feat(ts-sdk): add HuggingFace embedding provider

Summary

The Python SDK supports HuggingFace as an embedding provider, but the TypeScript OSS SDK (mem0ai/oss) does not. Add it to bring the TS SDK to parity.

Python reference	mem0/embeddings/huggingface.py
Registered in (Python)	mem0/utils/factory.py (EmbedderFactory)
Target file (TypeScript)	mem0-ts/src/oss/src/embeddings/huggingface.ts
Suggested implementation	API mode: @huggingface/inference. Optional local mode: @huggingface/transformers (transformers.js).

Requirements

• Implement HuggingFaceEmbedder in mem0-ts/src/oss/src/embeddings/huggingface.ts, extending Embedder (mem0-ts/src/oss/src/embeddings/base.ts) and mirroring the Python provider's behavior (embed / embedBatch).
• Register the "huggingface" provider in mem0-ts/src/oss/src/utils/factory.ts (EmbedderFactory).
• Add config typing in mem0-ts/src/oss/src/types/.
• Add a unit test under mem0-ts/src/oss/src/tests/.
• Add @huggingface/inference to mem0-ts/package.json (optional/peer dependency, lazy-imported like other providers).
• Update docs under docs/ if this provider is user-facing.

Reference pattern

Mirror an existing TS provider: embeddings/openai.ts.

Notes

Python defaults to LOCAL sentence-transformers. Start with the HF Inference API for hosted-model parity; a local transformers.js path can follow. Document which models are supported.

---

Part of the TypeScript ↔ Python SDK provider-parity effort. One provider per issue (atomic).