Gemini多场景-Python代码示例

资源准备

• API Key：此项配置填写在一步API官网创建API令牌，一键直达API令牌创建页面
• 创建API令牌步骤请参考API Key的获取和使用
• API Host：此项配置填写https://yibuapi.com/v1
• 查看支持的模型请参在这里复制模型在线查询

如使用 yibuapi.com 中转：将 base_url 改为 https://yibuapi.com，并使用你在 yibuapi 控制台创建的 API Key。

快速开始：仅需三行改动

变更点（仅三行）：

1. api_key="sk-***"： 您生成的秘钥。
2. base_url="https://yibuapi.com"：
3. model="gemini-2.0-flash"（或 "gemini-2.5-flash" 等）：选择兼容的 Gemini 模型。

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://yibuapi.com"
)

response = client.chat.completions.create(
    model="gemini-2.5-flash",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain to me how AI works"}
    ]
)

print(response.choices[0].message)

在 yibuapi.com 使用（可选）

client = OpenAI(api_key="sk-***", base_url="https://yibuapi.com/v1")

推理控制（reasoning_effort / thinking budget）

Gemini 2.5 系列提供思考/推理控制。

• OpenAI 兼容字段：reasoning_effort ∈ {"low","medium","high","none"}
• 或 使用 extra_body.google.thinking_config.thinking_budget（单位：token）精细控制
• 注意：reasoning_effort 与 thinking_budget 不能同时使用

方式一：reasoning_effort

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://yibuapi.com/"
)

response = client.chat.completions.create(
    model="gemini-2.5-flash",
    reasoning_effort="low",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain to me how AI works"}
    ]
)

print(response.choices[0].message)

方式二：thinking_budget（并可返回思考摘要）

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://yibuapi.com/"
)

response = client.chat.completions.create(
    model="gemini-2.5-flash",
    messages=[{"role": "user", "content": "Explain to me how AI works"}],
    extra_body={
      "extra_body": {
        "google": {
          "thinking_config": {
            "thinking_budget": 800,
            "include_thoughts": True
          }
        }
      }
    }
)

print(response.choices[0].message)

流式输出（SSE）

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://yibuapi.com/"
)

response = client.chat.completions.create(
    model="gemini-2.0-flash",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ],
    stream=True
)

for chunk in response:
    print(chunk.choices[0].delta)

函数调用（Tools / Function Calling）

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://yibuapi.com/"
)

tools = [
  {
    "type": "function",
    "function": {
      "name": "get_weather",
      "description": "Get the weather in a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {"type": "string", "description": "The city and state, e.g. Chicago, IL"},
          "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
        },
        "required": ["location"]
      }
    }
  }
]

messages = [{"role": "user", "content": "What's the weather like in Chicago today?"}]
response = client.chat.completions.create(
  model="gemini-2.0-flash",
  messages=messages,
  tools=tools,
  tool_choice="auto"
)

print(response)

图片理解（多模态：image_url/base64）

import base64
from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://yibuapi.com/"
)

def encode_image(image_path: str) -> str:
    with open(image_path, "rb") as f:
        return base64.b64encode(f.read()).decode("utf-8")

b64 = encode_image("Path/to/agi/image.jpeg")

response = client.chat.completions.create(
  model="gemini-2.0-flash",
  messages=[
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "What is in this image?"},
        {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{b64}"}}
      ]
    }
  ]
)

print(response.choices[0])

生成图片（付费层级）

import base64
from io import BytesIO
from PIL import Image
from openai import OpenAI

client = OpenAI(
    api_key="sk-***",
    base_url="https://yibuapi.com/",
)

response = client.images.generate(
    model="imagen-3.0-generate-002",
    prompt="a portrait of a sheepadoodle wearing a cape",
    response_format="b64_json",
    n=1,
)

for item in response.data:
    img = Image.open(BytesIO(base64.b64decode(item.b64_json)))
    img.show()