{"record":{"id":"69bd1f2a34d9eae8","repo":"mlflow/mlflow","slug":"this-method-is-not-implemented-for-openaideployme","errorCode":null,"errorMessage":"This method is not implemented for `OpenAIDeploymentClient`.","messagePattern":"This method is not implemented for `OpenAIDeploymentClient`\\.","errorType":"exception","errorClass":"NotImplementedError","httpStatus":null,"severity":"error","filePath":"mlflow/deployments/openai/__init__.py","lineNumber":54,"sourceCode":"\n        client = get_deploy_client(\"openai\")\n        client.predict(\n            endpoint=\"gpt-4o-mini\",\n            inputs={\n                \"messages\": [\n                    {\"role\": \"user\", \"content\": \"Hello!\"},\n                ],\n            },\n        )\n    \"\"\"\n\n    def create_deployment(self, name, model_uri, flavor=None, config=None, endpoint=None):\n        \"\"\"\n        .. warning::\n\n            This method is not implemented for `OpenAIDeploymentClient`.\n        \"\"\"\n        raise NotImplementedError\n\n    def update_deployment(self, name, model_uri=None, flavor=None, config=None, endpoint=None):\n        \"\"\"\n        .. warning::\n\n            This method is not implemented for `OpenAIDeploymentClient`.\n        \"\"\"\n        raise NotImplementedError\n\n    def delete_deployment(self, name, config=None, endpoint=None):\n        \"\"\"\n        .. warning::\n\n            This method is not implemented for `OpenAIDeploymentClient`.\n        \"\"\"\n        raise NotImplementedError\n\n    def list_deployments(self, endpoint=None):","sourceCodeStart":36,"sourceCodeEnd":72,"githubUrl":"https://github.com/mlflow/mlflow/blob/6a27f2decc0b76eb1b54af31849784addb357dbc/mlflow/deployments/openai/__init__.py#L36-L72","documentation":"The OpenAI deployment plugin only supports prediction against OpenAI routes; per-deployment CRUD operations are intentionally unimplemented and raise NotImplementedError. create_deployment has no meaning for OpenAI-backed endpoints.","triggerScenarios":"Calling OpenAIDeploymentClient.create_deployment(name, model_uri[, flavor, config, endpoint]).","commonSituations":"Generic deployment scripts written for the sagemaker plugin reused with target='openai'; attempts to register model URIs as OpenAI deployments.","solutions":["Use create_endpoint/update_endpoint on the OpenAI client (which is how routes are configured), or create the deployment via the MLflow deployments server config.","Use predict() against an existing route.","Catch NotImplementedError and branch per target capability."],"exampleFix":"// before\nclient = mlflow.deployments.get_deploy_client(\"openai\")\nclient.create_deployment(\"gpt-4\", \"models:/gpt-4/1\")\n// after\nclient = mlflow.deployments.get_deploy_client(\"openai\")\nclient.create_endpoint(\"gpt-4-endpoint\", config={\"name\": \"gpt-4\", ...})","handlingStrategy":"validation","validationCode":"if isinstance(client, mlflow.deployments.openai.OpenAIDeploymentClient):\n    raise RuntimeError(\"create_deployment unsupported for openai target; use create_endpoint\")","typeGuard":"def supports_deployment_crud(client):\n    from mlflow.deployments.openai import OpenAIDeploymentClient\n    return not isinstance(client, OpenAIDeploymentClient)","tryCatchPattern":"try:\n    client.create_deployment(name, model_uri)\nexcept NotImplementedError:\n    client.create_endpoint(name, config={...})","preventionTips":["Use endpoint-level APIs for the openai plugin","Branch on deployment target before calling CRUD methods","Read the plugin's method docstrings - unimplemented ones warn explicitly"],"tags":["not-implemented","openai","mlflow-deployments"],"backgroundTag":"method-not-implemented","analyzedSha":"6a27f2decc0b76eb1b54af31849784addb357dbc","analyzedAt":"2026-08-29T20:54:51.419Z","schemaVersion":2},"datasetVersion":"2026-08-29T22:17:34.462Z"}