Setting Up Your AI Engineering Environment

Your AI Engineering Workstation

Before building LLM applications, you need a properly configured development environment. This lesson walks you through setting up everything from scratch — Python, API keys, GPU access, and essential libraries.

Step 1: Python Environment with uv

We use uv — the modern Python package manager that is 10-100x faster than pip:

# Install uv (macOS/Linux)
curl -LsSf https://astral.sh/uv/install.sh | sh

# Create project directory
mkdir ai-engineer-core && cd ai-engineer-core

# Initialize Python 3.12 project
uv init --python 3.12
uv venv
source .venv/bin/activate

Step 2: Install Core Libraries

# LLM APIs
uv add openai anthropic google-generativeai

# AI/ML frameworks
uv add langchain langchain-openai langchain-community langgraph
uv add transformers datasets accelerate peft bitsandbytes
uv add sentence-transformers chromadb faiss-cpu

# Web and UI
uv add gradio streamlit fastapi uvicorn

# Utilities
uv add python-dotenv requests beautifulsoup4 pandas

Step 3: API Keys Configuration

Create a file — never commit this to Git:

OPENAI_API_KEY=sk-proj-your-key-here
ANTHROPIC_API_KEY=sk-ant-your-key-here
HUGGINGFACE_TOKEN=hf_your-token-here

Load them safely in Python:

from dotenv import load_dotenv
import os

load_dotenv()

# Verify keys are loaded
assert os.getenv("OPENAI_API_KEY"), "Missing OpenAI key"
assert os.getenv("ANTHROPIC_API_KEY"), "Missing Anthropic key"
print("All API keys loaded successfully!")

Step 4: GPU Access Options

Step 5: Verify Everything Works

from openai import OpenAI
from anthropic import Anthropic

# Test OpenAI
openai_client = OpenAI()
response = openai_client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Say hello in one word"}],
    max_tokens=5
)
print(f"OpenAI: {response.choices[0].message.content}")

# Test Anthropic
anthropic_client = Anthropic()
response = anthropic_client.messages.create(
    model="claude-haiku-4-5-20251001",
    max_tokens=5,
    messages=[{"role": "user", "content": "Say hello in one word"}]
)
print(f"Anthropic: {response.content[0].text}")
print("Environment setup complete!")

Key Takeaway

A clean, reproducible environment is the foundation of every AI project. Use uv for speed, .env files for security, and cloud GPUs for fine-tuning. You are now ready to build.