UNPKG

@claude-flow/embeddings

Version:

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

17 lines • 718 B
/** * ADR-121 Phase 1 — tests for RuvectorOnnxEmbeddingService. * * Fast unit tests that don't require downloading the 23MB MiniLM model: * - Service construction + provider tag * - Lazy load: optional peer dep missing → clean error naming the dep * - Factory wiring: createEmbeddingService({ provider: 'ruvector-onnx' }) * returns the right concrete class * - Mocked-embedder round-trip: embed/embedBatch shape, normalization, * cache behavior * * Live model parity vs Xenova baseline runs in a separate slow-path * test (gated by an env flag) and in the CI smoke — keeps the * default test suite under 1s. */ export {}; //# sourceMappingURL=ruvector-onnx-embedding-service.test.d.ts.map