Panduan ini akan membantu Anda mulai menggunakan API generateContent lama. Untuk project dan aplikasi baru, sebaiknya gunakan Interactions API baru, yang menyediakan antarmuka yang disederhanakan untuk alur kerja agentik dan model terbaru.
Panduan memulai ini menunjukkan cara menginstal
library kami dan membuat permintaan pertama, melakukan streaming
respons, membangun percakapan multi-turn, dan menggunakan alat menggunakan metode
generateContent standar.
Sebelum memulai
Untuk menggunakan Gemini API, Anda harus memiliki kunci API untuk mengautentikasi permintaan, menerapkan batas keamanan, dan melacak penggunaan ke akun Anda.
Buat secara gratis di AI Studio untuk memulai:
Menginstal Google GenAI SDK
Python
Dengan menggunakan Python 3.9+, instal
paket google-genai
menggunakan
perintah pip berikut:
pip install -q -U google-genai
JavaScript
Dengan menggunakan Node.js v18+, instal Google Gen AI SDK for TypeScript and JavaScript menggunakan perintah npm berikut:
npm install @google/genai
Buat teks
Gunakan metode models.generate_content untuk
membuat respons teks.
Python
from google import genai
client = genai.Client()
response = client.models.generate_content(
model="gemini-3.5-flash",
contents="Explain how AI works in a few words"
)
print(response.text)
JavaScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
async function main() {
const response = await ai.models.generateContent({
model: "gemini-3.5-flash",
contents: "Explain how AI works in a few words",
});
console.log(response.text);
}
main();
REST
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-flash:generateContent" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-X POST \
-d '{
"contents": [
{
"parts": [
{
"text": "Explain how AI works in a few words"
}
]
}
]
}'
Aktifkan respons bertahap
Secara default, model hanya menampilkan respons setelah seluruh proses pembuatan selesai. Untuk pengalaman yang lebih cepat dan interaktif, Anda dapat mengalirkan potongan respons saat potongan tersebut dibuat.
Python
response = client.models.generate_content_stream(
model="gemini-3.5-flash",
contents="Explain how AI works in detail"
)
for chunk in response:
print(chunk.text, end="", flush=True)
JavaScript
async function main() {
const responseStream = await ai.models.generateContentStream({
model: "gemini-3.5-flash",
contents: "Explain how AI works in detail",
});
for await (const chunk of responseStream) {
process.stdout.write(chunk.text);
}
}
main();
REST
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-flash:streamGenerateContent" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
--no-buffer \
-X POST \
-d '{
"contents": [
{
"parts": [
{
"text": "Explain how AI works in detail"
}
]
}
]
}'
Percakapan multi-giliran
Untuk percakapan multi-turn, SDK menyediakan helper chats stateful untuk
membangun pengalaman multi-turn chat
yang otomatis mengelola histori percakapan.
Python
chat = client.chats.create(model="gemini-3.5-flash")
response1 = chat.send_message("I have 2 dogs in my house.")
print("Response 1:", response1.text)
response2 = chat.send_message("How many paws are in my house?")
print("Response 2:", response2.text)
JavaScript
async function main() {
const chat = ai.chats.create({ model: "gemini-3.5-flash" });
let response = await chat.sendMessage({ message: "I have 2 dogs in my house." });
console.log("Response 1:", response.text);
response = await chat.sendMessage({ message: "How many paws are in my house?" });
console.log("Response 2:", response.text);
}
main();
REST
# REST is stateless. You must pass the full conversation history in the request.
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-flash:generateContent" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-X POST \
-d '{
"contents": [
{
"role": "user",
"parts": [{"text": "I have 2 dogs in my house."}]
},
{
"role": "model",
"parts": [{"text": "That is nice! Two dogs mean you have plenty of company."}]
},
{
"role": "user",
"parts": [{"text": "How many paws are in my house?"}]
}
]
}'
Menggunakan alat
Perluas kemampuan model dengan melakukan grounding respons dengan Google Penelusuran untuk mengakses konten web real-time. Model secara otomatis memutuskan kapan harus melakukan penelusuran, menjalankan kueri, dan menyintesis respons.
Python
from google import genai
from google.genai import types
config = types.GenerateContentConfig(
tools=[types.Tool(google_search=types.GoogleSearch())]
)
response = client.models.generate_content(
model="gemini-3.5-flash",
contents="Who won the euro 2024?",
config=config
)
print(response.text)
metadata = response.candidates[0].grounding_metadata
if metadata.web_search_queries:
print("\nSearch queries executed:")
for query in metadata.web_search_queries:
print(f" - {query}")
if metadata.grounding_chunks:
print("\nSources:")
for chunk in metadata.grounding_chunks:
print(f" - [{chunk.web.title}]({chunk.web.uri})")
JavaScript
async function main() {
const response = await ai.models.generateContent({
model: "gemini-3.5-flash",
contents: "Who won the euro 2024?",
config: {
tools: [{ googleSearch: {} }]
}
});
console.log(response.text);
const metadata = response.candidates[0]?.groundingMetadata;
if (metadata?.webSearchQueries) {
console.log("\nSearch queries executed:");
for (const query of metadata.webSearchQueries) {
console.log(` - ${query}`);
}
}
if (metadata?.groundingChunks) {
console.log("\nSources:");
for (const chunk of metadata.groundingChunks) {
console.log(` - [${chunk.web.title}](${chunk.web.uri})`);
}
}
}
main();
REST
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-flash:generateContent" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-X POST \
-d '{
"contents": [
{
"parts": [
{"text": "Who won the euro 2024?"}
]
}
],
"tools": [
{
"google_search": {}
}
]
}'
Gemini API juga mendukung alat bawaan lainnya:
- Eksekusi kode: Memungkinkan model menulis dan menjalankan kode Python untuk memecahkan masalah matematika yang kompleks.
- Konteks URL: Memungkinkan Anda mendasarkan respons pada URL halaman web tertentu yang Anda berikan.
- Penelusuran file: Memungkinkan Anda mengupload file dan mendasarkan respons pada kontennya menggunakan penelusuran semantik.
- Google Maps: Memungkinkan Anda mendasarkan respons pada data lokasi dan menelusuri tempat, rute, dan peta.
- Penggunaan komputer: Memungkinkan model berinteraksi dengan layar, keyboard, dan mouse komputer virtual untuk melakukan tugas.
Memanggil fungsi kustom
Gunakan panggilan fungsi untuk menghubungkan
model ke alat dan API kustom Anda. Model menentukan kapan harus memanggil fungsi Anda dan menampilkan functionCall dalam respons agar aplikasi Anda dapat dieksekusi.
Contoh ini mendeklarasikan fungsi temperatur tiruan dan memeriksa apakah model ingin memanggilnya.
Python
from google import genai
from google.genai import types
weather_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"],
},
}
tools = types.Tool(function_declarations=[weather_function])
config = types.GenerateContentConfig(tools=[tools])
contents = ["What's the temperature in London?"]
response = client.models.generate_content(
model="gemini-3.5-flash",
contents=contents,
config=config,
)
part = response.candidates[0].content.parts[0]
if part.function_call:
fc = part.function_call
print(f"Model requested function: {fc.name} with args {fc.args}")
mock_result = {"temperature": "15C", "condition": "Cloudy"}
contents.append(response.candidates[0].content)
fn_response_part = types.Part.from_function_response(
name=fc.name,
response=mock_result,
id=fc.id
)
contents.append(types.Content(role="user", parts=[fn_response_part]))
final_response = client.models.generate_content(
model="gemini-3.5-flash",
contents=contents,
config=config,
)
print("Final Response:", final_response.text)
JavaScript
import { GoogleGenAI, Type } from '@google/genai';
async function main() {
const weatherFunction = {
name: 'get_current_temperature',
description: 'Gets the current temperature for a given location.',
parameters: {
type: Type.OBJECT,
properties: {
location: {
type: Type.STRING,
description: 'The city name, e.g. San Francisco',
},
},
required: ['location'],
},
};
const contents = [{
role: 'user',
parts: [{ text: "What's the temperature in London?" }]
}];
const response = await ai.models.generateContent({
model: 'gemini-3.5-flash',
contents: contents,
config: {
tools: [{ functionDeclarations: [weatherFunction] }],
},
});
if (response.functionCalls && response.functionCalls.length > 0) {
const fc = response.functionCalls[0];
console.log(`Model requested function: ${fc.name}`);
const mockResult = { temperature: "15C", condition: "Cloudy" };
contents.push(response.candidates[0].content);
contents.push({
role: 'user',
parts: [{
functionResponse: {
name: fc.name,
response: mockResult,
id: fc.id
}
}]
});
const finalResponse = await ai.models.generateContent({
model: 'gemini-3.5-flash',
contents: contents,
config: {
tools: [{ functionDeclarations: [weatherFunction] }],
},
});
console.log("Final Response:", finalResponse.text);
}
}
main();
REST
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-flash:generateContent" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-X POST \
-d '{
"contents": [
{
"role": "user",
"parts": [{"text": "What'\''s the temperature in London?"}]
}
],
"tools": [
{
"functionDeclarations": [
{
"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"]
}
}
]
}
]
}'
Langkah berikutnya
Setelah mulai menggunakan Gemini API, pelajari panduan berikut untuk membuat aplikasi yang lebih canggih: