Multi-Agent AI Shopping Assistant

Heramb Vengurlekar Thadomal Shahani Engineering College vengurlekarheramb19@gmail.com
Code

Keywords: Multi-Agent Systems, FastAPI, ChromaDB, RAG, Sentence-Transformers, Google Gemini API

Overview

A multi-agent conversational e-commerce assistant engineered to streamline online shopping through intelligent agent coordination, preference parsing, semantic vector retrieval (RAG), and interactive cart/order management.

Architecture & Technical Highlights

  1. Coordinated Multi-Agent Orchestration: Specialized agents (Preference Agent, Recommendation Agent, and Order Agent) collaborate sequentially to understand natural language requirements, curate items, and handle state transitions.
  2. Semantic Vector Search with ChromaDB: Utilized Sentence-Transformers for dense embeddings alongside ChromaDB for real-time similarity search across product catalogs and categories.
  3. LLM Context Synthesis: Powered by Google Gemini API for structured query decomposition, conversational memory, and dynamic recommendation explanations.
  4. Interactive Asynchronous Web UI: Integrated with a FastAPI backend for low-latency search, real-time cart updates, and guided checkout flow.