Data Scientist

AI is my thing, I even make machines overthink.

Abhishek Kapoor

Releases

Coming soon Small Language Model

More details will be shared once the project is released. Stay tuned!

March 2026 OpenMultiRAG

Advanced realtime Retrieval-Augmented Generation (RAG) system handling multiple documents, multimodal parsing, and strict citation tracking.

FastAPI, Streamlit, LangGraph, Groq, Qdrant, PostgreSQL, Redis, Langfuse, Docker

January 2026 AI Data Analyst Agent

A multi agent AI system that automates ETL, cleaning, analysis with always human in the loop and self correcting capabilities, and allow users to query and clean the data using natural language.

LangGraph, LangChain, Groq, FastAPI, Docker, PostgreSQL, Redis

August 2025 MLOps Platform for Real time Churn Prediction

Production scale churn prediction system with monitoring, reproducibility, and full ML lifecycle automation.

Dask, DVC, LightGBM, MLflow, FastAPI, Docker, GitHub Actions, Docker-Hub Image

March 2025 MiniCLIP Vision Language Model

Lightweight CLIP style vision language model trained from scratch and optimized for low resource deployment.

PyTorch, Transformers, ONNX