AI本地开发

Python本地调用deepseek安装 Ollama官网下载安装后打开 cmd 验证ollama --version拉取模型ollama pull deepseek-r1:7b7B低配电脑首选安装 python 依赖pip install openaiollama 兼容 openai 接口2本地电脑环境变量配置api-key的使用方法import os from openai import OpenAI client OpenAI( api_keyos.environ.get(DEEPSEEK_API_KEY), base_urlhttps://api.deepseek.com) response client.chat.completions.create( modeldeepseek-flash, messages[ {role: system, content: 你是中文领域的专家}, {role: user, content: 你好你可以做什么}, ], streamFalse, reasoning_efforthigh, extra_body{thinking: {type: enabled}} ) print(response.choices[0].message.content)python项目要安装pip install openaipython开发简单的前端页面pip install streamlit streamlit run xxx.py