GenAI · Automation

Riya — AI Property Broker

Multi-channel RAG assistant that books site visits end-to-end

Feb – Mar 2026View source Live demo

WhatsApp · Web · TG
Channels: pgvector RAG
Retrieval: Oracle Cloud VM
Deploy

Overview

A full-stack, multi-channel AI property assistant that guides buyers from first interest to a confirmed site visit over WhatsApp, Telegram, or web (Live Demo: https://144-24-156-187.sslip.io) — while keeping the broker in the loop.

Conversational RAG (pgvector + hybrid re-ranking) over Lucknow inventory — understands budget, area, BHK, property type, landmarks, distances, and amenities from plain language.
Rich property cards with photo carousels, maps and distance badges; a favourites system, and a full negotiation + reschedule loop.
Two-way broker confirmation over WhatsApp and email with auto-calendar booking, plus a complete CRM driven entirely through WhatsApp commands and morning-of / hour-before visit reminders.

Tech stack

Python
Claude API
Groq
LangChain
pgvector
PostgreSQL
WhatsApp Cloud API
Telegram
Google Calendar API
Gmail API

Screens & results

Web landing — Riya greets buyers across WhatsApp, Telegram and the web app.

Conversational property search with natural-language budget, BHK and location filters.

Rich property cards with photo carousels, maps and distance badges.

Broker dashboard — a CRM that also runs entirely from WhatsApp commands.

Pipeline analytics tracking discovery → booking across every channel.

Cross-channel WhatsApp discovery flow with broker hand-off.

Next project

InvenIQ