Skip to content

Data Science · One build, frame by frame

NLP Book Recommendation

Embeddings that actually recommend.

A semantic book recommendation engine using Hugging Face embeddings to surface suggestions by meaning rather than keywords.

Data SciencePythonHugging FaceJupyterNLP

01The problem

Keyword search misses books that are conceptually similar but worded differently.

02What I built

Embedded titles/descriptions with Hugging Face models and ranked recommendations by semantic similarity.

03What changed

A recommender that suggests by meaning, surfacing relevant books keyword search would miss.

See it for yourself

← All work