baidu/Familia

Health v2 · maintenance only

Adoption not part of the score

2644 stars · 583 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

nlp machine-learning search-engine machine-learning cpp topic-modeling lda sentence-lda topical-word-embedding semantic-matching chinese-text pretrained-models natural-language-processing search linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="baidu/Familia")