From b987d99486059b1b2b090ac66e5aeee25cfe0145 Mon Sep 17 00:00:00 2001
From: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Date: Sat, 21 Sep 2024 18:00:18 -0700
Subject: [PATCH] handle hf rate limit error

---
 litellm/tests/test_text_completion.py | 3 +++
 litellm/utils.py                      | 8 ++++++++
 2 files changed, 11 insertions(+)

diff --git a/litellm/tests/test_text_completion.py b/litellm/tests/test_text_completion.py
index e6a4a0499cc..7e599012eb4 100644
--- a/litellm/tests/test_text_completion.py
+++ b/litellm/tests/test_text_completion.py
@@ -3951,6 +3951,9 @@ def test_completion_hf_prompt_array():
         print(response.choices)
         assert len(response.choices) == 2
         # response_str = response["choices"][0]["text"]
+    except litellm.RateLimitError:
+        print("got rate limit error from hugging face... passsing")
+        return
     except Exception as e:
         print(str(e))
         if "is currently loading" in str(e):
diff --git a/litellm/utils.py b/litellm/utils.py
index 2bb5e15296d..2b97e9d71aa 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -7455,6 +7455,14 @@ def exception_type(
                         model=model,
                         response=original_exception.response,
                     )
+                elif "Rate limit reached" in error_str:
+                    exception_mapping_worked = True
+                    raise RateLimitError(
+                        message=error_str,
+                        llm_provider="huggingface",
+                        model=model,
+                        response=original_exception.response,
+                    )
                 if hasattr(original_exception, "status_code"):
                     if original_exception.status_code == 401:
                         exception_mapping_worked = True