Full-Stack AI with Python: LLMs, RAG, Agents & LangGraph

Source: https://www.udemy.com/course/full-stack-ai-with-python/

What you’ll learn

• Write Python programs from scratch, using Git for version control and Docker for deployment.
• Use Pydantic to handle structured data and validation in Python applications.
• Understand how Large Language Models (LLMs) work: tokenization, embeddings, attention, and transformers.
• Call and integrate APIs from OpenAI and Gemini with Python.
• Design effective prompts: zero-shot, one-shot, few-shot, chain-of-thought, persona-based, and structured prompting.
• Run and deploy models locally using Ollama, Hugging Face, and Docker.
• Implement Retrieval-Augmented Generation (RAG) pipelines with LangChain and vector databases.
• Use LangGraph to design stateful AI systems with nodes, edges, and checkpointing.
• Understand Model Context Protocol (MCP) and build MCP servers with Python.

Requirements

• No prior AI knowledge is required — we start from the basics.
• A computer (Windows, macOS, or Linux) with internet access.
• Basic programming knowledge is helpful but not mandatory (the course covers Python from scratch).