Ananthu M s

Machine Learning - AI Aspirant

[email protected] +91 7907260964

Resume

Hello, I am

Ananthu M s.

1

GenAI
Project

About Me

I Completed my Diploma in Data Science from IIT MADRAS in 2026. I also holds a BTech degree in Mechanical Engineering from Kerala University

Key Skills

Python

SQL

Excel

Machine Learning Algorithms

Pytorch

Langchain

ChromaDB

My Projects

FINANCIAL-RESEARCH-RAG

Domain/Function: Financial Research / Question Answering

My Experience

Supply Chain Talent Bridge, Ontario, Canada – Machine Learning Teaching Assistant (Remote, Part-Time)
Dec 2025 – Apr 2026

Guided learners through core Machine Learning concepts using practical examples, demonstrations, and hands-on exercises.
Supported students during practical and project-based sessions, helping them resolve conceptual and implementation-related doubts.
Simplified complex Machine Learning topics and connected theoretical concepts with real-world applications to improve understanding.
Assisted learners with problem-solving approaches, model-building exercises, and interpreting Machine Learning workflows.
Conducted one-on-one doubt-clearing sessions and provided continuous support to help students progress through course activities and projects.

Awards & Certificate

Python: Beginner to Advanced For Data Professionals

SQL for Data Science

Math and Statistics For AI, Data Science

Master Machine Learning for Data Science & AI: Beginner to Advanced

Excel: Mother of Business Intelligence

Deep Learning: Beginner to Advanced

Natural Language Processing

Diploma in Data Science (IIT MADRAS)

Foundation certificate in programming and data science

Let's Connect

Feel free to get in touch with me. I am always open to discussing new projects, creative ideas or opportunities to be part of your visions.

Mail Me

[email protected]

https://www.linkedin.com/in/ananthu-ms-7a9150308/

Call Me

+91 7907260964

GitHub

https://github.com/ananthumangalan

GenAI Project

FINANCIAL-RESEARCH-RAG

Domain/Function: Financial Research / Question Answering

A RAG-based financial research tool that lets users add article URLs and ask questions from the retrieved content. It uses embeddings, ChromaDB and an LLM to return grounded answers with source links through a simple Streamlit interface.

View Project
Engagement

View Project
on GitHUB

Streamlit interface where users can enter article URLs, process them, and ask questions. The generated answer is shown along with the source links used by the retriever.

Backend RAG flow: webpage loading and validation, text chunking, Hugging Face embeddings, ChromaDB storage, semantic retrieval, prompt construction and answer generation using a Groq-hosted LLM.

Project Details

This project helped me understand how Retrieval-Augmented Generation works in a practical application. Users can provide financial article URLs, process their content and ask questions based on those sources. The application loads and validates webpages, splits the text into chunks, creates embeddings using a Hugging Face model and stores them in ChromaDB. When a question is asked, the retriever finds the most relevant chunks and passes them as context to a Groq-hosted LLM, which generates an answer using only the retrieved information. I also added source links, error handling and validation for blocked or invalid webpages. A Streamlit frontend makes the workflow easy to use without interacting directly with the Python code. The main learning from this project was understanding that a good RAG system depends not only on the LLM, but also on data quality, retrieval and validation.

Already have an account? Sign in