Articles for category: AI Tools

Building Cost-Efficient Enterprise RAG applications with Intel Gaudi 2 and Intel Xeon

Retrieval-augmented generation (RAG) enhances text generation with a large language model by incorporating fresh domain knowledge stored in an external datastore. Separating your company data from the knowledge learned by language models during training is essential to balance performance, accuracy, and security privacy goals. In this blog, you will learn how Intel can help you develop and deploy RAG applications as part of OPEA, the Open Platform for Enterprise AI. You will also discover how Intel Gaudi 2 AI accelerators and Xeon CPUs can significantly enhance enterprise performance through a real-world RAG use case. Before diving into the details, let’s

OMSCS CS7641 (Machine Learning) Review and Tips

You might also be interested in this OMSCS FAQ I wrote after graduation. Or view all OMSCS related writing here: omscs. I haven’t had time to write the past few months because I was away in Hangzhou to collaborate and integrate with Alibaba. The intense 9-9-6 work schedule (9am – 9pm, 6 days a week) and time-consuming OMSCS Machine Learning class (CS7641) left little personal time to write. Thankfully, CS7641 has ended, and the Christmas holidays provide a lull to share my thoughts on it. Why take this class? Why take another machine learning course? How will it add to

Best Warehouse Inventory Management Software

Warehouse inventory management is critical for businesses looking to maintain accurate stock levels, streamline operations, and enhance order fulfillment. The right warehouse inventory management software (WIMS) can optimize tracking, reduce errors, and improve efficiency. This blog explores some of the best warehouse inventory management software solutions available today. 1. NetSuite WMS Overview:NetSuite Warehouse Management System (WMS) is a cloud-based solution designed to streamline warehouse operations by automating key processes like inventory tracking, order fulfillment, and real-time reporting. It integrates seamlessly with NetSuite’s ERP, making it ideal for businesses looking for a comprehensive solution.Key Features: Bin & Shelf Management: Organizes inventory

Introducing spaCy v3.5 · Explosion

We’re excited to release v3.5 of the spaCy Natural Language Processing library. spaCy v3.5 introduces three new CLI commands, adds fuzzy matching, provides improvements to our entity linking functionality, and includes a range of language updates and bug fixes. New CLI commands apply applies a pipeline to one or more .txt, .jsonl or .spacy files benchmark speed profiles a pipeline’s speed with a warmup and a confidence interval find-threshold tests a range of threshold values for spancat, textcat_multilabel, etc, to identify the most optimal one. Examples on how to run these commands can be found in our CLI documentation as

License to Call: Introducing Transformers Agents 2.0

We are releasing Transformers Agents 2.0! ⇒ 🎁 On top of our existing agent type, we introduce two new agents that can iterate based on past observations to solve complex tasks. ⇒ 💡 We aim for the code to be clear and modular, and for common attributes like the final prompt and tools to be transparent. ⇒ 🤝 We add sharing options to boost community agents. ⇒ 💪 Extremely performant new agent framework, allowing a Llama-3-70B-Instruct agent to outperform GPT-4 based agents in the GAIA Leaderboard! 🚀 Go try it out and climb ever higher on the GAIA leaderboard! transformers.agents has

INSEAD Lunchtime Talks – How Lazada uses Data

I was recently invited by Tracy Lim to INSEAD to share on how Lazada applies Data Science to e-commerce, as well as my personal journey towards becoming a VP of Data Science. The talk was extremely well organized, and I was surprised at the large turnout (~100) of students given that it was over lunch time. Sharing My sharing had three main threads. Firstly, we discussed on the problems that Lazada solves through data science and machine learning. For this, we dived deep into two use cases (i) Automated User Review Classification, which reduced manpower by >90% leading to 5

From Full Stack to Full Circle: My Journey Towards Technical Architecture

“You’re either building the product… or you’re building yourself while building it.” I’m Vinay, a full-stack engineer from Bengaluru—Node.js, React, and an obsession for clean, scalable systems. But beyond code, my journey is shaped by crossing roles, carving paths, and confronting assumptions. 🎢 From Developer to Product Whisperer I started as the typical “heads-down” dev. Feature tickets in, PRs out. But I always found myself asking: Why are we building this? Who is this really for? That curiosity led me to blur the lines between engineering and product ownership. Soon, I was leading conversations—not just commits. I wasn’t just writing

Our Year in Review · Explosion

It’s been another exciting year at Explosion! We’ve developed a new end-to-end neural coref component for spaCy, improved the speed of our CNN pipelines up to 60%, and published new pre-trained pipelines for Finnish, Korean, Swedish, Croatian and Ukrainian. We’ve also released several updates to Prodigy and introduced new recipes to kickstart annotation with zero- or few-shot learning. During 2022, we also launched two popular new services – spaCy Tailored Pipelines and spaCy Tailored Analysis. We’ve published several technical blog posts and reports, and created a bunch of new videos covering many tips and tricks to get the most out

PaliGemma – Google’s Cutting-Edge Open Vision Language Model

Updated on 23-05-2024: We have introduced a few changes to the transformers PaliGemma implementation around fine-tuning, which you can find in this notebook. PaliGemma is a new family of vision language models from Google. PaliGemma can take in an image and a text and output text. The team at Google has released three types of models: the pretrained (pt) models, the mix models, and the fine-tuned (ft) models, each with different resolutions and available in multiple precisions for convenience. All models are released in the Hugging Face Hub model repositories with their model cards and licenses and have transformers integration.

Building a Strong Data Science Team Culture

I know, I know. I’m guilty of not posting over the past four months. Things have been super hectic at Lazada with Project Voyager (i.e., migrating to Alibaba’s tech stack) since last September and then preparing for our birthday campaign in end Apr. In fact, I’m writing this while on vacation =) One of my first objectives after becoming Data Science Lead at Lazada—a year ago—was to build a strong team culture. Looking back, based on feedback from the team and leadership, this endeavor was largely a success and contributed to increased team productivity and engagement. Why culture? When I