Timeout Error on /memory Endpoint During OpenAI API request

[sami-bensalah]

After building the services outlined here: https://redhat-developer-demos.github.io/quarkus-tutorial/quarkus-tutorial/18_chains_memory.html

The following error occurs when accessing http://localhost:8080/memory:

io.vertx.core.impl.NoStackTraceTimeoutException: The timeout period of 10000ms has been exceeded while executing POST /v1/chat/completions for server null Resulted in: jakarta.ws.rs.ProcessingException: The timeout period of 10000ms has been exceeded while executing POST /v1/chat/completions for server null at org.jboss.resteasy.reactive.client.impl.InvocationBuilderImpl.unwrap(InvocationBuilderImpl.java:212) at org.jboss.resteasy.reactive.client.impl.InvocationBuilderImpl.method(InvocationBuilderImpl.java:328) at io.quarkiverse.langchain4j.openai.common.OpenAiRestApi$$QuarkusRestClientInterface.blockingChatCompletion(Unknown Source) at io.quarkiverse.langchain4j.openai.common.QuarkusOpenAiClient$3.execute(QuarkusOpenAiClient.java:200) at io.quarkiverse.langchain4j.openai.common.QuarkusOpenAiClient$3.execute(QuarkusOpenAiClient.java:197) at dev.langchain4j.model.openai.OpenAiChatModel.lambda$doChat$3(OpenAiChatModel.java:171) at dev.langchain4j.internal.ExceptionMapper.withExceptionMapper(ExceptionMapper.java:27) at dev.langchain4j.internal.RetryUtils.lambda$withRetryMappingExceptions$1(RetryUtils.java:292) at dev.langchain4j.internal.RetryUtils$RetryPolicy.withRetry(RetryUtils.java:195) at dev.langchain4j.internal.RetryUtils.withRetry(RetryUtils.java:247) at dev.langchain4j.internal.RetryUtils.withRetryMappingExceptions(RetryUtils.java:292) at dev.langchain4j.internal.RetryUtils.withRetryMappingExceptions(RetryUtils.java:276) at dev.langchain4j.model.openai.OpenAiChatModel.doChat(OpenAiChatModel.java:170) at dev.langchain4j.model.chat.ChatLanguageModel.chat(ChatLanguageModel.java:47) at dev.langchain4j.model.chat.ChatLanguageModel_XNMsOaekknG7BdNZ5YSUkjh1SqE_Synthetic_ClientProxy.chat(Unknown Source) at io.quarkiverse.langchain4j.runtime.aiservice.AiServiceMethodImplementationSupport.executeRequest(AiServiceMethodImplementationSupport.java:476) at io.quarkiverse.langchain4j.runtime.aiservice.AiServiceMethodImplementationSupport.executeRequest(AiServiceMethodImplementationSupport.java:485) at io.quarkiverse.langchain4j.runtime.aiservice.AiServiceMethodImplementationSupport.executeRequest(AiServiceMethodImplementationSupport.java:491) at io.quarkiverse.langchain4j.runtime.aiservice.AiServiceMethodImplementationSupport.doImplement(AiServiceMethodImplementationSupport.java:346) at io.quarkiverse.langchain4j.runtime.aiservice.AiServiceMethodImplementationSupport.implement(AiServiceMethodImplementationSupport.java:145) at com.redhat.developers.AssistantWithMemory$$QuarkusImpl.chat(Unknown Source) at com.redhat.developers.AssistantWithMemory$$QuarkusImpl_ClientProxy.chat(Unknown Source) at com.redhat.developers.DeveloperResource.memory(DeveloperResource.java:22) at com.redhat.developers.DeveloperResource$quarkusrestinvoker$memory_0a019baa5a981f3b9c2f00af0857d15163a5d656.invoke(Unknown Source) at org.jboss.resteasy.reactive.server.handlers.InvocationHandler.handle(InvocationHandler.java:29) at io.quarkus.resteasy.reactive.server.runtime.QuarkusResteasyReactiveRequestContext.invokeHandler(QuarkusResteasyReactiveRequestContext.java:141) at org.jboss.resteasy.reactive.common.core.AbstractResteasyReactiveContext.run(AbstractResteasyReactiveContext.java:147) at io.quarkus.vertx.core.runtime.VertxCoreRecorder$15.runWith(VertxCoreRecorder.java:637) at org.jboss.threads.EnhancedQueueExecutor$Task.doRunWith(EnhancedQueueExecutor.java:2675) at org.jboss.threads.EnhancedQueueExecutor$Task.run(EnhancedQueueExecutor.java:2654) at org.jboss.threads.EnhancedQueueExecutor.runThreadBody(EnhancedQueueExecutor.java:1627) at org.jboss.threads.EnhancedQueueExecutor$ThreadBody.run(EnhancedQueueExecutor.java:1594) at org.jboss.threads.DelegatingRunnable.run(DelegatingRunnable.java:11) at org.jboss.threads.ThreadLocalResettingRunnable.run(ThreadLocalResettingRunnable.java:11) at io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base/java.lang.Thread.run(Thread.java:1583)

Works successfully after adding quarkus.langchain4j.openai.timeout=30s to the application.properties file. Could the configuration for the application.properties file be changed to include this line?

[kdubois]

Hi @sami-bensalah, thanks for sharing this issue. Were you using the openai service? It's usually quite fast so I'm surprised it took over 10 seconds to get a response. We do set a 60s timeout in the tool calling chapter when we're using a Ollama, but it might be a good idea to set a timeout on the first instructions too I guess.