# Settings for Hugging Face bge-large-en embeddings? -\> RAG bots unresponsive!

**URL:** https://meta.discourse.org/t/settings-for-hugging-face-bge-large-en-embeddings-rag-bots-unresponsive/309494
**Category:** Support
**Tags:** embedding, ai, ai-bot
**Created:** [May 26, 2024, 10:54pm UTC](https://meta.discourse.org/t/settings-for-hugging-face-bge-large-en-embeddings-rag-bots-unresponsive/309494 "2024-05-26T22:54:23Z")
**Posts on this page:** 1
**Showing post:** 4

<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: [May 28, 2024, 1:18pm UTC](https://meta.discourse.org/t/settings-for-hugging-face-bge-large-en-embeddings-rag-bots-unresponsive/309494/4 "2024-05-28T13:18:38Z")

</div>

What is the output of running the following commands in a rails console?

```ruby
strategy = DiscourseAi::Embeddings::Strategies::Truncation.new
vector_rep = DiscourseAi::Embeddings::VectorRepresentations::Base.current_representation(strategy)
vector_rep.vector_from("test")

```

Also, our API is designed to work against someone running [GitHub - huggingface/text-embeddings-inference: A blazing fast inference solution for text embeddings models · GitHub](https://github.com/huggingface/text-embeddings-inference) themselves per the [documentation](https://meta.discourse.org/t/self-hosting-embeddings-for-discourseai/290925) so it’s possible that it doesn’t work against the hosted version.

If you provide the backtrace we can look into making it work.

---

_[View the full topic](https://meta.discourse.org/t/settings-for-hugging-face-bge-large-en-embeddings-rag-bots-unresponsive/309494)._