I'm using open-webui for ollama's web pages, but would like to get a faster response time. #1234

New Issue

2025-11-11T14:40:44-06:00

GiteaMirror commented

2025-11-11 14:40:44 -06:00

Originally created by @BA7LWN on GitHub (Jun 12, 2024).

To preload the mistral model using the generate endpoint, use:

curl http://localhost:11434/api/generate -d '{"model": "mistral"}'

To use the chat completions endpoint, use:

curl http://localhost:11434/api/chat -d '{"model": "mistral"}'

I want to know which one I should choose to get faster response time

Originally created by @BA7LWN on GitHub (Jun 12, 2024). ### To preload the mistral model using the generate endpoint, use: ```curl http://localhost:11434/api/generate -d '{"model": "mistral"}'``` ### To use the chat completions endpoint, use: ```curl http://localhost:11434/api/chat -d '{"model": "mistral"}'``` ### I want to know which one I should choose to get faster response time

GiteaMirror closed this issue

2025-11-11 14:40:44 -06:00

GiteaMirror referenced this issue

2026-04-19 19:19:47 -05:00

[GH-ISSUE #1234] deploying ollama web ui from helm chart with argo cd never sync #12407

GiteaMirror referenced this issue

2026-04-25 02:42:16 -05:00

[GH-ISSUE #1234] deploying ollama web ui from helm chart with argo cd never sync #27935

GiteaMirror referenced this issue

2026-05-05 11:55:44 -05:00

[GH-ISSUE #1234] deploying ollama web ui from helm chart with argo cd never sync #51072

GiteaMirror referenced this issue