# "Net::HTTPBadResponse" errors on Gemini Embeddings

**URL:** <https://meta.discourse.org/t/net-httpbadresponse-errors-on-gemini-embeddings/296952>\
**Category:** Bug\
**Tags:** ai, related-topics\
**Created:** [February 14, 2024, 9:07pm UTC](https://meta.discourse.org/t/net-httpbadresponse-errors-on-gemini-embeddings/296952 "2024-02-14T21:07:52Z")\
**Posts on this page:** 1\
**Showing post:** 5

<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:** [February 16, 2024, 3:57pm UTC](https://meta.discourse.org/t/net-httpbadresponse-errors-on-gemini-embeddings/296952/5 "2024-02-16T15:57:32Z")

</div>

> [@RBoy](#):
>
> Can I assume that the AI module keeps trying to backfill unprocessed topics indefinitely without any intervention if it hits a limit or fails for whatever reason (e.g. connectivity or loss of authentication)?

Yes

> [@Discourse AI - Related topics](https://meta.discourse.org/t/discourse-ai-related-topics/281807/18):
>
> What else can I do/check here?

What’s the output of running the command below with your API key?

```plaintext
curl https://generativelanguage.googleapis.com/v1beta/models/embedding-001:embedContent?key=API_KEY_GOES_HERE -H 'Content-Type: application/json' -X POST -d '{ "content": { "parts":[{ "text": "Why use Discourse for my online community?"}]}}' 

```

---

_[View the full topic](https://meta.discourse.org/t/net-httpbadresponse-errors-on-gemini-embeddings/296952)._