README.md

metadata

title: Brock Events Assistant
emoji: 🎓
colorFrom: red
colorTo: indigo
sdk: gradio
sdk_version: 5.9.1
app_file: app.py
pinned: false
license: mit

🎓 Brock University Events Assistant

An AI-powered chatbot that helps you discover events at Brock University. Using Natural Language Processing and real-time event data, this assistant provides personalized event recommendations and information.

✨ Features

• Natural Language Understanding: Ask questions in everyday language
• Real-time Event Updates: Fresh data from ExperienceBU's rss feed.
• Smart Filtering: Find events by category, date, or location
• Responsive Interface: User-friendly chat experience
• Cache System: Efficient data management
• Automatic Updates: Events refresh every 24 hours

💡 Example Questions

• "What's happening on campus this week?"
• "Are there any academic workshops tomorrow?"
• "Tell me about events in the library"
• "What club meetings are coming up?"
• "Any career fairs this month?"

🛠️ Technical Details

Stack

• Frontend: Gradio 4.14.0
• NLP: Sentence Transformers (all-MiniLM-L6-v2)
• Vector DB: ChromaDB
• Data Source: ExperienceBU RSS Feed
• Processing: BeautifulSoup4, NLTK

Features

• Event caching for improved performance
• 14-day event window for relevance
• Natural language response generation
• Context-aware query understanding
• Automatic data refresh system

📊 Performance

• Processes next 14 days of events
• Response time: ~2-3 seconds
• Cache updates: Every 24 hours
• Memory usage: ~500MB

🚀 Development

1. Clone the repository
2. Install dependencies: pip install -r requirements.txt
3. Run locally: python app.py or on google colab (Remember to !pip install required repositories)!

📝 License

MIT License - See LICENSE file

🔗 Links

• ExperienceBU

👥 Contributing

Contributions welcome! Please check the issues page.

📫 Contact

Created by Aryan J - Feel free to connect!

• LinkedIn

Brock Events Assistant: Development Roadmap & Analysis

Current Limitations

1. Time Window Constraints

• Limited to 14-day window for event fetching
• No historical event data available
• Can't handle queries about past events
• No long-term event planning capabilities

2. Search and Response Limitations

• Basic semantic search without context awareness
• Responses are template-based and lack conversational flow
• No memory of previous interactions within the conversation
• Limited understanding of complex queries
• No handling of follow-up questions

3. Technical Constraints

• Single RSS feed dependency
• Basic caching system
• No real-time updates
• Limited error recovery
• No user preferences or personalization

Next Steps

1. Begin with conversation memory implementation
2. Enhance query understanding
3. Implement basic categorization
4. Add simple personalization features
5. Plan for expanded time window