@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
TypeScript
/**
* 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