目录

1、申请api

2、安装openai库

3、编写代码

4、终端调用

5、成果展示

---

1、申请api

2、安装openai库

python -m pip install openai

3、编写代码

import openai  # 假设 DeepSeek 的 API 与 OpenAI 类似


# 初始化客户端
client = openai.Client(api_key="你的key", base_url="https://api.deepseek.com")

# 初始化对话历史
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
]

# 连续对话循环
while True:
    # 获取用户输入
    user_input = input("\nYou: ")
    if user_input.lower() in ["exit", "quit"]:  # 输入 exit 或 quit 退出对话
        print("Goodbye!")
        break

    # 将用户输入添加到对话历史
    messages.append({"role": "user", "content": user_input})

    # 提示用户按回车键开始回答
    print("\nPress ENTER to generate the assistant's response...")

    # 调用 API 获取助手回复
    try:
        response = client.chat.completions.create(
            model="deepseek-chat",
            messages=messages,
            stream=True
        )

        # 处理流式响应
        assistant_reply = ""
        print("Assistant: ", end="", flush=True)
        for chunk in response:
            if chunk.choices[0].delta.content:
                content = chunk.choices[0].delta.content
                print(content, end="", flush=True)
                assistant_reply += content

        # 将助手回复添加到对话历史
        messages.append({"role": "assistant", "content": assistant_reply})

    except Exception as e:
        print(f"\nError occurred: {e}")

4、终端调用

python "文件路径"#终端输入

5、成果展示