Agent using the OpenAI SDK directly. Chat completions, function calling, and streaming — no framework overhead, just the official SDK.
What's included
- Direct OpenAI SDK — no abstraction layer, use the official client
- Chat completions — standard chat API with full control
- Function calling — define tools and let GPT invoke them
- Streaming — real-time token streaming via SSE
- GPT-4o — use the latest GPT models (GPT-4o, GPT-4o-mini, etc.)
When to use this
Pick this example when you want to:
- Use the OpenAI SDK directly without any framework
- Have full control over prompts, models, and parameters
- Build a simple agent with GPT-4o and function calling
Project structure
├── agents/
│ └── openai_agent.py # OpenAI SDK agent
├── main.py # Entry point — serve(agents)
├── pyproject.toml
└── reminix.config.toml
Quick start
Deploy the example and invoke the agent via the Reminix API. The OpenAI SDK handles chat completions, function calling, and streaming — you get a production REST endpoint with direct GPT-4o access.