AiReasoningEngineSpec class
Constructors
-
AiReasoningEngineSpec({Input<String?>? agentCard, Input<String?>? agentFramework, Input<AiReasoningEngineSpecBuildSpec?>? buildSpec, Input<String?>? classMethods, Input<AiReasoningEngineSpecContainerSpec?>? containerSpec, Input<AiReasoningEngineSpecDeploymentSpec?>? deploymentSpec, Input<String?>? effectiveIdentity, Input<String?>? exampleStore, Input<String?>? identityType, Input<AiReasoningEngineSpecPackageSpec?>? packageSpec, Input<String?>? serviceAccount, Input<AiReasoningEngineSpecSourceCodeSpec?>? sourceCodeSpec})
-
Creates a new AiReasoningEngineSpec.
agentCard Optional. The A2A Agent Card for the agent (if available).
agentFramework Optional. The OSS agent framework used to develop the agent.
buildSpec Optional. Configuration for building container image.
classMethods Optional. Declarations for object class methods in OpenAPI
containerSpec Deploy from a container image with a defined entrypoint and commands.
deploymentSpec Optional. The specification of a Reasoning Engine deployment.
effectiveIdentity The identity to use for the Reasoning Engine.
exampleStore Optional. The resource name of the linked ExampleStore.
identityType Optional. The identity type to use for the Reasoning Engine.
packageSpec Optional. User provided package spec of the ReasoningEngine.
serviceAccount Optional. The service account that the Reasoning Engine artifact runs
sourceCodeSpec Specification for deploying from source code.
const
-
AiReasoningEngineSpec.fromMap(Map<String, dynamic> map)
-
factory
Properties
-
agentCard
→ Input<String?>?
-
Optional. The A2A Agent Card for the agent (if available).
final
-
agentFramework
→ Input<String?>?
-
Optional. The OSS agent framework used to develop the agent.
final
-
buildSpec
→ Input<AiReasoningEngineSpecBuildSpec?>?
-
Optional. Configuration for building container image.
final
-
classMethods
→ Input<String?>?
-
Optional. Declarations for object class methods in OpenAPI
specification format.
Note: When deploying via Terraform, this field must be populated manually.
Otherwise, client SDKs (like
agent_engines.get()) will not be able to discover the methods, and calls to the engine (or A2A integrations) will fail.
Depending on the template/framework used (agentFramework), the required class methods and their parameters differ:
Warning: The configuration snippets below are illustrative, may not be exhaustive, and could stop working over time. For the most up-to-date method lists and schemas, please consult the respective SDK source code:
final
-
containerSpec
→ Input<AiReasoningEngineSpecContainerSpec?>?
-
Deploy from a container image with a defined entrypoint and commands.
final
-
deploymentSpec
→ Input<AiReasoningEngineSpecDeploymentSpec?>?
-
Optional. The specification of a Reasoning Engine deployment.
final
-
effectiveIdentity
→ Input<String?>?
-
The identity to use for the Reasoning Engine.
final
-
exampleStore
→ Input<String?>?
-
Optional. The resource name of the linked ExampleStore.
final
-
hashCode
→ int
-
The hash code for this object.
no setterinherited
-
identityType
→ Input<String?>?
-
Optional. The identity type to use for the Reasoning Engine.
If not specified, the 'service_account' field will be used if set,
otherwise the default Vertex AI Reasoning Engine Service Agent in the project will be used.
Possible values:
final
-
packageSpec
→ Input<AiReasoningEngineSpecPackageSpec?>?
-
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
fieldBehavior to avoid introducing breaking changes.
final
-
runtimeType
→ Type
-
A representation of the runtime type of the object.
no setterinherited
-
serviceAccount
→ Input<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.
final
-
sourceCodeSpec
→ Input<AiReasoningEngineSpecSourceCodeSpec?>?
-
Specification for deploying from source code.
final
