-
-
Notifications
You must be signed in to change notification settings - Fork 4.2k
Closed
Labels
Description
Might now be a good time to include updated error messages, so that VertexAIException is not the hard-coded error for Gemini API calls (which confused many of us who were initially trying to figure out what broke over the past 24 hr)?
litellm/litellm/litellm_core_utils/exception_mapping_utils.py
Lines 1170 to 1363 in 30c3e7b
| elif ( | |
| custom_llm_provider == "vertex_ai" | |
| or custom_llm_provider == "vertex_ai_beta" | |
| or custom_llm_provider == "gemini" | |
| ): | |
| if ( | |
| "Vertex AI API has not been used in project" in error_str | |
| or "Unable to find your project" in error_str | |
| ): | |
| exception_mapping_worked = True | |
| raise BadRequestError( | |
| message=f"litellm.BadRequestError: VertexAIException - {error_str}", | |
| model=model, | |
| llm_provider="vertex_ai", | |
| response=httpx.Response( | |
| status_code=400, | |
| request=httpx.Request( | |
| method="POST", | |
| url=" https://cloud.google.com/vertex-ai/", | |
| ), | |
| ), | |
| litellm_debug_info=extra_information, | |
| ) | |
| if "400 Request payload size exceeds" in error_str: | |
| exception_mapping_worked = True | |
| raise ContextWindowExceededError( | |
| message=f"VertexException - {error_str}", | |
| model=model, | |
| llm_provider=custom_llm_provider, | |
| ) | |
| elif ( | |
| "None Unknown Error." in error_str | |
| or "Content has no parts." in error_str | |
| ): | |
| exception_mapping_worked = True | |
| raise litellm.InternalServerError( | |
| message=f"litellm.InternalServerError: VertexAIException - {error_str}", | |
| model=model, | |
| llm_provider="vertex_ai", | |
| response=httpx.Response( | |
| status_code=500, | |
| content=str(original_exception), | |
| request=httpx.Request(method="completion", url="https://github.com/BerriAI/litellm"), # type: ignore | |
| ), | |
| litellm_debug_info=extra_information, | |
| ) | |
| elif "API key not valid." in error_str: | |
| exception_mapping_worked = True | |
| raise AuthenticationError( | |
| message=f"{custom_llm_provider}Exception - {error_str}", | |
| model=model, | |
| llm_provider=custom_llm_provider, | |
| litellm_debug_info=extra_information, | |
| ) | |
| elif "403" in error_str: | |
| exception_mapping_worked = True | |
| raise BadRequestError( | |
| message=f"VertexAIException BadRequestError - {error_str}", | |
| model=model, | |
| llm_provider="vertex_ai", | |
| response=httpx.Response( | |
| status_code=403, | |
| request=httpx.Request( | |
| method="POST", | |
| url=" https://cloud.google.com/vertex-ai/", | |
| ), | |
| ), | |
| litellm_debug_info=extra_information, | |
| ) | |
| elif ( | |
| "The response was blocked." in error_str | |
| or "Output blocked by content filtering policy" | |
| in error_str # anthropic on vertex ai | |
| ): | |
| exception_mapping_worked = True | |
| raise ContentPolicyViolationError( | |
| message=f"VertexAIException ContentPolicyViolationError - {error_str}", | |
| model=model, | |
| llm_provider="vertex_ai", | |
| litellm_debug_info=extra_information, | |
| response=httpx.Response( | |
| status_code=400, | |
| request=httpx.Request( | |
| method="POST", | |
| url=" https://cloud.google.com/vertex-ai/", | |
| ), | |
| ), | |
| ) | |
| elif ( | |
| "429 Quota exceeded" in error_str | |
| or "Quota exceeded for" in error_str | |
| or "IndexError: list index out of range" in error_str | |
| or "429 Unable to submit request because the service is temporarily out of capacity." | |
| in error_str | |
| ): | |
| exception_mapping_worked = True | |
| raise RateLimitError( | |
| message=f"litellm.RateLimitError: VertexAIException - {error_str}", | |
| model=model, | |
| llm_provider="vertex_ai", | |
| litellm_debug_info=extra_information, | |
| response=httpx.Response( | |
| status_code=429, | |
| request=httpx.Request( | |
| method="POST", | |
| url=" https://cloud.google.com/vertex-ai/", | |
| ), | |
| ), | |
| ) | |
| elif ( | |
| "500 Internal Server Error" in error_str | |
| or "The model is overloaded." in error_str | |
| ): | |
| exception_mapping_worked = True | |
| raise litellm.InternalServerError( | |
| message=f"litellm.InternalServerError: VertexAIException - {error_str}", | |
| model=model, | |
| llm_provider="vertex_ai", | |
| litellm_debug_info=extra_information, | |
| ) | |
| if hasattr(original_exception, "status_code"): | |
| if original_exception.status_code == 400: | |
| exception_mapping_worked = True | |
| raise BadRequestError( | |
| message=f"VertexAIException BadRequestError - {error_str}", | |
| model=model, | |
| llm_provider="vertex_ai", | |
| litellm_debug_info=extra_information, | |
| response=httpx.Response( | |
| status_code=400, | |
| request=httpx.Request( | |
| method="POST", | |
| url="https://cloud.google.com/vertex-ai/", | |
| ), | |
| ), | |
| ) | |
| if original_exception.status_code == 401: | |
| exception_mapping_worked = True | |
| raise AuthenticationError( | |
| message=f"VertexAIException - {original_exception.message}", | |
| llm_provider=custom_llm_provider, | |
| model=model, | |
| ) | |
| if original_exception.status_code == 404: | |
| exception_mapping_worked = True | |
| raise NotFoundError( | |
| message=f"VertexAIException - {original_exception.message}", | |
| llm_provider=custom_llm_provider, | |
| model=model, | |
| ) | |
| if original_exception.status_code == 408: | |
| exception_mapping_worked = True | |
| raise Timeout( | |
| message=f"VertexAIException - {original_exception.message}", | |
| llm_provider=custom_llm_provider, | |
| model=model, | |
| ) | |
| if original_exception.status_code == 429: | |
| exception_mapping_worked = True | |
| raise RateLimitError( | |
| message=f"litellm.RateLimitError: VertexAIException - {error_str}", | |
| model=model, | |
| llm_provider="vertex_ai", | |
| litellm_debug_info=extra_information, | |
| response=httpx.Response( | |
| status_code=429, | |
| request=httpx.Request( | |
| method="POST", | |
| url=" https://cloud.google.com/vertex-ai/", | |
| ), | |
| ), | |
| ) | |
| if original_exception.status_code == 500: | |
| exception_mapping_worked = True | |
| raise litellm.InternalServerError( | |
| message=f"VertexAIException InternalServerError - {error_str}", | |
| model=model, | |
| llm_provider="vertex_ai", | |
| litellm_debug_info=extra_information, | |
| response=httpx.Response( | |
| status_code=500, | |
| content=str(original_exception), | |
| request=httpx.Request(method="completion", url="https://github.com/BerriAI/litellm"), # type: ignore | |
| ), | |
| ) | |
| if original_exception.status_code == 503: | |
| exception_mapping_worked = True | |
| raise ServiceUnavailableError( | |
| message=f"VertexAIException - {original_exception.message}", | |
| llm_provider=custom_llm_provider, | |
| model=model, | |
| ) | |
| elif custom_llm_provider == "palm" or custom_llm_provider == "gemini": |
Originally posted by @noahkiss in #14563 (comment)