abc parcel

AI-powered customer service demo showcasing conversational AI with RAG-enhanced responses and voice call capabilities. Built as a PWA with trilingual support (EN/ES/LT) and audio-reactive animations.

Key Features

Category-aware RAG with ChromaDB (40% relevance boost)

Voice call integration with audio-reactive UI

Mid-conversation language switching

Lazy loading: 3s faster cold start

Exponential backoff with timeout escalation

Vue.js FastAPI LLMs RAG Voice / TTS Nginx
abc parcel

Overview

A demo built for a fictional parcel delivery company to show what AI customer support can look like in production. Users can chat or call, switch languages mid-conversation, and get answers grounded in a company FAQ knowledge base.

Technical Highlights

Audio-Reactive Voice UI

Real-time volume sampling from voice SDK with CSS custom property animations for visual feedback.

Unified Multilingual Prompts

Single system prompt with language detection. Adding new languages only requires translating FAQ content.

Lazy Loading Optimization

3s faster cold start. ML models and voice SDK load on-demand.

Tech Stack

Application

  • Vue.js + Quasar
  • FastAPI

AI / Voice

  • ChromaDB + RAG
  • ElevenLabs

Category-Aware RAG

Generic semantic search often returned tangentially related content. The solution: a two-phase retrieval strategy with 14 predefined categories. The system first detects query category from keywords, then filters ChromaDB results by category with graceful fallback to full search if filtered results are empty.

# Phase 1: Auto-detect query category
category = detect_category(query)  # 14 predefined categories

# Phase 2: Filter by category, fallback to full search
results = collection.query(
    query_embeddings=[embedding],
    where={"category": category}  # Precision filter
)

# Graceful fallback if filtered results empty
if not results['documents'][0]:
    results = collection.query(query_embeddings=[embedding])

Result: 40% improvement in response relevance for category-specific queries while maintaining recall through intelligent fallback.