An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

PII Anonymizer service based on python with FastAPI

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

Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+Tokenizers.cpp, supporting chat and function call, AI agents, distributed multi-GPU inference, multimodal capabilities, and a Gradio chat interface.

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.

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

GDSC Solution Challenge - Innovatrix

[ICLR 2025] xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation

Large Language Models (LLMs) applications and tools running on Apple Silicon in real-time with Apple MLX.

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

Phi3 中文后训练模型仓库

AI voice assistant made with Streamlit python and powered by Gemini, Mistral and PHI-3. This is a virtual assistant application built in Python that can understand voice commands and complete tasks like opening websites, playing music, telling the time, sending emails, searching Wikipedia, and more.

🚀 Easy, open-source LLM finetuning with one-line commands, seamless cloud integration, and popular optimization frameworks. ✨

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.

⚗️ Phi-3-mini 3.8B instruct model repository

Streamlit Chatbot using Ollama Open Source LLMs

Image Knowledge base / Idea / Problem Solve / Analysis

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

Multimodal-ChatBot-App, LLM Model Id Doesn't work outside, since it is opeartable inside the Huggingface Models. Recommended to Deploy inside Huggingface Spaces SDK as StreamLit.