{"record":{"id":"7e3031915aca6e7c","repo":"BerriAI/litellm","slug":"google-cloud-sdk-not-found-install-it-with-pip-i","errorCode":null,"errorMessage":"Google Cloud SDK not found. Install it with: pip install 'litellm[google]' or pip install google-cloud-aiplatform","messagePattern":"Google Cloud SDK not found\\. Install it with: pip install 'litellm\\[google\\]' or pip install google-cloud-aiplatform","errorType":"exception","errorClass":"ImportError","httpStatus":null,"severity":"error","filePath":"litellm/llms/vertex_ai/vertex_ai_aws_wif.py","lineNumber":69,"sourceCode":"\n    @staticmethod\n    def credentials_from_explicit_aws(json_obj, aws_params, scopes):\n        \"\"\"\n        Create GCP credentials using explicit AWS credentials for WIF.\n\n        Uses BaseAWSLLM to obtain AWS credentials (via STS AssumeRole, profile,\n        static keys, etc.), then wraps them in a custom AwsSecurityCredentialsSupplier\n        so that google-auth bypasses the EC2 metadata service.\n\n        Args:\n            json_obj: The WIF credential JSON dict (contains audience, token_url, etc.)\n            aws_params: Dict of aws_* params extracted from json_obj\n            scopes: OAuth scopes for the GCP credentials\n        \"\"\"\n        try:\n            from google.auth import aws\n        except ImportError:\n            raise ImportError(GOOGLE_IMPORT_ERROR_MESSAGE)\n\n        from litellm.llms.bedrock.base_aws_llm import BaseAWSLLM\n        from litellm.llms.vertex_ai.aws_credentials_supplier import (\n            AwsCredentialsSupplier,\n        )\n\n        # Validate region first — required for the GCP token exchange.\n        # Check before get_credentials() to avoid unnecessary AWS API calls\n        # (e.g. STS AssumeRole) on misconfiguration.\n        aws_region: Final = aws_params.get(\"aws_region_name\")\n        if not aws_region:\n            raise ValueError(\n                \"aws_region_name is required in the WIF credential JSON \"\n                \"when using explicit AWS authentication. Add \"\n                '\"aws_region_name\": \"<your-region>\" to your credential file.'\n            )\n\n        # Build a credentials provider that re-resolves AWS creds on each call.","sourceCodeStart":51,"sourceCodeEnd":87,"githubUrl":"https://github.com/BerriAI/litellm/blob/77b7c6c40c0c5aa5fbcb1d6a1825ac39ca8829b8/litellm/llms/vertex_ai/vertex_ai_aws_wif.py#L51-L87","documentation":"ImportError sentinel from the Vertex AI AWS workload-identity-federation path: google.auth is not installed (or lacks the aws module), so GCP credentials cannot be created from AWS credentials. The message names the pip extra that supplies the SDK.","triggerScenarios":"Thrown at litellm/llms/vertex_ai/vertex_ai_aws_wif.py:69 when the library encounters an invalid state.","commonSituations":"See trigger scenarios.","solutions":["Install the Google Cloud dependencies: pip install 'litellm[google]' or pip install google-cloud-aiplatform.","Verify the installation succeeded in the same Python environment running litellm."],"exampleFix":null,"handlingStrategy":"try-catch","validationCode":null,"typeGuard":null,"tryCatchPattern":null,"preventionTips":[],"tags":[],"backgroundTag":null,"analyzedSha":"77b7c6c40c0c5aa5fbcb1d6a1825ac39ca8829b8","analyzedAt":"2026-08-18T11:44:31.656Z","contentChangedAt":null,"schemaVersion":2},"datasetVersion":"2026-09-14T05:17:10.506Z"}