Ai Engineering Core / Build First LLM Product

Setting up LLM Development Environment

Step 1 — Open Terminal or PowerShell and navigate to your desired location

cd Desktop

Step 2 — Install uv

Follow the official installation guide based on your OS:

Once installed, verify it works:

uv --version

If you see a version number, you're good to go. If not, revisit the installation steps.

Step 3 — Create and initialize a new project (terminal)

mkdir llm_engineering
cd llm_engineering
uv init

uv init creates a pyproject.toml, .python-version, and main.py.

Then open the folder in your code editor (VS Code or Cursor).

Step 4 — Create a requirements.txt file in the project root

Paste the following into it:

python-dotenv
ipykernel
ipywidgets
requests
numpy
pandas
scipy
scikit-learn
matplotlib
torch
transformers
tqdm
openai
gradio
langchain
langchain-core
langchain-text-splitters
langchain-openai
langchain-chroma
langchain-community
datasets==3.6.0
google-generativeai
anthropic
chromadb
plotly
jupyter-dash
beautifulsoup4
pydub
modal
ollama
psutil
setuptools
speedtest-cli
sentence_transformers
feedparser
protobuf==3.20.2
wandb
jupyterlab

Step 5 — Open the integrated terminal in your editor

Press Ctrl + ~ or enable it from the top menu bar.

Step 6 — Create a virtual environment

In terminal:

uv venv
# or pin a specific Python version:
uv venv --python 3.11

This creates a .venv/ folder in your project directory.

Step 7 — Activate the virtual environment

macOS / Linux:

source .venv/bin/activate

Windows (CMD):

.venv\Scripts\activate.bat

Windows (PowerShell):

.venv\Scripts\Activate.ps1

Step 8 — Install all packages from requirements.txt

uv pip install -r requirements.txt

Step 9 — Install the Jupyter and Python Extensions in Your Editor

Open the Extensions panel (Ctrl + Shift + X) and install the following:

  • Search "Jupyter" → install the one by Microsoft

  • Search "Python" → install the one by ms-python

Step 10 — Create Your First Notebook

  1. Create a new file named demo.ipynb

  2. Add a code cell and type:

    print("Hello World")

Step 11 — Select the Kernel

  1. Click "Select Kernel" in the top-right corner of the notebook

  2. Choose "Python Environments"

  3. Select the .venv virtual environment we created earlier

Step 12 — Run the Code

Click the ▶ Run button on the left side of the code cell. You should see the output printed directly below it.

That's it — your environment is fully set up and ready to go! 🎉

✅ Special Note

What are .ipynb files?

.ipynb stands for Interactive Python Notebook. It's the file format used by Jupyter Notebook.

Instead of a plain .py script that runs top to bottom, a notebook is made up of cells that you can run individually — making it perfect for experimenting, visualizing data, and documenting your work all in one place.

Each .ipynb file stores:

  • Code cells — Python code you can run

  • Output — results, charts, printed values

  • Markdown cells — notes, explanations, headings

Under the hood it's just a JSON file, but Jupyter renders it as an interactive document in your editor.

Think of it as a mix between a Python script and a Word document — code and explanation, side by side.