PythonHub
2.35K subscribers
2.35K photos
49K links
News & links about Python programming.
https://pythonhub.dev/
Download Telegram
Langfun

Langfun, powered by PyGlove, makes working with language models (LM) more intuitive by treating language as functions. Using Object-Oriented Prompting, it enables users to prompt LLMs with objects and types, enhancing control and simplifying agent development.

https://github.com/google/langfun
Numpy QuadDType: Quadruple Precision for Everyone

Introducing the new data-type for Numpy providing cross-platform support of quadruple precision.

https://labs.quansight.org/blog/numpy-quaddtype-blog
What I’ve Learned in the Past Year Spent Building an AI Video Editor

Kirk Kaiser spent a year developing an AI video editor using LLMs and Diffusion models to enhance video workflows. His journey explored the intersection of AI and video editing, aiming to create dynamic, generative tools for customizable content.

https://www.makeartwithpython.com/blog/a-year-of-showing-up/
Building an image search engine on Postgres

This post demonstrates how to build a basic image search engine using Postgres, CLIP (a pre-trained AI model), and the pgvector extension. It explains the process of generating embeddings for images and text, storing them in Postgres, and performing similarity searches using both image and text queries1

https://tembo.io/blog/image-search
Building internal AI tools with Streamlit

The article explains how to build internal AI tools using Streamlit and PropelAuth for authentication. It walks through setting up secure user authentication and integrating with AI models, making it easier to build AI-driven web apps for internal company use.

https://www.propelauth.com/post/internal-ai-tools-with-streamlit
Scaling AI-Based Data Processing with Hugging Face + Dask

The article demonstrates how to scale AI-based data processing using Hugging Face and Dask, progressing from processing 100 rows locally with pandas to handling 211 million rows across multiple GPUs in the cloud. It showcases the use of Dask for distributed computing, enabling efficient data loading, preprocessing of large datasets, and parallel model inference, with a practical example ...

https://huggingface.co/blog/dask-scaling