Pembuatan teks

Gemini API dapat menghasilkan output teks dari input teks, gambar, video, dan audio.

Berikut contoh dasarnya:

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input="How does AI work?"
)
print(interaction.output_text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction = await ai.interactions.create({
    model: "gemini-3.5-flash",
    input: "How does AI work?",
  });
  console.log(interaction.output_text);
}

await main();

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": "How does AI work?"
  }'

SDK GenAI Google menyediakan properti praktis langsung pada objek Interaction yang ditampilkan untuk mengakses respons model.

Helper yang paling umum adalah interaction.output_text (String), yang menampilkan blok teks terakhir dalam respons model. Jika respons dibagi di beberapa blok TextContent berurutan, respons akan otomatis digabungkan. Perhatikan bahwa .output_text tidak menyertakan blok teks sebelumnya yang dipisahkan oleh konten non-teks (seperti pemikiran, gambar, audio, atau panggilan alat). Untuk respons multimodal yang kompleks atau berselang-seling, Anda harus melakukan iterasi secara manual pada steps sebagai gantinya. Untuk mempelajari lebih lanjut properti kemudahan media lainnya, lihat Ringkasan interaksi.

Berpikir dengan Gemini

Model Gemini sering kali mengaktifkan "penalaran" secara default, sehingga model dapat melakukan penalaran sebelum merespons permintaan.

Setiap model mendukung konfigurasi pemikiran yang berbeda sehingga Anda dapat mengontrol biaya, latensi, dan kecerdasan. Untuk mengetahui detail selengkapnya, lihat panduan pemikiran.

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input="How does AI work?",
    generation_config={
        "thinking_level": "low"
    }
)
print(interaction.output_text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction = await ai.interactions.create({
    model: "gemini-3.5-flash",
    input: "How does AI work?",
    generation_config: {
      thinking_level: "low",
    },
  });
  console.log(interaction.output_text);
}

await main();

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": "How does AI work?",
    "generation_config": {
      "thinking_level": "low"
    }
  }'

Petunjuk sistem dan konfigurasi lainnya

Anda dapat memandu perilaku model Gemini dengan petunjuk sistem. Teruskan parameter system_instruction untuk mengonfigurasi perilaku model.

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    system_instruction="You are a cat. Your name is Neko.",
    input="Hello there"
)

print(interaction.output_text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction = await ai.interactions.create({
    model: "gemini-3.5-flash",
    input: "Hello there",
    system_instruction: "You are a cat. Your name is Neko.",
  });
  console.log(interaction.output_text);
}

await main();

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",
    "system_instruction": "You are a cat. Your name is Neko.",
    "input": "Hello there"
  }'

Anda juga dapat mengganti parameter pembuatan default, seperti suhu, menggunakan parameter generation_config.

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input="Explain how AI works",
    generation_config={
        "temperature": 1.0
    }
)
print(interaction.output_text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction = await ai.interactions.create({
    model: "gemini-3.5-flash",
    input: "Explain how AI works",
    generation_config: {
      temperature: 1.0,
    },
  });
  console.log(interaction.output_text);
}

await main();

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",
    "generation_config": {
      "temperature": 1.0
    }
  }'

Lihat Referensi API Interaksi untuk mengetahui daftar lengkap parameter yang dapat dikonfigurasi dan deskripsinya.

Input multimodal

Gemini API mendukung input multimodal, sehingga Anda dapat menggabungkan teks dengan file media. Contoh berikut menunjukkan cara memberikan gambar:

Python

from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="path/to/organ.jpg")

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input=[
        {"type": "text", "text": "Tell me about this instrument"},
        {
            "type": "image",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        }
    ]
)
print(interaction.output_text)

JavaScript

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-3.5-flash",
    input: [
      {type: "text", text: "Tell me about this instrument"},
      {
        type: "image",
        uri: uploadedFile.uri,
        mime_type: uploadedFile.mimeType
      }
    ],
  });
  console.log(interaction.output_text);
}

await main();

REST

# First upload the file using the Files API, then use the URI:
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": [
      {"type": "text", "text": "Tell me about this instrument"},
      {
        "type": "image",
        "uri": "YOUR_FILE_URI",
        "mime_type": "image/jpeg"
      }
    ]
  }'

Untuk metode alternatif dalam menyediakan gambar dan pemrosesan gambar yang lebih canggih, lihat panduan pemahaman gambar kami. API ini juga mendukung input dan pemahaman dokumen, video, dan audio.

Respons aliran data

Secara default, model hanya menampilkan respons setelah seluruh proses pembuatan selesai.

Untuk interaksi yang lebih lancar, gunakan streaming untuk menangani potongan respons saat dibuat. Untuk panduan komprehensif yang mencakup jenis peristiwa, streaming dengan alat, pemikiran, agen, dan pembuatan gambar, lihat panduan Interaksi streaming khusus.

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:
    if event.event_type == "step.delta":
        if event.delta.type == "text":
            print(event.delta.text, end="")

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const stream = await ai.interactions.create({
    model: "gemini-3.5-flash",
    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

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
  }'

Percakapan multi-giliran

Interactions API mendukung percakapan multi-giliran dengan menggabungkan interaksi menggunakan previous_interaction_id. Setiap giliran adalah interaksi terpisah, dan API mengelola histori percakapan secara otomatis.

Python

from google import genai

client = genai.Client()

interaction1 = client.interactions.create(
    model="gemini-3.5-flash",
    input="I have 2 dogs in my house.",
)
print(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(interaction2.output_text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  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);
}

await main();

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')

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.5-flash",
    "input": "I have two dogs in my house. How many paws are in my house?",
    "previous_interaction_id": "'$INTERACTION_ID'"
  }'

Streaming juga dapat digunakan untuk percakapan multi-turn dengan menggabungkan previous_interaction_id dengan metode streaming.

Python

from google import genai

client = genai.Client()

interaction1 = client.interactions.create(
    model="gemini-3.5-flash",
    input="I have 2 dogs in my house.",
)
print(interaction1.output_text)

stream = client.interactions.create(
    model="gemini-3.5-flash",
    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

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  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 stream = await ai.interactions.create({
    model: "gemini-3.5-flash",
    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

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')

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?alt=sse" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  --no-buffer \
  -d '{
    "model": "gemini-3.5-flash",
    "input": "How many paws are in my house?",
    "previous_interaction_id": "'$INTERACTION_ID'",
    "stream": true
  }'

Percakapan stateless

Secara default, Interactions API mengelola status percakapan di sisi server saat Anda menggunakan previous_interaction_id. Namun, Anda juga dapat beroperasi dalam mode tanpa status dengan mengelola histori percakapan sendiri di sisi klien.

Untuk menggunakan mode stateless: 1. Tetapkan store=false dalam permintaan Anda untuk memilih tidak menggunakan penyimpanan sisi server. 2. Pertahankan histori percakapan sebagai array langkah di sisi klien. 3. Dalam permintaan berikutnya, teruskan langkah-langkah yang terakumulasi di kolom input, dan tambahkan giliran baru Anda sebagai langkah user_input.

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({});

async function main() {
  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);
}

await main();

REST

# Turn 1: Send request 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."
      }
    ]
  }')

# 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=$(jq -n \
  --argjson first_input '[{"type": "user_input", "content": "I have 2 dogs in my house."}]' \
  --argjson model_steps "$MODEL_STEPS" \
  --argjson second_input '[{"type": "user_input", "content": "How many paws are in my house?"}]' \
  "'"'"'$first_input + $model_steps + $second_input'"'"'")

# 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
  }"

Tips menulis perintah

Lihat panduan rekayasa perintah kami untuk mendapatkan saran tentang cara mengoptimalkan penggunaan Gemini.

Langkah berikutnya