{"record":{"id":"87e4a70d7c01ced2","repo":"BerriAI/litellm","slug":"managed-vector-stores-not-configured-please-ensur","errorCode":null,"errorMessage":"Managed vector stores not configured. Please ensure the proxy is initialized with database support.","messagePattern":"Managed vector stores not configured\\. Please ensure the proxy is initialized with database support\\.","errorType":"http","errorClass":"HTTPException","httpStatus":500,"severity":"error","filePath":"litellm/proxy/vector_store_endpoints/endpoints.py","lineNumber":226,"sourceCode":"    # Check for target_model_names parameter\n    target_model_names: Final = data.pop(\"target_model_names\", None)\n\n    if target_model_names:\n        # Use managed vector stores for multi-model support\n        if isinstance(target_model_names, str):\n            target_model_names_list = [m.strip() for m in target_model_names.split(\",\")]\n        elif isinstance(target_model_names, list):\n            target_model_names_list = target_model_names\n        else:\n            raise HTTPException(\n                status_code=400,\n                detail=\"target_model_names must be a comma-separated string or list of model names\",\n            )\n\n        # Get managed vector stores hook\n        managed_vector_stores: Final[Any] = proxy_logging_obj.get_proxy_hook(\"managed_vector_stores\")\n        if managed_vector_stores is None:\n            raise HTTPException(\n                status_code=500,\n                detail=\"Managed vector stores not configured. Please ensure the proxy is initialized with database support.\",\n            )\n\n        if llm_router is None:\n            raise HTTPException(\n                status_code=500,\n                detail=\"LLM Router not initialized. Ensure models are added to proxy.\",\n            )\n\n        # Create vector store across multiple models\n        response: Final = await managed_vector_stores.acreate_vector_store(\n            create_request=data,\n            llm_router=llm_router,\n            target_model_names_list=target_model_names_list,\n            litellm_parent_otel_span=user_api_key_dict.parent_otel_span,\n            user_api_key_dict=user_api_key_dict,\n        )","sourceCodeStart":208,"sourceCodeEnd":244,"githubUrl":"https://github.com/BerriAI/litellm/blob/77b7c6c40c0c5aa5fbcb1d6a1825ac39ca8829b8/litellm/proxy/vector_store_endpoints/endpoints.py#L208-L244","documentation":"The request asked for managed multi-model vector stores (target_model_names present) but the 'managed_vector_stores' proxy hook is not registered, which happens when the proxy runs without database support. Managed vector stores require DB-backed initialization; either drop target_model_names or start the proxy with a database.","triggerScenarios":"Thrown at litellm/proxy/vector_store_endpoints/endpoints.py:226 when the library encounters an invalid state.","commonSituations":"See trigger scenarios.","solutions":["Initialize the proxy with a database (set DATABASE_URL) so managed vector stores are configured."],"exampleFix":null,"handlingStrategy":"validation","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"}