{"adoption": {"forks": 324, "observed_at": "2026-08-28T04:08:13.530637+00:00", "stars": 3670}, "canonical_url": "https://ross.abutalabs.com/products/documentai", "card": {"archived": false, "artifact_type": "application", "description": "基于向量数据库与GPT3.5的通用本地知识库方案(A universal local knowledge base solution based on vector database and GPT3.5)", "domain": ["large-language-models", "artificial-intelligence", "databases"], "enriched": true, "function": ["rag", "vector-database", "search-engine", "llm-inference", "nlp", "machine-learning"], "health_score": 20, "homepage": null, "language": "Python", "license": "AGPL-3.0", "license_family": "copyleft", "maturity": "maintenance", "member_repos": ["GanymedeNil/document.ai"], "name": "GanymedeNil/document.ai", "platform": ["python", "self-hosted", "cross-platform"], "pushed_at": "2023-05-12T10:31:26+00:00", "repo": "GanymedeNil/document.ai", "stars": 3670, "tags": ["local-knowledge-base", "embeddings", "gpt3.5", "question-answering", "semantic-search", "chinese-nlp", "retrieval-augmented-generation", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["build a local knowledge base question answering system", "chat with my own documents using GPT", "semantic search over a private FAQ dataset", "improve retrieval accuracy for domain-specific Q&A", "combine vector search with LLM generation for customer support", "train custom Chinese embedding models for similarity search"], "what_it_is": "A universal local knowledge base solution that stores documents as vectors in a vector database and uses GPT3.5 to generate answers from retrieved similar content. It includes example code and write-ups on improving retrieval accuracy via question-answer splitting, topic extraction, and custom-trained embedding models.", "when_to_avoid": ["you need a production-ready maintained product - the project is a demo/exploration and last released in 2023", "you want fully local inference without OpenAI API dependency", "you need fine-grained document ingestion features out of the box"], "when_to_choose": ["you want a reference implementation of the classic RAG pipeline with GPT3.5", "you need Chinese-language embeddings and Q&A retrieval guidance", "you want example code plus design notes on improving retrieval quality"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/documentai", "repo": "GanymedeNil/document.ai", "role": "main", "score": 30}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.530637+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:31:19.432450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4b58f87f34e3101a698a05cc376e5c443be913d1850a4eb380bf9d1ce769b39e", "fetched_at": "2026-08-28T04:08:13.530637+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GanymedeNil/document.ai"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.530637+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:31:19.432450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4b58f87f34e3101a698a05cc376e5c443be913d1850a4eb380bf9d1ce769b39e", "fetched_at": "2026-08-28T04:08:13.530637+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GanymedeNil/document.ai"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:31:19.432450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4b58f87f34e3101a698a05cc376e5c443be913d1850a4eb380bf9d1ce769b39e", "fetched_at": "2026-08-28T04:08:13.530637+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GanymedeNil/document.ai"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.530637+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.530637+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.530637+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:31:19.432450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4b58f87f34e3101a698a05cc376e5c443be913d1850a4eb380bf9d1ce769b39e", "fetched_at": "2026-08-28T04:08:13.530637+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GanymedeNil/document.ai"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.530637+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.530637+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:31:19.432450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4b58f87f34e3101a698a05cc376e5c443be913d1850a4eb380bf9d1ce769b39e", "fetched_at": "2026-08-28T04:08:13.530637+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GanymedeNil/document.ai"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.530637+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.530637+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.530637+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:31:19.432450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4b58f87f34e3101a698a05cc376e5c443be913d1850a4eb380bf9d1ce769b39e", "fetched_at": "2026-08-28T04:08:13.530637+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GanymedeNil/document.ai"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.530637+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:13.530637+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:31:19.432450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4b58f87f34e3101a698a05cc376e5c443be913d1850a4eb380bf9d1ce769b39e", "fetched_at": "2026-08-28T04:08:13.530637+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GanymedeNil/document.ai"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:31:19.432450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4b58f87f34e3101a698a05cc376e5c443be913d1850a4eb380bf9d1ce769b39e", "fetched_at": "2026-08-28T04:08:13.530637+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GanymedeNil/document.ai"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:31:19.432450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4b58f87f34e3101a698a05cc376e5c443be913d1850a4eb380bf9d1ce769b39e", "fetched_at": "2026-08-28T04:08:13.530637+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GanymedeNil/document.ai"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:31:19.432450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4b58f87f34e3101a698a05cc376e5c443be913d1850a4eb380bf9d1ce769b39e", "fetched_at": "2026-08-28T04:08:13.530637+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GanymedeNil/document.ai"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 90, "rhythm": 35}, "computed_at": "2026-09-03T02:39:23.370411+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1273, "days_push": 1209, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 30, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}