Prerequisites

System Requirements

To participate fully in this workshop, your system should meet the following requirements:

Minimum Requirements

Recommended Specifications

For optimal performance:

• RAM: 16 GB or more
• Storage: 50 GB free (SSD preferred for faster model loading)
• GPU: Not required, but Apple Silicon (M1/M2/M3) or NVIDIA GPU will improve performance

Pre-Workshop Setup

Part 1: For Everyone

You can complete these steps before the workshop to save time during the live session:

1. Install Ollama

Download and install Ollama from the official website:

• macOS: Download the .dmg file and drag to Applications
• Windows: Download the .exe installer and run it
• Linux: Follow the installation script on the download page

2. Verify Installation

After installing, launch the Ollama application:

• On macOS/Windows: Look for the Ollama icon in your Applications folder or Start menu
• On Linux: Run ollama in the terminal

You should see the Ollama GUI interface open.

3. Download Llama 3.2 Model (Optional)

To save time during the workshop, you can pre-download the Llama 3.2 model:

Option 1: Using the GUI (Recommended)

1. Open Ollama
2. Click on the model dropdown
3. Search for “llama3.2”
4. Click download (approximately 2 GB)

Option 2: Using the Terminal

ollama pull llama3.2

This downloads the 3B parameter version, which is perfect for the workshop.

Part 2: For Python Integration (Optional)

If you plan to actively follow along with Part 2 of the workshop (Python, embeddings, and RAG), please set up your Python environment:

1. Install Python

Ensure you have Python 3.8 or later installed:

python --version
# or
python3 --version

If you need to install Python:

• macOS/Linux: Use your package manager or download from python.org
• Windows: Download from python.org (ensure “Add Python to PATH” is checked)

2. Install Jupyter Notebook

pip install jupyter notebook
# or
pip3 install jupyter notebook

3. Install Required Libraries

pip install ollama chromadb jinja2

What to Have Ready

On the day of the workshop, please have:

• Ollama installed and tested
• Llama 3.2 model downloaded (optional but recommended)
• Text editor or IDE of your choice (VS Code, PyCharm, Sublime, etc.)
• Terminal/Command Prompt access
• Jupyter Notebook (for Part 2)
• Workshop notebooks cloned from the repository (see below)

Cloning the Workshop Notebooks

Before or during the workshop, clone the companion notebook repository:

git clone https://github.com/nishad/llm-workshop-notebooks.git
cd llm-workshop-notebooks

If you don’t have git installed, you can download the repository as a ZIP file from GitHub.

Troubleshooting Before the Workshop

Ollama Won’t Start

• macOS: Check System Preferences → Privacy & Security → Allow Ollama
• Windows: Right-click Ollama → Run as Administrator
• Linux: Ensure you have the necessary permissions and dependencies

Model Download Fails

• Check your internet connection
• Ensure you have enough disk space (at least 5 GB free)
• Try downloading via terminal: ollama pull llama3.2
• If slow, the download will resume if interrupted

Python Issues

• Use a virtual environment: python -m venv workshop-env
• Activate it: source workshop-env/bin/activate (Mac/Linux) or workshop-env\Scripts\activate (Windows)
• Install packages in the virtual environment

Getting Help

If you encounter issues before the workshop:

1. Check the FAQ page
2. Review the Troubleshooting guide
3. Join the workshop with your questions - we’ll address setup issues at the start

Next Steps