peremartra/Large-Language-Model-Notebooks-Course

What it solves

This project provides a hands-on learning path for engineers and developers to master Large Language Models (LLMs). It bridges the gap between theoretical knowledge and practical implementation by offering a series of notebooks and articles that demonstrate how to build, evaluate, and optimize LLM-based applications.

How it works

The course is structured into practical lessons, each consisting of a Jupyter notebook and an accompanying explanatory article. Users are encouraged to follow along by running the notebooks—primarily hosted on Google Colab or Kaggle—while reading the detailed explanations. The content covers the full lifecycle of LLM development, from basic prompt engineering and chatbot creation to advanced topics like Retrieval Augmented Generation (RAG), agentic workflows, and model evaluation.

Who it’s for

This resource is designed for engineers, researchers, and developers who want to gain practical experience with LLMs. It is suitable for those who prefer learning by doing and want to understand how to integrate models from providers like OpenAI and Hugging Face into real-world projects.

Highlights

• Practical, hands-on projects including chatbots, SQL translators, and data analyst agents.
• Comprehensive coverage of essential tools like LangChain, ChromaDB, and various evaluation frameworks.
• Guidance on advanced techniques such as RAG, fine-tuning, and model monitoring.
• Clear separation of lessons into logical sections: Techniques, Projects, and Enterprise Solutions.
• Integration with industry-standard evaluation tools like Giskard, LangSmith, and EleutherAI’s lm-evaluation-harness.