Retrieval-augmented generation (RAG)

Improve the output of LLMs

An AI framework for retrieving facts from an external knowledge base to ground large language models (LLMs) on the most accurate, up-to-date information and improve the quality of LLM-generated responses.

06 February 2026

Tutorial

Build a custom RAG pipeline with Langflow and watsonx Orchestrate

Learn how to design and deploy a custom RAG workflow using Langflow, pgvector, MCP tools, and watsonx Orchestrate to build scalable document‑aware AI agents, automate enterprise knowledge retrieval, and create production‑ready generative AI applications.

02 February 2026

Article

Protecting AI embedding vectors by using approximate distance preserving encryption for RAG applications

Protect embedding vectors from reverse-engineering attacks using distance-comparison-preserving symmetric encryption (DCPE). Learn to implement DCPE in Java with IronCore Labs Alloy SDK for secure RAG applications.

26 January 2026

Blog post

Develop an AI-powered regulatory compliance assistant with Quarkus, Docling, and LangChain4j

Create an AI‑driven regulatory compliance service and master end‑to‑end document ingestion, metadata enrichment, and vector‑search tuning to deliver precise regulatory insights with Quarkus, Docling, and LangChain4j.

15 December 2025

Tutorial

Developing a voice-first, multi-domain AI assistant using watsonx Orchestrate and Apple Siri

Create intelligent RAG pipelines using Siri shortcuts and watsonx Orchestrate. Upload PDFs, generate API keys, and test queries in minutes.

14 November 2025

Article

Calculating vector embeddings for semantic search and retrieval augmented generation (RAG)

Get started with LangChain4j, a Java library designed to simplify the integration of large language models (LLMs), and learn how to leverage its features for vector embeddings, semantic search, and generative AI applications.

27 October 2025

Tutorial

Build context-aware AI agents with watsonx Orchestrate and Astra DB

Learn to build context-aware AI agents using watsonx Orchestrate and Astra DB with vector search, embeddings, and automated data retrieval.

03 October 2025

Article

The ultimate guide to Elasticsearch

Elasticsearch has transformed from a simple search engine into a powerful AI-powered platform capable of handling diverse search requirements. By mastering indexing, analyzers and hybrid search techniques, developers can build sophisticated search experiences that combine the precision of keyword search with the contextual understanding of semantic search.

01 August 2025

Article

Building an agentic RAG pipeline

The Agentic RAG architecture represents a significant advancement over traditional RAG systems, particularly for advanced technical domains. With the use of specialized agents, hybrid data structures, and intelligent orchestration, we achieved 95% accuracy while significantly improving user experience and operational efficiency.

15 July 2025

Tutorial

Build a RAG-powered Markdown documentation assistant

In this tutorial, build an intelligent documentation assistant that lets you chat with your project’s Markdown documentation (those .md files you see in GitHub, like READMEs). Using JavaScript, and a tool called LangChain, and a local AI system called Ollama, we’ll create a CLI that connects to your GitHub repository, pulls in your documentation, and answers your questions in plain language. It’s like having a super-seasoned teammate who knows every word of your project’s docs, akin to a pair programming buddy in your day to day workflows.

07 July 2025

Tutorial

Build an AI-powered document assistant with Quarkus and LangChain4j

Boost Java productivity with Quarkus and LangChain4j: With this step-by-step tutorial learn how to build a scalable AI document assistant, integrate embeddings, and deploy as a native executable for ultra‑quick startup.

25 June 2025

Article

How the ColBERT re-ranker model in a RAG system works

ColBERT (Contextualized Late Interaction over BERT) is a retrieval model that is designed to strike a balance between the efficiency of traditional methods like BM25 and the accuracy of deep learning models like BERT, an open source deep learning model used for natural language understanding. ColBERT uses the late interaction and MaxSim scoring method to rank the documents based on their relevance to the query. This scoring method furnishes better retrieval because of fine-grained matching and context awareness.

Items per page:

1–12 of 38 items

of 4 pages

Topics

Languages

Products

Open Source

Retrieval-augmented generation (RAG)

Improve the output of LLMs

Build a custom RAG pipeline with Langflow and watsonx Orchestrate

Protecting AI embedding vectors by using approximate distance preserving encryption for RAG applications

Top 10 generative AI articles, tutorials, and learning paths in 2025

Develop an AI-powered regulatory compliance assistant with Quarkus, Docling, and LangChain4j

Developing a voice-first, multi-domain AI assistant using watsonx Orchestrate and Apple Siri

Calculating vector embeddings for semantic search and retrieval augmented generation (RAG)

Build context-aware AI agents with watsonx Orchestrate and Astra DB

The ultimate guide to Elasticsearch

Building an agentic RAG pipeline

Build a RAG-powered Markdown documentation assistant

Build an AI-powered document assistant with Quarkus and LangChain4j

How the ColBERT re-ranker model in a RAG system works