Getting Started

Getting Started

Get up and running with the Avyay AI platform. Each product can be used independently or together through the unified API Gateway.

Prerequisites

  • Docker installed on your system
  • API keys for LLM providers (OpenAI, Anthropic) — required for MĀRGA
  • OpenAI API key — required for DevOps RAG

Quick Start with Docker

MĀRGA — LLM Router

docker pull ghcr.io/gaurav21/marga:latest
 
docker run -p 8080:8080 \
  -e OPENAI_API_KEY=your-key \
  -e ANTHROPIC_API_KEY=your-key \
  ghcr.io/gaurav21/marga:latest
 
# Test it
curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-4", "messages": [{"role": "user", "content": "Hello!"}]}'

Full MĀRGA quickstart →

RAKṢĀ — Security Scanner

docker pull ghcr.io/gaurav21/raksha:latest
 
docker run -p 8430:8080 ghcr.io/gaurav21/raksha:latest
 
# Scan a GitHub repo
curl -X POST http://localhost:8430/scan/github \
  -H "Content-Type: application/json" \
  -d '{"url": "https://github.com/your-org/your-repo"}'

Full RAKṢĀ quickstart →

DevOps RAG

docker pull ghcr.io/gaurav21/devops-rag:latest
 
docker run -p 8081:8080 \
  -e OPENAI_API_KEY=your-key \
  ghcr.io/gaurav21/devops-rag:latest
 
# Ask a question
curl -X POST http://localhost:8081/ask \
  -H "Content-Type: application/json" \
  -d '{"question": "How do I fix CrashLoopBackOff in Kubernetes?"}'

Full DevOps RAG quickstart →

DVĀRA — Unified Gateway

The API Gateway provides a single endpoint for all products:

docker pull ghcr.io/gaurav21/avyay-gateway:latest
 
docker run -p 9000:9000 \
  -e MARGA_URL=http://marga:8080 \
  -e RAKSHA_URL=http://raksha:8080 \
  -e DEVOPS_RAG_URL=http://devops-rag:8080 \
  ghcr.io/gaurav21/avyay-gateway:latest

All services are then available under one URL:

  • POST /v1/marga/chat/completions — LLM routing
  • POST /v1/raksha/scan/upload — Security scanning
  • POST /v1/devops-rag/ask — DevOps knowledge base

Full Gateway docs →

Next Steps

IntroductionOverview