{"adoption": {"forks": 297, "observed_at": "2026-08-28T04:05:08.560916+00:00", "stars": 1590}, "canonical_url": "https://ross.abutalabs.com/products/pke", "card": {"archived": false, "artifact_type": "library", "description": "Python Keyphrase Extraction module", "domain": [], "enriched": true, "function": ["nlp", "search-engine", "machine-learning"], "health_score": 20, "homepage": null, "language": "Python", "license": "GPL-3.0", "license_family": "copyleft", "maturity": "maintenance", "member_repos": ["boudinfl/pke"], "name": "boudinfl/pke", "platform": ["python", "cross-platform"], "pushed_at": "2023-07-12T16:18:04+00:00", "repo": "boudinfl/pke", "stars": 1590, "tags": ["keyphrase-extraction", "keyword-extraction", "spacy", "unsupervised-learning", "supervised-models", "benchmarking", "natural-language-processing", "information-retrieval", "computational-linguistics"], "topics": ["keyphrase-extraction", "natural-language-processing", "information-retrieval", "computational-linguistics", "keyword-extraction", "python", "keyword", "keyphrase"], "urls": [], "use_cases": ["extract keyphrases from documents in python", "extract keywords from text automatically", "compare keyphrase extraction models on benchmarks", "build a tagging system for articles", "implement a custom keyphrase extraction model", "get top n keywords for SEO or indexing"], "what_it_is": "pke is an open-source Python toolkit for keyphrase extraction that provides an end-to-end pipeline where each component (candidate selection, weighting, ranking) can be modified or extended. It implements many state-of-the-art unsupervised and supervised models and supports easy benchmarking on standard datasets.", "when_to_avoid": ["you need keyphrase generation (abstracting new phrases) rather than extraction from the text", "you need production-grade speed or heavy-duty NLP beyond keyphrases", "you cannot use GPL-3.0 licensed code in your project", "you need a maintained library with frequent updates and recent dependency support"], "when_to_choose": ["you need a standardized API to experiment with multiple keyphrase extraction algorithms", "you want to benchmark state-of-the-art keyphrase models like TopicRank or YAKE", "you need supervised keyphrase extraction models trained on SemEval-2010", "you want a pipeline where candidate selection and weighting are easily customizable"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pke", "repo": "boudinfl/pke", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.560916+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:54:46.909536+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfa66c3af64657fb4d64af85300016e957b2e30695988362f318df0722cf172", "fetched_at": "2026-08-28T04:05:08.560916+00:00", "kind": "readme", "missing": false, "url": "https://github.com/boudinfl/pke"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.560916+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:54:46.909536+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfa66c3af64657fb4d64af85300016e957b2e30695988362f318df0722cf172", "fetched_at": "2026-08-28T04:05:08.560916+00:00", "kind": "readme", "missing": false, "url": "https://github.com/boudinfl/pke"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:54:46.909536+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfa66c3af64657fb4d64af85300016e957b2e30695988362f318df0722cf172", "fetched_at": "2026-08-28T04:05:08.560916+00:00", "kind": "readme", "missing": false, "url": "https://github.com/boudinfl/pke"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.560916+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.560916+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.560916+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:54:46.909536+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfa66c3af64657fb4d64af85300016e957b2e30695988362f318df0722cf172", "fetched_at": "2026-08-28T04:05:08.560916+00:00", "kind": "readme", "missing": false, "url": "https://github.com/boudinfl/pke"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.560916+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.560916+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:54:46.909536+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfa66c3af64657fb4d64af85300016e957b2e30695988362f318df0722cf172", "fetched_at": "2026-08-28T04:05:08.560916+00:00", "kind": "readme", "missing": false, "url": "https://github.com/boudinfl/pke"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.560916+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.560916+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.560916+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:54:46.909536+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfa66c3af64657fb4d64af85300016e957b2e30695988362f318df0722cf172", "fetched_at": "2026-08-28T04:05:08.560916+00:00", "kind": "readme", "missing": false, "url": "https://github.com/boudinfl/pke"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.560916+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:08.560916+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:54:46.909536+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfa66c3af64657fb4d64af85300016e957b2e30695988362f318df0722cf172", "fetched_at": "2026-08-28T04:05:08.560916+00:00", "kind": "readme", "missing": false, "url": "https://github.com/boudinfl/pke"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:54:46.909536+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfa66c3af64657fb4d64af85300016e957b2e30695988362f318df0722cf172", "fetched_at": "2026-08-28T04:05:08.560916+00:00", "kind": "readme", "missing": false, "url": "https://github.com/boudinfl/pke"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:54:46.909536+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfa66c3af64657fb4d64af85300016e957b2e30695988362f318df0722cf172", "fetched_at": "2026-08-28T04:05:08.560916+00:00", "kind": "readme", "missing": false, "url": "https://github.com/boudinfl/pke"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:54:46.909536+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3cfa66c3af64657fb4d64af85300016e957b2e30695988362f318df0722cf172", "fetched_at": "2026-08-28T04:05:08.560916+00:00", "kind": "readme", "missing": false, "url": "https://github.com/boudinfl/pke"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "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": 3946, "days_push": 1148, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}