llm-usekit — DeepSeek Agents | Neura Market
    Neura MarketNeura Market/DeepSeek
    ChatGPTChatGPTClaudeClaudeGeminiGeminiCursorCursorGrokGrokPerplexityPerplexityDeepSeekDeepSeek
    CoPilotCoPilotStable DiffusionStable DiffusionMidjourneyMidjourney
    View All Directories
    OverviewRulesPromptsMCPsAgentsBlogVideosGuidesCoursesCommunityTrendingGenerate
    DeepSeekAgentsllm-usekit
    Back to Agents
    llm-usekit

    llm-usekit

    Shao0203 August 7, 2025
    1 copies 0 downloads

    Multi-llm app: Script generation, Chatbot, Docs RAG, Data analysis Agent.

    Agent Definition
    # 📦 llm-usekit
    
    ## 🚀 项目简介 (English Version below)
    `llm-usekit` 是一个基于 **LangChain + Streamlit + 多家大模型 API (OpenAI, DeepSeek, Kimi, Qwen 等)** 的多功能大模型工具集。访问/查看使用效果,可以点击右边的网址(streamlit cloud部署,长时间无人访问后app会睡眠,需要点击页面中间按钮唤醒app)https://llm-usekit.streamlit.app   
    
    它提供了多种开箱即用的 LLM 应用,包括:
    
    - 🎬 **视频脚本生成器**(Video Script Generator)  
    - 💬 **智能聊天助手**(Chat-Bot with memory)  
    - 📑 **文档问答 (RAG)** —— 上传文档后基于向量数据库进行精准问答  
    - 📊 **数据分析 Agent** —— 上传 CSV 文件后可进行数据分析和可视化  
    
    
    ## 📂 项目结构
    ```bash
    llm-usekit/  
    ├── utils/                 # 工具 & 后台逻辑  
    │ ├── vsgen.py             # 视频脚本生成器逻辑  
    │ ├── chat.py              # 聊天助手逻辑  
    │ ├── rag_tool.py          # RAG 文档问答逻辑  
    │ ├── agent_tool.py        # 数据分析 Agent 逻辑  
    │ ├── sidebar.py           # 通用侧边栏(语言切换 & 模型选择)  
    │ └── llm_factory.py       # 统一的大模型实例工厂  
    │  
    ├── pages/                 # Streamlit 多页面前端  
    │ ├── Chat-Bot.py          # 聊天助手页面  
    │ ├── Q&A-Rag.py           # 文档问答页面  
    │ └── Data-Agent.py        # 数据分析 Agent 页面  
    │  
    ├── VS-Gen.py              # 主入口页面(视频脚本生成器)  
    ├── texts.json             # 多语言文案配置  
    ├── requirements.txt       # 依赖文件  
    └── README.md              # 项目说明文档  
    ```
    
    
    ## ⚙️ 环境配置
    
    1. 克隆仓库:
       ```bash
       git clone https://github.com/Shao0203/llm-usekit.git
       ```
    2. 创建虚拟环境并安装依赖:  
       ```bash
       cd llm-usekit               # 进入项目目录
       python -m venv .venv        # 创建虚拟环境
       source .venv/bin/activate   # Mac/Linux
       .\.venv\Scripts\activate      # Windows
    
       pip install -r requirements.txt
       ```
    3. 配置 API Keys:  
       本地开发时可以在项目根目录下创建 `.env`文件: 
       ```bash
       # .env文件中存入以下api keys信息 - 
       OPENAI_API_KEY = "your_openai_key"
       DEEPSEEK_API_KEY = "your_deepseek_key"
       KIMI_API_KEY = "your_kimi_key"
       QWEN_API_KEY = "your_qwen_key"
       ```
       或在系统环境变量`.zshrc`中配置:
       ```bash
       # vi ~/.zshrc - 命令行进入系统环境变量,然后存入以下api keys信息:
       export OPENAI_API_KEY = "your_openai_key"
       export DEEPSEEK_API_KEY = "your_deepseek_key"
       export KIMI_API_KEY = "your_kimi_key"
       export QWEN_API_KEY = "your_qwen_key"
       ```
    
    
    ## ▶️ 运行项目
    启动主页面 - 视频

    Tags

    agentdeepseekkimilangchainllmopenaiqwenragstreamlit

    Comments

    More Agents

    View all
    hybrid-model-workflow

    hybrid-model-workflow

    HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。

    P
    ph4ble
    1
    Dynamic-Review-Agent

    Dynamic-Review-Agent

    An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.

    1
    1838177
    1
    StellarOS-Watch

    StellarOS-Watch

    基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。

    C
    chenshuang888
    1
    UAVagent1.0deepseek

    UAVagent1.0

    A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking

    S
    StarlitPupils
    2
    hermes-goai-agent

    hermes-go

    One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。

    L
    LAI-755
    1
    Agent

    Agent

    网页应用Agent,接入DeepSeek、Mimo等模型

    C
    Cosmos-815
    1

    Stay up to date

    Get the latest DeepSeek prompts, rules, and resources delivered to your inbox weekly.

    Neura Market LogoNeura Market

    Discover the best AI prompts, plugins, and resources for DeepSeek and more.

    Content Types

    • Rules
    • Prompts
    • MCPs
    • Agents
    • Guides

    Platforms

    • ChatGPT Directory
    • Claude Directory
    • Gemini Directory
    • Cursor Directory
    • Grok Directory
    • Perplexity Directory
    • DeepSeek Directory
    • CoPilot Directory
    • Stable Diffusion Directory
    • Midjourney Directory
    • All Directories

    Resources

    • Blog
    • Documentation
    • Help Center
    • Marketplace

    Legal

    • Privacy Policy
    • Terms of Service

    © 2026 Neura Market. All rights reserved.

    |

    Not affiliated with any AI platform vendors.