Never miss a brand new edition of , our weekly newsletter featuring a top-notch choice of editors’ picks, deep dives, community news, and more.
It’s very difficult to inform what phase of the hype cycle we’re in for any given AI tool. Things are moving fast: an idea that just weeks ago seemed leading edge can now appear stale, while an approach that was headed towards obsolescence might suddenly make a comeback.
Retrieval-augmented generation is an interesting working example. It dominated conversations a few years ago, quickly attracted a vocal crowd of skeptics, splintered into multiple types and flavors, and inspired a cottage industry of enhancements.
Today, it seems to have landed somewhere midway between exciting and mundane. It’s a method utilized by thousands and thousands of practitioners, but now not producing limitless buzz.
To assist us make sense of the present state of RAG, we turn to our expert authors, who cover a few of its current challenges, use cases, and up to date innovations.
Chunk Size as an Experimental Variable in RAG Systems
We start our exploration with Sarah Schürch‘s enlightening and detailed look into chunking—the means of splitting longer documents into shorter, more easily digestible ones—and its potential effects on the retrieval step in your LLM pipelines.
Retrieval for Time-Series: How Looking Back Improves Forecasts
Can we apply the facility of RAG beyond text? Sara Nobrega introduces us to the emerging idea of retrieval-augmented forecasting for time-series data.Â
When Does Adding Fancy RAG Features Work?
How complex should your RAG systems  be? Ida Silfverskiöld presents her latest testing, aiming to search out the fitting balance between performance, latency, and price.
This Week’s Most-Read Stories
Meet up with three articles that resonated with a large audience prior to now few days.
How LLMs Handle Infinite Context With Finite Memory, by Moulik Gupta
Why Supply Chain is the Best Domain for Data Scientists in 2026 (And How one can Learn It), by Samir Saci
HNSW at Scale: Why Your RAG System Gets Worse because the Vector Database Grows, by Partha Sarkar
Other Really helpful Reads
We hope you explore a few of our other recent must-reads on a various range of topics.
- Federated Learning, Part 1: The Basics of Training Models Where the Data Lives, by Parul Pandey
- YOLOv1 Loss Function Walkthrough: Regression for All, by Muhammad Ardi
- How one can Improve the Performance of Visual Anomaly Detection Models, by Aimira Baitieva
- The Geometry of Laziness: What Angles Reveal About AI Hallucinations, by Javier Marin
- The Best Data Scientists Are At all times Learning, by Jarom Hulet
Contribute to TDS
The previous few months have produced strong results for participants in our Writer Payment Program, so if you happen to’re excited about sending us an article, now’s nearly as good a time as any!
