텍스트 생성

Gemini API는 텍스트, 이미지, 동영상, 오디오 입력에서 텍스트 출력을 생성할 수 있습니다.

다음은 기본적인 예입니다.

Python

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

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

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-flash-preview",
    "input": "How does AI work?"
  }'

Gemini로 생각하기

Gemini 모델은 요청에 응답하기 전에 모델이 추론할 수 있도록 "생각" 이 기본적으로 사용 설정되어 있는 경우가 많습니다.

각 모델은 비용, 지연 시간, 인텔리전스를 제어할 수 있는 다양한 생각 구성을 지원합니다. 자세한 내용은 생각 가이드를 참고하세요.

Python

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

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

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-flash-preview",
    "input": "How does AI work?",
    "generation_config": {
      "thinking_level": "low"
    }
  }'

시스템 안내 및 기타 구성

시스템 안내를 사용하여 Gemini 모델의 동작을 안내할 수 있습니다. system_instruction 매개변수를 전달하여 모델의 동작을 구성합니다.

Python

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

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

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

generation_config 매개변수를 사용하여 온도와 같은 기본 생성 매개변수를 재정의할 수도 있습니다.

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Explain how AI works",
    generation_config={
        "temperature": 0.1
    }
)
print(interaction.steps[-1].content[0].text)

JavaScript

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: 0.1,
    },
  });
  console.log(interaction.steps.at(-1).content[0].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-flash-preview",
    "input": "Explain how AI works",
    "generation_config": {
      "temperature": 0.1
    }
  }'

구성 가능한 매개변수와 그 설명의 전체 목록은 Interactions API 참조를 참고하세요.

멀티모달 입력

Gemini API는 멀티모달 입력을 지원하므로 텍스트와 미디어 파일을 결합할 수 있습니다. 다음 예에서는 이미지를 제공하는 방법을 보여줍니다.

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-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

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,
        mimeType: 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:
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-flash-preview",
    "input": [
      {"type": "text", "text": "Tell me about this instrument"},
      {
        "type": "image",
        "uri": "YOUR_FILE_URI",
        "mime_type": "image/jpeg"
      }
    ]
  }'

이미지를 제공하는 대체 방법과 고급 이미지 처리는 이미지 이해 가이드를 참고하세요. API는 문서, 동영상, 및 오디오 입력 및 이해도 지원합니다.

스트리밍 응답

기본적으로 모델은 전체 생성 프로세스가 완료된 후에만 응답을 반환합니다.

더 원활한 상호작용을 위해 스트리밍을 사용하여 응답 청크가 생성될 때 처리합니다.

Python

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

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.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-flash-preview",
    "input": "Explain how AI works",
    "stream": true
  }'

멀티턴 대화

Interactions API는 previous_interaction_id를 사용하여 상호작용을 연결하여 멀티턴 대화를 지원합니다. 각 턴은 별도의 상호작용이며 API는 대화 기록을 자동으로 관리합니다.

Python

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

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?",
    previousInteractionId: interaction1.id,
  });
  console.log("Response 2:", interaction2.steps.at(-1).content[0].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-flash-preview",
    "input": "I have 2 dogs in my house."
  }')

INTERACTION_ID=$(echo "$RESPONSE1" | jq -r '.name')

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "I have two dogs in my house. How many paws are in my house?",
    "previous_interaction_id": "'$INTERACTION_ID'"
  }'

스트리밍은 previous_interaction_id를 스트리밍 메서드와 결합하여 멀티턴 대화에도 사용할 수 있습니다.

Python

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

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?",
    previousInteractionId: interaction1.id,
    stream: true,
  });
  for await (const event of stream) {
    if (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: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "I have 2 dogs in my house."
  }')
INTERACTION_ID=$(echo "$RESPONSE1" | jq -r '.name')

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?alt=sse" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  --no-buffer \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "How many paws are in my house?",
    "previous_interaction_id": "'$INTERACTION_ID'",
    "stream": true
  }'

프롬프트 작성 팁

Gemini를 최대한 활용하기 위한 제안은 프롬프트 엔지니어링 가이드를 참고하세요.

다음 단계