Quick Start

Get InferXgate up and running in under 5 minutes with Docker.

This guide will help you get InferXgate running in just a few minutes using Docker.

Prerequisites

Before you begin, make sure you have:

Docker and Docker Compose installed
At least one LLM API key (Anthropic, OpenAI, or Google Gemini)

Step 1: Clone the Repository

git clone https://github.com/jasmedia/inferxgate.git
cd inferxgate

Step 2: Configure Environment

Copy the example environment file:

cp .env.example .env

Edit .env and add your API keys:

# Required: Add at least one provider API key
ANTHROPIC_API_KEY=sk-ant-your-key-here
OPENAI_API_KEY=sk-your-key-here
GEMINI_API_KEY=your-gemini-key-here

# Database (uses default Docker settings)
DATABASE_URL=postgresql://postgres:postgres@db:5432/inferxgate

# Redis for caching (uses default Docker settings)
REDIS_URL=redis://redis:6379

# JWT Secret (generate a secure random string)
JWT_SECRET=your-secure-secret-key-here

Step 3: Start the Services

docker-compose up -d

This starts:

InferXgate API on port 3000
Dashboard on port 80
PostgreSQL database
Redis cache

Step 4: Verify Installation

Check that the services are running:

# Health check
curl http://localhost:3000/health

You should see:

{
  "status": "healthy",
  "version": "1.0.0"
}

Step 5: Make Your First Request

Use the OpenAI SDK or curl to make a request:

Using Python

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:3000/v1",
    api_key="your-api-key"  # Or use JWT token
)

response = client.chat.completions.create(
    model="claude-3-opus-20240229",  # Or gpt-4, gemini-1.5-pro
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

Using cURL

curl -X POST http://localhost:3000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "model": "claude-3-opus-20240229",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Step 6: Access the Dashboard

Open your browser and go to:

http://localhost

The dashboard provides:

Real-time usage statistics
Interactive API playground
Provider management
API key management

Model Naming Convention

InferXgate routes requests based on model names:

Prefix	Provider
`claude-*`	Anthropic
`gpt-*`	OpenAI
`gemini-*`	Google Gemini
`azure-*`	Azure OpenAI

Examples:

claude-3-opus-20240229 → Anthropic
gpt-4-turbo → OpenAI
gemini-1.5-pro → Google Gemini

What’s Next?

Now that you have InferXgate running:

Configure authentication to secure your API
Set up caching to reduce costs
Configure load balancing for high availability
Explore the API for all available endpoints

Troubleshooting

Port Already in Use

If port 3000 is already in use, modify the port mapping in docker-compose.yml:

ports:
  - "3001:3000"  # Use port 3001 instead

Container Won’t Start

Check the logs:

docker-compose logs -f inferxgate

Database Connection Error

Ensure PostgreSQL is running and the DATABASE_URL is correct:

docker-compose ps
docker-compose logs db

Cache Not Working

Verify Redis is running:

docker-compose logs redis
redis-cli -h localhost ping