fix: ColBERT dense fallback and increase Nginx proxy timeouts to 300s

feat: upgrade RAG conversational intent classification to multi-lingual LLM

Refactor LLM architecture to SOLID principles, add Gemini Judge, and self-reflective RAGAS logic

feat: Add RAG Execution Transparency, Technique Compatibility Matrix, and RAGAS Quality Dashboard

feat: Implement GLM-4.7-Flash RAGAS Judge and LLM fallback (Qwen -> GLM-4.7-Flash)

Fix file upload UI refresh and add Metadata Filters UI

Initial commit: Multimodal RAG Pipeline V3.0 with Fallback Logic