# veekaybee/what_are_embeddings

A deep dive into embeddings starting from fundamentals

Repository: https://github.com/veekaybee/what_are_embeddings
Canonical: https://ross.abutalabs.com/products/what_are_embeddings
Homepage: http://vickiboykis.com/what_are_embeddings/
Language: Jupyter Notebook
License Family: other
Topics: embeddings, machine-learning, machine-learning-algorithms, nlp-machine-learning
Last push: 2026-01-17T00:33:35+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 62, release rhythm 31, longevity 85
- inputs: {"age_days": 1198, "days_push": 229, "days_rel": 244, "gap_med": 409, "n_releases_24m": 2}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1096, forks 86 (observed 2026-08-28T04:03:34.483637+00:00)

## What it is
A survey paper and accompanying Jupyter notebooks by Vicki Boykis providing a deep dive into embeddings, from TF-IDF and Word2Vec through transformer-based representations. It includes the LaTeX source, a generated website, and complementary notebook code.

## Use cases
- understand what embeddings are from first principles
- learn the history of word and text representations like TF-IDF and Word2Vec
- get a conceptual foundation before working with transformer models
- find a generalist introduction to embeddings for recommendation systems
- study notebook examples of embedding techniques
- cite a reference on embeddings in industrial ML systems

## When to choose
- you want a conceptual, fundamentals-first explanation of embeddings
- you're a generalist or engineer needing background before deep learning work
- you want runnable notebooks alongside the reading material

## When to avoid
- you need a production embedding library or API
- you want cutting-edge research papers rather than a survey
- you need a maintained software tool with tests and CI

## Facets
- artifact type: learning-resource
- maturity: stable
- function: nlp, machine-learning, documentation
- domain: machine-learning, deep-learning, tutorials
- platform: python
- tags: embeddings, survey-paper, educational, jupyter-notebooks, latex, natural-language-processing

## Member repositories
- veekaybee/what_are_embeddings (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:34.483637+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:47:12.581322+00:00, confidence not recorded.
  - readme: https://github.com/veekaybee/what_are_embeddings (fetched 2026-08-28T04:03:34.483637+00:00, sha 79989c5e2cd8)
  - homepage: http://vickiboykis.com/what_are_embeddings/ (fetched 2026-08-29T12:50:20.739264+00:00, sha 2c33725276fd)
  - site_page: http://vickiboykis.com/what_are_embeddings/about.html (fetched 2026-08-29T12:50:20.748507+00:00, sha 2490adc07bcb)
- Data as of 2026-08-30T08:39:29.467469+00:00.