In this post, we will try to build a text summarizer using an LLM in a Python environment. If we can set up the LLM in an interactive environment, we can extend the functionalities to build an interface for this task using Gradio.

Argh provides a wrapper for argparse. Argparse is a very powerful tool; Argh just makes it easy to use.

The Email Summariser is a Python script designed to automatically retrieve, process, categorize, and summarize emails using AI models. It leverages Gmail for email fetching and ollama for AI-powered categorization and summarization.

requirements.txt (or “requirements in setup() call”) is not a valid way to manage dependencies — and it hasn’t been for the past 5+ years. If you are still using requirements.txt it shows you need professional help. luckily, i’m a professional.

Let’s go over some bad / good / example practices for living your best python life in 2024.

LLM provides a Python API for executing prompts, in addition to the command-line interface.

[...]

To run a prompt against the gpt-3.5-turbo model, run this:

import llm

model = llm.get_model("gpt-3.5-turbo")
model.key = 'YOUR_API_KEY_HERE'
response = model.prompt("Five surprising names for a pet pelican")
print(response.text())

Simple command line tool for text to image generation using OpenAI's CLIP and Siren.

Mist.io helps you manage and monitor your virtual machines, across different clouds, using any device that can access the web.

Define user behaviour with Python code, and swarm your system with millions of simultaneous users.

Python, on the other hand, has problems of its own. The biggest is that it has dozens of web application frameworks, but none of them are any good. Pythonists are well aware of the first part but apparently not of the second, since when I tell them that I’m using my own library, the universal response is “I don’t think Python needs another web application framework”. Yes, Python needs fewer web application frameworks. But it also needs one that doesn’t suck.

Detect the language of text.