Hardening RAG Intelligence: Restoration of perfect format decision table, optimized thresholds, and query expansion logic for GPT-4o-mini

Restore: Revert codebase to stable May 14th 6 PM state

Restore to latest backup from 13 May - 2026-05-15 17:56

Fix: Replace LLM expander with instant hybrid normalizer, fix re-index, fix prorata

Performance: Professional batched search and latency optimizations

Fix: Prioritize original query and enhance compound word analyzer for prorata

Upgrade: Professional intelligent retrieval pipeline with robust tokenization and LLM query expansion

Implement DeepSeek-R1, BGE-Large, and Hybrid Search

Upload 47 files

wipe space

Implement Deep Intelligence: Query Expansion, Reranking, and High-Precision Chunking

Update app/services/vector_store.py

feat: add secure admin panel, session store, localStorage tracking