Skip to content
 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Smart E-Commerce Personal Shopper and Recommendation Agent

This project was developed as a group Industrial Training project. Team members: Sneha Sidhu, Shoaib Ahmad (and others). This repository is my individual submission copy. Original repo: https://github.com/snehasidhu-06/smart-shopper-agent

Overview

A GenAI-powered shopping assistant that helps users find products through natural language conversations. Instead of searching with keywords, users can describe what they want, and the assistant recommends suitable products using AI.


Features

  • Chat-based shopping assistant
  • Understands natural language queries
  • Detects shopping requests and casual conversations
  • Recommends relevant products using AI
  • Displays product images, prices, ratings, and Buy Now links
  • Separate frontend and backend architecture

Tech Stack

  • Frontend: Streamlit
  • Backend: FastAPI
  • LLM: Groq (Llama 3.1 8B Instant)
  • Framework: LangChain
  • Embeddings: Sentence Transformers (all-MiniLM-L6-v2)
  • Vector Database: FAISS
  • Database: SQLite
  • Data Processing: Pandas

How It Works

  1. The user enters a message in the Streamlit interface.
  2. The message is sent to the FastAPI backend.
  3. The AI detects whether the user wants to shop or is simply chatting.
  4. For shopping requests, similar products are retrieved using FAISS.
  5. The LLM generates personalized recommendations.
  6. Product details are displayed to the user.

Dataset

The project uses a cleaned Amazon product dataset with approximately 700 products, including:

  • Product title
  • Brand
  • Category
  • Price
  • Rating
  • Product image
  • Product link

How to Run

  1. Clone the repository.
  2. Create and activate a virtual environment.
  3. Install dependencies:

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages