我们最先进的模型 Gemini 2.5 Pro Experimental 现已推出！了解详情

此页面由 Cloud Translation API 翻译。

文本生成

Gemini API 可以根据各种输入（包括文本、图片、视频和音频）生成文本输出。本指南介绍了如何使用文本和图片输入生成文本。还介绍了在线播放、聊天和系统说明。

文字输入

使用 Gemini API 生成文本的最简单方法是向模型提供单个纯文本输入，如以下示例所示：

from google import genai

client = genai.Client(api_key="GEMINI_API_KEY")

response = client.models.generate_content(
    model="gemini-2.0-flash",
    contents=["How does AI work?"]
)
print(response.text)

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

const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });

async function main() {
  const response = await ai.models.generateContent({
    model: "gemini-2.0-flash",
    contents: "How does AI work?",
  });
  console.log(response.text);
}

await main();

// import packages here

func main() {
  ctx := context.Background()
  client, err := genai.NewClient(ctx, option.WithAPIKey(os.Getenv("GEMINI_API_KEY")))
  if err != nil {
    log.Fatal(err)
  }
  defer client.Close()

  model := client.GenerativeModel("gemini-2.0-flash")
  resp, err := model.GenerateContent(ctx, genai.Text("How does AI work?"))
  if err != nil {
    log.Fatal(err)
  }
  printResponse(resp) // helper function for printing content parts
}

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "text": "How does AI work?"
          }
        ]
      }
    ]
  }'

图片输入

Gemini API 支持将文本和媒体文件组合在一起的多模态输入。以下示例展示了如何根据文本和图片输入生成文本：

PythonJavaScriptGoREST

from PIL import Image
from google import genai

client = genai.Client(api_key="GEMINI_API_KEY")

image = Image.open("/path/to/organ.png")
response = client.models.generate_content(
    model="gemini-2.0-flash",
    contents=[image, "Tell me about this instrument"]
)
print(response.text)

import {
  GoogleGenAI,
  createUserContent,
  createPartFromUri,
} from "@google/genai";

const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });

async function main() {
  const image = await ai.files.upload({
    file: "/path/to/organ.png",
  });
  const response = await ai.models.generateContent({
    model: "gemini-2.0-flash",
    contents: [
      createUserContent([
        "Tell me about this instrument",
        createPartFromUri(image.uri, image.mimeType),
      ]),
    ],
  });
  console.log(response.text);
}

await main();

model := client.GenerativeModel("gemini-2.0-flash")

imgData, err := os.ReadFile(filepath.Join(testDataDir, "organ.jpg"))
if err != nil {
  log.Fatal(err)
}

resp, err := model.GenerateContent(ctx,
  genai.Text("Tell me about this instrument"),
  genai.ImageData("jpeg", imgData))
if err != nil {
  log.Fatal(err)
}

printResponse(resp)

# Use a temporary file to hold the base64 encoded image data
TEMP_B64=$(mktemp)
trap 'rm -f "$TEMP_B64"' EXIT
base64 $B64FLAGS $IMG_PATH > "$TEMP_B64"

# Use a temporary file to hold the JSON payload
TEMP_JSON=$(mktemp)
trap 'rm -f "$TEMP_JSON"' EXIT

cat > "$TEMP_JSON" << EOF
{
  "contents": [
    {
      "parts": [
        {
          "text": "Tell me about this instrument"
        },
        {
          "inline_data": {
            "mime_type": "image/jpeg",
            "data": "$(cat "$TEMP_B64")"
          }
        }
      ]
    }
  ]
}
EOF

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -X POST \
  -d "@$TEMP_JSON"

流式输出

默认情况下，模型会在完成整个文本生成流程后返回回答。您可以使用流式传输在 GenerateContentResponse 实例生成时返回这些实例，从而实现更快的互动。

PythonJavaScriptGoREST

from google import genai

client = genai.Client(api_key="GEMINI_API_KEY")

response = client.models.generate_content_stream(
    model="gemini-2.0-flash",
    contents=["Explain how AI works"]
)
for chunk in response:
    print(chunk.text, end="")

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

const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });

async function main() {
  const response = await ai.models.generateContentStream({
    model: "gemini-2.0-flash",
    contents: "Explain how AI works",
  });

  for await (const chunk of response) {
    console.log(chunk.text);
  }
}

await main();

model := client.GenerativeModel("gemini-1.5-flash")
iter := model.GenerateContentStream(ctx, genai.Text("Write a story about a magic backpack."))
for {
  resp, err := iter.Next()
  if err == iterator.Done {
    break
  }
  if err != nil {
    log.Fatal(err)
  }
  printResponse(resp)
}

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:streamGenerateContent?alt=sse&key=${GEMINI_API_KEY}" \
  -H 'Content-Type: application/json' \
  --no-buffer \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "text": "Explain how AI works"
          }
        ]
      }
    ]
  }'

多轮对话

借助 Gemini SDK，您可以将多轮问题和回答收集到一个对话中。借助聊天格式，用户可以逐步获得答案，并在遇到多部分问题时获得帮助。此 SDK 聊天实现提供了一个界面来跟踪对话历史记录，但在后台，它使用相同的 generateContent 方法来创建响应。

以下代码示例展示了基本聊天功能的实现：

PythonJavaScriptGoREST

from google import genai

client = genai.Client(api_key="GEMINI_API_KEY")
chat = client.chats.create(model="gemini-2.0-flash")

response = chat.send_message("I have 2 dogs in my house.")
print(response.text)

response = chat.send_message("How many paws are in my house?")
print(response.text)

for message in chat.get_history():
    print(f'role - {message.role}',end=": ")
    print(message.parts[0].text)

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

const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });

async function main() {
  const chat = ai.chats.create({
    model: "gemini-2.0-flash",
    history: [
      {
        role: "user",
        parts: [{ text: "Hello" }],
      },
      {
        role: "model",
        parts: [{ text: "Great to meet you. What would you like to know?" }],
      },
    ],
  });

  const response1 = await chat.sendMessage({
    message: "I have 2 dogs in my house.",
  });
  console.log("Chat response 1:", response1.text);

  const response2 = await chat.sendMessage({
    message: "How many paws are in my house?",
  });
  console.log("Chat response 2:", response2.text);
}

await main();

model := client.GenerativeModel("gemini-1.5-flash")
cs := model.StartChat()

cs.History = []*genai.Content{
  {
    Parts: []genai.Part{
      genai.Text("Hello, I have 2 dogs in my house."),
    },
    Role: "user",
  },
  {
    Parts: []genai.Part{
      genai.Text("Great to meet you. What would you like to know?"),
    },
    Role: "model",
  },
}

res, err := cs.SendMessage(ctx, genai.Text("How many paws are in my house?"))
if err != nil {
  log.Fatal(err)
}
printResponse(res)

curl https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GEMINI_API_KEY \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "Hello"
          }
        ]
      },
      {
        "role": "model",
        "parts": [
          {
            "text": "Great to meet you. What would you like to know?"
          }
        ]
      },
      {
        "role": "user",
        "parts": [
          {
            "text": "I have two dogs in my house. How many paws are in my house?"
          }
        ]
      }
    ]
  }'

您还可以将流式传输与聊天功能搭配使用，如以下示例所示：

PythonJavaScriptGoREST

from google import genai

client = genai.Client(api_key="GEMINI_API_KEY")
chat = client.chats.create(model="gemini-2.0-flash")

response = chat.send_message_stream("I have 2 dogs in my house.")
for chunk in response:
    print(chunk.text, end="")

response = chat.send_message_stream("How many paws are in my house?")
for chunk in response:
    print(chunk.text, end="")

for message in chat.get_history():
    print(f'role - {message.role}', end=": ")
    print(message.parts[0].text)

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

const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });

async function main() {
  const chat = ai.chats.create({
    model: "gemini-2.0-flash",
    history: [
      {
        role: "user",
        parts: [{ text: "Hello" }],
      },
      {
        role: "model",
        parts: [{ text: "Great to meet you. What would you like to know?" }],
      },
    ],
  });

  const stream1 = await chat.sendMessageStream({
    message: "I have 2 dogs in my house.",
  });
  for await (const chunk of stream1) {
    console.log(chunk.text);
    console.log("_".repeat(80));
  }

  const stream2 = await chat.sendMessageStream({
    message: "How many paws are in my house?",
  });
  for await (const chunk of stream2) {
    console.log(chunk.text);
    console.log("_".repeat(80));
  }
}

await main();

model := client.GenerativeModel("gemini-1.5-flash")
cs := model.StartChat()

cs.History = []*genai.Content{
  {
    Parts: []genai.Part{
      genai.Text("Hello, I have 2 dogs in my house."),
    },
    Role: "user",
  },
  {
    Parts: []genai.Part{
      genai.Text("Great to meet you. What would you like to know?"),
    },
    Role: "model",
  },
}

iter := cs.SendMessageStream(ctx, genai.Text("How many paws are in my house?"))
for {
  resp, err := iter.Next()
  if err == iterator.Done {
    break
  }
  if err != nil {
    log.Fatal(err)
  }
  printResponse(resp)
}

curl https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:streamGenerateContent?alt=sse&key=$GEMINI_API_KEY \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "Hello"
          }
        ]
      },
      {
        "role": "model",
        "parts": [
          {
            "text": "Great to meet you. What would you like to know?"
          }
        ]
      },
      {
        "role": "user",
        "parts": [
          {
            "text": "I have two dogs in my house. How many paws are in my house?"
          }
        ]
      }
    ]
  }'

配置参数

您向模型发送的每个提示都包含控制模型如何生成回答的参数。您可以配置这些参数，也可以让模型使用默认选项。

以下示例展示了如何配置模型参数：

PythonJavaScriptGoREST

from google import genai
from google.genai import types

client = genai.Client(api_key="GEMINI_API_KEY")

response = client.models.generate_content(
    model="gemini-2.0-flash",
    contents=["Explain how AI works"],
    config=types.GenerateContentConfig(
        max_output_tokens=500,
        temperature=0.1
    )
)
print(response.text)

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

const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });

async function main() {
  const response = await ai.models.generateContent({
    model: "gemini-2.0-flash",
    contents: "Explain how AI works",
    config: {
      maxOutputTokens: 500,
      temperature: 0.1,
    },
  });
  console.log(response.text);
}

await main();

model := client.GenerativeModel("gemini-1.5-pro-latest")
model.SetTemperature(0.9)
model.SetTopP(0.5)
model.SetTopK(20)
model.SetMaxOutputTokens(100)
model.SystemInstruction = genai.NewUserContent(genai.Text("You are Yoda from Star Wars."))
model.ResponseMIMEType = "application/json"
resp, err := model.GenerateContent(ctx, genai.Text("What is the average size of a swallow?"))
if err != nil {
  log.Fatal(err)
}
printResponse(resp)

curl https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GEMINI_API_KEY \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "text": "Explain how AI works"
          }
        ]
      }
    ],
    "generationConfig": {
      "stopSequences": [
        "Title"
      ],
      "temperature": 1.0,
      "maxOutputTokens": 800,
      "topP": 0.8,
      "topK": 10
    }
  }'

以下是您可以配置的一些模型参数。（命名惯例因编程语言而异。）

stopSequences：指定一组将停止生成输出的字符序列（最多 5 个）。如果指定，API 会在 stop_sequence 首次出现时停止。停止序列不会包含在响应中。
temperature：控制输出的随机性。使用较高的值可获得更具创造性的回答，使用较低的值可获得更具确定性的回答。值的范围为 [0.0, 2.0]。
maxOutputTokens：设置候选项中包含的词元数上限。
topP：更改模型选择输出词元的方式。系统会按照概率从最高到最低的顺序选择 token，直到所选 token 的概率总和等于 topP 值。默认的 topP 值为 0.95。
topK：更改模型选择输出词元的方式。如果 topK 设为 1，则表示所选 token 是模型词汇表的所有 token 中概率最高的 token；如果 topK 设为 3，则表示系统将从 3 个概率最高的 token 中选择下一个 token（通过温度确定）。系统会根据 topP 进一步过滤词元，并使用温度采样选择最终的词元。

系统指令

借助系统说明，您可以根据具体用例来控制模型的行为。提供系统说明时，您可以为模型提供额外的上下文，帮助其了解任务并生成自定义程度更高的回答。模型应在与用户的完整互动过程中遵循系统说明，以便您能够指定产品级行为，而无需考虑最终用户提供的提示。

您可以在初始化模型时设置系统说明：

PythonJavaScriptGoREST

from google import genai
from google.genai import types

client = genai.Client(api_key="GEMINI_API_KEY")

response = client.models.generate_content(
    model="gemini-2.0-flash",
    config=types.GenerateContentConfig(
        system_instruction="You are a cat. Your name is Neko."),
    contents="Hello there"
)

print(response.text)

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

const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });

async function main() {
  const response = await ai.models.generateContent({
    model: "gemini-2.0-flash",
    contents: "Hello there",
    config: {
      systemInstruction: "You are a cat. Your name is Neko.",
    },
  });
  console.log(response.text);
}

await main();

// import packages here

func main() {
  ctx := context.Background()
  client, err := genai.NewClient(ctx, option.WithAPIKey(os.Getenv("GEMINI_API_KEY")))
  if err != nil {
    log.Fatal(err)
  }
  defer client.Close()

  model := client.GenerativeModel("gemini-2.0-flash")
  model.SystemInstruction = &genai.Content{
    Parts: []genai.Part{genai.Text(`
      You are a cat. Your name is Neko.
    `)},
  }
  resp, err := model.GenerateContent(ctx, genai.Text("Hello there"))
  if err != nil {
    log.Fatal(err)
  }
  printResponse(resp) // helper function for printing content parts
}

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "system_instruction": {
      "parts": [
        {
          "text": "You are a cat. Your name is Neko."
        }
      ]
    },
    "contents": [
      {
        "parts": [
          {
            "text": "Hello there"
          }
        ]
      }
    ]
  }'

然后，您可以像往常一样向模型发送请求。

支持的模型

整个 Gemini 系列模型都支持文本生成。如需详细了解这些模型及其功能，请参阅模型。

提示技巧

对于基本文本生成应用场景，您的问题可能不需要包含任何输出示例、系统说明或格式信息。这是一种零样本方法。对于某些用例，单次或少样本提示可能会生成更符合用户预期的输出。在某些情况下，您可能还需要提供系统说明，以帮助模型了解任务或遵循特定准则。

后续步骤

试用 Gemini API 使用入门 Colab。
了解如何使用 Gemini 的视觉理解功能处理图片和视频。
了解如何使用 Gemini 的音频理解功能处理音频文件。
了解多模态文件提示策略。