PythonHub

Poor mans autoreload server in single file python on linux The article describes a simple Python server that provides automatic browser page reload on content change, without requiring any additional setup or configuration. The server acts as a regular file server but also serves WebSocket messages over a specified path to trigger the page reload. https://hereket.com/posts/linux_live_reload_python_server/

Pyinfra: Automate Infrastructure Using Python https://pyinfra.com/

Cognita RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry https://github.com/truefoundry/cognita

tkforge Drag & drop in Figma to create a Python GUI with ease. https://github.com/Axorax/tkforge

TMElyralab / MuseV MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising https://github.com/TMElyralab/MuseV

Map Machine: Python renderer for OpenStreetMap with custom icons https://github.com/enzet/map-machine

tach A Python tool to enforce a modular, decoupled package architecture. https://github.com/Never-Over/tach

Django: An admin extension to prevent state leaking between requests Here’s a small protection I added to a project a few years ago. I was considering it again since I saw a similar potential bug in a Django middleware. https://adamj.eu/tech/2024/04/29/django-admin-prevent-leaking-requests/

LMDeploy LMDeploy is a toolkit for compressing, deploying, and serving LLMs. https://github.com/InternLM/lmdeploy

A Beginner’s Guide to Vector Embeddings In this article, we’ll examine vector embeddings in depth, including the types of vector embeddings, how neural networks create them, how vector embeddings work, and how you can create embeddings for your data. https://www.timescale.com/blog/a-beginners-guide-to-vector-embeddings/

torchtitan A native PyTorch Library for large model training. https://github.com/pytorch/torchtitan

TagStudio A file and photo management application and system. https://github.com/TagStudioDev/TagStudio

How to Build a Crystal Image Search App with Vector Search A demonstration of how to build an application to store and query data on crystals and precious stones using Astra DB. Built with RAGStack, this web app leverages the CLIP model to provide multi-modal search to retrieve data on all kinds of crystals. https://www.datastax.com/blog/building-a-generative-ai-crystal-image-search-app-with-vector-search

Sleepsort: Sorting while sleeping The post introduces the "sleepsort" algorithm, a quirky sorting method that utilizes thread sleep times to sort integers in ascending order. It provides a playful yet insightful exploration of the algorithm's functionality and limitations. https://animeshchouhan.com/posts/sleepsort

Doriandarko / maestro A framework for Claude Opus to intelligently orchestrate subagents. https://github.com/Doriandarko/maestro

TypeIs does what I thought TypeGuard would do in Python The article discusses the differences between the TypeGuard and TypeIs type annotations in Python. It explains that TypeIs has more intuitive behavior compared to TypeGuard, especially when dealing with union types, and recommends using TypeIs over TypeGuard in most cases. https://rednafi.com/python/typeguard_vs_typeis/

WebLlama Llama-3 agents that can browse the web by following instructions and talking to you. https://github.com/McGill-NLP/webllama

Patching requests for fun and (concurrent) profit Because life is too short to spam calls to SSLCTXloadverifylocations(). https://blog.borrego.dev/entries/patching-requests-for-fun-and-concurrent-profit.html

cohere-toolkit Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications. https://github.com/cohere-ai/cohere-toolkit

Local LLM-as-judge evaluation with lm-buddy, Prometheus and llamafile This post examines how different software components came together to allow LLM-as-judge evaluation without the need for expensive GPUs. All the components were built with and chosen for their user control, open source nature, and interoperability. https://blog.mozilla.ai/local-llm-as-judge-evaluation-with-lm-buddy-prometheus-and-llamafile