Vector Embed
Generate and store vector embeddings using the ruvector npm package.
When to use
Use this skill to embed text, code, or documents into 384-dimensional vectors for semantic search, similarity comparison, or clustering. ruvector uses ONNX all-MiniLM-L6-v2 with HNSW indexing (52,000+ inserts/sec, ~0.045ms search).
Steps
- Ensure ruvector@0.3.13 is available:
ruvector 0.3.3 bundles the ONNX runtime; no add-on is needed. Ifnpm ls ruvector 2>/dev/null | grep '0.3.3' || npm install ruvector@0.3.13embed textreportsONNX WASM files not bundled, an older ruvector (0.2.x) is being resolved — rerun with the pinnednpx -y ruvector@0.3.13. - Embed the input (use the
textsubcommand, with text as a positional arg):- Single string:
npx -y ruvector@0.3.13 embed text "your text here" - With output file:
npx -y ruvector@0.3.13 embed text "your text here" -o vec.json - For a file: read its content via the Read tool, then pass it as the positional argument.
- For batch: loop over files in shell — ruvector@0.3.13 has no built-in
--batch/--globflags.
- Single string:
- Adaptive (LoRA) variant:
npx -y ruvector@0.3.13 embed text "..." --adaptive --domain code - Confirm — report vector dimension (384), norm, and any output path written.
- Store metadata in AgentDB if needed:
mcp__plugin_ruflo-core_ruflo__memory_store({ key: "embed-SOURCE", value: "VECTOR_METADATA", namespace: "vector-patterns" })
MCP alternative
Register the MCP server once with the pinned version:
claude mcp add ruvector -- npx -y ruvector@0.3.13 mcp start
Then call MCP tools directly: hooks_rag_context (semantic context), brain_search (collective brain), hooks_ast_analyze, hooks_route.
Caveats
- The
embed --batch --globflags do not exist in ruvector@0.3.13.embed textaccepts one text,--stdin, or--input-file <path>(keeps sensitive text off argv); call it per file. - If embedding fails, run
npx -y ruvector@0.3.13 doctorto diagnose.
