IBM Developer

Still struggling to deliver the application updates that your business needs? 👉 Join speakers, Alasdair Nottingham, Isabella Rocha, and Louisa Gillies on Wednesday, July 23 at 9:00 AM EST to learn how EASeJ streamlines building, deploying, and running your Java applications so your team can ship faster, with less friction: https://lnkd.in/gPesMNCZ 👉 Register here: https://lnkd.in/gdt5QdBa 

Turn your Markdown files into a dynamic, interactive, and a conversational resource. 🚀 ▪️ In this tutorial, IBMer Aditya Gidh, explains how you can use JavaScript, LangChain, and the IBM Granite model via Ollama, to create a command-line interface (CLI) that connects to your GitHub repository, pulls in your documentation, and answers your questions in plain language. ▪️ Learn how to build a digital assistant tailored specifically for your project’s guides: https://ibm.co/6044BEeFK --------------- #AI #RAG #IBMGranite

Modernizing a 20-year-old system is no small feat, especially when it's powering core operations for IBM Financing. In this latest blog by IBMer Isabella Rocha, read how the GCMS team reduced Java modernization time by 70% using the JSphere Suite for Java: 🔹 160+ hours saved on remediation 🔹 99% faster discovery 🔹 Cloud-ready deployment with zero business disruption These tools were pressure-tested in the real world, by real teams, with real results. 🔗 Read more: https://ibm.co/6049BE8cS

Explore what #AI agent orchestration means, why it matters, and how watsonx Orchestrate helps developers to build powerful, multi-agent workflows without writing complex orchestration logic. Check this beginner's guide to multi-agent orchestration with watsonx Orchestrate and learn how to turn standalone agents into intelligent and connected workflows: https://ibm.co/6046BDSp2

If you're working with #AI, you already know data prep can take a LONG time, but it's critical to your success. Data Prep Kit is a toolkit to help you streamline your data preparation and build LLM-enabled applications using fine-tuning, #RAG, instruction-tuning, or agentic techniques. The new Get Started with Data Prep Kit learning path shows you how to use the kit to prepare data for #LLM apps, teaches you the fundamental concepts and features, and gives you the keys to unlock data ingestion. Turn your unstructured data into your most valuable resource. Data Prep Kit — let's get started! https://lnkd.in/g4E7ZcMB

A re-ranker is a model or system that reorders or refines a list of retrieved documents or items based on their relevance to a given query. ColBERT (Contextualized Late Interaction over BERT) is a retrieval model that strikes a balance between the efficiency of traditional methods like BM25 and the accuracy of deep learning models like BERT, an open source #deeplearning model used for natural language understanding. Find out what makes ColBERT especially effective in #RAG (retrieval-augmented generation) pipelines, where precise and contextually rich document retrieval directly impacts the quality of generated answers. https://lnkd.in/gKxj_GpM

Whether you're just getting started with #genAI or looking to operationalize your AI in production, there are always questions: What can LLMs do? How do #AI agents handle complex workflows? How can open source LLMs help me? 🤔 💠 We hear you. Discover “Open source LLMs unlock agentic and generative AI” to find answers to those questions and much more: http://ibm.co/6041B85mJ 💠 Hear from genAI leaders like IBM watsonx. ai Product Manager Vijesh Bhaktha Rajagopal 🙌 💠 Vijesh explains how to approach building agents and identify suitable use cases across business functions like customer support, IT automation, and insurance claims. Then, check out all the sessions, and unlock the power of open source #LLMs today! 🚀

IBM watsonx Orchestrate will help you scale your AI agent deployment across your business domains. It connects with all kinds of enterprise applications, automation tools, and third-party AI models, and will integrate seamlessly with your existing business systems. If you're tasked with deploying AI agents, or if you want to know more about AI agent integration, you need to check out this post from product manager Vinicius Maidana. Make your job a whole lot easier with this single, user-friendly interface for building and interacting with AI agents: https://lnkd.in/gWx3wpiE #watsonx #agenticAI #AI

Training and fine-tuning large language models (LLMs) is essential for modern AI applications. "Sharding" is the process of splitting a model’s data or components across multiple devices—such as GPUs or nodes—so that the training workload is distributed and each device only needs to manage a fraction of the total. In this article from Tushar Tiwary, you'll learn how sharding works, how to develop a strategy, and where to find the tools to make it easier. https://lnkd.in/gjSKdfAw #sharding #genAI #LLMs

The Java Virtual Machine (JVM) is the engine that runs your Java application. 🔻 VM performance tuning is the process of optimizing the Java Virtual Machine (JVM) configuration and behavior to improve the performance, scalability, and reliability of #Java applications. 🔻 Read this article to review two key performance tuning techniques: memory management and garbage collection: http://ibm.co/6049B85jH 🔻 By optimizing your JVM with these two techniques, you can improve the performance, scalability, and reliability of your Java applications.