Buildathon Projects Collection

A collection of 6 innovative AI-powered applications built for the Buildathon hackathon. Each project showcases different aspects of modern AI integration with practical use cases.

Projects Overview

1. Visual Search Engine

Directory: project-1-visual-search/

An intelligent visual memory system that indexes and searches through screenshots and images using AI-powered understanding.

Features:

• Screenshot indexing with ChromaDB vector database
• Natural language search across visual content
• Duplicate detection and management
• Context-aware image understanding

Tech Stack: Python, Streamlit, ChromaDB, OpenAI Vision API

---

2. Voice to Slide Generator

Directory: project-2-voice-to-slide/

Transform voice recordings into professional presentation slides automatically.

Features:

• Audio transcription and processing
• Automatic slide generation from speech
• Content structuring and formatting
• Real-time preview

Tech Stack: Python, Streamlit, OpenAI Whisper, GPT-4

---

3. Employee Engagement Pulse Dashboard

Directory: project-3-employee-engagement-pulse/ Port: 8524

Real-time employee sentiment analysis and engagement tracking dashboard.

Features:

• Slack integration for message analysis
• Sentiment analysis and trend detection
• Predictive insights
• Interactive visualizations

Tech Stack: Python, Streamlit, Slack API, OpenAI/Anthropic APIs

---

4. Codebase Time Machine

Directory: project-4-codebase-time-machine/ Port: 8508

Navigate and understand code evolution through semantic search and AI-powered analysis.

Features:

• Git history analysis
• Semantic code search
• Code evolution visualization
• AI-powered code explanations

Tech Stack: Python, Streamlit, GitPython, ChromaDB, OpenAI API

---

5. Knowledge Graph Builder

Directory: project-5-knowledge-graph/

Extract and visualize knowledge graphs from documents with interactive 3D visualization.

Features:

• Entity and relationship extraction
• Neo4j graph database integration
• 3D graph visualization
• Question answering over graphs
• Story mode for literature analysis

Tech Stack: Python, Streamlit, Neo4j, OpenAI API, PyVis

---

6. Inbox Triage Assistant

Directory: project-6-inbox-triage-assistant/

Smart email organization and prioritization using AI clustering and analysis.

Features:

• Gmail integration
• Email clustering and categorization
• Priority detection
• Visual email analytics

Tech Stack: Python, Streamlit, Gmail API, OpenAI API

Quick Start

Prerequisites

• Python 3.8+
• Node.js (for project-5)
• Neo4j database (optional, for project-5)
• API Keys:
  • OpenAI API key
  • Anthropic API key (optional)
  • Slack Bot Token (for project-3)
  • Gmail API credentials (for project-6)

General Setup

1. Clone the repository:

git clone https://github.com/yourusername/buildathon.git
cd buildathon

2. Navigate to any project directory:

cd project-X-name

3. Create a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

4. Install dependencies:

pip install -r requirements.txt

5. Set up environment variables:

cp .env.example .env
# Edit .env with your API keys

6. Run the application:

# Most projects use:
./run.sh
# Or directly:
streamlit run app.py

Environment Configuration

Each project includes a .env.example file showing required environment variables. Copy this to .env and add your credentials:

# Example for most projects:
OPENAI_API_KEY=your-openai-api-key
ANTHROPIC_API_KEY=your-anthropic-api-key  # Optional

# Project-specific keys:
SLACK_BOT_TOKEN=xoxb-your-token  # Project 3
NEO4J_URI=neo4j+s://your-instance  # Project 5

Project-Specific Setup

Project 3 - Employee Engagement Pulse

Requires Slack workspace setup:

1. Create a Slack app at api.slack.com
2. Add OAuth scopes: channels:history, channels:read, groups:history, groups:read
3. Install to workspace and get Bot User OAuth Token

Project 5 - Knowledge Graph

Optional Neo4j setup:

1. Create free instance at neo4j.com/aura
2. Add credentials to .env
3. Or run without Neo4j for in-memory mode

Project 6 - Inbox Triage

Gmail API setup:

1. Enable Gmail API in Google Cloud Console
2. Create OAuth 2.0 credentials
3. Download credentials.json
4. Run app and complete OAuth flow

Features Highlights

• AI-Powered Analysis: All projects leverage state-of-the-art AI models
• Real-time Processing: Streaming capabilities and live updates
• Interactive Visualizations: Rich UI with charts, graphs, and 3D views
• Production Ready: Error handling, logging, and performance optimizations
• Extensible Architecture: Modular design for easy enhancements

Technologies Used

• Backend: Python 3.8+
• Frontend: Streamlit
• AI/ML: OpenAI GPT-4, Anthropic Claude, Embeddings
• Databases: ChromaDB, Neo4j, SQLite
• APIs: Slack, Gmail, GitHub
• Visualization: Plotly, PyVis, Streamlit Components

Development

Each project is self-contained with its own:

• Requirements file
• Environment configuration
• Documentation
• Test suite (where applicable)

Contributing

Feel free to fork, modify, and use these projects. If you make improvements, pull requests are welcome!

License

This project collection is open source and available under the MIT License.

Author

Built with passion for the Buildathon hackathon.

---

For detailed documentation on each project, see the README.md file in the respective project directory.