I installed a Docker image and used WebUI to associate it with the local server. After I successfully deployed it, for example, I retrieved llama3-7b from the Ollama library and asked questions on the Web-UI interface. If there were any problems, it would take a long time to respond and the generation process would be slow. What is the problem
Originally created by @LyingDoc on GitHub (May 17, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/2334
I installed a Docker image and used WebUI to associate it with the local server. After I successfully deployed it, for example, I retrieved llama3-7b from the Ollama library and asked questions on the Web-UI interface. If there were any problems, it would take a long time to respond and the generation process would be slow. What is the problem
I noticed this as well. My solution was to install Ollama locally and OpenWebUI in docker. This fixed that issue for me. I do not know what causes this issue other than just Ollama not liking the extra layer of virtualization in some setups.
<!-- gh-comment-id:2117456801 -->
@pkeffect commented on GitHub (May 17, 2024):
I noticed this as well. My solution was to install Ollama locally and OpenWebUI in docker. This fixed that issue for me. I do not know what causes this issue other than just Ollama not liking the extra layer of virtualization in some setups.
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 @LyingDoc on GitHub (May 17, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/2334
I installed a Docker image and used WebUI to associate it with the local server. After I successfully deployed it, for example, I retrieved llama3-7b from the Ollama library and asked questions on the Web-UI interface. If there were any problems, it would take a long time to respond and the generation process would be slow. What is the problem
@pkeffect commented on GitHub (May 17, 2024):
I noticed this as well. My solution was to install Ollama locally and OpenWebUI in docker. This fixed that issue for me. I do not know what causes this issue other than just Ollama not liking the extra layer of virtualization in some setups.