Portfolio
BuySmart AI
A microservices application that pulls live product data, asks Google Gemini to analyse it and returns a score with a Buy or Not Buy recommendation.
Developed by AkbarAli N.
The challenge
Shoppers face long lists of reviews and specifications that are slow to read and hard to compare before a purchase.
The approach
Separate the work into three services: a React frontend, a Spring Boot API for users and products, and a FastAPI service for AI analysis.
What we did
Akbar built the application across its frontend, Spring Boot backend, AI service and Docker setup. The original commit history, from January to March 2026, is Akbar's.
The solution
Users search for a product and receive an overall score, a recommendation and a feature breakdown, with their history and metrics kept on a personal dashboard.
Key features
- Gemini-based scoring and Buy or Not Buy recommendations
- Live product data through RapidAPI
- JWT authentication with personal dashboards
- Search and analysis history
- Docker Compose setup for all services
Where it stands
The core analysis and accounts run on PostgreSQL. The project's own notes list two limits: the wishlist is held in memory, and advanced search filters are not yet connected to the backend.
More projects
Personal projectResearch projectTIPS
Developed by AbrarAli S.
A six-stage Python pipeline that analyses recorded interviews across speech, audio and video to produce scores that show how a candidate's answers change over time.
- Python
- FastAPI
- OpenCV
- MediaPipe
- Personal projectWorking project
DataTalk Pro
Developed by AbrarAli S.
A conversational tool that answers plain-English questions about a MySQL database by generating and running SQL with Google Gemini.
- Python
- Streamlit
- LangChain
- Google Gemini
- Personal projectWorking project
Orqen
Developed by AbrarAli S.
A platform for building AI workflows visually, connecting Google Gemini, external APIs, conditions, database writes and human approval steps.
- Next.js
- TypeScript
- React Flow
- GraphQL
