Skip to content

tailormst/Ecommerce-Amazon-Recommendation-Assistant

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 

Repository files navigation

ShopShield AI

AI-Powered E-commerce Recommendation System

ShopShield AI is an AI-powered product recommendation system that helps users discover relevant products through natural language queries. The project uses Retrieval-Augmented Generation (RAG) with vector search to retrieve product information and generate personalized recommendations.


Features

  • User authentication (username & password)
  • AI-powered product recommendations using Google Gemini
  • Retrieval-Augmented Generation (RAG) pipeline
  • Product retrieval using vector embeddings
  • Semantic product search using ChromaDB
  • REST APIs built with FastAPI
  • Modular backend architecture for future feature expansion

Tech Stack

Backend

  • Python
  • FastAPI

AI & Retrieval

  • Google Gemini API
  • LangChain
  • HuggingFace Embeddings
  • ChromaDB

Database

  • PostgreSQL

Project Workflow

  1. Product information is converted into vector embeddings.
  2. Embeddings are stored in ChromaDB.
  3. User submits a query through the API.
  4. Relevant products are retrieved using semantic search.
  5. Retrieved context is passed to Gemini.
  6. Gemini generates personalized recommendations.

RAG Pipeline

The recommendation workflow consists of:

  • Chunking product information
  • Generating embeddings
  • Vector storage in ChromaDB
  • Similarity-based retrieval
  • Context generation using Gemini

API Endpoints

Generate Recommendations

POST /recommend

Returns personalized product recommendations.

Search Products

POST /search

Performs semantic product search.


Running Locally

Clone Repository

git clone https://github.com/tailormst/Ecommerce-Amazon-Recommendation-Assistant.git

Install Dependencies

pip install -r requirements.txt

Configure Environment

Create a .env file:

GOOGLE_API_KEY=your_api_key

Run Application

uvicorn app.main:app --reload

Learning Outcomes

Through this project, I gained practical experience with:

  • FastAPI backend development
  • REST API design
  • Retrieval-Augmented Generation (RAG)
  • Embeddings and vector databases
  • ChromaDB integration
  • Semantic search systems
  • Gemini API integration

Future Improvements

  • Chat history support
  • Product comparison features
  • Recommendation analytics
  • Multi-modal product search

Author

Mohammed Saifuddin Tailor

GitHub: https://github.com/tailormst

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors