使用系統指令

本頁說明如何使用系統指令引導模型行為。如需概念總覽和最佳做法，請參閱「系統指令簡介」。

本頁面涵蓋下列主題：

• 用途：系統指令的常見應用。
• 程式碼範例：瞭解如何使用 Vertex AI SDK 和 REST API 實作系統指令。
• 提示範例：程式碼生成和資料格式化等工作的具體範例。

系統指令是一組您在提示前提供給模型的指令。建議您使用系統指令來調整模型行為，告訴模型應如何回應。舉例來說，您可以加入角色或人物、背景資訊和格式設定指示：

You are a friendly and helpful assistant.
Ensure your answers are complete, unless the user requests a more concise approach.
When generating code, offer explanations for code segments as necessary and maintain good coding practices.
When presented with inquiries seeking information, provide answers that reflect a deep understanding of the field, guaranteeing their correctness.
For any non-english queries, respond in the same language as the prompt unless otherwise specified by the user.
For prompts involving reasoning, provide a clear explanation of each step in the reasoning process before presenting the final answer.

系統指令會套用至整個要求，包括對話中的多個使用者和模型回合。雖然系統指令與提示內容分開，但仍屬於整體提示的一部分，因此須遵守標準資料使用政策。

系統指令可引導模型遵循指令，但無法完全防止越獄或洩漏。建議您謹慎行事，避免在系統指令中加入私密資訊。

用途

您可以透過多種方式使用系統指令，包括：

• 定義人物角色或角色：例如聊天機器人。
• 定義輸出格式：例如 Markdown 或 YAML。
• 定義輸出內容的風格和語氣：例如詳細程度、正式程度和目標閱讀程度。
• 定義工作目標或規則：例如，傳回程式碼片段，不必提供進一步說明。
• 提供提示的其他背景資訊：例如知識截止日期。

• 指定回覆語言：有時即使提示使用其他語言，模型仍會以當地語言回覆。如果提示使用非英文語言，建議您在系統指令中加入下列內容：

  All questions should be answered comprehensively with details, unless the user requests a concise response specifically. Respond in the same language as the query.
  

程式碼範例

下列分頁中的程式碼範例，說明如何在生成式 AI 應用程式中使用系統指令。

Python

安裝

pip install --upgrade google-genai

詳情請參閱 SDK 參考說明文件。

設定環境變數，透過 Vertex AI 使用 Gen AI SDK：

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

from google import genai
from google.genai.types import GenerateContentConfig, HttpOptions

client = genai.Client(http_options=HttpOptions(api_version="v1"))
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Why is the sky blue?",
    config=GenerateContentConfig(
        system_instruction=[
            "You're a language translator.",
            "Your mission is to translate text in English to French.",
        ]
    ),
)
print(response.text)
# Example response:
# Pourquoi le ciel est-il bleu ?

Go

瞭解如何安裝或更新 Go。

詳情請參閱 SDK 參考說明文件。

設定環境變數，透過 Vertex AI 使用 Gen AI SDK：

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

import (
	"context"
	"fmt"
	"io"

	genai "google.golang.org/genai"
)

// generateWithSystem shows how to generate text using a text prompt and system instruction.
func generateWithSystem(w io.Writer) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	modelName := "gemini-2.5-flash"
	contents := genai.Text("Why is the sky blue?")
	config := &genai.GenerateContentConfig{
		SystemInstruction: &genai.Content{
			Parts: []*genai.Part{
				{Text: "You're a language translator. Your mission is to translate text in English to French."},
			},
		},
	}

	resp, err := client.Models.GenerateContent(ctx, modelName, contents, config)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	respText := resp.Text()

	fmt.Fprintln(w, respText)

	// Example response:
	// Pourquoi le ciel est-il bleu ?

	return nil
}

Node.js

安裝

npm install @google/genai

詳情請參閱 SDK 參考說明文件。

設定環境變數，透過 Vertex AI 使用 Gen AI SDK：

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

const {GoogleGenAI} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION = process.env.GOOGLE_CLOUD_LOCATION || 'global';

async function generateContent(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const ai = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const prompt = `
  User input: I like bagels.
  Answer:
  `;

  const response = await ai.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: prompt,
    config: {
      systemInstruction: [
        'You are a language translator.',
        'Your mission is to translate text in English to French.',
      ],
    },
  });

  console.log(response.text);

  return response.text;
}

Java

瞭解如何安裝或更新 Java。

詳情請參閱 SDK 參考說明文件。

設定環境變數，透過 Vertex AI 使用 Gen AI SDK：

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

import com.google.genai.Client;
import com.google.genai.types.Content;
import com.google.genai.types.GenerateContentConfig;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.HttpOptions;
import com.google.genai.types.Part;

public class TextGenerationWithSystemInstruction {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash";
    generateContent(modelId);
  }

  // Generates text with text and system instruction input
  public static String generateContent(String modelId) {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests.
    try (Client client =
        Client.builder()
            .location("global")
            .vertexAI(true)
            .httpOptions(HttpOptions.builder().apiVersion("v1").build())
            .build()) {

      GenerateContentConfig config =
          GenerateContentConfig.builder()
              .systemInstruction(
                  Content.fromParts(
                      Part.fromText("You're a language translator."),
                      Part.fromText("Your mission is to translate text in English to French.")))
              .build();

      GenerateContentResponse response =
          client.models.generateContent(modelId, "Why is the sky blue?", config);

      System.out.print(response.text());
      // Example response:
      // Pourquoi le ciel est-il bleu ?
      return response.text();
    }
  }
}

REST

設定環境後，您可以使用 REST 測試文字提示。下列範例會將要求傳送至發布商模型端點。

使用任何要求資料之前，請先替換以下項目：

• GENERATE_RESPONSE_METHOD：您希望模型生成的回應類型。 選擇生成模型回覆傳回方式的方法：
  • streamGenerateContent：在生成回覆時串流傳輸，減少人類觀眾的延遲感。
  • generateContent：系統會在完整生成回覆後傳回。
• LOCATION：處理要求的區域。可用的選項包括：

  按一下即可展開可用地區的部分清單

  • us-central1
  • us-west4
  • northamerica-northeast1
  • us-east4
  • us-west1
  • asia-northeast3
  • asia-southeast1
  • asia-northeast1
• PROJECT_ID：您的專案 ID。
• MODEL_ID：您要使用的多模態模型 ID。
• ROLE： 與內容相關聯的對話角色。即使是單輪對話，也必須指定角色。可接受的值包括：
  • USER：指定您傳送的內容。
  • MODEL：指定模型的回覆。
• TEXT

  要加入提示的文字指令。 例如：User input: I like bagels。
• SAFETY_CATEGORY： 要設定門檻的安全類別。可接受的值包括：

  按一下即可展開安全類別

  • HARM_CATEGORY_SEXUALLY_EXPLICIT
  • HARM_CATEGORY_HATE_SPEECH
  • HARM_CATEGORY_HARASSMENT
  • HARM_CATEGORY_DANGEROUS_CONTENT
• THRESHOLD： 根據機率封鎖可能屬於指定安全類別的回應。可接受的值包括：

  按一下即可展開封鎖門檻

  • BLOCK_NONE
  • BLOCK_ONLY_HIGH
  • BLOCK_MEDIUM_AND_ABOVE (預設)
  • BLOCK_LOW_AND_ABOVE
  BLOCK_LOW_AND_ABOVE 封鎖最多內容，而 BLOCK_ONLY_HIGH 封鎖最少內容。
• SYSTEM_INSTRUCTION

  (選填) 不適用於所有型號。指示模型，引導模型提升成效。 JSON 不支援換行符。將這個欄位中的所有換行符號替換為 \n。例如：You are a helpful language translator.\nYour mission is to translate text in English to French.
• TEMPERATURE： 溫度用於在生成回覆期間取樣，這會在套用 topP 和 topK 時發生。溫度參數會決定選取詞元時的隨機程度。 如果希望提示生成較不具開放性和創意性的回覆，建議調低溫度參數。另一方面，如果溫度參數較高，則可能產生較多元或有創意的結果。如果溫度參數為 0，模型一律會選取可能性最高的詞元。在這種情況下，特定提示的回覆大多是確定性的，但仍可能出現少量差異。

  如果模型的回覆太普通、太短或提供了備用回覆，再試試看調高 Temperature。

• TOP_P： Top-P 會影響模型選取輸出詞元的方式。模型會按照可能性最高到最低的順序選取符記，直到所選符記的可能性總和等於 Top-P 值。舉例來說，假設詞元 A、B 和 C 的可能性分別為 0.3、0.2 和 0.1，而「Top-P」值為 0.5，模型會依據 temperature 選擇 A 或 B 做為下一個詞元，並排除 C。

  如要取得較不隨機的回覆，請指定較低的值；如要取得較隨機的回覆，請調高此值。

• TOP_K： Top-K 會影響模型選取輸出詞元的方式。如果 Top-K 設為 1，代表下一個所選詞元是模型詞彙表的所有詞元中可能性最高者 (也稱為「貪婪解碼」)。如果 Top-K 設為 3，則代表模型會依據 temperature，從可能性最高的 3 個詞元中選取下一個詞元。

  在每個符記選取步驟中，模型會對機率最高的「Top-K」符記取樣，接著進一步根據「Top-P」篩選詞元，最後依 temperature 選出最終詞元。

  如要取得較不隨機的回覆，請指定較低的值；如要取得較隨機的回覆，請調高此值。

• MAX_OUTPUT_TOKENS： 回覆內可以生成的詞元數量上限。一個詞元約為四個字元。100 個符記約等於 60 到 80 個字。

  如要取得較短的回覆，請指定較低的值；如要取得可能較長的回覆，請調高此值。

• STOP_SEQUENCES： 指定字串清單，如果模型在回覆中遇到其中一個字串，就會停止生成文字。如果字串在回應中出現多次，系統會在第一次遇到該字串時截斷回應。字串須區分大小寫。
  
  舉例來說，如果未指定 stopSequences 時傳回的回應如下：
  
  public static string reverse(string myString)
  
  則將 stopSequences 設為 ["Str", "reverse"] 時傳回的回應如下：
  
  public static string
  
  如要停用停止序列，請指定空陣列 ([])。

如要傳送要求，請選擇以下其中一個選項：

curl

注意： 下列指令假設您已執行 gcloud init 或 gcloud auth login，透過使用者帳戶登入 gcloud CLI，或使用 Cloud Shell，自動登入 gcloud CLI。 您可以執行 gcloud auth list 查看目前有效的帳戶。

將要求主體儲存在名為 request.json 的檔案中。 在終端機中執行下列指令，在目前目錄中建立或覆寫這個檔案：

cat > request.json << 'EOF'
{
  "contents": {
    "role": "ROLE",
    "parts": { "text": "TEXT" }
  },
  "system_instruction":
  {
    "parts": [
      {
        "text": "SYSTEM_INSTRUCTION"
      }
    ]
  },
  "safety_settings": {
    "category": "SAFETY_CATEGORY",
    "threshold": "THRESHOLD"
  },
  "generation_config": {
    "temperature": TEMPERATURE,
    "topP": TOP_P,
    "topK": TOP_K,
    "candidateCount": 1,
    "maxOutputTokens": MAX_OUTPUT_TOKENS,
    "stopSequences": STOP_SEQUENCES
  }
}
EOF

接著，請執行下列指令來傳送 REST 要求：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:GENERATE_RESPONSE_METHOD"

PowerShell

注意： 下列指令假設您已執行 gcloud init 或 gcloud auth login，透過使用者帳戶登入 gcloud CLI。 您可以執行 gcloud auth list 查看目前有效的帳戶。

將要求主體儲存在名為 request.json 的檔案中。 在終端機中執行下列指令，在目前目錄中建立或覆寫這個檔案：

@'
{
  "contents": {
    "role": "ROLE",
    "parts": { "text": "TEXT" }
  },
  "system_instruction":
  {
    "parts": [
      {
        "text": "SYSTEM_INSTRUCTION"
      }
    ]
  },
  "safety_settings": {
    "category": "SAFETY_CATEGORY",
    "threshold": "THRESHOLD"
  },
  "generation_config": {
    "temperature": TEMPERATURE,
    "topP": TOP_P,
    "topK": TOP_K,
    "candidateCount": 1,
    "maxOutputTokens": MAX_OUTPUT_TOKENS,
    "stopSequences": STOP_SEQUENCES
  }
}
'@  | Out-File -FilePath request.json -Encoding utf8

接著，請執行下列指令來傳送 REST 要求：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:GENERATE_RESPONSE_METHOD" | Select-Object -Expand Content

您應該會收到類似如下的 JSON 回應。

回應

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "J'aime les bagels. \n"
          }
        ]
      },
      "finishReason": "STOP",
      "safetyRatings": [
        {
          "category": "HARM_CATEGORY_HATE_SPEECH",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.1481704,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.07921032
        },
        {
          "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.07185127,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.10302442
        },
        {
          "category": "HARM_CATEGORY_HARASSMENT",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.11920293,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.07626997
        },
        {
          "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.20212802,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.13386749
        }
      ]
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 25,
    "candidatesTokenCount": 8,
    "totalTokenCount": 33
  }
}

請注意這個範例網址中的以下部分：

• 使用 generateContent 方法，要求在完整生成回覆後再傳回。 如要減少人類觀眾的延遲感，請使用 streamGenerateContent 方法，在生成回覆的同時串流回覆內容。
• 多模態模型 ID 位於網址尾端，方法之前 (例如 gemini-2.0-flash)。這個範例也可能支援其他模型。

提示範例

以下是定義模型預期行為的系統提示範例。

程式碼生成

程式碼生成

系統操作說明： You are a coding expert that specializes in rendering code for front-end interfaces. When I describe a component of a website I want to build, please return the HTML and CSS needed to do so. Do not give an explanation for this code. Also offer some UI design suggestions. 提示： Create a box in the middle of the page that contains a rotating selection of images each with a caption. The image in the center of the page should have shadowing behind it to make it stand out. It should also link to another page of the site. Leave the URL blank so that I can fill it in.

產生格式化資料

生成格式化資料

系統操作說明： You are an assistant for home cooks. You receive a list of ingredients and respond with a list of recipes that use those ingredients. Recipes which need no extra ingredients should always be listed before those that do. Your response must be a JSON object containing 3 recipes. A recipe object has the following schema: * name: The name of the recipe * usedIngredients: Ingredients in the recipe that were provided in the list * otherIngredients: Ingredients in the recipe that were not provided in the list (omitted if there are no other ingredients) * description: A brief description of the recipe, written positively as if to sell it 提示： * 1 lb bag frozen broccoli * 1 pint heavy cream * 1 lb pack cheese ends and pieces

音樂聊天機器人

音樂聊天機器人

系統操作說明： You will respond as a music historian, demonstrating comprehensive knowledge across diverse musical genres and providing relevant examples. Your tone will be upbeat and enthusiastic, spreading the joy of music. If a question is not related to music, the response should be, "That is beyond my knowledge." 提示： If a person was born in the sixties, what was the most popular music genre being played when they were born? List five songs by bullet point.

財務分析

財務分析

系統操作說明： As a financial analysis expert, your role is to interpret complex financial data, offer personalized advice, and evaluate investments using statistical methods to gain insights across different financial areas. Accuracy is the top priority. All information, especially numbers and calculations, must be correct and reliable. Always double-check for errors before giving a response. The way you respond should change based on what the user needs. For tasks with calculations or data analysis, focus on being precise and following instructions rather than giving long explanations. If you're unsure, ask the user for more information to ensure your response meets their needs. For tasks that are not about numbers: * Use clear and simple language to avoid confusion and don't use jargon. * Make sure you address all parts of the user's request and provide complete information. * Think about the user's background knowledge and provide additional context or explanation when needed. Formatting and Language: * Follow any specific instructions the user gives about formatting or language. * Use proper formatting like JSON or tables to make complex data or results easier to understand. 提示： Please summarize the key insights of given numerical tables. CONSOLIDATED STATEMENTS OF INCOME (In millions, except per share amounts) |Year Ended December 31 | 2020 | 2021 | 2022 | |--- | --- | --- | --- | |Revenues | $ 182,527| $ 257,637| $ 282,836| |Costs and expenses:| |Cost of revenues | 84,732 | 110,939 | 126,203| |Research and development | 27,573 | 31,562 | 39,500| |Sales and marketing | 17,946 | 22,912 | 26,567| |General and administrative | 11,052 | 13,510 | 15,724| |Total costs and expenses | 141,303| 178,923| 207,994| |Income from operations | 41,224 | 78,714 | 74,842| |Other income (expense), net | 6,858 | 12,020 | (3,514)| |Income before income taxes | 48,082 | 90,734 | 71,328| |Provision for income taxes | 7,813 | 14,701 | 11,356| |Net income | $40,269| $76,033 | $59,972| |Basic net income per share of Class A, Class B, and Class C stock | $2.96| $5.69| $4.59| |Diluted net income per share of Class A, Class B, and Class C stock| $2.93| $5.61| $4.56| Please list important, but no more than five, highlights from 2020 to 2022 in the given table. Please write in a professional and business-neutral tone. The summary should only be based on the information presented in the table.

市場情緒分析

市場情緒分析

系統操作說明： You are a stock market analyst who analyzes market sentiment given a news snippet. Based on the news snippet, you extract statements that impact investor sentiment. Respond in JSON format and for each statement: * Give a score 1 - 10 to suggest if the sentiment is negative or positive (1 is most negative 10 is most positive, 5 will be neutral). * Reiterate the statement. * Give a one sentence explanation. 提示： Mobileye reported a build-up of excess inventory by top-tier customers following supply-chain constraints in recent years. Revenue for the first quarter is expected to be down about 50% from $458 million generated a year earlier, before normalizing over the remainder of 2024, Mobileye said. Mobileye forecast revenue for full-year 2024 at between $1.83 billion and $1.96 billion, down from the about $2.08 billion it now expects for 2023.

後續步驟

• 如需更多提示範例，請前往提示庫。