# ddangelov/Top2Vec

Top2Vec learns jointly embedded topic, document and word vectors.

Repository: https://github.com/ddangelov/Top2Vec
Canonical: https://ross.abutalabs.com/products/top2vec
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: topic-modeling, word-embeddings, document-embedding, topic-vector, topic-search, text-search, text-semantic-similarity, topic-modelling, semantic-search, bert, top2vec, sentence-transformers, sentence-encoder, pre-trained-language-models
Last push: 2024-11-14T23:47:51+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2357, "days_push": 657, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3102, forks 374 (observed 2026-08-28T04:07:43.604584+00:00)

## What it is
Top2Vec is a Python library that learns jointly embedded topic, document, and word vectors for topic modeling and semantic search. It supports transformer-based embedding models and a contextual mode that finds multiple topics and topic segments within documents.

## Use cases
- discover topics in a document corpus
- find semantically similar documents
- search documents by topic
- generate word and document embeddings for text
- segment a long document into topic spans
- get topic distributions per document

## When to choose
- you need unsupervised topic modeling without specifying the number of topics
- you want joint topic, document, and word embeddings
- you want semantic search over a text corpus
- you need multi-topic or per-document topic segmentation

## When to avoid
- you need a simple keyword or full-text search engine
- you need heavily supervised text classification
- you cannot run transformer embedding models locally

## Facets
- artifact type: library
- maturity: stable
- function: nlp, machine-learning, search-engine, data-science
- domain: machine-learning, data-science
- platform: python, cross-platform
- tags: topic-modeling, word-embeddings, document-embedding, semantic-search, sentence-transformers, bert, natural-language-processing, search

## Member repositories
- ddangelov/Top2Vec (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:43.604584+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 2026-08-29T18:46:20.477560+00:00, confidence not recorded.
  - readme: https://github.com/ddangelov/Top2Vec (fetched 2026-08-28T04:07:43.604584+00:00, sha 83b8252e90a3)
  - registry_pypi: https://pypi.org/pypi/top2vec/json (fetched 2026-08-29T09:42:09.581265+00:00, sha c8911890691f)
- Data as of 2026-08-30T08:39:29.467469+00:00.