-
Bug
-
Resolution: Unresolved
-
Undefined
-
None
-
None
-
None
-
False
-
-
False
-
-
Description of problem:
Sometimes when using Ollama and LS, the request times out, this is because Ollama cannot handle a lot of models and may need a few seconds to generate responses.
We had this discussion in the thread about adding timeouts to the LS backed to requests to deal with this.
Additional info (Such as Logs, Screenshots, etc):