Hands-on lab

Time to make this concrete. Open the Text Processing notebooks:

01-text-processing/01_text_cleaning_pipeline.ipynb, build a real cleaning + normalization pipeline.
01-text-processing/02_tokenization_showdown.ipynb, compare tokenizers on the three metrics from §1.2 and see fertility differ across languages.
01-text-processing/03_tfidf_search_engine.ipynb, implement TF-IDF and BM25 and turn them into a working search engine.

cd exercices/01-text-processing
jupyter lab

Lab notebooks

This module's notebooks are free — they just need an account so we know where to save your progress. No card, no charge.

Keep going

15 more modules, 57 lessons, and every lab notebook

Retrieval and RAG, agents and MCP, fine-tuning, alignment, evaluation, and production observability — plus the quizzes and progress tracking.

A free account saves your progress and unlocks the lab notebooks for this module.