概览
dsh-kb-rag
源码级技术说明Repo-root manifest for dsh-kb-rag. The installable plugin bundle is published from npm-package/ as dsh-kb-rag; this file exists so the repository itself declares a dsh.bundle (registry tooling reads /HEAD/package.json) and points at that bundle. Not published: version is intentionally 0.0.0, the real version lives only in npm-package/package.json.收起技术说明
README / ZH
插件文档
目录摘要
dsh.pub 核对固定版本的组合包契约、运行时事实与分发语义；完整 README 请查看源仓库。
在 GitHub 阅读完整 READMELIMITATIONS
已知限制
- Scanned PDFs are not supported. Documents without a text layer are skipped; OCR is out of scope. - Page anchors are PDF-only. TXT, MD and DOCX files, and documents indexed before schema v3, fall back to section-level location until re-ingested with `force`. - Citation linking requires a re-ingest. Superscript detection and reference splitting run at parse time. - Metadata is only as good as the PDF. It is never 100% accurate; when it is missing, title and year are judged from the cover page, and existing Zotero metadata is preferred. - Captions are searchable as text; content that exists only inside a figure is not. - Keyword matching is in memory. Beyond a few hundred thousand chunks, FAISS HNSW or SQLite FTS5 would be the next step. - Some publishers redirect automated PDF requests to a login page. `kb_fetch` reports the failure and leaves the manual path (download, then `kb_ingest`) as the fallback.