Incident Compression Engine

AI-assisted grouping and resolution suggestion for enterprise support tickets using Google Gemini.

Features

200 synthetic support tickets across 6 categories
AI-powered clustering and root cause analysis via Gemini
REST API with FastAPI
Minimal web UI for viewing tickets and clusters

Quick Start

1. Install Dependencies

pip install -r requirements.txt

2. Configure Gemini API Key

cp .env.example .env
# Edit .env and add your Gemini API key:
# GEMINI_API_KEY=your_key_here

Get a key at: https://makersuite.google.com/app/apikey

Note: The app works without a key, but uses fallback analysis instead of AI.

3. Run the Server

uvicorn main:app --reload

Open http://localhost:8000 in your browser.

Usage

View the ticket list on the main page
Click "Run Analysis" to cluster tickets
Switch to Clusters tab to see:
- Grouped incidents by category
- AI-generated root cause analysis
- Suggested resolution steps
- Confidence scores

API Endpoints

Method	Endpoint	Description
GET	`/api/tickets`	List tickets (supports `skip`, `limit`, `category`, `severity`)
POST	`/api/cluster`	Run clustering + AI analysis
GET	`/api/clusters`	Get clustered results with root cause & resolution
GET	`/api/status`	System health check

Ticket Categories

Authentication Failure
Database Connection Error
Configuration Mismatch
Permission Issue
Service Timeout
Integration Failure

Project Structure

ICE/
├── main.py           # FastAPI app
├── models.py         # SQLAlchemy models
├── database.py       # Database setup
├── gemini_service.py # Gemini API integration
├── clustering.py     # Clustering logic
├── seed_data.py      # Synthetic data generator
├── requirements.txt  # Dependencies
├── .env.example      # Environment template
└── static/
    └── index.html    # Web UI

Tech Stack

Backend: Python, FastAPI, SQLAlchemy, SQLite
AI: Google Gemini API
Clustering: scikit-learn (K-Means)
Frontend: Vanilla HTML/CSS/JS