In the case of openai embedding, it is very fast because requests are made in parallel. However, when performing embedding through ollama, it is very slow because it waits until one embedding is finished before performing the next one. We therefore request the ability to perform embedding in parallel.
Originally created by @codeMonkey-shin on GitHub (Jul 18, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/3965
In the case of openai embedding, it is very fast because requests are made in parallel. However, when performing embedding through ollama, it is very slow because it waits until one embedding is finished before performing the next one. We therefore request the ability to perform embedding in parallel.
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 @codeMonkey-shin on GitHub (Jul 18, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/3965
In the case of openai embedding, it is very fast because requests are made in parallel. However, when performing embedding through ollama, it is very slow because it waits until one embedding is finished before performing the next one. We therefore request the ability to perform embedding in parallel.