Oreilly Openai Agentkit

O'Reilly Live Training - OpenAI AgentKit

Welcome to the O'Reilly Live Training on OpenAI AgentKit! This course covers the full OpenAI agent stack — from raw API calls with the Responses API, through the Agents SDK, up to the AgentKit product platform (Agent Builder, ChatKit, Connector Registry, and Evals). You'll build real demo applications along the way.

Setup

**Using uv (Recommended)**

This project uses [uv](https://github.com/astral-sh/uv), a fast Python package installer and resolver. The Makefile handles most setup automatically.

1. **Install uv:**

   curl -LsSf https://astral.sh/uv/install.sh | sh

2. **One-command setup:**

   make all

   This creates a virtual environment in `.venv`, installs dependencies, and sets up Jupyter kernel.

3. **Activate the environment:**

   source .venv/bin/activate

4. **Setup your OpenAI API key:**

   • Get your API key from OpenAI Platform
   • Create a .env file in the project root:

   echo "OPENAI_API_KEY=your-api-key-here" > .env

**Using Pip (Traditional Method)**

1. **Create a Virtual Environment:** Navigate to your project directory. Make sure you have Python 3.11+ installed!

   python -m venv .venv

2. **Activate the Virtual Environment:**

   • On macOS and Linux: source .venv/bin/activate
   • On Windows: .\.venv\Scripts\activate

3. **Install Dependencies:**

   pip install --upgrade pip
   pip install -r ./requirements/requirements.txt

4. **Setup Jupyter Kernel:**

   python -m ipykernel install --user --name=openai-agentkit

5. **Setup your OpenAI API key:** Create a `.env` file in the project root:

   echo "OPENAI_API_KEY=your-api-key-here" > .env

Remember to deactivate the virtual environment when done: `deactivate`

**Using Conda**

• Install anaconda or [miniconda](https: