phatjkk
Follow
Lists (1)
Stars
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Headless TypeScript ORM with a head. Runs on Node, Bun and Deno. Lives on the Edge and yes, it's a JavaScript ORM too 😅
Use late-interaction multi-modal models such as ColPali in just a few lines of code.
✨ Innovative and open-source visualization application that transforms various data formats, such as JSON, YAML, XML, CSV and more, into interactive graphs.
HunyuanVideo: A Systematic Framework For Large Video Generation Model
Port of OpenAI's Whisper model in C/C++
Agent Framework / shim to use Pydantic with LLMs
A fully custom chatbot built with Agentic RAG (Retrieval-Augmented Generation), combining OpenAI models with a local knowledge base for accurate, context-aware, and explainable responses. Features …
DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception
A modern, real-time speech recognition application built with OpenAI's Whisper and PySide6. This application provides a beautiful, native-looking interface for transcribing audio in real-time with …
An open source eCommerce platform giving you full control and customizability. Modular and API-first. Multi-vendor, multi-tenant, multi-store, multi-currency, multi-language. Built using Ruby on Ra…
This repository is based on AI and Machine learning for Coders book, I note my knowledge I have learned from the book in Vietnamese.
Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
Simple, unified interface to multiple Generative AI providers
Find your trading edge, using the fastest engine for backtesting, algorithmic trading, and research.
🔎 📈 🐍 💰 Backtest trading strategies in Python.
Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI
libSQL is a fork of SQLite that is both Open Source, and Open Contributions.
DuckDB is an analytical in-process SQL database management system
Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key
Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.
Make websites accessible for AI agents
tailwindcss-motion is a Tailwind CSS Plugin made at RomboHQ. It’s a simple, yet powerful, animation library with a simple syntax.
Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。
Code of Pyramidal Flow Matching for Efficient Video Generative Modeling