Merge GitHub repo and resolve conflicts

Add comprehensive mass indexing and matching test

fix: update sentence-transformers>=2.7.0 for ru-en-RoSBERTa compatibility

v2.2.0: ai-forever/ru-en-RoSBERTa + normalize_embeddings + cache fix

Add reindex endpoints for updating entity embeddings

fix: remove model.half() - LayerNorm not supported for Half on CPU

Simplify embedding service to stateless, add backend integration docs

Simplify to stateless service - remove storage, keep only embedding generation

feat: add HuggingFace deployment files and documentation

add: root endpoint / for HuggingFace Space homepage

trigger rebuild: restart Space with fixed dependencies

fix: update dependencies and use L12-v2 model (better quality, 16GB RAM is enough)

Fix README.md: proper YAML metadata for HuggingFace Space

Deploy FastAPI embedding service: optimized for HuggingFace with Docker, torch 2.1.2, numpy<2

initial commit

fix: pin compatible versions - numpy<2, torch 2.1.2, transformers 4.36.2 for Render free tier

fix: optimize for Render free tier - pin numpy<2, use L6-v2 model, CPU-only torch

замена на облегченную модель

Fix: Configure Render for Python runtime instead of Docker, add Swagger documentation info

Initial commit: Embedding service ready for Render deployment