Slow bot eye and antenna animations

Max blinking: 6x rapid eye blinks, fast antenna flash, dual ring pulse

Enhance bot blinking: triple-blink eyes, rapid antenna flash, ring pulse effect

Redesign bot UI: Vibhu dark theme, blinking bot character, smaller compact widget

api keys in .env.example for security reasons

removed commit message

Fix: catch Firebase init errors so chat works even if credentials are invalid

Re-apply Firebase Firestore lead storage integration

Add Firebase Firestore integration for persistent lead storage

Add full contact details (address) to bot responses and contact rule

Fix: grant user write access to /app so ingest.py can create faiss_db

api key updates

Update .gitignore to exclude .env.example files

api key update

Groq model update and environment variable override

Fix: check error type before printing traceback — no noise for known errors

Fix: handle network/connection errors gracefully instead of 500 crash

Add full contact details: phone, email, address to knowledge base

Improve Dockerfile: PYTHONUNBUFFERED, pip upgrade, COPY --chown, HEALTHCHECK, better .dockerignore

Update widget.js to match new UI + add /leads endpoint for captured contacts

Redesign chat UI: animated dots, clickable links, timestamps, mobile fullscreen, auto-grow input

Add multi-key Groq rotation, session cleanup, smarter FAISS chunking

Expand knowledge base: add 30+ new FAQ entries covering common questions

Fix: correct local port in docstring to 8500

add GROQ_API_KEY to .env.example and remove extra keys from .env and app.py

Fix: remove scripted responses from knowledge base, remove real API keys, remove prices

Fix: use system+human message structure to stop prompt leaking in responses

api

Fix: handle greetings naturally instead of treating them as out-of-scope

Fix: stop greeting user on every reply

Remove office hours from all bot responses

Fix portfolio response: no fake project names, redirect to website

Fix host: bind to 0.0.0.0 so HuggingFace can reach the app

Simplify to single Groq API key

Fix UnboundLocalError: declare _retriever,_prompt global in chat()

Speed up startup: lazy-load embedding model on first request

api keys updated in .env.example

Add emoji favicon to fix 404 on /favicon.ico

Fix SyntaxError: move global declaration to top of chat function

Add multi-key Groq fallback + embeddable widget.js for vibhusolutions.com

url update

groq model update

Revert to Groq: OpenAI quota exceeded, use llama-3.1-8b-instant free tier

api key update

Switch LLM: Groq -> OpenAI gpt-4o-mini

Update env example with model config

Fix API: add retry logic, 30s/60s timeout, disable input during request

Fix rate limit: switch to llama-3.1-8b-instant (500K TPD), handle 429 gracefully, clean hero page

Remove hero section: clean background with login modal only

Redesign UI: dark hero page visible before and after login