Gemini 原生格式调用

pip install google-genai

npm install @google/genai

from google import genai

client = genai.Client(
    api_key="sk-your-api-key",  # 替换为您的令牌
    http_options={"base_url": "https://api.zestai.pro"},
)

response = client.models.generate_content(
    model="gemini-2.5-pro",  # 替换为您想使用的模型
    contents="你好，请介绍一下你自己。",
)

print(response.text)

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

const ai = new GoogleGenAI({
  apiKey: "sk-your-api-key", // 替换为您的令牌
  httpOptions: {
    baseUrl: "https://api.zestai.pro",
  },
});

const response = await ai.models.generateContent({
  model: "gemini-2.5-pro", // 替换为您想使用的模型
  contents: "你好，请介绍一下你自己。",
});

console.log(response.text);

{
  "contents": [
    {
      "parts": [{ "text": "你好，请介绍一下你自己。" }]
    }
  ]
}

from google import genai
from google.genai import types

client = genai.Client(
    api_key="sk-your-api-key",
    http_options={"base_url": "https://api.zestai.pro"},
)

response = client.models.generate_content(
    model="gemini-2.5-pro",
    contents="写一首关于秋天的诗。",
    config=types.GenerateContentConfig(
        system_instruction="你是一位擅长写古典诗词的诗人，请用古诗词风格回答。",
        temperature=0.8,
        max_output_tokens=512,
    ),
)

print(response.text)

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

const ai = new GoogleGenAI({
  apiKey: "sk-your-api-key",
  httpOptions: { baseUrl: "https://api.zestai.pro" },
});

const response = await ai.models.generateContent({
  model: "gemini-2.5-pro",
  contents: "写一首关于秋天的诗。",
  config: {
    systemInstruction: "你是一位擅长写古典诗词的诗人，请用古诗词风格回答。",
    temperature: 0.8,
    maxOutputTokens: 512,
  },
});

console.log(response.text);

{
  "system_instruction": {
    "parts": [{ "text": "你是一位擅长写古典诗词的诗人，请用古诗词风格回答。" }]
  },
  "contents": [
    {
      "parts": [{ "text": "写一首关于秋天的诗。" }]
    }
  ],
  "generationConfig": {
    "temperature": 0.8,
    "maxOutputTokens": 512
  }
}

from google import genai

client = genai.Client(
    api_key="sk-your-api-key",
    http_options={"base_url": "https://api.zestai.pro"},
)

for chunk in client.models.generate_content_stream(
    model="gemini-2.5-pro",
    contents="请详细介绍一下黑洞的形成过程。",
):
    print(chunk.text, end="", flush=True)

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

const ai = new GoogleGenAI({
  apiKey: "sk-your-api-key",
  httpOptions: { baseUrl: "https://api.zestai.pro" },
});

const stream = await ai.models.generateContentStream({
  model: "gemini-2.5-pro",
  contents: "请详细介绍一下黑洞的形成过程。",
});

for await (const chunk of stream) {
  process.stdout.write(chunk.text ?? "");
}

{
  "contents": [
    {
      "parts": [{ "text": "请详细介绍一下黑洞的形成过程。" }]
    }
  ]
}

from google import genai
from google.genai import types

client = genai.Client(
    api_key="sk-your-api-key",
    http_options={"base_url": "https://api.zestai.pro"},
)

# 创建 Chat 会话（历史自动维护）
chat = client.chats.create(
    model="gemini-2.5-pro",
    config=types.GenerateContentConfig(
        system_instruction="你是一个有帮助的助手。",
    ),
)

response1 = chat.send_message("我叫小明，我是一名程序员。")
print(f"助手: {response1.text}")

response2 = chat.send_message("你还记得我是做什么的吗？")
print(f"助手: {response2.text}")

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

const ai = new GoogleGenAI({
  apiKey: "sk-your-api-key",
  httpOptions: { baseUrl: "https://api.zestai.pro" },
});

// 创建 Chat 会话（历史自动维护）
const chat = ai.chats.create({
  model: "gemini-2.5-pro",
  config: {
    systemInstruction: "你是一个有帮助的助手。",
  },
});

const response1 = await chat.sendMessage({ message: "我叫小明，我是一名程序员。" });
console.log(`助手: ${response1.text}`);

const response2 = await chat.sendMessage({ message: "你还记得我是做什么的吗？" });
console.log(`助手: ${response2.text}`);

{
  "contents": [
    {
      "role": "user",
      "parts": [{ "text": "我叫小明，我是一名程序员。" }]
    },
    {
      "role": "model",
      "parts": [{ "text": "你好，小明！很高兴认识你，有什么我可以帮助你的吗？" }]
    },
    {
      "role": "user",
      "parts": [{ "text": "你还记得我是做什么的吗？" }]
    }
  ]
}

import httpx
from google import genai
from google.genai import types

client = genai.Client(
    api_key="sk-your-api-key",
    http_options={"base_url": "https://api.zestai.pro"},
)

# 从 URL 获取图片字节
image_bytes = httpx.get("https://example.com/image.jpg").content

response = client.models.generate_content(
    model="gemini-2.5-pro",
    contents=[
        types.Part.from_bytes(
            data=image_bytes,
            mime_type="image/jpeg",  # 支持 image/jpeg, image/png, image/webp, image/gif
        ),
        "请描述这张图片的内容。",
    ],
)

print(response.text)

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

const ai = new GoogleGenAI({
  apiKey: "sk-your-api-key",
  httpOptions: { baseUrl: "https://api.zestai.pro" },
});

// 从 URL 获取图片并转为 base64
const imageResp = await fetch("https://example.com/image.jpg");
const imageBytes = await imageResp.arrayBuffer();
const base64Image = Buffer.from(imageBytes).toString("base64");

const response = await ai.models.generateContent({
  model: "gemini-2.5-pro",
  contents: [
    {
      parts: [
        {
          inlineData: {
            mimeType: "image/jpeg",
            data: base64Image,
          },
        },
        { text: "请描述这张图片的内容。" },
      ],
    },
  ],
});

console.log(response.text);

{
  "contents": [
    {
      "parts": [
        {
          "inline_data": {
            "mime_type": "image/jpeg",
            "data": "<base64 编码的图片字符串>"
          }
        },
        { "text": "请描述这张图片的内容。" }
      ]
    }
  ]
}