projects

A growing collection of my cool projects. * indicates on-going work.

anada
A lightweight, terminal-first note-taking tool with Markdown support and bi-directional linking for personal knowledge management.
InterpBoard *
A library for interpreting and analyzing transformer language models. Currently work in progress (will hopefully be better than TransformerLens!).
MCRAG
This LLM-based system, inspired by GAN design, uses a generator and two critics to generate and iteratively improve written code based on critics' feedback.
mlboardkit
This Python library streamlines data processing, model training and analysis in machine learning, with CLI commands and Python interfaces for dataset quality checks, format conversion, metric computation, plotting and model training.
QueryMind
An AI agent that connects to real-time databases through the MCP allowing natural language to SQL query translation and secure live data access. It supports full CRUD operations, enabling data management through natural language commands.
Fetch REcent Papers (FREP)
A web API that fetches and displays the latest research papers from arXiv based on user-specified topics and keywords, helping researchers stay updated with recent publications in their field.
FusionGraph
A multimodal RAG system that extracts and combines information from text and images into a unified knowledge source with knowledge graph-based reasoning to handle complex queries with reduced risk of hallucination.
Scorj: Evaluate your job-fit
This tool scores your resume against a job description out of 100 and generates a detailed feedback highlighting your fit and suitability for the role. It is currently being extended to support multilingual resumes, thanks to a grant from Cohere Labs.
ComplyGraph
A prototype that evaluates the financial compliance of a transaction against a set of rules stored in Neo4j database using semantic search + rule-based system.
NoBase: Text-to-SQL bot
A PEFT-optimized chatbot powered by Llama-3.3-70B that translates user prompts into SQL queries efficiently. The model was fine-tuned on a custom dataset of 6K SQL query-natural language pairs and achieved 94% query generation accuracy.
Adaptron
A RL-based trading agent for the BSE Sensex that executes buy/sell trades, achieving an average annualized return of 9%. This was trained on 15 years of historical Sensex data and was benchmarked against RL algorithms like Deep Q-network and A3C.