Articles for category: AI Tools

March 30, 2025

ikayaniaamirshahzad@gmail.com

Introducing spaCy v2.1 · Explosion

Version 2.1 of the spaCy Natural Language Processing library includes a huge number of features, improvements and bug fixes. In this post, we highlight some of the things we’re especially pleased with, and explain some of the most challenging parts of preparing this big release. Our annotation tool Prodigy Prodigy is a fully scriptable annotation tool that complements spaCy extremely well. Most NLP projects are easier if you have a way to train models on exactly your data. This lets you improve accuracy, and customize the label set. Prodigy’s community has been growing quickly, allowing us to keep spaCy fully

March 30, 2025

ikayaniaamirshahzad@gmail.com

Accelerating Vision-Language Models: BridgeTower on Habana Gaudi2

Update (29/08/2023): A benchmark on H100 was added to this blog post. Also, all performance numbers have been updated with newer versions of software. Optimum Habana v1.7 on Habana Gaudi2 achieves x2.5 speedups compared to A100 and x1.4 compared to H100 when fine-tuning BridgeTower, a state-of-the-art vision-language model. This performance improvement relies on hardware-accelerated data loading to make the most of your devices. These techniques apply to any other workloads constrained by data loading, which is frequently the case for many types of vision models. This post will take you through the process and benchmark we used to compare BridgeTower

March 30, 2025

ikayaniaamirshahzad@gmail.com

Comprehensive Guide for Understanding the Self-Taught Web Developer Path in 2025

This guide provides an in-depth exploration of the journey for self-taught web developers in 2025, drawing from recent articles, forums, and personal experiences shared by developers. It covers challenges, strategies, and resources, ensuring a thorough understanding for those embarking on this path, especially given the current tech job market trends as of March 30, 2025. Overview of the Self-Taught Path in 2025 Self-taught web development remains a viable option in 2025, as evidenced by success stories like a developer employed full-time after starting in January 2024, as shared on Dev.to. The process involves learning through online resources, tutorials, and practice

March 30, 2025

ikayaniaamirshahzad@gmail.com

Advanced NLP with spaCy · A free online course

About this course spaCy is a modern Python library for industrial-strength Natural Language Processing. In this free and interactive online course, you’ll learn how to use spaCy to build advanced natural language understanding systems, using both rule-based and machine learning approaches. About me I’m Ines, one of the core developers of spaCy and the co-founder of Explosion. I specialize in modern developer tools for AI, Machine Learning and NLP. I also really love building stuff for the web. Source link

March 30, 2025

ikayaniaamirshahzad@gmail.com

Leveraging Hugging Face for complex generative AI use cases

In this conversation, Jeff Boudier asks Waseem Alshikh, Co-founder and CTO of Writer, about their journey from a Hugging Face user, to a customer and now an open source model contributor. why was Writer started? what are the biggest misconceptions in Generative AI today? why is Writer now contributing open source models? what has been the value of the Hugging Face Expert Acceleration Program service for Writer? how it Writer approaching production on CPU and GPU to serve LLMs at scale? how important is efficiency and using CPUs for production? If you’re interested in Hugging Face Expert Acceleration Program for

March 30, 2025

ikayaniaamirshahzad@gmail.com

How I Saved a Startup $15k/month on AWS Without Downtime

The Problem [StartupX] was burning $32k/month on AWS due to: Database Overkill: RDS instances running at 15% utilization Zombie Servers: 12 EC2 instances left running for “future needs” Static Scaling: Angular app crashing during traffic spikes The Fix (3 Tactics Anyone Can Use) Database Diet Downsized from db.r5.2xlarge → db.t3.large Enabled auto-scaling based on CPU pressure Savings: $8k/month EC2 Vampire Slayer Automated start/stop schedules using Lambda + CloudWatch Tagged resources for accountability Savings: $4k/month Frontend Tune-Up Lazy-loaded Angular modules Moved static assets to CloudFront Bonus: Load time dropped from 4s → 1.2s Results Total Saved: $15k/month (recurring) Implementation Time: 12

March 30, 2025

ikayaniaamirshahzad@gmail.com

Practical Natural Language Processing with spaCy and Prodigy with Ines Montani

In this episode of PyDataSci, we’re joined by Ines Montani, Co-founder of Explosion, Co-developer of SpaCy, and lead developer of Prodigy. Ines and I caught up to discuss her various projects, including the aforementioned SpaCy, an open-source NLP library built with a focus on industry and production use cases. In our conversation, Ines gives us an overview of the SpaCy Library, a look at some of the use cases that excite her, and the Spacy community and contributors. We also discuss her work with Prodigy, an annotation service tool that uses continuous active learning to train models, and finally, what

March 30, 2025

ikayaniaamirshahzad@gmail.com

Making a web app generator with open ML models

As more code generation models become publicly available, it is now possible to do text-to-web and even text-to-app in ways that we couldn’t imagine before. This tutorial presents a direct approach to AI web content generation by streaming and rendering the content all in one go. Try the live demo here! → Webapp Factory Using LLM in Node apps While we usually think of Python for everything related to AI and ML, the web development community relies heavily on JavaScript and Node. Here are some ways you can use large language models on this platform. By running a model locally

March 30, 2025

ikayaniaamirshahzad@gmail.com

uv: Up to 100x Faster Than pip—Is This Python’s Future?

While developing Python projects, we’ve all watched pip install crawl through dependencies while our productivity stalls. Enter uv, the Rust-powered package manager released in January 2024 by Astral that solves pip’s biggest pain points: Slow Performance: No more waiting minutes for dependency installations Lack of Native Locking: Consistent builds across all environments Tool Fragmentation: One tool instead of juggling pip, virtualenv, and pip-tools Outdated Formats: Modern support for pyproject.toml and more What is uv? uv is a comprehensive Python toolchain that replaces multiple tools in one unified solution. It’s 10-100x faster than pip, provides universal lockfiles for reproducible environments, manages