swiss_army_llama

A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.

https://github.com/Dicklesworthstone/swiss_army_llama

genai-stack

This GenAI application stack will get you started building your own GenAI application in no time. The demo applications can serve as inspiration or as a starting point.

https://github.com/docker/genai-stack

streaming-llm

Efficient Streaming Language Models with Attention Sinks.

https://github.com/mit-han-lab/streaming-llm

RealtimeSTT

A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription. Designed for real-time applications like voice assistants.

https://github.com/KoljaB/RealtimeSTT

LLM-scientific-feedback

Can large language models provide useful feedback on research papers? A large-scale empirical analysis.

https://github.com/Weixin-Liang/LLM-scientific-feedback

ExecuTorch

End-to-end solution for enabling on-device AI across mobile and edge devices for PyTorch models.

https://github.com/pytorch/executorch

OpenAgents

An Open Platform for Language Agents in the Wild.

https://github.com/xlang-ai/OpenAgents

Django Day Copenhagen 2023 Videos

The videos of the talks from the fourth edition of Django Day Copenhagen are now available.

https://www.youtube.com/playlist?list=PLEpW1LzVyQWgtT_i_IlUmx2FSP2jHcroX

Python 3.11 vs Python 3.12 – performance testing

This article describes the performance testing results of Python 3.12 compared to Python 3.11. A total of 91 various benchmark tests were conducted on computers with the AMD Ryzen 7000 series and the 13th-generation of Intel Core processors for desktops, laptops or mini PCs.

https://en.lewoniewski.info/2023/python-3-11-vs-python-3-12-performance-testing/

Building Custom Middleware in FastAPI

In this article you’ll see how to build custom middleware, enabling you to extend the functionality of your APIs in unique ways by building function-based and class-based middleware to modify request and response objects to suit your need and to handle rate limiting. You’ll also see how to write test cases and the best practices to follow.

https://semaphoreci.com/blog/custom-middleware-fastapi

Practical AI: HuggingFace Transformers and Diffusers for Beginners

This presentation provides a straightforward overview of the HuggingFace Transformers and Diffusers libraries. Aimed at those without a deep understanding of AI or ML, we’ll focus on practical, hands-on applications. We conclude by setting up a Flask app that generates AI images, demonstrating how these tools can be used to create useful applications.

https://www.youtube.com/watch?v=rK02eXm3mfI