Merge pull request #4706 from BerriAI/litellm_retry_after

Return `retry-after` header for rate limited requests
BerriAI · Jul 14, 2024 · d0fb685 · d0fb685
2 parents 4d7d650 + de8230e
commit d0fb685
Show file tree

Hide file tree

Showing 7 changed files with 93 additions and 22 deletions.
diff --git a/litellm/proxy/_experimental/out/404.html b/litellm/proxy/_experimental/out/404.html
diff --git a/litellm/proxy/_experimental/out/model_hub.html b/litellm/proxy/_experimental/out/model_hub.html
diff --git a/litellm/proxy/_experimental/out/onboarding.html b/litellm/proxy/_experimental/out/onboarding.html
diff --git a/litellm/proxy/_types.py b/litellm/proxy/_types.py
@@ -1624,11 +1624,17 @@ def __init__(
         type: str,
         param: Optional[str],
         code: Optional[int],
+        headers: Optional[Dict[str, str]] = None,
     ):
         self.message = message
         self.type = type
         self.param = param
         self.code = code
+        if headers is not None:
+            for k, v in headers.items():
+                if not isinstance(v, str):
+                    headers[k] = str(v)
+        self.headers = headers or {}
 
         # rules for proxyExceptions
         # Litellm router.py returns "No healthy deployment available" when there are no deployments available