{"adoption": {"forks": 2279, "observed_at": "2026-08-28T04:09:58.511827+00:00", "stars": 7363}, "canonical_url": "https://ross.abutalabs.com/products/qasystemonmedicalkg", "card": {"archived": false, "artifact_type": "application", "description": " A tutorial and implement of disease centered Medical knowledge graph and qa system based on it。知识图谱构建，自动问答，基于kg的自动问答。以疾病为中心的一定规模医药领域知识图谱，并以该知识图谱完成自动问答与分析服务。", "domain": ["healthcare", "artificial-intelligence", "databases"], "enriched": true, "function": ["nlp", "search-engine", "chatbot", "web-scraping", "parser"], "health_score": 20, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["liuhuanyong/QASystemOnMedicalKG"], "name": "liuhuanyong/QASystemOnMedicalKG", "platform": ["python", "self-hosted"], "pushed_at": "2024-08-08T07:55:05+00:00", "repo": "liuhuanyong/QASystemOnMedicalKG", "stars": 7363, "tags": ["knowledge-graph", "neo4j", "question-answering", "medical", "tutorial", "chinese-nlp", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["build a medical knowledge graph from scratch", "question answering over a knowledge graph", "learn how to construct a domain knowledge graph with neo4j", "medical chatbot that answers disease, drug, and symptom questions", "extract structured medical entities from web data", "tutorial on knowledge graph construction and QA"], "what_it_is": "A tutorial-style Python project that builds a disease-centered medical knowledge graph (44k entities, 300k relations) in Neo4j from scraped vertical medical website data, and implements a question-answering chatbot on top of it. It covers the full pipeline from data collection and dictionary-based entity extraction to graph import and intent-based question parsing.", "when_to_avoid": ["you need production-grade, clinically validated medical information", "you need a scalable multi-user QA service with modern LLM-based understanding", "you need a maintained library with a license and active development"], "when_to_choose": ["you want an end-to-end educational example of building and querying a domain knowledge graph", "you need a Chinese-language medical QA demo based on Neo4j", "you are learning NLP pipelines for entity extraction and question classification"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/qasystemonmedicalkg", "repo": "liuhuanyong/QASystemOnMedicalKG", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.511827+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:38:24.742353+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906fd3b0afab48d80cce6ff2d5b1f77d3e95ce7164be6b4ee0300e02d1cc1da6", "fetched_at": "2026-08-28T04:09:58.511827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/liuhuanyong/QASystemOnMedicalKG"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.511827+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:38:24.742353+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906fd3b0afab48d80cce6ff2d5b1f77d3e95ce7164be6b4ee0300e02d1cc1da6", "fetched_at": "2026-08-28T04:09:58.511827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/liuhuanyong/QASystemOnMedicalKG"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:38:24.742353+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906fd3b0afab48d80cce6ff2d5b1f77d3e95ce7164be6b4ee0300e02d1cc1da6", "fetched_at": "2026-08-28T04:09:58.511827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/liuhuanyong/QASystemOnMedicalKG"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.511827+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.511827+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.511827+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:38:24.742353+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906fd3b0afab48d80cce6ff2d5b1f77d3e95ce7164be6b4ee0300e02d1cc1da6", "fetched_at": "2026-08-28T04:09:58.511827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/liuhuanyong/QASystemOnMedicalKG"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.511827+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.511827+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:38:24.742353+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906fd3b0afab48d80cce6ff2d5b1f77d3e95ce7164be6b4ee0300e02d1cc1da6", "fetched_at": "2026-08-28T04:09:58.511827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/liuhuanyong/QASystemOnMedicalKG"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.511827+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.511827+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.511827+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:38:24.742353+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906fd3b0afab48d80cce6ff2d5b1f77d3e95ce7164be6b4ee0300e02d1cc1da6", "fetched_at": "2026-08-28T04:09:58.511827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/liuhuanyong/QASystemOnMedicalKG"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.511827+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:58.511827+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:38:24.742353+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906fd3b0afab48d80cce6ff2d5b1f77d3e95ce7164be6b4ee0300e02d1cc1da6", "fetched_at": "2026-08-28T04:09:58.511827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/liuhuanyong/QASystemOnMedicalKG"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:38:24.742353+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906fd3b0afab48d80cce6ff2d5b1f77d3e95ce7164be6b4ee0300e02d1cc1da6", "fetched_at": "2026-08-28T04:09:58.511827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/liuhuanyong/QASystemOnMedicalKG"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:38:24.742353+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906fd3b0afab48d80cce6ff2d5b1f77d3e95ce7164be6b4ee0300e02d1cc1da6", "fetched_at": "2026-08-28T04:09:58.511827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/liuhuanyong/QASystemOnMedicalKG"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:38:24.742353+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "906fd3b0afab48d80cce6ff2d5b1f77d3e95ce7164be6b4ee0300e02d1cc1da6", "fetched_at": "2026-08-28T04:09:58.511827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/liuhuanyong/QASystemOnMedicalKG"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2890, "days_push": 755, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}