# Problemi con gli embeddings (argomenti correlati diventano troppo costosi)

**URL:** <https://meta.discourse.org/t/something-bad-with-embeddings-related-topics-getting-too-costly/340345>\
**Category:** Bug\
**Tags:** ai, related-topics\
**Created:** [4 Dicembre 2024, 11:40am UTC](https://meta.discourse.org/t/something-bad-with-embeddings-related-topics-getting-too-costly/340345 "2024-12-04T11:40:26Z")\
**Posts on this page:** 1\
**Showing post:** 21

<div class="post-metadata">

**Author:** ![Falco](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/falco/32/179432_2.png) [@Falco](https://meta.discourse.org/u/Falco)\
**Post date:** [5 Dicembre 2024, 7:12pm UTC](https://meta.discourse.org/t/something-bad-with-embeddings-related-topics-getting-too-costly/340345/21 "2024-12-05T19:12:04Z")

</div>

> [@Don](#):
>
> Ho aggiornato il mio sito

Abbiamo unito un’altra correzione 5 ore fa, per favore aggiorna di nuovo.

> <https://github.com/discourse/discourse-ai/pull/1002>
>
> I'm trying to solve two issues here:
> 
> 1. Using \`find\_in\_batches\` or \`find\_each…\` will ignore the limit because it relies on it to specify a batch size.
> 2. We need to individually apply the limit on each step since \`rebaked\` gets bigger every time we process a batch.

Dopo di che, per favore fammi sapere come sta andando il tasso.

cc @Jagster.

---

_[View the full topic](https://meta.discourse.org/t/something-bad-with-embeddings-related-topics-getting-too-costly/340345)._