# Best way to deploy using open source huggingface embeddings?

**URL:** https://community.pinecone.io/t/best-way-to-deploy-using-open-source-huggingface-embeddings/3397
**Category:** Support
**Tags:** sentence-transformer, embeddings
**Created:** [October 14, 2023, 2:13pm UTC](https://community.pinecone.io/t/best-way-to-deploy-using-open-source-huggingface-embeddings/3397 "2023-10-14T14:13:44Z")
**Posts on this page:** 3
**Page:** 1

<div class="post-metadata">

### Author: ![burberg92](https://sea2.discourse-cdn.com/flex020/user_avatar/community.pinecone.io/burberg92/32/1519_2.png) [@burberg92](https://community.pinecone.io/u/burberg92)
#### Post date: [October 14, 2023, 2:13pm UTC](https://community.pinecone.io/t/best-way-to-deploy-using-open-source-huggingface-embeddings/3397/1 "2023-10-14T14:13:44Z")

</div>

In an application where users constantly upload documents, generating embeddings would be one of the biggest cost if using paid embeddings such as openai’s embedding. Using open source embeddings would be free but I am wondering on the best way to deploy using huggingface embeddings without degrading user experience too much. Any recommendations are appreciated.

---

<div class="post-metadata">

### Author: ![gdj0nes](https://sea2.discourse-cdn.com/flex020/user_avatar/community.pinecone.io/gdj0nes/32/223_2.png) [@gdj0nes](https://community.pinecone.io/u/gdj0nes)
#### Post date: [October 14, 2023, 2:35pm UTC](https://community.pinecone.io/t/best-way-to-deploy-using-open-source-huggingface-embeddings/3397/2 "2023-10-14T14:35:44Z")

</div>

A smaller model that can run on a CPU may be an option. SentenceTransformers has a list of models including their [inference speed](https://www.sbert.net/docs/pretrained_models.html#model-overview). The [intfloat/e5-small-v2 · Hugging Face](https://huggingface.co/intfloat/e5-small-v2) is a new small model. One option for deployment is HF’s [Inference Endpoints](https://docs.pinecone.io/docs/hugging-face-endpoints).

Hope this helps!

---

<div class="post-metadata">

### Author: ![system](https://us1.discourse-cdn.com/flex020/uploads/pinecone/original/1X/d16664eba369eeee623700cf12feab5562b37eaf.jpeg) [@system](https://community.pinecone.io/u/system)
#### Post date: [October 15, 2023, 2:35pm UTC](https://community.pinecone.io/t/best-way-to-deploy-using-open-source-huggingface-embeddings/3397/3 "2023-10-15T14:35:52Z")

</div>

This topic was automatically closed 24 hours after the last reply. New replies are no longer allowed.
