30k IKEA items in flat text
OP here. I took the unofficial IKEA US dataset (originally scraped by jeffreyszhou) and converted all 30,511 products into a flat, markdown-like protocol called CommerceTXT. The goal: See if a flatter structure is more efficient for LLM context windows. The results: - Size: 30k products across 632 categories. - Efficiency: The text version uses ~24% fewer tokens (3.6M saved total) compared to the equivalent minified JSON. - Structure: Files are organized in folders (e.g. /products/category/), which helps with testing hierarchical retrieval routers. The link goes to the dataset…
In plain words
This dataset contains 30,511 IKEA products converted from JSON into CommerceTXT, a flat markdown-like format designed to reduce token usage in large language models. The 3.6 million products span 632 categories organized in hierarchical folders for testing retrieval systems. The text format uses approximately 24% fewer tokens than minified JSON, making it useful for developers and researchers optimizing LLM context windows and experimenting with different data structures for product catalogs.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
OP here. I took the unofficial IKEA US dataset (originally scraped by jeffreyszhou) and converted all 30,511 products into a flat, markdown-like protocol called CommerceTXT. The goal: See if a flatter structure is more efficient for LLM context windows. The results: - Size: 30k products across 632 categories. - Efficiency: The text version uses ~24% fewer tokens (3.6M saved total) compared to the equivalent minified JSON. - Structure: Files are organized in folders (e.g. /products/category/), which helps with testing hierarchical retrieval routers. The link goes to the dataset on Hugging Face which has the full benchmarks. Parser code is here: https://github.com/commercetxt/commercetxt Happy to answer questions about the conversion logic!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
