@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
TypeScript
/**
* 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