Mark Pollack

Closing, please reopen if necessary @williamspindox

I'm not sure what we can do to solve this. Seems that you found a (crude) workaround. Closing for now, open to suggestions for a fix.

Thanks for the votes. Will prioritize

Hi. I added comments [here](https://github.com/spring-projects/spring-ai/issues/354#issuecomment-1971456155), I think for 0.8.1 we can make an interim approach before tackling the general problem.

Sorry, i was confusing retry timeout with http timeout. We will address this issue, sorry for the confusion.

Hi. I think we can achieve what is needed but in a different way. The code you added to merge the property `spring.ai.openai.base-url` with `spring.ai.openai.chat.base-url` is already in the code...

I understand the confusion with a constructor that has both a `RestClient.Builder` and a `ClientHttpRequestFactory` I need to think about it more. I would like to have the top level...

Just to update, there are many issues floating around on this topic, i'm trying to reconcile and figure out the best approach.

I found out that the only way to do this on a per-call request is to use the netty infra. https://projectreactor.io/docs/netty/release/reference/index.html#response-timeout https://docs.spring.io/spring-framework/reference/web/webflux-webclient/client-builder.html#webflux-client-builder-reactor-timeout ``` WebClient.create().get() .uri("https://example.org/path") .httpRequest(httpRequest -> { HttpClientRequest reactorRequest...

Closing as model specific images are not going to be provided by ollama. We will pick this up as part of a larger effort to have more CI coverage outside...