README.md

metadata

title: Intelligent Bug Triage
emoji: 👁
colorFrom: red
colorTo: yellow
sdk: gradio
sdk_version: 5.49.0
app_file: app.py
pinned: false
python_version: 3.12
license: apache-2.0

🐛 Intelligent Bug Triage & Resolution System

An AI-powered multi-agent system for automated bug classification, intelligent developer assignment, and solution recommendations using Knowledge Graphs and RAG.

🎯 Features

• Automated Bug Classification: ML-powered categorization (UI, API, Database, Performance)
• Priority Assignment: Smart P0-P4 priority levels based on impact
• Severity Detection: Critical, High, Medium, Low severity scoring
• Knowledge Graph: Neo4j-based relationships between bugs, developers, and components
• RAG-Enabled Solutions: Vector search for similar bug resolutions
• Multi-Agent Architecture: Specialized agents for triage, assignment, resolution, analytics

🏗️ Architecture

intelligent-bug-triage/ ├── agents/ # Multi-agent implementations │ ├── triage/ # Bug classification agent ✅ │ ├── assignment/ # Developer routing agent 🔄 │ ├── resolution/ # Solution recommendation agent ⏳ │ └── analytics/ # Metrics and insights agent ⏳ ├── knowledge-graph/ # Neo4j schemas and clients ├── rag-system/ # Vector store and embeddings ├── api/ # FastAPI backend services ├── data/ # Training and sample data ├── models/ # ML model checkpoints └── metrics/ # Experiment tracking

🚀 Quick Start

Local Development

1. Clone the repository: git clone https://huggingface.co/spaces/YOUR-USERNAME/intelligent-bug-triage cd intelligent-bug-triage

2. Create virtual environment: python3 -m venv venv source venv/bin/activate

3. Install dependencies: pip install -r requirements.txt

4. Run the application: python app.py

5. Open browser to http://localhost:7860

Hugging Face Space

This app is deployed on Hugging Face Spaces with:

• Compute: CPU Basic (2 vCPU, 16 GB RAM)
• Storage: 100 GB ephemeral
• Status: ✅ Active

📊 Current Status

Phase 1: Foundation ✅ (Complete)

• Project structure setup
• Triage Agent with zero-shot classification
• Neo4j knowledge graph schema
• Qdrant vector store foundation
• Gradio web interface
• Sample dataset

Phase 2: Multi-Agent System 🔄 (In Progress)

• Assignment Agent implementation
• Developer expertise modeling
• Workload balancing algorithm
• Agent coordination framework

Phase 3: RAG Implementation ⏳ (Planned)

• Fine-tuned BERT for classification
• Historical bug pattern analysis
• Solution recommendation engine
• Semantic search optimization

Phase 4: Production Deployment ⏳ (Planned)

• FastAPI backend services
• JIRA/GitHub integration
• Kubernetes deployment
• Prometheus monitoring

🛠️ Technology Stack

• ML/AI: Transformers, BART, BERT, Sentence-Transformers
• Knowledge Graph: Neo4j Community Edition
• Vector DB: Qdrant
• Agent Framework: LangChain
• Backend: FastAPI, Python 3.12+
• Frontend: Gradio
• Storage: PostgreSQL, Redis
• Monitoring: Prometheus, Grafana

📈 Performance Targets

Metric	Target	Current
Triage Time	<5 min	✅ <1 min
Classification Accuracy	>90%	🔄 87%
Assignment Accuracy	>85%	⏳ TBD
Solution Relevance	>80%	⏳ TBD

🤝 Contributing

This is an open-source project. Contributions welcome!

1. Fork the repository
2. Create feature branch (git checkout -b feature/amazing-feature)
3. Commit changes (git commit -m 'Add amazing feature')
4. Push to branch (git push origin feature/amazing-feature)
5. Open Pull Request

📝 License

Apache 2.0 License - see LICENSE file

🙏 Acknowledgments

• Built with Hugging Face Transformers
• Knowledge Graph powered by Neo4j
• Vector search by Qdrant
• UI powered by Gradio

📧 Contact

For questions or collaboration:

• GitHub Issues: [Report bugs or request features]
• Hugging Face Discussions: [Community support]

---

Built with ❤️ using Hugging Face Spaces