JitKnow
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 2
- JitArchives unveiled as an evidence-grounded AI enterprise archive system
The JitArchives team introduced an enterprise electronic archive platform built around JitWord collaborative documents, an archive AI assistant, and a knowledge graph. The Vue3, TypeScript, NestJS, and SQLite system uses FTS5/BM25 retrieval and TF-IDF similarity rather than separate vector or graph databases, while its AI assistant operates through permission-filtered, read-only tools with source citations. The team also documented limits including weak deep semantic generalization, no text extraction from scanned image PDFs, role-based rather than custom per-archive permissions, and deployment configuration still requiring validation.
掘金 · 人工智能 · 🔥 0 - JitKnow 4.8 Adds Knowledge-Graph-Enhanced Retrieval
JitKnow 4.8 upgrades the AI knowledge base's retrieval architecture from pure vector search to ontology-driven, knowledge-graph-enhanced hybrid retrieval. The JitKnow team says the release adds entity-alias normalization, editable extraction, source linking, feedback workflows, and routing between knowledge-graph and existing text-based retrieval.
掘金 · 人工智能 · 🔥 0
Experience and discussion from the community
Share my JitKnow experienceAsk about JitKnow
Nobody has shared their experience with JitKnow yet.