uv-package-manager

PyO3 FFI layer for uv's pip_install internals — call uv directly from Python without CLI overhead. Fork of astral-sh/uv v0.10.8.

A fastapi starter template NOT FOR beginners

A Virtual Hardware-in-the-Loop (HIL) testing framework demonstrating automotive ECU testing with Robot Framework, UV, and REST API. Showcase of modern test automation practices for software-in-the-loop simulation.

Claude Code agent for automating Taiwan Medical Association (TMA) continuing education exams—fetches questions, researches answers via web search, and submits results using Python.

A strictly minimalist, editorial-grade blog application built with Django 5.1

A basic RAG pipeline which uses gpt-oss-20b model to answer the user query with the external knowledge stored in a vector database.

UV tool called `uv-launcher` that builds launchers from `uv-scripts`

A exmaple for yaka-llm in python.with a gemini chat model

[FOR EDUCATIONAL PURPOSE] Assignment task by Vindiata Consulting Private Limited. Here I do analysis on loyalty points of individual players based on their game played, deposit, withdrawal.

A lanchain rebuild. smaller and simpler

[FOR EDUCATIONAL PURPOSE] Assignment task by Sarva Suvidhan Pvt. Ltd. Goal is to develop an API to connect with flutter frontend.

A minimal Retrieval-Augmented Generation (RAG) pipeline built with LangChain, Qdrant, and HuggingFace embeddings. Ingest PDF documents into a vector store and query them using an LLM with grounded, context-aware responses.

Unofficial Python wrapper for the undocumented API of streamable.com

Car price prediction model using a PyTorch regression neural network. Features advanced preprocessing (One-Hot Encoding), Dropout regularization, and real-time monitoring via TensorBoard.

AutoVisual AI is a Streamlit-based data analysis app that transforms messy CSV/Excel/JSON files into clean, insightful datasets with AI-assisted guidance. Upload, clean, visualize, and archive datasets effortlessly.

🍷 Sophisticated, persona-driven AI assistant built with Gemini 3 Flash. Features stateless history management, dynamic context injection, and modular prompt engineering

PyTorch-based ANN for Boston Housing price regression. Features an MLP optimized for tabular data, data scaling, and GPU/CPU support. Managed with uv and Python 3.14.

Advanced RAG system for tech docs. Powered by Qdrant (dense vector), Neo4j (GraphRAG), BM25 (lexical), Cross-Encoder reranking, and query transformations.