Skip to content

ogx-ai/ogx-demos

Repository files navigation

OGX Demos

A collection of hands-on demos for OGX, covering everything from basic chat completions to RAG, agents, observability, and end-to-end applications. All demos run locally in your terminal.

Quick Start

Prerequisites

  • Python >= 3.12
  • uv (recommended) or pip
  • Ollama (for local model serving)

1. Install dependencies

uv sync

2. Set up a model backend

These demos use Ollama as the default model backend, but OGX supports many others (vLLM, Together, Fireworks, OpenAI, etc.). See the OGX documentation for the full list of supported providers.

# Install Ollama from https://ollama.com/download, then:
ollama pull llama3.2:3b

3. Start a local OGX server

Start the server in a separate terminal:

uvx --from 'ogx[starter]' ogx run starter

The server listens on localhost:8321 by default.

4. Run a demo

# Example: basic client setup
uv run python -m demos.01_foundations.01_client_setup localhost 8321

Available Demos

All demos live under the demos/ directory and can be run directly from the terminal.

Directory Topic Description
01_foundations Foundations Client setup, chat completions, vector DBs, tool registration, MCP
02_responses_basics Responses API Higher-level response generation with tools and structured outputs
03_rag RAG Retrieval-augmented generation with vector stores and search
04_agents Agents Conversational agents with chat, tools, RAG, and multi-agent coordination
05_observability Observability OpenTelemetry, Jaeger, Prometheus, and Grafana integration
06_openai_compatibility OpenAI Compatibility Using OpenAI-compatible endpoints with OGX
07-end-to-end-apps End-to-End Apps Full applications (e.g. Knowledge Assistant)

Each demo directory has its own README with detailed instructions and learning objectives. Start with 01_foundations if you are new to OGX.

Optional: Kubernetes Deployment

If you want to deploy OGX on Kubernetes instead of running locally, see deployment/kubernetes/ for manifests and instructions covering vLLM, the OGX Kubernetes operator, and MCP servers on a Kind cluster.

Resources

About

Collection of demos for building Llama Stack based apps on OpenShift

Resources

License

Contributing

Stars

65 stars

Watchers

9 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors