# Suddenly, Rows Can Now Have Meaning **URL:** \ **Category:** Airtable Developers\ **Created:** [March 9, 2023, 1:32pm UTC](https://air.tableforums.com/t/suddenly-rows-can-now-have-meaning/386 "2023-03-09T13:32:19Z")\ **Posts on this page:** 1\ **Showing post:** 8
**Author:** ![bfrench](https://yyz1.discourse-cdn.com/flex029/user_avatar/air.tableforums.com/bfrench/32/46_2.png) [@bfrench](https://air.tableforums.com/u/bfrench)\ **Post date:** [April 12, 2023, 12:57pm UTC](https://air.tableforums.com/t/suddenly-rows-can-now-have-meaning/386/8 "2023-04-12T12:57:29Z")
A few questions from afar, and by that, I mean the mother of another community. 😉 > I wonder if it’ll be possible to create vector representations within Airtable Tables itself using a script. Absolutely. It’s just an API call to an embedding service using an LLM. > … vector DBs are pretty complex. But not as complex as you might think. You can actually use a one-line javascript function to compare two vectors for similarities. This is what a vector DB does at scale. [Read this](https://air.tableforums.com/t/ai-discovering-dupe-similarities-is-just-the-beginning/466). > … if a script can create vector representations of data, I wonder if I could set GPT to search more accurately within Airtable. You can. Should you? That’s another debate. In this [sneak peak to a future post](https://impertinent.substack.com/p/1f6a7b03-53e5-4e20-8143-6cde28d7cc2a) to my paid subscribers, I explore the future of tags as they succumb to the pressure by all vendors to abandon legacy search index architectures and lean into not only semantic search based on embeddings but reasoned search based on field-level attributes. --- _[View the full topic](https://air.tableforums.com/t/suddenly-rows-can-now-have-meaning/386)._