Open source

Python tools I’ve built for topic modeling, keyword extraction, and string matching.

BERTopic

Topic modeling with transformer embeddings and c-TF-IDF, designed to make clusters of documents interpretable.

Keyword and keyphrase extraction using embeddings from BERT and related language models.

Fuzzy string matching and grouping, with several matching methods behind one interface.

The open-source companions to our books. All examples are free to explore.

The notebooks and code examples that accompany our illustrated introduction to language models.

Build along with the book: practical examples for tools, memory, reasoning, and autonomous systems.

More projects and source code on GitHub.