{"record":{"id":"e31653f2267fedec","repo":"microsoft/semantic-kernel","slug":"the-amazon-bedrock-text-embedding-model-id-is-miss","errorCode":null,"errorMessage":"The Amazon Bedrock Text Embedding Model ID is missing.","messagePattern":"The Amazon Bedrock Text Embedding Model ID is missing\\.","errorType":"exception","errorClass":"ServiceInitializationError","httpStatus":null,"severity":"error","filePath":"python/semantic_kernel/connectors/ai/bedrock/services/bedrock_text_embedding.py","lineNumber":71,"sourceCode":"            model_provider: The Bedrock model provider to use.\n            service_id: The Service ID for the text embedding service.\n            runtime_client: The Amazon Bedrock runtime client to use.\n            client: The Amazon Bedrock client to use.\n            env_file_path: The path to the .env file to load settings from.\n            env_file_encoding: The encoding of the .env file.\n        \"\"\"\n        try:\n            bedrock_settings = BedrockSettings(\n                embedding_model_id=model_id,\n                model_provider=model_provider,\n                env_file_path=env_file_path,\n                env_file_encoding=env_file_encoding,\n            )\n        except ValidationError as e:\n            raise ServiceInitializationError(\"Failed to initialize the Amazon Bedrock Text Embedding Service.\") from e\n\n        if bedrock_settings.embedding_model_id is None:\n            raise ServiceInitializationError(\"The Amazon Bedrock Text Embedding Model ID is missing.\")\n\n        super().__init__(\n            ai_model_id=bedrock_settings.embedding_model_id,\n            service_id=service_id or bedrock_settings.embedding_model_id,\n            runtime_client=runtime_client,\n            client=client,\n            bedrock_model_provider=bedrock_settings.model_provider,\n        )\n\n    @override\n    async def generate_embeddings(\n        self,\n        texts: list[str],\n        settings: \"PromptExecutionSettings | None\" = None,\n        **kwargs: Any,\n    ) -> ndarray:\n        if not settings:\n            settings = BedrockEmbeddingPromptExecutionSettings()","sourceCodeStart":53,"sourceCodeEnd":89,"githubUrl":"https://github.com/microsoft/semantic-kernel/blob/c028a0c7dc4f0814cdcbaba9d998f187a41197bf/python/semantic_kernel/connectors/ai/bedrock/services/bedrock_text_embedding.py#L53-L89","documentation":"Raised during BedrockTextEmbedding construction when BedrockSettings parses but embedding_model_id resolves to None. The embedding service needs a concrete embedding model id; without one it cannot target a model for generate_embeddings.","triggerScenarios":"Calling BedrockTextEmbedding() without model_id and no BEDROCK embedding model id in the environment, or providing only model_provider without a resolvable embedding_model_id.","commonSituations":"Forgetting to pass model_id; expecting env to provide it but it is unset; constructing from provider only.","solutions":["Pass a valid embedding model_id explicitly.","Set the relevant BEDROCK embedding model env var if configured.","Always supply model_id even when model_provider is given."],"exampleFix":"# before\nservice = BedrockTextEmbedding()  # no model id → error\n\n# after\nservice = BedrockTextEmbedding(model_id=\"amazon.titan-embed-text-v2:0\")","handlingStrategy":"validation","validationCode":"assert model_id, \"An embedding model_id is required for BedrockTextEmbedding\"\nservice = BedrockTextEmbedding(model_id=model_id)","typeGuard":"def has_embedding_model_id(model_id) -> bool:\n    return bool(model_id)","tryCatchPattern":"from semantic_kernel.exceptions import ServiceInitializationError\ntry:\n    service = BedrockTextEmbedding(model_id=model_id)\nexcept ServiceInitializationError as e:\n    if \"Embedding Model ID\" in str(e):\n        service = BedrockTextEmbedding(model_id=\"amazon.titan-embed-text-v2:0\")","preventionTips":["Always pass a concrete embedding model_id.","Seed model config in env for CI.","Don't rely on provider-only construction."],"tags":["bedrock","configuration","service-init","model-id","embeddings","python"],"backgroundTag":null,"analyzedSha":"c028a0c7dc4f0814cdcbaba9d998f187a41197bf","analyzedAt":"2026-08-13T13:48:05.040Z","schemaVersion":2},"datasetVersion":"2026-08-13T14:17:21.547Z"}