Projects
Designed a conversational AI Streamlit app using LangChain and
Hugging Face models.
Enhanced user experience by incorporating features like
Conversational Memory, dynamic interaction, and session management,
improving context awareness and user experience.
Utilised Retrieval Augmented Generation with OpenAI embeddings and
FAISS vector database for precise and relevant real-time responses,
ensuring efficient FAQ handling and user interactions.
Designed, developed, and deployed a comprehensive university guide
using the MERN stack, emphasising backend-to-frontend connectivity.
Integrated state-of-the-art UX techniques, responsive design, and
intuitive colour schemes, ensuring an engaging user experience
across all devices.
Seamlessly incorporated OAuth, email notifications, and OpenAI's GPT
API to elevate platform functionality and content delivery.
Prioritised data security with advanced authentication methods,
leveraging sessions and cookies.
Administered end-to-end deployment, including domain procurement,
SSL, CDN integration, and NoSQL database management.
Developed an interactive Streamlit app designed to simplify and
enhance users' image journey by offering advanced features such as
object detection, image captioning, and metadata tagging.
Introduced a system to annotate photos with metadata, facilitating
better organisation and searchability, especially beneficial for
Adobe Lightroom users.
Leveraged the SERP API and OpenAI's GPT API for efficient article
search, selection, and summarisation tailored for Instagram content.
Utilised Langchain for content retrieval, coupled with AI-driven
techniques to distil article essence into concise summaries.
Transformed AI-summarised content into engaging Instagram posts with
strategically chosen hashtags to maximise visibility.
In today's academic landscape, Final Year Projects (FYPs) are
integral to every university student's journey. To streamline the
management and monitoring of these projects, an effective system is
essential.
To achieve scalability, modularity, and easy maintenance, our system
leverages Object-Oriented Programming (OOP) and adopts the
Model-View-Controller (MVC) Architecture in Java. OOP principles
enable a clear separation of concerns, while the MVC Architecture
ensures distinct layers for the Model, View, and Controller
components.
This project management system accommodates various user roles, each
with specific permissions. Students can submit project requests,
Supervisors can evaluate and assign projects, and the FYP
Coordinator has the ability to oversee and monitor the overall
project progress. By implementing this system, we aim to streamline
the FYP process.
In today's world of social media and online news, it's becoming
harder to know what to believe. With a rise in deepfakes and
disinformation, it poses a growing threat that needs to be
addressed.
This project is all about fighting fake news by building a model
that uses natural language processing techniques to analyse the
content of news articles and determine their credibility.
Some deep learning models used include Keras (TF-IDF) and Pytorch
(BERT-UNCASED). I aim to include models that can detect sarcasm and
irony based on context in the future.
Developed a Python-driven flight deals tracker through a fusion of
GSpread API, Kiwi API, Twilio API, BS4, and Excel to reduce travel
expenses by 20% on average.
I automated Spotify Playlist creation by web-scrapping Billboard's
Top 100 Songs. This is done through Spotipy API and BS4 in Python.
I built a working flask application with HTML5UP, CSS, JS to create
a digital name card. This is deployed on PythonAnywhere.
I used Open Weather API and Twilio API in Python to send rain alerts
via SMS to user to bring an umbrella when the forcast detects rain.
I implemented the classic snake game with object-oriented
programming and turtle module in Python.