Robust Judge API parsing and schemas validation default values for 0.5B model support

Update schemas.py EmbeddingModel enum to replace EmbeddingGemma with bge-small-en

Replace Gemma embedding model with BAAI/bge-small-en-v1.5 and cache at build time

Fix Gemma model repository name to google/embeddinggemma-300m

Pass HF_TOKEN explicitly to SentenceTransformer for gated model download

Optimize PyTorch threading, run generation in thread, and pre-warm model at startup

Optimize referee model to Qwen2.5-0.5B-Instruct for CPU and add warning popup

Swap Qwen3-Embedding-0.6B for distilled C10X/Qwen3-Embedding-TurboX.v2

Configure for 100% self-contained CPU deployment

Few tweaks

RAG retreival updates

Restore Phase 5 advanced RAG changes and clean schemas.py

Merge branch 'main' into feature/advanced-rag

Pushing the changes for judge as LLM

changes for readme file and UI changes

initial: RAG Visualizer (Phases 1-4)

local: phase 5 arena and text highlighter