Enables configuration of environment variables for the server through a .env file to store API keys and other settings
Provides the backend framework for the MCP server, handling API endpoints and request processing
Used for processing and converting PPT documents to enable content extraction for the RAG engine
Utilizes OpenAI Embeddings for vectorizing document content to enable semantic search capabilities
Supports project configuration through TOML files as indicated by the pyproject.toml in the project structure
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ChatPPT-MCPsummarize the key points from the quarterly presentation"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ChatPPT-MCP: 多文档RAG引擎的 MCP Server
一个基于MCP（Model Context Protocol）的多文档RAG（Retrieval-Augmented Generation）引擎应用，支持PPT文档的智能问答和分析。
功能特性
🔍 多文档处理: 支持索引多个PPT文档，基于视觉模型
🤖 智能问答: 基于RAG技术的文档问答
🔄 MCP集成: 使用Model Context Protocol进行工具调用
📊 交互式测试: 提供命令行交互测试界面
Related MCP server: DuckDB-RAG-MCP-Sample
技术栈
后端框架: FastAPI
向量数据库: ChromaDB
LLM: Doubao Vision
文档处理: LibreOffice, pypdfium2
协议: Model Context Protocol (MCP)
向量化: OpenAI Embeddings
安装使用
1. 安装依赖
pip install -e .2. 环境配置
复制环境变量模板文件，并修改：
cp .env.example .env3. 运行应用
RAG引擎测试模式
python rag_interactive_test.pyMCP测试模式(先sse启动：python mcp_ppt_server.py --transport sse)
python mcp_interactive_test.py项目结构
app_chatppt/
├── src/ # 源代码目录
│ ├── multi_doc_rag_engine.py # RAG引擎核心
│ ├── document_processor.py # 文档处理器
│ └── ...
├── data/ # 示例数据
├── rag_interactive_test.py # 交互式测试入口
├── mcp_interactive_test.py # MCP集成测试
├── pyproject.toml # 项目配置
├── .env.example # 环境变量模板
└── README.md # 项目文档许可证
MIT License