Operational Intelligence Engine 🚀

An advanced, agentic AI assistant designed to streamline Incident Response and SRE workflows.

Leveraging the power of CrewAI, RAG (Retrieval-Augmented Generation), and modern LLMs (Google Gemini), the Operational Intelligence Engine automates log analysis, root cause identification, and remediation planning, acting as a force multiplier for your operations team.

---

🌟 Key Features

• Automated Incident Analysis: Intelligently parses and analyzes messy, unstructured logs to detect anomalies and extract structured data.
• Agentic Root Cause Analysis (RCA): Uses multi-agent collaboration via CrewAI to pinpoint the exact source of failures.
• Smart Remediation: Suggests actionable, step-by-step fixes based on historical incident data and SRE best practices.
• RAG-Powered Intelligence: Semantic search across historical incident records using vector embeddings (pgvector) to find similar past issues.
• Comprehensive Reporting: Automatically generates detailed incident reports and post-mortems for stakeholders.
• Built-in Observability: Includes Prometheus instrumentation for real-time API monitoring.

🏗️ Architecture

The system follows a microservices-based architecture powered by Docker containers, separating the API layer, the intelligent agentic workflow, and the data storage layer.

🛠️ Tech Stack

Core Technologies

• Backend Framework: FastAPI (Python)
• AI Orchestration: CrewAI, LangChain
• Large Language Model: Google Gemini (Pro/Flash)

Infrastructure & Data

• Database: PostgreSQL (extended with pgvector for AI embeddings)
• Caching & Task Queue: Redis
• Containerization: Docker & Docker Compose
• Monitoring: Prometheus

🚀 Getting Started

Prerequisites

• Docker & Docker Compose installed
• Python 3.10+ (if developing locally without Docker)
• A valid Google Gemini API Key

Installation & Setup

1. Clone the repository:

   git clone https://github.com/abhishek09827/Operational-Intelligence-Engine.git
   cd Operational-Intelligence-Engine

2. Configure Environment Variables: Create a .env file in the root directory based on the provided template:

   GOOGLE_API_KEY=your_google_api_key_here
   POSTGRES_USER=postgres
   POSTGRES_PASSWORD=postgres
   POSTGRES_DB=operational_intelligence_engine
   DATABASE_URL=postgresql://postgres:postgres@db:5432/operational_intelligence_engine

3. Spin up the Infrastructure via Docker:

   docker-compose up --build -d

4. Access the Services:

   • Interactive API Docs (Swagger): http://localhost:8000/docs
   • Health Check: http://localhost:8000/health

🧪 Testing

We use pytest for unit and integration testing. To run the test suite within the Docker environment:

docker-compose run app pytest

📸 Screenshots & Output Examples

Here is a glimpse of the Operational Intelligence Engine in action:

Architecture	Agent Execution	Example Output

[Updates] UI Enhancements

🤝 Contributing

We welcome contributions from the community! If you'd like to improve the Operational Intelligence Engine, please follow these steps:

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

---

Built with ❤️ for Site Reliability Engineers.