首页 星云 工具 资源 星选 资讯 热门工具
:

PDF转图片 完全免费 小红书视频下载 无水印 抖音视频下载 无水印 数字星空

deepseek-engineer-main

人工智能 20.03KB 7 需要积分: 1
立即下载

资源介绍:

deepseek-engineer-main
# DeepSeek Engineer 🐋 ## Overview This repository contains a powerful coding assistant application that integrates with the DeepSeek API to process user conversations and generate structured JSON responses. Through an intuitive command-line interface, it can read local file contents, create new files, and apply diff edits to existing files in real time. ## Key Features 1. DeepSeek Client Configuration - Automatically configures an API client to use the DeepSeek service with a valid DEEPSEEK_API_KEY. - Connects to the DeepSeek endpoint specified in the environment variable to stream GPT-like completions. 2. Data Models - Leverages Pydantic for type-safe handling of file operations, including: • FileToCreate – describes files to be created or updated. • FileToEdit – describes specific snippet replacements in an existing file. • AssistantResponse – structures chat responses and potential file operations. 3. System Prompt - A comprehensive system prompt (system_PROMPT) guides conversation, ensuring all replies strictly adhere to JSON output with optional file creations or edits. 4. Helper Functions - read_local_file: Reads a target filesystem path and returns its content as a string. - create_file: Creates or overwrites a file with provided content. - show_diff_table: Presents proposed file changes in a rich, multi-line table. - apply_diff_edit: Applies snippet-level modifications to existing files. 5. "/add" Command - Users can type "/add path/to/file" to quickly read a file's content and insert it into the conversation as a system message. - This allows the assistant to reference the file contents for further discussion, code generation, or diff proposals. 6. Conversation Flow - Maintains a conversation_history list to track messages between user and assistant. - Streams the assistant's replies via the DeepSeek API, parsing them as JSON to preserve both the textual response and the instructions for file modifications. 7. Interactive Session - Run the script (for example: "python3 main.py") to start an interactive loop at your terminal. - Enter your requests or code questions. Enter "/add path/to/file" to add file contents to the conversation. - When the assistant suggests new or edited files, you can confirm changes directly in your local environment. - Type "exit" or "quit" to end the session. ## Getting Started 1. Prepare a .env file with your DeepSeek API key: DEEPSEEK_API_KEY=your_api_key_here 2. Install dependencies and run (choose one method): ### Using pip ```bash pip install -r requirements.txt python3 main.py ``` ### Using uv (faster alternative) ```bash uv venv uv run main.py ``` 3. Enjoy multi-line streaming responses, file read-ins with "/add path/to/file", and precise file edits when approved. > **Note**: This is an experimental project developed by Skirano to test the new DeepSeek v3 API capabilities. It was developed as a rapid prototype and should be used accordingly.

资源文件列表:

deepseek-engineer-main.zip 大约有8个文件
  1. deepseek-engineer-main/
  2. deepseek-engineer-main/.gitignore 823B
  3. deepseek-engineer-main/.python-version 5B
  4. deepseek-engineer-main/README.md 3.03KB
  5. deepseek-engineer-main/main.py 15.71KB
  6. deepseek-engineer-main/pyproject.toml 258B
  7. deepseek-engineer-main/requirements.txt 35B
  8. deepseek-engineer-main/uv.lock 35.76KB
0评论
提交 加载更多评论
其他资源 新能源锂电池 欧姆龙梯形图程序模板 欧姆龙程序 包膜机程序 包蓝膜机程序,某新能源乙方大厂kr程序模板,程序标准化 plc程序,触摸屏,电气接线图,易损件bom清单 程序密码 库均已解开(可看
新能源锂电池 欧姆龙梯形图程序模板 欧姆龙程序 包膜机程序 包蓝膜机程序,某新能源乙方大厂kr程序模板,程序标准化。 plc程序,触摸屏,电气接线图,易损件bom清单 程序密码 库均已解开(可看程序源码) 自动流程 初始化流程 手自动安全条件 型 配方保存加载 程序和触摸屏来自真实产线,配套使用
新能源锂电池 欧姆龙梯形图程序模板 欧姆龙程序 包膜机程序
包蓝膜机程序,某新能源乙方大厂kr程序模板,程序标准化 
plc程序,触摸屏,电气接线图,易损件bom清单
程序密码 库均已解开(可看
comsol多孔介质流固耦合案例,孔压、位移时空演化特征
comsol多孔介质流固耦合案例,孔压、位移时空演化特征。
comsol多孔介质流固耦合案例,孔压、位移时空演化特征
fluent激光熔覆案例#增材制造,流体仿真 质量源
fluent激光熔覆案例#增材制造,流体仿真。 质量源
fluent激光熔覆案例#增材制造,流体仿真 
质量源
comsol瓦斯抽采模型模拟负压抽采条件下煤层瓦斯压力变化comsol流固耦合模型
comsol瓦斯抽采模型模拟负压抽采条件下煤层瓦斯压力变化comsol流固耦合模型
comsol瓦斯抽采模型模拟负压抽采条件下煤层瓦斯压力变化comsol流固耦合模型
大模型微调入门 LLM-quickstart-main
大模型微调入门
自动语音翻译 seamless
seamless
双馈风力发电系统的建模与仿真(含模型和实验报告)
双馈风力发电系统的建模与仿真(含模型和实验报告)
双馈风力发电系统的建模与仿真(含模型和实验报告)
基于两轮差速移动机器人的模型预测控制(mpc)轨迹跟踪(simulnk模型加matlab代码,无联合仿真,横纵向跟踪) ,最新 1.轮式移动机器人(WMR,wheeled mobile robot)
基于两轮差速移动机器人的模型预测控制(mpc)轨迹跟踪(simulnk模型加matlab代码,无联合仿真,横纵向跟踪) ,最新 1.轮式移动机器人(WMR,wheeled mobile robot) 基于两轮差速移动机器人的模型预测控制轨迹跟踪,既可以实现车速的跟踪,又可以实现对路径的跟踪; 2.采用simulnk搭建模型主体,matlab代码搭建MPC控制器,无联合仿真 3.设置了5种轨迹,包括三种车速的圆形轨迹,单车速的直线轨迹,单车速的双移线轨迹,仿真效果如图。 4.包含绘制对比分析图片的代码,可一键绘制轨迹对北比图 5.为了使控制量输出平稳,MPCc控制器采用控制增量建立 6.代码规范,重点部分有注释 7.,有参考lunwen
基于两轮差速移动机器人的模型预测控制(mpc)轨迹跟踪(simulnk模型加matlab代码,无联合仿真,横纵向跟踪) ,最新
1.轮式移动机器人(WMR,wheeled mobile robot)