Skip to content
View abyshergill's full-sized avatar

Block or report abyshergill

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.

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
abyshergill/README.md

Hi there, I'm Aby Shergill 👋

I'm a Senior FA Engineer | Python & AI Enthusiast passionate about building scalable systems and exploring the depths of LLM and Computer Vision. I enjoy bridging the gap between complex AI models and production-ready applications.


🛠️ Tech Stack & Tools

Category Technologies
Languages C, Rust, Python, JavaScript
AI / ML PyTorch, OpenCV, Scikit-Learn
Backend FastAPI, Flask, Django
Database/Cloud PostgreSQL, MongoDB, SQLite, CockrochDB Docker, GCP
Embedding System C, Micropython

🧪 Featured Projects

  • inferX_llm_stack - A self-hosted, GPU-accelerated LLM inference stack running behind HTTPS. This setup gives you a ChatGPT-like web interface powered by your own models via vLLM, secured with SSL through Nginx, and backed by PostgreSQL for persistent storage.

  • Spreadsheet Agent - our Private Spreadsheet Assistant Many AI tools can help with spreadsheets, but your company's rules might not allow you to upload sensitive data to just any online platform – and for good reason! I ran into the same problem, so I built my own solution.

  • File-Sharing-Web-App - A simple Streamlit-based web app to upload and share files using randomly generated access codes — no email or direct file sharing links needed.

  • EDS_Database_Management - A modern, secure data collection application for managing EDS (Energy Dispersive X-ray Spectroscopy) analysis results with VHX microscopy images.

  • Ultralytics_YOLO_Object_Detection_Testing_GUI - This is a desktop application for real-time object detection using the YOLO (You Only Look Once) model build with ultralytics libarary. The application allows users to load a YOLO model, adjust detection settings, and perform object detection on media.

  • Label Craft - A simple yet powerful Tkinter-based GUI tool to create, edit, and export bounding box annotations in YOLO format for image datasets. Ideal for training YOLO-based object detection models.


📊 GitHub Stats

Aby's GitHub stats Top Langs


📫 Connect with me:

LinkedIn Portfolio Email

"Code is like humor. When you have to explain it, it’s bad."

Pinned Loading

  1. File-Sharing-Web-App File-Sharing-Web-App Public

    A simple Streamlit-based web app to upload and share files using randomly generated access codes — no email or direct file sharing links needed.

    Python 3 1

  2. spreadsheet_agent spreadsheet_agent Public

    Your Private Spreadsheet Assistant Many AI tools can help with spreadsheets, but your company's rules might not allow you to upload sensitive data to just any online platform – and for good reason!…

    Python 4

  3. EDS_Database_Management EDS_Database_Management Public

    A modern, secure data collection application for managing EDS (Energy Dispersive X-ray Spectroscopy) analysis results with VHX microscopy images.

    Python 2

  4. Ultralytics_YOLO_Object_Detection_Testing_GUI Ultralytics_YOLO_Object_Detection_Testing_GUI Public

    This is a desktop application for real-time object detection using the YOLO (You Only Look Once) model build with ultralytics libarary. It's built with PyQt5 for the graphical user interface and Op…

    Python 1

  5. inferX_llm_stack inferX_llm_stack Public

    A self-hosted, GPU-accelerated LLM inference stack running behind HTTPS. This setup gives you a ChatGPT-like web interface powered by your own models via vLLM, secured with SSL through Nginx, and b…

  6. Label_Craft Label_Craft Public

    A simple yet powerful Tkinter-based GUI tool to create, edit, and export bounding box annotations in YOLO format for image datasets. Ideal for training YOLO-based object detection models.

    Python