0) break;
}
console.log(interaction.output_text);
REST
# Turn 1: Send request with tools and store: false
RESPONSE1=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.5-flash",
"store": false,
"input": [
{
"type": "user_input",
"content": "What is the temperature in London?"
}
],
"tools": [{
"type": "function",
"name": "get_current_temperature",
"description": "Gets the current temperature for a given location.",
"parameters": {
"type": "object",
"properties": {
"location": {"type": "string", "description": "The city name"}
},
"required": ["location"]
}
}]
}')
# Extract model steps (thought, function_call)
MODEL_STEPS=$(echo "$RESPONSE1" | jq '.steps')
FC_NAME=$(echo "$RESPONSE1" | jq -r '.steps[] | select(.type=="function_call") | .name')
FC_ID=$(echo "$RESPONSE1" | jq -r '.steps[] | select(.type=="function_call") | .id')
echo "Function: $FC_NAME, Call ID: $FC_ID"
# Assume local execution returns:
RESULT="{\"location\": \"London\", \"temperature\": \"22\", \"unit\": \"celsius\"}"
# Reconstruct history for Turn 2
HISTORY=$(jq -n \
--argjson first_input '[{"type": "user_input", "content": "What is the temperature in London?"}]' \
--argjson model_steps "$MODEL_STEPS" \
--arg fc_name "$FC_NAME" \
--arg fc_id "$FC_ID" \
--arg result "$RESULT" \
'$first_input + $model_steps + [{"type": "function_result", "name": $fc_name, "call_id": $fc_id, "result": [{"type": "text", "text": $result}]}]')
# Turn 2: Send the full history
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\",
\"store\": false,
\"input\": $HISTORY,
\"tools\": [{
\"type\": \"function\",
\"name\": \"get_current_temperature\",
\"description\": \"Gets the current temperature for a given location.\",
\"parameters\": {
\"type\": \"object\",
\"properties\": {
\"location\": {\"type\": \"string\", \"description\": \"The city name\"}
},
\"required\": [\"location\"]
}
}]
}"
Respons:
Selama Turn 1, model menampilkan respons dengan status requires_action dan langkah function_call:
{
"id": "v1_Chd...",
"status": "requires_action",
"steps": [
{
"type": "function_call",
"id": "call_abc123",
"name": "get_current_temperature",
"arguments": {
"location": "London"
}
}
],
"object": "interaction",
"model": "gemini-3.5-flash"
}
Setelah Anda menjalankan fungsi secara lokal dan mengirimkan hasilnya (Giliran 2), interaksi akhir yang telah selesai akan ditampilkan:
{
"id": "v1_Chd...",
"status": "completed",
"steps": [
{
"type": "function_call",
"id": "call_abc123",
"name": "get_current_temperature",
"arguments": {
"location": "London"
}
},
{
"type": "model_output",
"content": [
{
"type": "text",
"text": "The temperature in London is currently 22°C."
}
]
}
],
"object": "interaction",
"model": "gemini-3.5-flash",
}
Untuk fitur lanjutan seperti panggilan fungsi paralel atau mode pilihan fungsi, lihat panduan panggilan fungsi.
10. Menjalankan agen terkelola
Agen terkelola berjalan di sandbox jarak jauh dengan akses ke alat seperti eksekusi kode dan pengelolaan file. Teruskan agent, bukan model, dan tetapkan environment="remote".
Python
from google import genai
client = genai.Client()
interaction = client.interactions.create(
agent="antigravity-preview-05-2026",
input="Write a Python script that generates the first 20 Fibonacci numbers and saves them to fibonacci.txt. Then read the file and print its contents.",
environment="remote",
)
print(f"Environment: {interaction.environment_id}")
print(interaction.output_text)
JavaScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
agent: "antigravity-preview-05-2026",
input: "Write a Python script that generates the first 20 Fibonacci numbers and saves them to fibonacci.txt. Then read the file and print its contents.",
environment: "remote",
});
console.log(`Environment: ${interaction.environment_id}`);
console.log(interaction.output_text);
REST
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"agent": "antigravity-preview-05-2026",
"input": "Write a Python script that generates the first 20 Fibonacci numbers and saves them to fibonacci.txt. Then read the file and print its contents.",
"environment": "remote"
}'
Anda juga dapat menentukan dan menyimpan agen kustom dengan petunjuk, kemampuan, dan sumber data Anda sendiri.
Panduan memulai
Lakukan panggilan agen pertama Anda, streaming respons, dan bangun agen kustom.
Agen Antigravity
Kemampuan, alat, input multimodal, dan harga untuk agen default.
Agen di AI Studio
Playground visual untuk membuat prototipe agen tanpa menulis kode.
11. Menjalankan tugas di latar belakang
Tetapkan background=True untuk menjalankan tugas yang panjang secara asinkron. Lakukan polling untuk hasil dengan interactions.get().
Python
import time
from google import genai
client = genai.Client()
interaction = client.interactions.create(
model="gemini-3.5-flash",
input="Write a detailed analysis of the impact of artificial intelligence on modern healthcare.",
background=True,
)
print(f"Started background task: {interaction.id}")
print(f"Status: {interaction.status}")
# Poll for completion
while True:
result = client.interactions.get(interaction.id)
print(f"Status: {result.status}")
if result.status == "completed":
print(f"\nResult:\n{result.output_text}")
break
elif result.status == "failed":
print(f"Failed: {result.error}")
break
time.sleep(5)
JavaScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
model: "gemini-3.5-flash",
input: "Write a detailed analysis of the impact of artificial intelligence on modern healthcare.",
background: true,
});
console.log(`Started background task: ${interaction.id}`);
console.log(`Status: ${interaction.status}`);
// Poll for completion
while (true) {
const result = await ai.interactions.get(interaction.id);
console.log(`Status: ${result.status}`);
if (result.status === "completed") {
console.log(`\nResult:\n${result.output_text}`);
break;
} else if (result.status === "failed") {
console.log(`Failed: ${result.error}`);
break;
}
await new Promise(r => setTimeout(r, 5000));
}
REST
# Start a background task
RESPONSE=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "gemini-3.5-flash",
"input": "Write a detailed analysis of the impact of artificial intelligence on modern healthcare.",
"background": true
}')
INTERACTION_ID=$(echo "$RESPONSE" | jq -r '.id')
echo "Started background task: $INTERACTION_ID"
# Poll for completion
while true; do
RESULT=$(curl -s "https://generativelanguage.googleapis.com/v1beta/interactions/$INTERACTION_ID" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Api-Revision: 2026-05-20")
STATUS=$(echo "$RESULT" | jq -r '.status')
echo "Status: $STATUS"
if [ "$STATUS" = "completed" ]; then
echo "$RESULT" | jq -r '.steps[] | select(.type=="model_output") | .content[] | select(.type=="text") | .text'
break
elif [ "$STATUS" = "failed" ]; then
echo "Failed"
break
fi
sleep 5
done
Respons:
Respons awal segera ditampilkan dengan status in_progress:
{
"id": "v1_abc123",
"status": "in_progress",
"object": "interaction",
"model": "gemini-3.5-flash"
}
Setelah tugas latar belakang dieksekusi sepenuhnya, memeriksa status interaksi akan menampilkan:
{
"id": "v1_abc123",
"status": "completed",
"steps": [
{
"type": "model_output",
"content": [
{
"type": "text",
"text": "Artificial intelligence has transformed modern healthcare in several..."
}
]
}
],
"object": "interaction",
"model": "gemini-3.5-flash",
}
Baca tentang cara menjalankan model dan agen secara asinkron dalam panduan eksekusi latar belakang.
Langkah berikutnya
- Pembuatan teks: Petunjuk sistem, konfigurasi pembuatan, dan pola teks lanjutan.
- Pembuatan gambar: Rasio aspek, pengeditan gambar, dan referensi gaya.
- Pemahaman gambar: Klasifikasi, deteksi objek, dan tanya jawab visual.
- Penalaran: Menggunakan chain-of-thought untuk tugas yang kompleks.
- Panggilan fungsi: Mode fungsi paralel, komposisional, dan terbatas.
- Google Penelusuran: Grounding, kutipan, dan saran penelusuran.
- Agen Terkelola: Agen bawaan dengan eksekusi kode dan pengelolaan file.
- Deep Research: Riset multi-langkah otonom dengan perencanaan dan sintesis.
- Output terstruktur: Skema JSON, enum, dan definisi jenis rekursif.