Add mobile responsive CSS styles for grid columns, header, and Arena modal

Show warnings in Arena columns when retrieved chunks lists are empty

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

Add accelerate dependency for GGUF model loading support

dockerfile updates

Cache public models at build time in Dockerfile to prevent runtime hangs

Add einops dependency for nomic-embed model support

Defer model downloads to runtime to support gated models via HF_TOKEN

Optimize build model caching via snapshot_download to avoid OOM

Add hf deployment helper script

Add Hugging Face metadata frontmatter

Ignore assets and env

Configure for 100% self-contained CPU deployment

Few tweaks

RAG retreival updates

Add Visualizer and Grand Arena GIFs to README.md

Restore Phase 5 advanced RAG changes and clean schemas.py

Merge pull request #1 from vazanth/feature/advanced-rag

Merge branch 'main' into feature/advanced-rag

Pushing the changes for judge as LLM

changes for readme file and UI changes

update changes

initial: RAG Visualizer (Phases 1-4)

local: phase 5 arena and text highlighter