This is a cache of https://developer.ibm.com/technologies/rag/. It is a snapshot of the page as it appeared on 2026-02-17T06:15:41.915+0000.
Retrieval-augmented generation (RAG) - IBM Developer
IBM Developer

Retrieval-augmented generation (RAG)

Improve the quality of LLM-generated responses

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.

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.

Build a RAG-powered Markdown documentation assistant

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.

How the ColBERT re-ranker model in a RAG system works
1–12 of 38 items
of 4 pages