Last Updated on June 3, 2024 by Editorial Team Author(s): Towards AI Editorial Team Originally published on Towards AI. Good morning, fellow learners. If you’ve enjoyed the list of courses at Gen AI 360, wait for this… Today, I am super excited to finally announce that we at towards_AI have released our first book: Building LLMs for Production. Put a dozen experts (graduates and industry) and 1.5 years of work together, and that’s what you get. “…the most comprehensive textbook to date on building LLM applications, and helps learners understand everything from fundamentals to the simple-to-advanced building blocks of constructing LLM applications […] — all essential topics in an AI Engineer’s toolkit.” — Jerry Liu, CEO of LlamaIndex One of the reasons I quit my PhD in AI was to help others in the real world and improve what exists, and we are pursuing this goal with a book. This 470-page book is all about LLMs and how to work with them. Right now, this means working with LlamaIndex, LangChain, Activeloop, and other amazing tools, but we believe the book still teaches concepts that will stay relevant for a long time even as LLMs get better, such as reducing hallucinations, teaching how to work and use them, some cool theory and tips and more. Get your copy now! What’s AI Weekly This week, of course, I made a video giving more details about the book if you are curious. I think it can be useful to those who want more details before making the move to purchase the book. I’ll be sharing lots of content related to the book as well on the channel in the upcoming weeks! — Louis-François Bouchard, Towards AI Co-founder & Head of Community Learn AI Together Community section! Featured Community post from the Discord Frikyfriks just released their first paper on exploring the creative process in the human brain and comparing it to the SOTA text-to-image architectures. It compares the cognitive aspects of creativity, including memory and the creative process, with state-of-the-art AI architectures. The aim is to identify similarities and differences between the two systems. Check it out in the Discord thread and share your thoughts and feedback on the topic and the paper! AI poll of the week! It’s fantastic to see that most of our communities are “old school” like us! We think sometimes it is better to let your thoughts flow through your hands first; it could be a great way to test an idea! Of course, we would love to hear more creative ways of taking notes. Drop them in the thread! Collaboration Opportunities The Learn AI Together Discord community is flooding with collaboration opportunities. If you are excited to dive into applied AI, want a study partner, or even want to find a partner for your passion project, join the collaboration channel! Keep an eye on this section, too — we share cool opportunities every week! 1. Moses1750 is making a small flutter app (a Codecademy project) and looking for someone to join them. If this sounds fun, connect with them in the thread! 2. Prime_otter_86438 is working on a Python library to make ML training and running models on any microcontroller in real time for classification easy for beginners. They are seeking assistance from an expert to improve the model and make the Python package easier for the end user. If you are interested, reach out to them in the thread! 3. Siyaprincess is looking for a guide/teacher to dive into AI. If you can help or want to learn together, contact them in the thread! Meme of the week! Meme shared by bin4ry_d3struct0r TAI Curated section Article of the week Graph Neural Networks (GNN) — Concepts and Applications by Tan Pengshi Alvin Graph Neural Networks (GNN) are a very interesting application in deep learning and have strong potential for important use cases, albeit a less well-known and more niche domain. This article explains Graph Data and demonstrates how to apply Deep Learning to Graph Data or GNNs. Our must-read articles 1. Exploring LaMa: Resolution-robust Large Mask Inpainting with Fourier Convolutions: A Brief Overview by Vincent Liu LaMa specializes in restoring large masked areas with its innovative structure and loss functions. This article covers its model architecture and concepts used, such as Spectrum Transform, Fast and Fourier Convolution, and Adversarial Loss. 2. Build and Run Data Pipelines with Sagemaker Pipelines by Jake Teo This article shows how to run long-running, repetitive, centrally managed, and traceable data pipelines leveraging AWS’s MLOps platform, Sagemaker, and its underlying services, Sagemaker pipelines, and Studio. Sagemaker is a fully managed AWS service comprising a suite of tools and services to facilitate an end-to-end machine learning (ML) lifecycle. 3. Zero-Shot Audio Classification Using HuggingFace CLAP Open-Source Model by Youssef Hosni Zero-shot audio classification tasks present a significant challenge in machine learning, particularly when labeled data is scarce. This article explores the application of Hugging Face’s open-source models, specifically the Contrastive Language-Audio Pretraining (CLAP) models, for addressing this challenge. If you are interested in publishing with Towards AI, check our guidelines and sign up. We will publish your work to our network if it meets our editorial policies and standards. If you enjoyed reading this newsletter, you might also like our latest book ‘Building LLMs for Production’. Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor. Published via Towards AI