convaiinnovations/travel-agent-mcp

🤗 Hugging Face 来源mit-other⚠ 没有 SHA-256 权重今天更新
一条命令提交

在你的模型文件夹旁边运行它。它会制作种子、将文件与 Hugging Face 比对,然后提交。你只需开始做种,并粘贴你账户中的密钥。它只读取你的文件,绝不修改。如果愿意,可以先阅读脚本。

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo convaiinnovations/travel-agent-mcp ./model-folder
需要做种者 →

Agentic AI Travel Booker (MCP)

This repository contains a single-agent multi-tool travel booking assistant built with Pydantic AI and FastMCP.

Features

  • Weather Integration: Uses python-weather for real-time updates.
  • Web Search: Scrapes hotel options using DuckDuckGo.
  • MCP Architecture: Tools are decoupled via the Model Context Protocol (MCP).
  • Local LLM: Optimized for use with Ollama and Qwen 3.5.

Setup

  1. Install dependencies: pip install pydantic-ai fastmcp python-weather beautifulsoup4 aiohttp.
  2. Ensure Ollama is running locally with qwen3.5:4b.
  3. Run app.py.