Maria Khalusova

A tiny bit of mirroring? :)

PS: That said, I’ll probably still keep an eye on what’s happening and may even share some posts every now and then. I’ve got a lot of thoughts on RAG, data processing, LLMs/VLMs, etc., so I likely won’t disappear fully.

The work will still be here when I return. The AI won’t slow down, but also a couple of months won’t make a dent in the field. This moment, however, this chance to be fully present with my family? That’s something I don’t want to miss.

And even more grateful to work with a team that’s so supportive. Stepping away from work, especially in a field moving at warp speed, can feel counterintuitive. But for me, it’s a way to reconnect with what matters most.

Kids won’t be kids forever, and mine are getting ever so close to becoming teenagers. Now is time I know I’ll never get back.
I’m incredibly grateful to be in a place, both professionally and personally, where this is possible.

Next week, I’m stepping away for a couple of months to take a sabbatical and spend time with my kids. I’m not burnt out. I’m following my own advice: do the thing you’ll regret not doing when you’re old.

Things move fast in AI. Every week brings new models, new capabilities, or new ideas to chase. It’s exciting, but also easy to get swept up in the pace and forget to pause, to touch grass, to zoom out and see the bigger picture.
🧵

RAG exists to solve different problems across varied domains. Understand the problem you’re solving and look at your data.

Once you have some answers to these, you can get further into the technical weeds and experiment with chunking to find an optimal size.
Bottom line, however, is - there's no universal "best" chunk size.

* How much context do you typically need to retrieve to satisfy a typical query? Simple facts may only require a sentence or two. Creative tasks may require larger context. Analytical queries may need a whole bunch of supporting evidence.

They all vary in structure, style, and length.
* What is your use case? Are you trying to answer questions with specific facts? Are you gathering multiple documents to summarize for a report? Do you pull from transcripts and need to preserve speaker attribution?

Same goes for chunking. The “best” chunk size depends on a range of factors, and without those, the question is incomplete.
Here are some of the questions to ask instead:
* What does your data look like? Financial statements, technical manuals, customer support transcripts are not the same.

Asking “What is the best chunk size for RAG?” without any additional context is like asking, “What’s the best thing to wear?” Wear where? What’s the weather like? What size are you? Are you going to a wedding or hiking a trail? There’s no single answer that works for every situation.

🧵

Do the thing that you will regret not doing when you're old.

I went to check what new courses deeplearning.ai has, and was pleasantly surprised to see that the short course Marc Sun, Younes Belkada, and I have built over a year ago is still featured as one of the Top Rated courses 😍

At least I have interrupted your doomscrolling with some cuteness!

I'm taking this whole developer becoming a farmer dream way too far, am I?

If you've been prioritizing urgent work,
make sure to prioritize important work.

How anyone can like peanut butter is beyond me.

Similar ≠ relevant

Level Up Your GenAI Apps: Overview of Advanced RAG Techniques – Unstructured Explore advanced RAG retrieval techniques—including re-ranking, hybrid search, metadata filtering, and Agentic RAG—that go beyond basic vector similarity to deliver more relevant, high-precision resul...

Part 2 is a high-level overview of advanced RAG techniques: unstructured.io/blog/level-u...

Nothing starts a Wednesday morning quite like your dog getting sprayed by a skunk 🤢

I have some epic plans for this summer and none of you’ll be able to guess what they are.

Level Up Your GenAI Apps: RAG Beyond the Basics – Unstructured Learn why naive implementations fall short—and how smarter data preprocessing lays the foundation for reliable, high-performance RAG.

I'm starting a series of blog posts on RAG beyond the basic set up. In the first part, we're setting the stage. Why naive RAG is not enough, and how a lot of the issues can be traced back to data processing choices.
Part 1: unstructured.io/blog/level-u...

What you're not changing, you're choosing.
This is a gentle reminder for the next time you're prioritizing a cool new shiny thing over building the foundation or addressing tech debt.

Word of the day seems to be "sycophantic".
Thanks AI community for increasing my vocabulary :)

32 pages - is it still a blog or do I call it a book now?

you’re doing the work. You’re still making decisions, solving problems, and putting together something useful.

Coding with AI only becomes “vibe coding” if you’re not paying attention or care to what you or your tools are doing.

good code. Are we now repeating the same sentiment but with LLMs?

AI is just another tool - like a refactoring feature in the IDE or a debugger. Debugger doesn’t find the issue - you do, faster with its help. So does AI help you work faster or more efficiently, but at the end of the day,

Though there used to be people saying things along the lines of “You’re not a real programmer if you don't code without your IDE’s fancy features!" or "True devs only need Notepad and a terminal”. Surely, we’ve long moved past that. It doesn't matter what tools you are using - it's about writing