Skip to content

Next Gen UI Agent A2A Server Container

This module is part of the Next Gen UI Agent project.

Module Category Module Status

Provides

Installation

podman pull quay.io/next-gen-ui/a2a

Usage

podman run --rm -p 9999:9999 \
    -e INFERENCE_MODEL=llama3.2 \
    -e OPEN_API_URL=http://host.containers.internal:11434/v1 \
    quay.io/next-gen-ui/a2a

Configuration

The A2A Server container can be configured via environment variables. For available env variables and their meaning see A2A Server Guide.

Dependencien necessary for openai inference provider are installed in the image.

json and rhds renderers are installed. Create child image to install additional ones.

Default values are changed for some configurations in the image!

Environment Variable Default Value Description
A2A_HOST 0.0.0.0 Host to bind to (for HTTP transports)
A2A_PORT 9999 Port to bind to (for HTTP transports)
NGUI_MODEL gpt-4o Model name

Usage Examples

Basic Usage with Ollama (Local LLM)

podman run --rm -it -p 5000:5000 \
    --env A2A_PORT="5000" \
    --env NGUI_PROVIDER="openai" \
    --env NGUI_MODEL="llama3.2" \
    --env NGUI_PROVIDER_API_BASE_URL="http://host.containers.internal:11434/v1" \
    --env NGUI_PROVIDER_API_KEY="ollama" \
    quay.io/next-gen-ui/a2a

OpenAI API Configuration

podman run --rm -it -p 5000:5000 \
    --env NGUI_PROVIDER="openai" \
    --env NGUI_MODEL="gpt-4o" \
    --env NGUI_PROVIDER_API_KEY="your-openai-api-key" \
    quay.io/next-gen-ui/a2a

Remote LlamaStack Server

podman run --rm -it -p 5000:5000 \
    --env NGUI_PROVIDER="openai" \
    --env NGUI_MODEL="llama3.2-3b" \
    --env NGUI_PROVIDER_API_BASE_URL="http://host.containers.internal:5001/v1" \
    quay.io/next-gen-ui/a2a

Configuration Using Environment File

Create a .env file:

# .env file
A2A_PORT=5000
A2A_HOST=0.0.0.0
NGUI_COMPONENT_SYSTEM=json
NGUI_PROVIDER=openai
NGUI_MODEL=gpt-4o
NGUI_PROVIDER_API_KEY=your-api-key-here

Run with environment file: 

podman run --rm -it -p 5000:5000 --env-file .env quay.io/next-gen-ui/a2a

Network Configuration

For local development connecting to services running on the host machine:

  • Use host.containers.internal to access host services (works with Podman and Docker Desktop)
  • For Linux with Podman, you may need to use host.docker.internal or the host's IP address
  • Ensure the target services (like Ollama) are accessible from containers