UNPKG

@claude-flow/embeddings

Version:

V3 Embedding Service - OpenAI, Transformers.js, Agentic-Flow (ONNX), Mock providers with hyperbolic embeddings, normalization, and chunking

20 lines • 787 B
/** * ADR-121 Phase 12 — averageEmbeddings (HyDE) tests. * * Coverage: * - Single vector returns (a normalized copy of) the input * - N orthogonal unit vectors average to their geometric centroid * - normalizeOutput=true produces a unit vector * - normalizeOutput=false returns the raw mean * - normalizeInputs=true makes magnitude irrelevant (only direction matters) * - normalizeInputs=false → larger-magnitude vectors dominate * - weights bias the result toward higher-weighted vectors * - all-zero weights returns zero vector (no NaN) * - dimension mismatch throws * - empty input throws * - negative weights throw * - weights length mismatch throws * - isUnitNorm helper correctness */ export {}; //# sourceMappingURL=embedding-fusion.test.d.ts.map