[Inference API] add rate-limited retries for Elastic Inference Service (elastic#127487)

brendan-jugan-elastic · web-flow · commit 9cb8990553df · 2025-05-01T14:38:11.000-04:00
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elastic/ElasticInferenceServiceResponseHandler.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elastic/ElasticInferenceServiceResponseHandler.java
@@ -40,6 +40,8 @@ protected void checkForFailureStatusCode(Request request, HttpResult result) thr
             throw new RetryException(false, buildError(METHOD_NOT_ALLOWED, request, result));
         } else if (statusCode == 413) {
             throw new ContentTooLargeException(buildError(CONTENT_TOO_LARGE, request, result));
+        } else if (statusCode == 429) {
+            throw new RetryException(true, buildError(RATE_LIMIT, request, result));
         }
 
         throw new RetryException(false, buildError(UNSUCCESSFUL, request, result));

Original file line number	Diff line number	Diff line change
`@@ -40,6 +40,8 @@ protected void checkForFailureStatusCode(Request request, HttpResult result) thr`
`40`	`40`	`throw new RetryException(false, buildError(METHOD_NOT_ALLOWED, request, result));`
`41`	`41`	`} else if (statusCode == 413) {`
`42`	`42`	`throw new ContentTooLargeException(buildError(CONTENT_TOO_LARGE, request, result));`
	`43`	`+ } else if (statusCode == 429) {`
	`44`	`+ throw new RetryException(true, buildError(RATE_LIMIT, request, result));`
`43`	`45`	`}`
`44`	`46`
`45`	`47`	`throw new RetryException(false, buildError(UNSUCCESSFUL, request, result));`