30k IKEA items in flat text
Details
- External ID
- 46526809
- Source
- HN
- Company
- —
- Product
- 30k IKEA items in flat text
- Website domain
- huggingface.co
- Launched
- Jan. 7, 2026
- Cohort
- —
- Upvotes
- 55
- Upvotes percentile
- 0.8155467720685112
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
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/commercetxtHappy to answer questions about the conversion logic!
Enrichment
- Theme
- e-commerce operations and data utilities
- Vertical
- Retail & commerce
- Function
- Marketplace
- Audience
- B2C
- AI stance
- Not AI
- Project type
- Hobby / open-source project
- Normalized one-liner
- ikea product catalog in text format
- Manually corrected
- False
Could you build this?
Yes This is simply an ETL script that converts an existing open dataset into formatted plain text/markdown and publishes it to Hugging Face.
Discussion
20 comments analyzed.
Competitors mentioned: JSON-LD, UCP (Unified Commerce Platform), TaskRabbit
Concerns raised: Unclear use case - why less-technical people need to access machine-readable format, Requires parsing full DOM for metadata extraction vs. efficient discovery, GET requests with body not standard practice; POST more conventional
Feature requests: Support for encrypted parameters by default, Better handling of arrays in query strings
Competitors
Other products that read as similar to this one — 26 launches clear the similarity bar, closest 8 shown.
Attention rank: #3 of 27 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 54 days after the earliest competitor.
- CommerceTXT · hn · 2025-12-16 · 20 upvotes · similarity 0.46
- Design Studio by Monday Merch · ph · 2026-09-11 · 92 upvotes · similarity 0.39
- IKEA Complexity Index · hn · 2026-07-18 · 179 upvotes · similarity 0.37
- FlatStock · ph · 2026-09-23 · 2 upvotes · similarity 0.36
- Knitting Bag · ph · 2026-09-30 · 1 upvotes · similarity 0.35
- Infinite canvas product search and decision making · hn · 2025-11-14 · 8 upvotes · similarity 0.35
- LineSheetFlow · ph · 2026-09-14 · 2 upvotes · similarity 0.34
- Fashionme · ph · 2026-09-18 · 1 upvotes · similarity 0.34
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a marketplace tool for Horizontal yet.