视觉画布设计
canvas-design
基于设计原则创作静态视觉作品,用于海报与品牌图形。
index-build【文档与办公】Use PixelRAG to build visual retrieval indexes from rendered documents, tile chunks, embeddings, FAISS, or Qdrant.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
Use this sub-skill when a task asks to make documents searchable with PixelRAG, build a local visual index, debug pixelrag.yaml, run chunk/embed/build-index stages, or choose FAISS versus Qdrant.
../render-capture/SKILL.md.pixelrag index build --config pixelrag.yaml.pixelrag chunk, pixelrag embed, and pixelrag build-index.device: auto chooses CUDA, MPS, then CPU in the local embedder path.tiles/, embeddings/shard_*.npz, index.faiss or Qdrant summary.json, metadata.npz, and articles.json.pixelrag.yaml, source adapters, chunk manifests, embeddings, and index layouts.| Request | Action |
|---|---|
| "Index this folder of PDFs/Markdown/images" | Generate a local-source pixelrag.yaml; use pixelrag index build --device auto for small runs or CUDA for production. |
| "Use Qdrant instead of FAISS" | Set index.backend: qdrant and provide URL/collection/client/quantization config as needed. |
| "Re-run after source files changed" | Trust the source-stamped tile manifests; use --force only for a clean rebuild. |
| "Department-filter search" | Preserve subdirectory layout under the local source; articles.json stores the first subdirectory as department. |
| "I already have embeddings" | Use pixelrag build-index build --embeddings-dir ... --output-dir .... |
| "Now query this index" | Route to ../serve-search/SKILL.md. |
pixelrag index build --help lists --device {auto,cpu,mps,cuda}..pdf, .html, .htm, .png, .jpg, .jpeg, .md, and .txt.article_id is propagated into chunks.json and embedding metadata.articles.json titles, URLs/paths, and department fields match the source set.append and recreate are explicit choices, never accidental overwrites.