Originally created by @buroa on GitHub (Apr 11, 2024).
Example: https://github.com/UKPLab/sentence-transformers/blob/master/examples/applications/computing-embeddings/computing_embeddings_multi_gpu.py
why though, if you actually cared about performance you should be using proper embeddings inference like HF text-embedding and then connecting to it as an OpenAI endpoint, open-webui already supports custom OpenAI endpoints.
Or you could connect everything through litellm which also allows you to configure embedding endpoints and model endpoints all in one place.
@FarisHijazi commented on GitHub (Mar 19, 2025):
why though, if you actually cared about performance you should be using proper embeddings inference like [HF text-embedding](https://github.com/huggingface/text-embeddings-inference) and then connecting to it as an OpenAI endpoint, open-webui already supports custom OpenAI endpoints.
Or you could connect everything through litellm which also allows you to configure embedding endpoints and model endpoints all in one place.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @buroa on GitHub (Apr 11, 2024).
Example: https://github.com/UKPLab/sentence-transformers/blob/master/examples/applications/computing-embeddings/computing_embeddings_multi_gpu.py
@FarisHijazi commented on GitHub (Mar 19, 2025):
why though, if you actually cared about performance you should be using proper embeddings inference like HF text-embedding and then connecting to it as an OpenAI endpoint, open-webui already supports custom OpenAI endpoints.
Or you could connect everything through litellm which also allows you to configure embedding endpoints and model endpoints all in one place.