feat: Enhance RAG LLM prompt with few-shot examples to enforce polite and complete sentences

feat: Implement Phase 2 - pyvi tokenizer, Global FAISS Index, and Hierarchical Summary

Optimize LLM lazy loading and refine RAG prompt for full sentences

feat: production-hardening, upload validation, admin auth, threadpool, logging & HF dataset repo integration

Implement OUT_OF_SCOPE intent separation, multi-signal relevance check, and strict Grounding System Prompt

Implement Negative Rejection and Grounding Guardrails to suppress fake citations for out-of-document queries

Finalize smooth LLM reader responses and pure Agentic LLM intent router

Implement Two-Level Map-Reduce Hierarchical LLM Summarization for META_DOC intent

Make chitchat LLM response dynamic with system prompt and temperature=0.7

Add accelerate dependency and fix Local LLM loading error

Fix intent classification and emotional response for chitchat queries

DocBrain RAG official release for HF Space