fix(vertex_ai.py): fix exception mapping for vertex ai

docs/my-website/docs/proxy_server.md

@@ -1,7 +1,7 @@
 import Tabs from '@theme/Tabs';
 import TabItem from '@theme/TabItem';
 
-# Local OpenAI Proxy Server
+# [OLD PROXY 👉 [**NEW** proxy here](./simple_proxy.md)] Local OpenAI Proxy Server
 
 A fast, and lightweight OpenAI-compatible server to call 100+ LLM APIs. 
 

litellm/llms/vertex_ai.py

@@ -73,7 +73,8 @@ def completion(
     try:
         import vertexai
     except:
-        raise Exception("vertexai import failed please run `pip install google-cloud-aiplatform`")
+        raise VertexAIError(status_code=400,message="vertexai import failed please run `pip install google-cloud-aiplatform`")
+    try: 
         from vertexai.preview.language_models import ChatModel, CodeChatModel, InputOutputTextPair
         from vertexai.language_models import TextGenerationModel, CodeGenerationModel
 
@@ -160,6 +161,8 @@ def completion(
             )
         model_response.usage = usage
         return model_response
+    except Exception as e: 
+        raise VertexAIError(status_code=500, message=str(e))
 
 
 def embedding():

litellm/tests/test_exceptions.py

@@ -64,7 +64,7 @@ def test_context_window_with_fallbacks(model):
 
 # for model in litellm.models_by_provider["bedrock"]:
 #     test_context_window(model=model)
-# test_context_window(model="command-nightly")
+# test_context_window(model="chat-bison")
 # test_context_window_with_fallbacks(model="command-nightly")
 # Test 2: InvalidAuth Errors
 @pytest.mark.parametrize("model", models)

litellm/utils.py

@@ -3816,6 +3816,23 @@ def exception_type(
                         llm_provider="vertex_ai",
                         response=original_exception.response
                     )
+                if hasattr(original_exception, "status_code"):
+                    if original_exception.status_code == 400:
+                        exception_mapping_worked = True
+                        raise BadRequestError(
+                            message=f"VertexAIException - {error_str}",
+                            model=model,
+                            llm_provider="vertex_ai",
+                            response=original_exception.response
+                        )
+                    if original_exception.status_code == 500: 
+                        exception_mapping_worked = True
+                        raise APIError(
+                            message=f"VertexAIException - {error_str}",
+                            model=model,
+                            llm_provider="vertex_ai",
+                            request=original_exception.request
+                        )
             elif custom_llm_provider == "palm":
                 if "503 Getting metadata" in error_str:
                     # auth errors look like this