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.

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.

At least I have interrupted your doomscrolling with some cuteness!

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