ytc/WoMenQuNaJu

Fork 0

Files

ytc1012 0f3ee050dc first commit

2026-02-04 16:11:55 +08:00

9.6 KiB

Raw Blame History

MeetSpot

AI Agent for Multi-Person Meeting Point Recommendations

Not just a search tool. An autonomous agent that decides the fairest meeting point for everyone.

English | 简体中文

Why MeetSpot?

Most location tools return results near you. MeetSpot calculates the geographic center of all participants and returns AI-ranked venues that minimize everyone's travel time.

Traditional Tools	MeetSpot
Search near your location	Calculate fair center for all
Keyword-based ranking	AI-powered multi-factor scoring
Static results	Adaptive dual-mode routing
No reasoning	Explainable AI with chain-of-thought

Agent Architecture

MeetSpot is an AI Agent - it makes autonomous decisions based on request complexity, not just executes searches.

                              User Request
                                   │
                    ┌──────────────┴──────────────┐
                    │      Complexity Router      │
                    │    (Autonomous Decision)    │
                    └──────────────┬──────────────┘
                                   │
              ┌────────────────────┼────────────────────┐
              │                    │                    │
              ▼                    │                    ▼
    ┌─────────────────┐            │          ┌─────────────────┐
    │    Rule Mode    │            │          │   Agent Mode    │
    │   (2-4 sec)     │            │          │   (8-15 sec)    │
    │  Deterministic  │            │          │  LLM-Enhanced   │
    └────────┬────────┘            │          └────────┬────────┘
             │                     │                   │
             └─────────────────────┼───────────────────┘
                                   │
                    ┌──────────────┴──────────────┐
                    │    5-Step Processing        │
                    │        Pipeline             │
                    └──────────────┬──────────────┘
                                   │
        ┌──────────┬──────────┬────┴────┬──────────┬──────────┐
        │          │          │         │          │          │
        ▼          ▼          ▼         ▼          ▼          ▼
    Geocode    Center     POI      Ranking     HTML      Result
              Calc      Search               Gen

Intelligent Mode Selection

The Agent autonomously decides which processing mode to use:

Factor	Score	Example
Location count	+10/location	4 locations = 40 pts
Complex keywords	+15	"quiet business cafe with private rooms"
Special requirements	+10	"parking, wheelchair accessible, WiFi"

Score < 40: Rule Mode (fast, deterministic, pattern-matched)
Score >= 40: Agent Mode (LLM reasoning, semantic understanding)

Agent Mode Scoring

Final Score = Rule Score × 0.4 + LLM Score × 0.6

The LLM analyzes semantic fit between venues and requirements, then blends with rule-based scoring. Results include Explainable AI visualization showing the agent's reasoning process.

5-Step Pipeline

Step	Function	Details
Geocode	Address → Coordinates	90+ smart mappings (universities, landmarks)
Center Calc	Fair point calculation	Spherical geometry for accuracy
POI Search	Venue discovery	Concurrent async search, auto-fallback
Ranking	Multi-factor scoring	Base(30) + Popularity(20) + Distance(25) + Scenario(15) + Requirements(10)
HTML Gen	Interactive map	Amap JS API integration

Quick Start

# Clone and install
git clone https://github.com/calderbuild/MeetSpot.git && cd MeetSpot
pip install -r requirements.txt

# Configure (get key from https://lbs.amap.com/)
cp config/config.toml.example config/config.toml
# Edit config.toml and add your AMAP_API_KEY

# Run
python web_server.py

Open http://127.0.0.1:8000

API Reference

Main Endpoint

POST /api/find_meetspot

{
  "locations": ["Peking University", "Tsinghua University", "Renmin University"],
  "keywords": "cafe restaurant",
  "user_requirements": "parking, quiet environment"
}

Response:

{
  "success": true,
  "html_url": "/workspace/js_src/recommendation_xxx.html",
  "center": {"lat": 39.99, "lng": 116.32},
  "venues_count": 8
}

Other Endpoints

Endpoint	Method	Description
`/api/find_meetspot_agent`	POST	Force Agent Mode (LLM reasoning)
`/api/ai_chat`	POST	AI customer service chat
`/health`	GET	System health check
`/docs`	GET	Interactive API documentation

Screenshots

Agent Chain-of-Thought	Interactive Map View
Multi-Factor AI Scoring	Venue Recommendation Cards

More Screenshots

Homepage	Meeting Point Finder
Results Summary	AI Customer Service

Tech Stack

Layer	Technologies
Backend	FastAPI, Pydantic, aiohttp, SQLAlchemy 2.0, asyncio
Frontend	HTML5, CSS3, Vanilla JavaScript, Boxicons
Maps	Amap (Gaode) - Geocoding, POI Search, JS API
AI	DeepSeek / GPT-4o-mini for semantic analysis
Deploy	Render, Railway, Docker, Vercel

Project Structure

MeetSpot/
├── api/
│   └── index.py                 # FastAPI application entry
├── app/
│   ├── tool/
│   │   └── meetspot_recommender.py  # Core recommendation engine
│   ├── config.py                # Configuration management
│   └── design_tokens.py         # WCAG-compliant color system
├── templates/                   # Jinja2 templates
├── public/                      # Static assets
└── workspace/js_src/            # Generated result pages

Development

# Development server with hot reload
uvicorn api.index:app --reload

# Run tests
pytest tests/ -v

# Code quality
black . && ruff check . && mypy app/

Contributing

Contributions are welcome! Please:

Fork the repository
Create a feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request

Contact

Email: Johnrobertdestiny@gmail.com

GitHub: Issues

Blog: jasonrobert.me

Personal WeChat

WeChat Group

License

MIT License - see LICENSE for details.

If MeetSpot helps you, please give it a star!

9.6 KiB Raw Blame History Unescape Escape