A Graph Convolutional Network-based solution for PHI prediction.

Redact PHI/PII data using AWS comprehend API's

A simple implementation of Euler's totient function ("Phi function").

ChatGPT interface with custom UI

A modular multi-agent AI system that classifies and routes documents (Email, JSON, PDF) using LLMs, with shared memory and format-intent detection. Built with Python and Ollama. This project was developed as part of an internship task focused on building a practical multi-agent AI document processing pipeline using LLMs and shared memory.

A powerful multi-agent LLM system for real-time financial data analysis and web search, built using Phi’s agent framework and Groq’s LLaMA 3.3 model. Integrates YFinance and DuckDuckGo tools for fetching stock prices, analyst recommendations, fundamentals, and live news. Supports markdown-based tabular output and custom function calling

Strip PHI from HL7 v2 messages for safe testing & sharing. Built by SmaRTy Saini Corp

module system for question classification and answer enhancement using the Phi model, with Arabic & English support and an interactive Streamlit UI.

AI Playground using Gemini API or HuggingFace Token to conduct specific tasks to fulfill specific needs.

A data catalog for database tables and columns to track PII and PHI.

Developed a Financial Advisor application using Streamlit as the interface and integrated the Ollama (phi) model. The application has been successfully deployed on an Azure Virtual Machine.

GDSC Solution Challenge - Innovatrix

⚗️ Phi-3-mini 3.8B instruct model repository

This code plots prime numbers, their position, spin, and rotation in the prime hexagon. See The Prime Hexagon video at: https://www.youtube.com/watch?v=fQL4KRH3wUQ

A Python script for looking up numbers in Pi and viewing their properties, as well as analyzing dates, and calculating the Gematria of text.

An AI-powered system using Groq for model inference and Phi framework. It integrates YFinance for financial data (stock prices, analyst recommendations) and DuckDuckGo for web research. Built with FastAPI and Streamlit, it supports querying financial and web data, storing interactions in an SQLite database.

A Python 3 package to parse the Ibycus format, used by the TLG & PHI CD-ROM.

Streamlit Chatbot using Ollama Open Source LLMs

This is an an experimental implementation of field-level data masking of Personally Identifiable Information (PII) for use in Django.

Inference and Training Engine for LLMs, Image2Image and Other Models