{"adoption": {"forks": 539, "observed_at": "2026-08-28T04:08:14.956678+00:00", "stars": 3701}, "canonical_url": "https://ross.abutalabs.com/products/sumy", "card": {"archived": false, "artifact_type": "library", "description": "Module for automatic summarization of text documents and HTML pages.", "domain": ["developer-tools"], "enriched": true, "function": ["nlp", "parser", "cli"], "health_score": 99, "homepage": "https://miso-belica.github.io/sumy/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["miso-belica/sumy"], "name": "miso-belica/sumy", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2026-08-14T19:17:56+00:00", "repo": "miso-belica/sumy", "stars": 3701, "tags": ["text-summarization", "extractive-summarization", "textrank", "lexrank", "lsa", "html-extraction", "natural-language-processing"], "topics": ["python", "lsa", "textteaser", "html-page", "summarizer", "pagerank-algorithm", "reduction", "text-extraction", "html-extraction", "html-extractor", "sumy", "summarization", "summary", "nlp"], "urls": [], "use_cases": ["summarize long articles into key sentences", "extract summaries from HTML web pages", "summarize text in multiple languages", "evaluate summarization quality against reference summaries", "add extractive summarization to a Python application", "quickly condense a Wikipedia page from the command line"], "what_it_is": "Sumy is a Python library and command-line utility for automatic extractive summarization of plain text documents and HTML pages. It implements multiple summarization algorithms (LexRank, LSA, TextRank, Luhn, Edmundson) with multilingual tokenizer support and a simple evaluation framework.", "when_to_avoid": ["you need abstractive summaries that rewrite text in new sentences", "you need state-of-the-art neural summarization quality", "you need to summarize very long documents beyond its design scope"], "when_to_choose": ["you need lightweight extractive summarization without GPU or deep learning models", "you want a CLI tool for quick one-off summarization of URLs or text files", "you need support for many natural languages including Czech/Slovak", "you want a simple, dependency-light Python API for summarization"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/sumy", "repo": "miso-belica/sumy", "role": "main", "score": 89}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.956678+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:31:02.065791+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "094c2c935fb04e1a9c1e09b59a50c71c405b9df34c0e72fffc81ba02011b87d9", "fetched_at": "2026-08-28T04:08:14.956678+00:00", "kind": "readme", "missing": false, "url": "https://github.com/miso-belica/sumy"}, {"content_hash": "ebbdfbb87f210f950bbf5fd824f7c8bebf7a3fbbdf4d35a61e64e2b7e3173ee9", "fetched_at": "2026-08-29T09:24:38.799090+00:00", "kind": "homepage", "missing": false, "url": "https://miso-belica.github.io/sumy/"}, {"content_hash": "2f1ebb96cc7e21a2628a5227dd838166f4f8d747448b26a2db4eca37fd272cb5", "fetched_at": "2026-08-29T09:24:38.808407+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sumy/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.956678+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:31:02.065791+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "094c2c935fb04e1a9c1e09b59a50c71c405b9df34c0e72fffc81ba02011b87d9", "fetched_at": "2026-08-28T04:08:14.956678+00:00", "kind": "readme", "missing": false, "url": "https://github.com/miso-belica/sumy"}, {"content_hash": "ebbdfbb87f210f950bbf5fd824f7c8bebf7a3fbbdf4d35a61e64e2b7e3173ee9", "fetched_at": "2026-08-29T09:24:38.799090+00:00", "kind": "homepage", "missing": false, "url": "https://miso-belica.github.io/sumy/"}, {"content_hash": "2f1ebb96cc7e21a2628a5227dd838166f4f8d747448b26a2db4eca37fd272cb5", "fetched_at": "2026-08-29T09:24:38.808407+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sumy/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:31:02.065791+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "094c2c935fb04e1a9c1e09b59a50c71c405b9df34c0e72fffc81ba02011b87d9", "fetched_at": "2026-08-28T04:08:14.956678+00:00", "kind": "readme", "missing": false, "url": "https://github.com/miso-belica/sumy"}, {"content_hash": "ebbdfbb87f210f950bbf5fd824f7c8bebf7a3fbbdf4d35a61e64e2b7e3173ee9", "fetched_at": "2026-08-29T09:24:38.799090+00:00", "kind": "homepage", "missing": false, "url": "https://miso-belica.github.io/sumy/"}, {"content_hash": "2f1ebb96cc7e21a2628a5227dd838166f4f8d747448b26a2db4eca37fd272cb5", "fetched_at": "2026-08-29T09:24:38.808407+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sumy/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.956678+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.956678+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.956678+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:31:02.065791+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "094c2c935fb04e1a9c1e09b59a50c71c405b9df34c0e72fffc81ba02011b87d9", "fetched_at": "2026-08-28T04:08:14.956678+00:00", "kind": "readme", "missing": false, "url": "https://github.com/miso-belica/sumy"}, {"content_hash": "ebbdfbb87f210f950bbf5fd824f7c8bebf7a3fbbdf4d35a61e64e2b7e3173ee9", "fetched_at": "2026-08-29T09:24:38.799090+00:00", "kind": "homepage", "missing": false, "url": "https://miso-belica.github.io/sumy/"}, {"content_hash": "2f1ebb96cc7e21a2628a5227dd838166f4f8d747448b26a2db4eca37fd272cb5", "fetched_at": "2026-08-29T09:24:38.808407+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sumy/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.956678+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.956678+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:31:02.065791+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "094c2c935fb04e1a9c1e09b59a50c71c405b9df34c0e72fffc81ba02011b87d9", "fetched_at": "2026-08-28T04:08:14.956678+00:00", "kind": "readme", "missing": false, "url": "https://github.com/miso-belica/sumy"}, {"content_hash": "ebbdfbb87f210f950bbf5fd824f7c8bebf7a3fbbdf4d35a61e64e2b7e3173ee9", "fetched_at": "2026-08-29T09:24:38.799090+00:00", "kind": "homepage", "missing": false, "url": "https://miso-belica.github.io/sumy/"}, {"content_hash": "2f1ebb96cc7e21a2628a5227dd838166f4f8d747448b26a2db4eca37fd272cb5", "fetched_at": "2026-08-29T09:24:38.808407+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sumy/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.956678+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.956678+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.956678+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:31:02.065791+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "094c2c935fb04e1a9c1e09b59a50c71c405b9df34c0e72fffc81ba02011b87d9", "fetched_at": "2026-08-28T04:08:14.956678+00:00", "kind": "readme", "missing": false, "url": "https://github.com/miso-belica/sumy"}, {"content_hash": "ebbdfbb87f210f950bbf5fd824f7c8bebf7a3fbbdf4d35a61e64e2b7e3173ee9", "fetched_at": "2026-08-29T09:24:38.799090+00:00", "kind": "homepage", "missing": false, "url": "https://miso-belica.github.io/sumy/"}, {"content_hash": "2f1ebb96cc7e21a2628a5227dd838166f4f8d747448b26a2db4eca37fd272cb5", "fetched_at": "2026-08-29T09:24:38.808407+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sumy/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.956678+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:14.956678+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:31:02.065791+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "094c2c935fb04e1a9c1e09b59a50c71c405b9df34c0e72fffc81ba02011b87d9", "fetched_at": "2026-08-28T04:08:14.956678+00:00", "kind": "readme", "missing": false, "url": "https://github.com/miso-belica/sumy"}, {"content_hash": "ebbdfbb87f210f950bbf5fd824f7c8bebf7a3fbbdf4d35a61e64e2b7e3173ee9", "fetched_at": "2026-08-29T09:24:38.799090+00:00", "kind": "homepage", "missing": false, "url": "https://miso-belica.github.io/sumy/"}, {"content_hash": "2f1ebb96cc7e21a2628a5227dd838166f4f8d747448b26a2db4eca37fd272cb5", "fetched_at": "2026-08-29T09:24:38.808407+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sumy/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:31:02.065791+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "094c2c935fb04e1a9c1e09b59a50c71c405b9df34c0e72fffc81ba02011b87d9", "fetched_at": "2026-08-28T04:08:14.956678+00:00", "kind": "readme", "missing": false, "url": "https://github.com/miso-belica/sumy"}, {"content_hash": "ebbdfbb87f210f950bbf5fd824f7c8bebf7a3fbbdf4d35a61e64e2b7e3173ee9", "fetched_at": "2026-08-29T09:24:38.799090+00:00", "kind": "homepage", "missing": false, "url": "https://miso-belica.github.io/sumy/"}, {"content_hash": "2f1ebb96cc7e21a2628a5227dd838166f4f8d747448b26a2db4eca37fd272cb5", "fetched_at": "2026-08-29T09:24:38.808407+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sumy/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:31:02.065791+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "094c2c935fb04e1a9c1e09b59a50c71c405b9df34c0e72fffc81ba02011b87d9", "fetched_at": "2026-08-28T04:08:14.956678+00:00", "kind": "readme", "missing": false, "url": "https://github.com/miso-belica/sumy"}, {"content_hash": "ebbdfbb87f210f950bbf5fd824f7c8bebf7a3fbbdf4d35a61e64e2b7e3173ee9", "fetched_at": "2026-08-29T09:24:38.799090+00:00", "kind": "homepage", "missing": false, "url": "https://miso-belica.github.io/sumy/"}, {"content_hash": "2f1ebb96cc7e21a2628a5227dd838166f4f8d747448b26a2db4eca37fd272cb5", "fetched_at": "2026-08-29T09:24:38.808407+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sumy/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:31:02.065791+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "094c2c935fb04e1a9c1e09b59a50c71c405b9df34c0e72fffc81ba02011b87d9", "fetched_at": "2026-08-28T04:08:14.956678+00:00", "kind": "readme", "missing": false, "url": "https://github.com/miso-belica/sumy"}, {"content_hash": "ebbdfbb87f210f950bbf5fd824f7c8bebf7a3fbbdf4d35a61e64e2b7e3173ee9", "fetched_at": "2026-08-29T09:24:38.799090+00:00", "kind": "homepage", "missing": false, "url": "https://miso-belica.github.io/sumy/"}, {"content_hash": "2f1ebb96cc7e21a2628a5227dd838166f4f8d747448b26a2db4eca37fd272cb5", "fetched_at": "2026-08-29T09:24:38.808407+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/sumy/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 97, "longevity": 100, "rhythm": 73}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4942, "days_push": 19, "days_rel": 21, "gap_med": 178, "n_releases_24m": 2}, "score": 89, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}