Fix LLM hallucinations with strict prompt and 0 temperature

Implemented HTML Bolding protocol and strictly prohibited hallucinated HR categories

Implemented Precision Protocol: removed headers and enforced strict, bullet-only responses to maximize conciseness

Implemented the Goldilocks Protocol: optimized for answers that are both complete and concise

Implemented Strict Ground Truth protocol and synonym-aware retrieval to prevent hallucinations in HR answers

Upgraded RAG pipeline for ChatGPT-level depth and intelligence (Multi-query, larger context, smarter prompts)

Upload 47 files

wipe space

Implement Clarification Intelligence: Ambiguity detection and multi-turn clarification protocol

Fix RAGPipeline instantiation in ui_gradio.py

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

Fix Admin sidebar sync and increase relevance threshold to 0.45

Update assistant identity and push

Peak Synthesis Protocol and Universal Multi-User Name Fetching

Peak Intelligence, fix truncation, and 5s name-fetch delay

Hard ban 'handbook' and 'documents' words from AI

Fix truncation and enforce strict 30-word limit

Enforce strict 30-word limit and intelligent summarization

Change to general greetings and remove name personalization

Remove name-based greetings as requested

Consolidate master strict rules for the AI

Restore greetings and common questions with strict brevity

Strictly enforce zero yapping and no document mentions

Enhance AI intelligence and personalization with user names

Initialize user_name as 'default name' and rename upon profile fetch

Implement session renaming so user name replaces session ID

Integrate user name fetching, session persistence, and local lottie icon

security: block direct browser access to root URL

feat: add chat export functionality (Excel/JSON) to admin panel

Force IPv4 and improve SMTP logging for OTP emails

Switch to SMTP_SSL on port 465 for better reliability on Hugging Face

Fix blocking SMTP call causing login hang

Implement email-based OTP and enforce verification state

Add two-step OTP authentication for admin panel

Fix admin panel auth: remove browser popup and implement persistent login

Fix HF persistence: diagnostics, non-root user for permissions, and dynamic path retrieval

Fix database persistence: added sessions volume and robust path handling for /data

Update app/services/vector_store.py

Hard revert to known working state 77f8b73

Revert to stable working state

Fix CORS and loading issues for widget

Add logging to debug session saving

Implement background chat saving to JSON and session persistence

Add static directory for addon.html and update main.py

Fix 500 Internal Server Error: Fix schema types and catch API errors

Update app/ui_gradio.py

Aggressive CSS for height auto and hiding footer

Fix CSS height/footer and add customization guide

Update app/ui_gradio.py

Update app/ui_gradio.py