> ## Documentation Index
> Fetch the complete documentation index at: https://docs.crazyrouter.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Python 基础对话

> Python 实现基础聊天、连续对话和流式输出

> 更新日期：2026-06-06

## 安装依赖

```bash theme={null}
pip install openai requests
```

## 基础对话

<CodeGroup>
  ```python OpenAI SDK theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="sk-xxx",
      base_url="https://api.crazyrouter.com/v1"
  )

  response = client.chat.completions.create(
      model="gpt-5.5",
      messages=[
          {"role": "system", "content": "你是一个有帮助的助手。"},
          {"role": "user", "content": "用一句话解释什么是人工智能"}
      ]
  )

  print(response.choices[0].message.content)
  ```

  ```python requests theme={null}
  import requests

  response = requests.post(
      "https://api.crazyrouter.com/v1/chat/completions",
      headers={
          "Authorization": "Bearer sk-xxx",
          "Content-Type": "application/json"
      },
      json={
          "model": "gpt-5.5",
          "messages": [
              {"role": "user", "content": "用一句话解释什么是人工智能"}
          ]
      }
  )

  data = response.json()
  print(data["choices"][0]["message"]["content"])
  ```
</CodeGroup>

## 连续对话

通过维护 `messages` 列表实现多轮对话：

```python theme={null}
from openai import OpenAI

client = OpenAI(api_key="sk-xxx", base_url="https://api.crazyrouter.com/v1")

messages = [
    {"role": "system", "content": "你是一个 Python 编程助手。"}
]

def chat(user_input):
    messages.append({"role": "user", "content": user_input})

    response = client.chat.completions.create(
        model="gpt-5.5",
        messages=messages
    )

    reply = response.choices[0].message.content
    messages.append({"role": "assistant", "content": reply})
    return reply

# 多轮对话
print(chat("如何读取 CSV 文件？"))
print(chat("如果文件很大怎么办？"))
print(chat("能用 pandas 实现吗？"))
```

## 流式输出

```python theme={null}
from openai import OpenAI

client = OpenAI(api_key="sk-xxx", base_url="https://api.crazyrouter.com/v1")

stream = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{"role": "user", "content": "写一首关于编程的诗"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
print()
```

## 使用 requests 实现流式

```python theme={null}
import requests
import json

response = requests.post(
    "https://api.crazyrouter.com/v1/chat/completions",
    headers={
        "Authorization": "Bearer sk-xxx",
        "Content-Type": "application/json"
    },
    json={
        "model": "gpt-5.5",
        "messages": [{"role": "user", "content": "你好"}],
        "stream": True
    },
    stream=True
)

for line in response.iter_lines():
    if line:
        line = line.decode("utf-8")
        if line.startswith("data: ") and line != "data: [DONE]":
            data = json.loads(line[6:])
            content = data["choices"][0]["delta"].get("content", "")
            print(content, end="", flush=True)
print()
```

<Note>
  所有示例默认使用 2026 年 3 月 23 日已在生产环境实测成功的 `gpt-5.5`。如果你要切换模型，优先改成同样已验证的 `claude-opus-4-8` 或 `gemini-3.1-pro`。
</Note>