Output only. timestamp when this ReasoningEngine was created.
Uses RFC 3339, where generated output will always be Z-normalized and uses 0, 3, 6 or 9 fractional digits. Offsets other than "Z" are also accepted. Examples: "2014-10-02T15:01:23Z", "2014-10-02T15:01:23.045123456Z" or "2014-10-02T15:01:23+05:30".
Output only. timestamp when this ReasoningEngine was most recently updated.
Uses RFC 3339, where generated output will always be Z-normalized and uses 0, 3, 6 or 9 fractional digits. Offsets other than "Z" are also accepted. Examples: "2014-10-02T15:01:23Z", "2014-10-02T15:01:23.045123456Z" or "2014-10-02T15:01:23+05:30".
etag
string
Optional. Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
Customer-managed encryption key spec for a ReasoningEngine. If set, this ReasoningEngine and all sub-resources of this ReasoningEngine will be secured by this key.
Optional. user provided package spec of the ReasoningEngine. Ignored when users directly specify a deployment image through deploymentSpec.first_party_image_override, but keeping the field_behavior to avoid introducing breaking changes.
Optional. Declarations for object class methods in OpenAPI specification format.
agentFramework
string
Optional. The OSS agent framework used to develop the agent. Currently supported values: "google-adk", "langchain", "langgraph", "ag2", "llama-index", "custom".
serviceAccount
string
Optional. The service account that the Reasoning Engine artifact runs as. It should have "roles/storage.objectViewer" for reading the user project's Cloud Storage and "roles/aiplatform.user" for using Vertex extensions. If not specified, the Vertex AI Reasoning Engine service Agent in the project will be used.
Optional. Environment variables to be set with the Reasoning Engine deployment. The environment variables can be updated through the reasoningEngines.patch API.
Optional. Environment variables where the value is a secret in Cloud Secret Manager. To use this feature, add 'Secret Manager Secret Accessor' role (roles/secretmanager.secretAccessor) to AI Platform Reasoning Engine service Agent.
Optional. Configuration for how to perform similarity search on memories. If not set, the Memory Bank will use the default embedding model text-embedding-005.
Required. The model used to generate memories. Format: projects/{project}/locations/{location}/publishers/google/models/{model}.
JSON representation
{"model": string}
SimilaritySearchConfig
Configuration for how to perform similarity search on memories.
Fields
embeddingModel
string
Required. The model used to generate embeddings to lookup similar memories. Format: projects/{project}/locations/{location}/publishers/google/models/{model}.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-21 UTC."],[],[],null,["# REST Resource: projects.locations.reasoningEngines\n\nResource: ReasoningEngine\n-------------------------\n\nReasoningEngine provides a customizable runtime for models to determine which actions to take and in which order.\nFields `name` `string` \nIdentifier. The resource name of the ReasoningEngine. Format: `projects/{project}/locations/{location}/reasoningEngines/{reasoningEngine}`\n`displayName` `string` \nRequired. The display name of the ReasoningEngine.\n`description` `string` \nOptional. The description of the ReasoningEngine.\n`spec` `object (`[ReasoningEngineSpec](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.reasoningEngines#ReasoningEngineSpec)`)` \nOptional. Configurations of the ReasoningEngine\n`createTime` `string (`[Timestamp](https://protobuf.dev/reference/protobuf/google.protobuf/#timestamp)` format)` \nOutput only. timestamp when this ReasoningEngine was created.\n\nUses RFC 3339, where generated output will always be Z-normalized and uses 0, 3, 6 or 9 fractional digits. Offsets other than \"Z\" are also accepted. Examples: `\"2014-10-02T15:01:23Z\"`, `\"2014-10-02T15:01:23.045123456Z\"` or `\"2014-10-02T15:01:23+05:30\"`.\n`updateTime` `string (`[Timestamp](https://protobuf.dev/reference/protobuf/google.protobuf/#timestamp)` format)` \nOutput only. timestamp when this ReasoningEngine was most recently updated.\n\nUses RFC 3339, where generated output will always be Z-normalized and uses 0, 3, 6 or 9 fractional digits. Offsets other than \"Z\" are also accepted. Examples: `\"2014-10-02T15:01:23Z\"`, `\"2014-10-02T15:01:23.045123456Z\"` or `\"2014-10-02T15:01:23+05:30\"`.\n`etag` `string` \nOptional. Used to perform consistent read-modify-write updates. If not set, a blind \"overwrite\" update happens.\n`contextSpec` `object (`[ReasoningEngineContextSpec](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.reasoningEngines#ReasoningEngineContextSpec)`)` \nOptional. Configuration for how Agent Engine sub-resources should manage context.\n`encryptionSpec` `object (`[EncryptionSpec](/vertex-ai/docs/reference/rest/v1beta1/EncryptionSpec)`)` \nCustomer-managed encryption key spec for a ReasoningEngine. If set, this ReasoningEngine and all sub-resources of this ReasoningEngine will be secured by this key.\n`labels` `map (key: string, value: string)` \nLabels for the ReasoningEngine. \n\nReasoningEngineSpec\n-------------------\n\nReasoningEngine configurations\nFields `packageSpec` `object (`[PackageSpec](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.reasoningEngines#PackageSpec)`)` \nOptional. user provided package spec of the ReasoningEngine. Ignored when users directly specify a deployment image through `deploymentSpec.first_party_image_override`, but keeping the field_behavior to avoid introducing breaking changes.\n`deploymentSpec` `object (`[DeploymentSpec](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.reasoningEngines#DeploymentSpec)`)` \nOptional. The specification of a Reasoning Engine deployment.\n`classMethods[]` `object (`[Struct](https://protobuf.dev/reference/protobuf/google.protobuf/#struct)` format)` \nOptional. Declarations for object class methods in OpenAPI specification format.\n`agentFramework` `string` \nOptional. The OSS agent framework used to develop the agent. Currently supported values: \"google-adk\", \"langchain\", \"langgraph\", \"ag2\", \"llama-index\", \"custom\".\n`serviceAccount` `string` \nOptional. The service account that the Reasoning Engine artifact runs as. It should have \"roles/storage.objectViewer\" for reading the user project's Cloud Storage and \"roles/aiplatform.user\" for using Vertex extensions. If not specified, the Vertex AI Reasoning Engine service Agent in the project will be used. \n\nPackageSpec\n-----------\n\nuser provided package spec like pickled object and package requirements.\nFields `pickleObjectGcsUri` `string` \nOptional. The Cloud Storage URI of the pickled python object.\n`dependencyFilesGcsUri` `string` \nOptional. The Cloud Storage URI of the dependency files in tar.gz format.\n`requirementsGcsUri` `string` \nOptional. The Cloud Storage URI of the `requirements.txt` file\n`pythonVersion` `string` \nOptional. The Python version. Currently support 3.8, 3.9, 3.10, 3.11. If not specified, default value is 3.10. \n\nDeploymentSpec\n--------------\n\nThe specification of a Reasoning Engine deployment.\nFields `env[]` `object (`[EnvVar](/vertex-ai/docs/reference/rest/v1beta1/EnvVar)`)` \nOptional. Environment variables to be set with the Reasoning Engine deployment. The environment variables can be updated through the reasoningEngines.patch API.\n`secretEnv[]` `object (`[SecretEnvVar](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.reasoningEngines#SecretEnvVar)`)` \nOptional. Environment variables where the value is a secret in Cloud Secret Manager. To use this feature, add 'Secret Manager Secret Accessor' role (roles/secretmanager.secretAccessor) to AI Platform Reasoning Engine service Agent.\n`pscInterfaceConfig` `object (`[PscInterfaceConfig](/vertex-ai/docs/reference/rest/v1beta1/PscInterfaceConfig)`)` \nOptional. Configuration for PSC-I.\n`resourceLimits` `map (key: string, value: string)` \nOptional. Resource limits for each container. Only 'cpu' and 'memory' keys are supported. Defaults to {\"cpu\": \"4\", \"memory\": \"4Gi\"}.\n\n- The only supported values for CPU are '1', '2', '4', '6' and '8'. For more information, go to \u003chttps://cloud.google.com/run/docs/configuring/cpu\u003e.\n- The only supported values for memory are '1Gi', '2Gi', ... '32 Gi'.\n- For required cpu on different memory values, go to \u003chttps://cloud.google.com/run/docs/configuring/memory-limits\u003e\n`minInstances` `integer` \nOptional. The minimum number of application instances that will be kept running at all times. Defaults to 1. Range: \\[0, 10\\].\n`maxInstances` `integer` \nOptional. The maximum number of application instances that can be launched to handle increased traffic. Defaults to 100. Range: \\[1, 1000\\].\n\nIf VPC-SC or PSC-I is enabled, the acceptable range is \\[1, 100\\].\n`containerConcurrency` `integer` \nOptional. Concurrency for each container and agent server. Recommended value: 2 \\* cpu + 1. Defaults to 9. \n\nSecretEnvVar\n------------\n\nRepresents an environment variable where the value is a secret in Cloud Secret Manager.\nFields `name` `string` \nRequired. name of the secret environment variable.\n`secretRef` `object (`[SecretRef](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.reasoningEngines#SecretRef)`)` \nRequired. Reference to a secret stored in the Cloud Secret Manager that will provide the value for this environment variable. \n\nSecretRef\n---------\n\nReference to a secret stored in the Cloud Secret Manager that will provide the value for this environment variable.\nFields `secret` `string` \nRequired. The name of the secret in Cloud Secret Manager. Format: {secret_name}.\n`version` `string` \nThe Cloud Secret Manager secret version. Can be 'latest' for the latest version, an integer for a specific version, or a version alias. \n\nReasoningEngineContextSpec\n--------------------------\n\nConfiguration for how Agent Engine sub-resources should manage context.\nFields `memoryBankConfig` `object (`[MemoryBankConfig](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.reasoningEngines#MemoryBankConfig)`)` \nOptional. Specification for a Memory Bank, which manages memories for the Agent Engine. \n\nMemoryBankConfig\n----------------\n\nSpecification for a Memory Bank.\nFields `generationConfig` `object (`[GenerationConfig](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.reasoningEngines#GenerationConfig)`)` \nOptional. Configuration for how to generate memories for the Memory Bank.\n`similaritySearchConfig` `object (`[SimilaritySearchConfig](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.reasoningEngines#SimilaritySearchConfig)`)` \nOptional. Configuration for how to perform similarity search on memories. If not set, the Memory Bank will use the default embedding model `text-embedding-005`. \n\nGenerationConfig\n----------------\n\nConfiguration for how to generate memories.\nFields `model` `string` \nRequired. The model used to generate memories. Format: `projects/{project}/locations/{location}/publishers/google/models/{model}`. \n\nSimilaritySearchConfig\n----------------------\n\nConfiguration for how to perform similarity search on memories.\nFields `embeddingModel` `string` \nRequired. The model used to generate embeddings to lookup similar memories. Format: `projects/{project}/locations/{location}/publishers/google/models/{model}`."]]