{"adoption": {"forks": 917, "observed_at": "2026-08-28T04:10:05.144236+00:00", "stars": 7804}, "canonical_url": "https://ross.abutalabs.com/products/bertopic", "card": {"archived": false, "artifact_type": "library", "description": "Leveraging BERT and c-TF-IDF to create easily interpretable topics. ", "domain": ["machine-learning", "data-science"], "enriched": true, "function": ["nlp", "machine-learning", "data-science", "data-visualization"], "health_score": 95, "homepage": "https://maartengr.github.io/BERTopic/", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "stable", "member_repos": ["MaartenGr/BERTopic"], "name": "MaartenGr/BERTopic", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-22T06:36:06+00:00", "repo": "MaartenGr/BERTopic", "stars": 7804, "tags": ["topic-modeling", "bert", "transformers", "sentence-embeddings", "ctfidf", "clustering", "unsupervised-learning", "natural-language-processing"], "topics": ["bert", "transformers", "topic-modeling", "sentence-embeddings", "nlp", "machine-learning", "topic", "ldavis", "topic-modelling", "topic-models"], "urls": [], "use_cases": ["discover topics in a corpus of documents", "cluster customer reviews into themes", "track how topics evolve over time", "visualize topics like pyLDAvis", "do zero-shot topic modeling with seed keywords", "summarize topic descriptions with LLMs", "model topics from images", "incrementally model topics in a stream of documents"], "what_it_is": "BERTopic is a Python library for topic modeling that leverages transformer-based sentence embeddings and class-based TF-IDF (c-TF-IDF) to discover easily interpretable topics in document collections. It supports guided, supervised, hierarchical, dynamic, online, multimodal, zero-shot, and LLM-enhanced topic modeling variants.", "when_to_avoid": ["you need a lightweight classic LDA implementation without transformer dependencies", "you work outside Python or need a hosted no-code service", "your corpus is tiny and embedding models would be overkill"], "when_to_choose": ["you need interpretable topics from text using modern transformer embeddings", "you want flexible topic modeling modes (supervised, dynamic, hierarchical, online)", "you are working in Python and want an actively maintained, well-documented topic modeling library"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/bertopic", "repo": "MaartenGr/BERTopic", "role": "main", "score": 77}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:05.144236+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:34:37.026577+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "580b203c8a0468162cc439a1812cb0524fe6245fa5f4624a865b72948b07433f", "fetched_at": "2026-08-28T04:10:05.144236+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MaartenGr/BERTopic"}, {"content_hash": "ddf33edda9a4a2c1dfbc30e335667dae6adb1e3f5dabc5315a03facffa4796b6", "fetched_at": "2026-08-29T08:30:46.751540+00:00", "kind": "homepage", "missing": false, "url": "https://maartengr.github.io/BERTopic/"}, {"content_hash": "015368be8a95a54daa47185562973014e546d18884f1473e2454735beec9a02a", "fetched_at": "2026-08-29T08:30:46.760856+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bertopic/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:05.144236+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:34:37.026577+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "580b203c8a0468162cc439a1812cb0524fe6245fa5f4624a865b72948b07433f", "fetched_at": "2026-08-28T04:10:05.144236+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MaartenGr/BERTopic"}, {"content_hash": "ddf33edda9a4a2c1dfbc30e335667dae6adb1e3f5dabc5315a03facffa4796b6", "fetched_at": "2026-08-29T08:30:46.751540+00:00", "kind": "homepage", "missing": false, "url": "https://maartengr.github.io/BERTopic/"}, {"content_hash": "015368be8a95a54daa47185562973014e546d18884f1473e2454735beec9a02a", "fetched_at": "2026-08-29T08:30:46.760856+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bertopic/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:34:37.026577+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "580b203c8a0468162cc439a1812cb0524fe6245fa5f4624a865b72948b07433f", "fetched_at": "2026-08-28T04:10:05.144236+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MaartenGr/BERTopic"}, {"content_hash": "ddf33edda9a4a2c1dfbc30e335667dae6adb1e3f5dabc5315a03facffa4796b6", "fetched_at": "2026-08-29T08:30:46.751540+00:00", "kind": "homepage", "missing": false, "url": "https://maartengr.github.io/BERTopic/"}, {"content_hash": "015368be8a95a54daa47185562973014e546d18884f1473e2454735beec9a02a", "fetched_at": "2026-08-29T08:30:46.760856+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bertopic/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:05.144236+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:05.144236+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:05.144236+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:34:37.026577+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "580b203c8a0468162cc439a1812cb0524fe6245fa5f4624a865b72948b07433f", "fetched_at": "2026-08-28T04:10:05.144236+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MaartenGr/BERTopic"}, {"content_hash": "ddf33edda9a4a2c1dfbc30e335667dae6adb1e3f5dabc5315a03facffa4796b6", "fetched_at": "2026-08-29T08:30:46.751540+00:00", "kind": "homepage", "missing": false, "url": "https://maartengr.github.io/BERTopic/"}, {"content_hash": "015368be8a95a54daa47185562973014e546d18884f1473e2454735beec9a02a", "fetched_at": "2026-08-29T08:30:46.760856+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bertopic/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:05.144236+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:05.144236+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:34:37.026577+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "580b203c8a0468162cc439a1812cb0524fe6245fa5f4624a865b72948b07433f", "fetched_at": "2026-08-28T04:10:05.144236+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MaartenGr/BERTopic"}, {"content_hash": "ddf33edda9a4a2c1dfbc30e335667dae6adb1e3f5dabc5315a03facffa4796b6", "fetched_at": "2026-08-29T08:30:46.751540+00:00", "kind": "homepage", "missing": false, "url": "https://maartengr.github.io/BERTopic/"}, {"content_hash": "015368be8a95a54daa47185562973014e546d18884f1473e2454735beec9a02a", "fetched_at": "2026-08-29T08:30:46.760856+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bertopic/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:05.144236+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:05.144236+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:05.144236+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:34:37.026577+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "580b203c8a0468162cc439a1812cb0524fe6245fa5f4624a865b72948b07433f", "fetched_at": "2026-08-28T04:10:05.144236+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MaartenGr/BERTopic"}, {"content_hash": "ddf33edda9a4a2c1dfbc30e335667dae6adb1e3f5dabc5315a03facffa4796b6", "fetched_at": "2026-08-29T08:30:46.751540+00:00", "kind": "homepage", "missing": false, "url": "https://maartengr.github.io/BERTopic/"}, {"content_hash": "015368be8a95a54daa47185562973014e546d18884f1473e2454735beec9a02a", "fetched_at": "2026-08-29T08:30:46.760856+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bertopic/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:05.144236+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:05.144236+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:34:37.026577+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "580b203c8a0468162cc439a1812cb0524fe6245fa5f4624a865b72948b07433f", "fetched_at": "2026-08-28T04:10:05.144236+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MaartenGr/BERTopic"}, {"content_hash": "ddf33edda9a4a2c1dfbc30e335667dae6adb1e3f5dabc5315a03facffa4796b6", "fetched_at": "2026-08-29T08:30:46.751540+00:00", "kind": "homepage", "missing": false, "url": "https://maartengr.github.io/BERTopic/"}, {"content_hash": "015368be8a95a54daa47185562973014e546d18884f1473e2454735beec9a02a", "fetched_at": "2026-08-29T08:30:46.760856+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bertopic/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:34:37.026577+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "580b203c8a0468162cc439a1812cb0524fe6245fa5f4624a865b72948b07433f", "fetched_at": "2026-08-28T04:10:05.144236+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MaartenGr/BERTopic"}, {"content_hash": "ddf33edda9a4a2c1dfbc30e335667dae6adb1e3f5dabc5315a03facffa4796b6", "fetched_at": "2026-08-29T08:30:46.751540+00:00", "kind": "homepage", "missing": false, "url": "https://maartengr.github.io/BERTopic/"}, {"content_hash": "015368be8a95a54daa47185562973014e546d18884f1473e2454735beec9a02a", "fetched_at": "2026-08-29T08:30:46.760856+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bertopic/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:34:37.026577+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "580b203c8a0468162cc439a1812cb0524fe6245fa5f4624a865b72948b07433f", "fetched_at": "2026-08-28T04:10:05.144236+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MaartenGr/BERTopic"}, {"content_hash": "ddf33edda9a4a2c1dfbc30e335667dae6adb1e3f5dabc5315a03facffa4796b6", "fetched_at": "2026-08-29T08:30:46.751540+00:00", "kind": "homepage", "missing": false, "url": "https://maartengr.github.io/BERTopic/"}, {"content_hash": "015368be8a95a54daa47185562973014e546d18884f1473e2454735beec9a02a", "fetched_at": "2026-08-29T08:30:46.760856+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bertopic/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:34:37.026577+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "580b203c8a0468162cc439a1812cb0524fe6245fa5f4624a865b72948b07433f", "fetched_at": "2026-08-28T04:10:05.144236+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MaartenGr/BERTopic"}, {"content_hash": "ddf33edda9a4a2c1dfbc30e335667dae6adb1e3f5dabc5315a03facffa4796b6", "fetched_at": "2026-08-29T08:30:46.751540+00:00", "kind": "homepage", "missing": false, "url": "https://maartengr.github.io/BERTopic/"}, {"content_hash": "015368be8a95a54daa47185562973014e546d18884f1473e2454735beec9a02a", "fetched_at": "2026-08-29T08:30:46.760856+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/bertopic/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2171, "days_push": 11, "days_rel": 273, "gap_med": 129.0, "n_releases_24m": 5}, "score": 77, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}