Skip to content
View SanaliSLokuge's full-sized avatar
🏢
Working from home
🏢
Working from home

Highlights

  • Pro

Block or report SanaliSLokuge

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
SanaliSLokuge/README.md

Sanali Lokuge

Software Engineer | AI & Data Science Developer | Automation Enthusiast

Based in Sri Lanka • Open to Internships and Graduate Opportunities

Profile Views


About Me

I build practical software solutions using Python, Java, and modern AI tools. My experience spans machine learning, large language model applications, automation pipelines, and full-stack development.

I enjoy turning real-world problems into scalable, production-oriented systems—from object detection models and retrieval-augmented chatbots to REST APIs and intelligent automation workflows.


Featured Projects

Smart Article Assistant

AI-powered application that summarizes articles from URLs or RSS feeds and generates multiple-choice flashcards for learning.

Tech Stack: Python, Streamlit, LangChain, OpenRouter, BeautifulSoup


Document Question Answering System

Retrieval-augmented application that answers questions from uploaded documents using TF-IDF search and LLM-based response generation.

Tech Stack: Python, NLP, GPT-4o-mini


Memory-Augmented AI Agent

Conversational agent with persistent memory and context-aware responses.

Tech Stack: Python, Agno, Mem0, DistilGPT-2


Breast Cancer Survival Prediction

Machine learning pipeline using classification, regression, and ensemble models to predict mortality status and survival months from SEER data.

Tech Stack: Python, Scikit-learn, Pandas, Matplotlib


Land Evaluation Object Detection

Computer vision system that detects land-use features from satellite images using Faster R-CNN and COCO evaluation metrics.

Tech Stack: Python, PyTorch, OpenCV, Labelme


Real-Time Event Ticketing System

Multi-threaded ticket booking platform with Spring Boot backend and vendor-customer simulation.


Technical Skills

Languages: Python, Java, JavaScript, SQL, HTML, CSS

Frameworks & Libraries: Spring Boot, React, Scikit-learn, PyTorch, OpenCV, LangChain, Pandas, NumPy

Tools & Platforms: Git, GitHub, Docker, Maven, Jupyter, Google Colab, Postman, Jenkins, Selenium

Core Areas: Machine Learning, LLM Applications, Retrieval-Augmented Generation (RAG), Automation, REST APIs, Computer Vision


Connect With Me

Pinned Loading

  1. Mem0-Agno-Agent-Interaction-with-Chaining-Logic Mem0-Agno-Agent-Interaction-with-Chaining-Logic Public

    An interactive AI agent system demonstrating how to store, retrieve, and reason with long-term memory using Mem0, Agno agents, and GPT-2 in a simple command-line interface.

    Jupyter Notebook 3

  2. Breast-Cancer-ML-Prediction Breast-Cancer-ML-Prediction Public

    Machine Learning project using classification, regression, and ensemble techniques to predict breast cancer mortality status and survival months using clinical data. Built with scikit-learn, decisi…

    Jupyter Notebook

  3. id-tagging-schema id-tagging-schema Public

    Forked from openstreetmap/id-tagging-schema

    🆔🏷 The presets and other tagging data used by the iD editor

    JavaScript

  4. BookStore-API BookStore-API Public

    A Bookstore application using Java JAX-RS. It simulates an e-commerce environment with CRUD functionality for books, authors, customers, shopping carts, and orders.

    Java