AI/ML Resources

The Delegated Chain of Thought Architecture

The D-CoT architecture decouples reasoning from execution in LLM by centralizing reasoning in a "modulith" and delegating execution tasks to specialized modules.

February 18, 2025

by Pier-Jean MALANDRINO

CORE

· 3,392 Views · 4 Likes

Generate Unit Tests With AI Using Ollama and Spring Boot

Run Ollama LLM locally with Spring Boot to generate unit tests for Java. Ensure data privacy, easy setup, and seamless integration with Spring AI.

February 18, 2025

by Amol Gote

CORE

· 3,865 Views · 4 Likes

Multimodal RAG With Colpali, Milvus, and VLMs

Build a multimodal RAG app with ColPali, Milvus, and a visual language model to enable Q&A on PDFs using text and visual data indexed for efficient search.

February 18, 2025

by Saumitra Srivastav

· 1,687 Views · 3 Likes

Search: From Basic Document Retrieval to Answer Generation

Exploring the evolution of document retrieval systems from traditional text-matching and frequency-based methods to advanced ingestion and retrieval strategies.

February 18, 2025

by Meghana Puvvadi

· 2,125 Views · 1 Like

The Slides of Hands-On Agile 2025

The virtual Hands-on Agile 2025 conference held last month discussed embracing the shift to context-based agility, from leadership to strategy to AI.

February 17, 2025

by Stefan Wolpers

CORE

· 4,885 Views · 1 Like

Scaling ML Models Efficiently With Shared Neural Networks

A shared encoder architecture to decouple customer-specific fine-tuned models from the shared encoder to deploy at scale.

February 17, 2025

by Meghana Puvvadi

· 2,485 Views · 7 Likes

Have LLMs Solved the Search Problem?

LLMs, while strong in content generation, need techniques like semantic chunking and vector embeddings to address the search problem in complex data environments.

February 17, 2025

by Avi Dubey

· 1,990 Views · 1 Like

ETL Generation Using GenAI

Learn about how GenAI automates ETL pipelines, generates code, adapts to schema changes, and improves data processes with speed, efficiency, and precision.

February 14, 2025

by Ramesh Daddala

· 4,367 Views · 2 Likes

Unlocking Local AI: Build RAG Apps Without Cloud or API Keys

In this tutorial, we will use Chipper, an open-source framework that simplifies building local RAG applications without cloud dependencies or API keys.

February 14, 2025

by Santhosh Vijayabaskar

CORE

· 3,823 Views · 2 Likes

AI Summarization: Extractive and Abstractive Techniques

Learn how to create an AI-powered summarization tool using Hugging Face and OpenAI, combining extractive and abstractive methods for concise, accurate results.

February 13, 2025

by Vaibhavi Tiwari

· 2,683 Views · 1 Like

Cloud Security Is a Data Problem

As cloud data evolves, we need to learn how data integration, AI, and machine learning help mitigate risks in complex cloud environments and prevent breaches.

February 12, 2025

by Ryan Henrich

· 3,583 Views · 1 Like

Upcoming DZone Events

This article highlights DZone’s upcoming events, which offer insights into key industry trends and opportunities for professionals to learn, discuss, and grow.

Updated February 12, 2025

by Alanna Lovejoy

· 7,841 Views · 4 Likes

Chat Completion Models vs OpenAI Assistants API

In this article, you will learn the key differences between chat completion (like those provided via the Chat Completions endpoint) and OpenAI's Assistants API.

February 11, 2025

by Mohammed Talib

· 2,994 Views · 1 Like

SQL as the Backbone of Big Data and AI Powerhouses

SQL powers Big Data and AI with tools like BigQuery, remaining a cornerstone of data-driven innovation through its simplicity and adaptability.

February 11, 2025

by Medha Gupta

· 2,486 Views · 1 Like

An In-Depth Guide to Threads in OpenAI Assistants API

Learn how to use OpenAI's Assistants API to manage threads and messages — create, list, retrieve, modify, delete — plus handle files, metadata, and more.

February 10, 2025

by Mohammed Talib

· 4,151 Views · 3 Likes

Explore Open WebUI: Your Offline AI Interface

Discussing Open WebUI, a self-hosted AI interface that runs entirely offline. Learn how to install, configure, and use it with inference engines like Ollama.

February 10, 2025

by Gunter Rotsaert

CORE

· 1,776 Views

Designing AI Multi-Agent Systems in Java

We will design an AI Multi Agent, using Fibry. Being backed by Actors, it allows us to take control the parallelism in great detail.

February 10, 2025

by Luca Venturi

· 6,533 Views · 1 Like

A Guide to Using Amazon Bedrock Prompts for LLM Integration

Easily integrate LLMs into your application, manage prompts effectively and leverage the latest in LLM application development with Amazon Bedrock.

February 7, 2025

by Adit Jamdar

· 5,679 Views

A View on Understanding Non-Human Identities Governance

Rethinking the governance, lifecycles, and interdependencies of your machine identities is essential for eliminating secrets sprawl and reducing your attack surface.

February 7, 2025

by Dwayne McDaniel

· 3,840 Views · 5 Likes

Build an AI Browser Agent With LLMs, Playwright, Browser Use

A guide on how to build an AI browser agent using LLMs, Playwright, and Browser Use to automate web interactions, extract data, and navigate sites efficiently.

February 7, 2025

by Kailash Pathak

CORE

· 6,180 Views · 3 Likes

The Latest AI/ML Topics