# baidu/Familia

A Toolkit for Industrial Topic Modeling

Repository: https://github.com/baidu/Familia
Canonical: https://ross.abutalabs.com/products/familia
Language: C++
License: BSD-3-Clause
License Family: permissive
Topics: topic-modeling, topic-models, lda, sentence-lda, twe, nlp
Last push: 2021-07-01T08:28:33+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3367, "days_push": 1889, "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 2644, forks 583 (observed 2026-08-28T04:07:06.627366+00:00)

## What it is
Familia is a C++ toolkit for industrial topic modeling, providing document topic inference and semantic matching tools along with pretrained topic models (LDA, SentenceLDA, Topical Word Embedding) trained on industrial-scale Chinese corpora. It supports text classification, clustering, keyword extraction, and document similarity computation out of the box.

## Use cases
- infer topic distributions for documents
- compute similarity between short text and long documents
- compute similarity between two long documents
- extract keywords from documents
- classify or cluster Chinese text by topic
- build personalized recommendation features based on topic representations
- measure semantic distance between two documents

## When to choose
- you need pretrained topic models for Chinese text without training your own
- you want industrial-grade LDA/SentenceLDA/TWE models for semantic matching
- you need topic-based document representation for downstream tasks like CTR prediction or recommendation

## When to avoid
- you need topic models for languages other than Chinese
- you want actively maintained software with recent updates
- you need deep-learning-based embeddings rather than topic models
- you require Windows support

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, machine-learning, search-engine
- domain: machine-learning
- platform: cpp
- tags: topic-modeling, lda, sentence-lda, topical-word-embedding, semantic-matching, chinese-text, pretrained-models, natural-language-processing, search, linux, macos

## Member repositories
- baidu/Familia (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:06.627366+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 2026-08-30T02:19:00.560475+00:00, confidence not recorded.
  - readme: https://github.com/baidu/Familia (fetched 2026-08-28T04:07:06.627366+00:00, sha 5223c4d10e2d)
- Data as of 2026-08-30T08:39:29.467469+00:00.