deepseek在线API调用

1.获取密钥

https://platform.deepseek.com/api_keys

2.将密钥配置到环境变量或者配置到项目的“.env”文件里

环境变量配置密钥

Windows系统​​：在命令提示符中设置 setx DEEPSEEK_API_KEY "your_actual_key"

代码读取：

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get('DEEPSEEK_API_KEY'),
    base_url="https://api.deepseek.com")

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

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

.env里配置密钥

代码读取：

import os
from dotenv import load_dotenv
from openai import OpenAI

# 加载.env文件中的环境变量
load_dotenv()

# 从环境变量中获取API密钥
api_key = os.getenv('DEEPSEEK_API_KEY')

# 创建OpenAI客户端
client = OpenAI(
    api_key=api_key,  # 使用从.env文件读取的密钥
    base_url="https://api.deepseek.com"
)


response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[
        {"role": "system", "content": "你是一位杂技演员，完全不知道人工智能是什么。"},
        {"role": "user", "content": "请你详细的介绍一下：什么是人工智能？"},
    ],
    stream=False
)
print(response.choices[0].message.content)