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

01 - The problem

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

02 - What I built

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

03 - What changed

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

See it for yourself

← All work