WeKnora
Tencent
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
PROJECT TOPICS
INSTALL REFERENCE
dsh plugin --profile web add github:niyongsheng/free-vision-skill
该命令指向仓库当前默认分支;尚无绑定当前 commit 的完整验证结果。
PROJECT README
Fully-local image understanding (OCR / table extraction / description) via macOS Vision. Images never leave your Mac.
dsh plugin add @niyongsheng/free-vision-skill
Then add to cordis.patch.yml:
- insert:
- id: free-vision-skill
name: '@niyongsheng/free-vision-skill'
config:
timeout: 120000
view_image — describe image content (scene, people, QR, composition)ocr_image — extract text; layout=true for table structure + coordinatesInput: http(s) URL / base64 / local path.
Paste (⌘V) an image in the DSH web input box → its local absolute path is inserted. Loopback-only upload, magic-byte checked: PNG / JPEG / GIF / WebP / HEIC / HEIF.
swift scripts/ocr.swift image.png # OCR
swift scripts/ocr.swift --layout image.png # table + coordinates
swift scripts/ocr.swift --describe image.png # describe image
MIT © 2026 Nico
CLASSIFICATION EVIDENCE
系统优先读取 GitHub Topics,再与站内分类词典和词根规则比对。当前命中: dsh-skill、skills、ocr、vision。