google.cloud.gcp_vertexai_reasoning_engine module – Manages a VertexAI.ReasoningEngine resource

Note

This module is part of the google.cloud collection (version 1.15.0).

You might already have this collection installed if you are using the ansible package. It is not included in ansible-core. To check whether it is installed, run ansible-galaxy collection list.

To install it, use: ansible-galaxy collection install google.cloud. You need further requirements to be able to use this module, see Requirements for details.

To use it in a playbook, specify: google.cloud.gcp_vertexai_reasoning_engine.

Synopsis

  • ReasoningEngine provides a customizable runtime for models to determine which actions to take and in which order.

Requirements

The below requirements are needed on the host that executes this module.

  • python >= 3.8

  • requests >= 2.18.4

  • google-auth >= 2.25.1

Parameters

Parameter

Comments

access_token

string

The access token used to authenticate.

auth_kind

string / required

The type of credential used.

Choices:

  • "accesstoken"

  • "application"

  • "machineaccount"

  • "serviceaccount"

context_spec

dictionary

Configuration for how Agent Engine sub-resources should manage context.

example_store_config

dictionary

Specification for an Example Store, which manages few-shot examples for the Agent Engine.

similarity_search_config

dictionary

Configuration for how to perform similarity search on examples.

embedding_model

string / required

The Gemini model used to generate embeddings to lookup similar examples.

memory_bank_config

dictionary

Specification for a Memory Bank, which manages memories for the Agent Engine.

customization_configs

list / elements=dictionary

Customization configs for how Agent Engine sub-resources manage context at different scope levels.

consolidation_config

dictionary

Configuration for how many memory revisions Memory Bank considers when consolidating each memory candidate.

revisions_per_candidate_count

integer

Number of revisions to consider per candidate count.

disable_natural_language_memories

boolean

Indicates whether natural language memory generation should be disabled.

Choices:

  • false

  • true

enable_third_person_memories

boolean

Generate memories in the third person if set to true.

Choices:

  • false

  • true

generate_memories_examples

list / elements=dictionary

Provides examples of how to generate memories for a particular scope.

conversation_source

dictionary

A conversation source for the example.

events

list / elements=dictionary

Represents the input conversation events for the example.

content

dictionary / required

Represents the content of the event.

parts

list / elements=dictionary / required

A list of Part objects that make up a single message.

audio_transcription

dictionary

Audio (input or output) transcription.

This is only set when this Part contains audio data.

speaker_label

string

A label identifying the speaker of this audio segment (e.g.

spk_1, spk_2).

Present when diarization is set.

text

string / required

The transcription text of this audio segment.

words

list / elements=dictionary

Detailed word-level transcriptions and timing details.

Present when word_timestamp is set.

end_offset

string

End offset in time of the word relative to the start of the audio.

start_offset

string

Start offset in time of the word relative to the start of the audio.

word

string / required

Transcript of the word.

code_execution_result

dictionary

Result of executing the ExecutableCode.

id

string

The identifier of the ExecutableCode part this result is for.

outcome

string / required

Outcome of the code execution.

Possible values: [“OUTCOME_UNSPECIFIED”, “OUTCOME_OK”, “OUTCOME_FAILED”, “OUTCOME_DEADLINE_EXCEEDED”].

output

string

Contains stdout when code execution is successful, stderr or other description otherwise.

executable_code

dictionary

Code generated by the model that is intended to be executed.

code

string / required

The code to be executed.

id

string

Unique identifier of the ExecutableCode part.

language

string / required

Supported programming languages for the generated code.

Possible values: [“LANGUAGE_UNSPECIFIED”, “PYTHON”, “BASH”].

file_data

dictionary

URI based data.

file_uri

string / required

The URI of the file in Google Cloud Storage.

mime_type

string / required

The IANA standard MIME type of the source data.

function_call

dictionary

A predicted function call returned from the model.

args

string

The function parameters and values in JSON object format.

id

string

The unique id of the function call.

name

string

The name of the function to call.

function_response

dictionary

The result of a function call.

id

string

The id of the function call this response is for.

name

string / required

The name of the function to call.

response

string

The function response in JSON object format.

inline_data

dictionary

The inline data content of the part.

data

string / required

Raw bytes, which should be base64-encoded.

mime_type

string / required

The IANA standard MIME type of the source data.

text

string

The text content of the part.

thought

boolean

Indicates whether the part represents the model’s thought process or reasoning.

Choices:

  • false

  • true

video_metadata

dictionary

Video metadata.

end_offset

string

The end offset of the video.

start_offset

string

The start offset of the video.

role

string

The producer of the content.

Must be either ‘user’ or ‘model’.

If not set, the service will default to ‘user’.

generated_memories

list / elements=dictionary

Represents the memories that are expected to be generated from the input conversation.

fact

string / required

Represents the fact to generate a memory from.

topics

list / elements=dictionary

Represents the list of topics that the memory should be associated with.

custom_memory_topic_label

string

Represents the custom memory topic label.

managed_memory_topic

string

Represents the managed memory topic.

Possible values: [“USER_PERSONAL_INFO”, “USER_PREFERENCES”, “KEY_CONVERSATION_DETAILS”, “EXPLICIT_INSTRUCTIONS”].

memory_topics

list / elements=dictionary

List of topics that the memory should be associated with.

custom_memory_topic

dictionary

Custom memory topic.

description

string

Description of custom memory topic.

label

string

Label of custom memory topic.

managed_memory_topic

dictionary

Managed memory topic.

managed_topic_enum

string

Managed topic enum (e.g.

USER_PREFERENCES, EXPLICIT_INSTRUCTIONS).

scope_keys

list / elements=string

List of scope keys that this customization config applies to.

disable_memory_revisions

boolean

If true, no memory revisions will be created for any requests to the Memory Bank.

Choices:

  • false

  • true

generation_config

dictionary

Configuration for how to generate memories for the Memory Bank.

generation_trigger_config

dictionary

Configuration for triggering memory generation.

generation_rule

dictionary

The active rule that determines when to flush the buffer.

If not set, then the stream will be force flushed immediately.

event_count

integer

Specifies to trigger generation when the event count reaches this limit.

fixed_interval

string

Specifies to trigger generation at a fixed interval.

The duration must have a minute-level granularity.

idle_duration

string

Specifies to trigger generation if the stream is inactive for the specified duration after the most recent event.

The duration must have a minute-level granularity.

overlap_event_count

integer

Re-include the last N already-processed events in the next window.

model

string / required

The model used to generate memories.

Format: projects/{project}/locations/{location}/publishers/google/models/{model}.

similarity_search_config

dictionary

Configuration for how to perform similarity search on memories.

embedding_model

string / required

The model used to generate embeddings to lookup similar memories.

Format: projects/{project}/locations/{location}/publishers/google/models/{model}.

structured_memory_configs

list / elements=dictionary

Structured memory configurations for Agent Engine sub-resources.

schema_configs

list / elements=dictionary

List of schema configs that this structured memory config applies to.

id

string / required

Unique ID identifying the memory schema.

memory_schema

string

The memory schema defined as an OpenAPI Schema Object JSON string.

scope_keys

list / elements=string

List of scope keys that this structured memory config applies to.

ttl_config

dictionary

Configuration for automatic TTL (“time-to-live”) of the memories in the Memory Bank.

default_ttl

string

The default TTL duration of the memories in the Memory Bank.

granular_ttl_config

dictionary

The granular TTL configuration of the memories in the Memory Bank.

create_ttl

string

The TTL duration for memories uploaded via CreateMemory.

generate_created_ttl

string

The TTL duration for memories newly generated via GenerateMemories.

generate_updated_ttl

string

The TTL duration for memories updated via GenerateMemories.

memory_revision_default_ttl

string

The default TTL duration of the memory revisions in the Memory Bank.

description

string

The description of the ReasoningEngine.

display_name

string / required

The display name of the ReasoningEngine.

encryption_spec

dictionary

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.

This property is immutable, to change it, you must delete and recreate the resource.

kms_key_name

string / required

The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource.

Has the form: projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key.

The key needs to be in the same region as where the compute resource is created.

env_type

string

Specifies which Ansible environment you’re running this module within.

This should not be set unless you know what you’re doing.

This only alters the User Agent string for any API requests.

labels

dictionary

The labels associated with this ReasoningEngine.

You can use these to organize and group your ReasoningEngines.

**Note**: This field is non-authoritative, and will only manage the labels present in your configuration.

project

string

The Google Cloud Platform project to use.

region

string

The region of the reasoning engine.

eg us-central1.

This property is immutable, to change it, you must delete and recreate the resource.

scopes

list / elements=string

Array of scopes to be used.

service_account_contents

jsonarg

The contents of a Service Account JSON file,

either in a dictionary or as a JSON string that represents it.

service_account_email

string

An optional service account email address if machineaccount is

selected and the user does not wish to use the default email.

service_account_file

path

The path of a Service Account JSON file if serviceaccount

is selected as type.

spec

dictionary

Configurations of the ReasoningEngine.

agent_card

string

The A2A Agent Card for the agent (if available).

agent_framework

string

The OSS agent framework used to develop the agent.

build_spec

dictionary

Configuration for building container image.

service_account

string

The service account that the Cloud Build builder runs as.

worker_pool

string

The resource name of the Cloud Build WorkerPool to use for the build.

class_methods

string

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 (`agent_framework`), 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: * For Google ADK: See [ADK Python SDK cli_deploy.py](https://github.com/google/adk-python/blob/68a780306e3bdd648a882ef34c0abf8e5148353e/src/google/adk/cli/cli_deploy.py#L109).

* For Langchain: See [Vertex AI Python SDK langchain.py](https://github.com/googleapis/python-aiplatform/blob/c8a38a085931b01f4d6071f0ab7a64cb42851829/agentplatform/agent_engines/templates/langchain.py#L642-L717).

### 1.

Langchain Template * `query` (api_mode = “sync” or empty) * `stream_query` (api_mode = “stream”) Example for Langchain: ```hcl class_methods = jsonencode([ { name = “query” api_mode = “sync” description = “Queries the reasoning engine” parameters = { type = “object” required = [“input”] properties = { input = { type = “string” description = “The input prompt” } } } }, { name = “stream_query” api_mode = “stream” description = “Streams queries from the reasoning engine” parameters = { type = “object” required = [“input”] properties = { input = { type = “string” description = “The input prompt” } } } } ]) ``` ### 2.

Google ADK Template (Standard - No A2A) For standard Google ADK (Agent Development Kit) deployments, you must define the following 11 methods: Example for Standard ADK: ```hcl class_methods = jsonencode([ { name = “get_session” api_mode = “” description = “Retrieve session by ID” parameters = { type = “object” required = [“user_id”, “session_id”] properties = { user_id = { type = “string” } session_id = { type = “string” } } } }, { name = “async_get_session” api_mode = “async” description = “Retrieve session asynchronously by ID” parameters = { type = “object” required = [“user_id”, “session_id”] properties = { user_id = { type = “string” } session_id = { type = “string” } } } }, { name = “list_sessions” api_mode = “” description = “List all sessions for a user” parameters = { type = “object” required = [“user_id”] properties = { user_id = { type = “string” } } } }, { name = “async_list_sessions” api_mode = “async” description = “List all sessions for a user asynchronously” parameters = { type = “object” required = [“user_id”] properties = { user_id = { type = “string” } } } }, { name = “create_session” api_mode = “” description = “Create a new session” parameters = { type = “object” required = [“user_id”] properties = { user_id = { type = “string” } session_id = { type = “string” } state = { type = “object” } } } }, { name = “async_create_session” api_mode = “async” description = “Create a new session asynchronously” parameters = { type = “object” required = [“user_id”] properties = { user_id = { type = “string” } session_id = { type = “string” } state = { type = “object” } } } }, { name = “delete_session” api_mode = “” description = “Delete session by ID” parameters = { type = “object” required = [“user_id”, “session_id”] properties = { user_id = { type = “string” } session_id = { type = “string” } } } }, { name = “async_delete_session” api_mode = “async” description = “Delete session asynchronously by ID” parameters = { type = “object” required = [“user_id”, “session_id”] properties = { user_id = { type = “string” } session_id = { type = “string” } } } }, { name = “stream_query” api_mode = “stream” description = “Stream queries from the agent” parameters = { type = “object” required = [“message”, “user_id”] properties = { message = { description = “Message string or object” } user_id = { type = “string” } session_id = { type = “string” } run_config = { type = “object” } } } }, { name = “async_stream_query” api_mode = “async_stream” description = “Stream queries asynchronously from the agent” parameters = { type = “object” required = [“message”, “user_id”] properties = { message = { description = “Message string or object” } user_id = { type = “string” } session_id = { type = “string” } session_events = { type = “array”, items = { type = “object” } } run_config = { type = “object” } } } }, { name = “streaming_agent_run_with_events” api_mode = “async_stream” description = “Stream agent run with events asynchronously” parameters = { type = “object” required = [“request_json”] properties = { request_json = { type = “string” } } } } ]) ``` ### 3.

Google ADK Template (A2A-Enabled) If the agent integrates with the Gemini Enterprise Agent Registry (A2A), you must inject the `a2a_agent_card` JSON metadata as a string **specifically inside the `async_create_session` method definition**: Example for A2A-Enabled ADK: ```hcl locals { # Construct the A2A endpoint URL a2a_url = “https://us-central1-aiplatform.googleapis.com/v1/projects/my-project/locations/us-central1/reasoningEngines/my-agent/a2a” agent_card = { name = “my-agent” description = “A2A Agent” version = “1.0.0” preferred_transport = “HTTP_JSON” supported_interfaces = [{ url = local.a2a_url, protocol_binding = “HTTP_JSON” }] capabilities = { streaming = true } } } # In class_methods, append “a2a_agent_card” key ONLY to the “async_create_session” method: class_methods = jsonencode([ # ..

other 10 standard methods (same as Standard ADK) ..

{ name = “async_create_session” api_mode = “async” description = “Create a new session asynchronously” parameters = { type = “object” required = [“user_id”] properties = { user_id = { type = “string” } session_id = { type = “string” } state = { type = “object” } } } # Inject the serialized Agent Card here a2a_agent_card = jsonencode(local.agent_card) } ]) ```.

container_spec

dictionary

Deploy from a container image with a defined entrypoint and commands.

image_uri

string / required

The Artifact Registry Docker image URI (e.g., `us-central1-docker.pkg.dev/my-project/my-repo/my-image:tag`) of the container image that is to be run on each worker replica.

port

integer

The port that the container listens on for incoming requests.

If not specified, defaults to 8080.

deployment_spec

dictionary

The specification of a Reasoning Engine deployment.

agent_gateway_config

dictionary

Agent Gateway configuration for a Reasoning Engine deployment.

agent_to_anywhere_config

dictionary

Configuration for traffic originating from the Reasoning Engine.

agent_gateway

string / required

The resource name of the Agent Gateway for outbound traffic.

client_to_agent_config

dictionary

Configuration for traffic targeting the Reasoning Engine.

agent_gateway

string / required

The resource name of the Agent Gateway to use for inbound traffic.

agent_server_mode

string

The agent server mode specifies what features are used when deploy the agent to agent engine.

Possible values: * `STABLE`: Stable agent server mode.

* `EXPERIMENTAL`: Experimental agent server mode.

Choices:

  • "STABLE"

  • "EXPERIMENTAL"

container_concurrency

integer

Concurrency for each container and agent server.

Recommended value: 2 * cpu + 1.

Defaults to 9.

dedicated_ingress_endpoint_enabled

boolean

Whether to enable dedicated ingress endpoint for the deployment.

If true, the deployment will be accessible via a dedicated endpoint.

This is required to enable GKE V2 runtime.

Choices:

  • false

  • true

env

list / elements=dictionary

Environment variables to be set with the Reasoning Engine deployment.

name

string / required

The name of the environment variable.

Must be a valid C identifier.

value

string / required

Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables.

If a variable cannot be resolved, the reference in the input string will be unchanged.

The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME).

Escaped references will never be expanded, regardless of whether the variable exists or not.

keep_alive_probe

dictionary

Specifies the configuration for keep-alive probe.

http_get

dictionary

Specifies the HTTP GET configuration for the probe.

path

string / required

Specifies the path of the HTTP GET request (e.g., `”/is_busy”`).

port

integer

Specifies the port number on the container to which the request is sent.

max_seconds

integer

Specifies the maximum duration (in seconds) to keep the instance alive via this probe.

Can be a maximum of 3600 seconds (1 hour).

max_instances

integer

The maximum number of application instances that can be launched to handle increased traffic.

Defaults to 100.

Range: [1, 1000].

If VPC-SC or PSC-I is enabled, the acceptable range is [1, 100].

min_instances

integer

The minimum number of application instances that will be kept running at all times.

Defaults to 1.

Range: [0, 10].

psc_interface_config

dictionary

Configuration for PSC-Interface.

dns_peering_configs

list / elements=dictionary

DNS peering configurations.

When specified, Vertex AI will attempt to configure DNS peering zones in the tenant project VPC to resolve the specified domains using the target network’s Cloud DNS.

The user must grant the dns.peer role to the Vertex AI service Agent on the target project.

domain

string / required

The DNS name suffix of the zone being peered to, e.g., “my-internal-domain.corp.”.

Must end with a dot.

target_network

string / required

The VPC network name in the targetProject where the DNS zone specified by ‘domain’ is visible.

target_project

string / required

The project id hosting the Cloud DNS managed zone that contains the ‘domain’.

The Vertex AI service Agent requires the dns.peer role on this project.

network_attachment

string

The name of the Compute Engine network attachment to attach to the resource within the region and user project.

To specify this field, you must have already created a network attachment.

This field is only used for resources using PSC-Interface.

resource_limits

dictionary

Resource limits for each container.

Only ‘cpu’ and ‘memory’ keys are supported.

Defaults to {“cpu”: “4”, “memory”: “4Gi”}.

The only supported values for CPU are ‘1’, ‘2’, ‘4’, ‘6’ and ‘8’.

For more information, go to https://cloud.google.com/run/docs/configuring/cpu.

The only supported values for memory are ‘1Gi’, ‘2Gi’, ..

‘32 Gi’.

For more information, go to https://cloud.google.com/run/docs/configuring/memory-limits.

secret_env

list / elements=dictionary

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.

name

string / required

The name of the environment variable.

Must be a valid C identifier.

secret_ref

dictionary / required

Reference to a secret stored in the Cloud Secret Manager that will provide the value for this environment variable.

secret

string / required

The name of the secret in Cloud Secret Manager.

Format: {secret_name}.

version

string

The Cloud Secret Manager secret version.

Can be ‘latest’ for the latest version, an integer for a specific version, or a version alias.

effective_identity

string

The identity to use for the Reasoning Engine.

example_store

string

The resource name of the linked ExampleStore.

identity_type

string

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: * `SERVICE_ACCOUNT`: Use a custom service account if the `service_account` field is set, otherwise use the default Vertex AI Reasoning Engine Service Agent in the project.

* `AGENT_IDENTITY`: Use Agent Identity.

The `service_account` field must not be set.

Choices:

  • "SERVICE_ACCOUNT"

  • "AGENT_IDENTITY"

package_spec

dictionary

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.

dependency_files_gcs_uri

string

The Cloud Storage URI of the dependency files in tar.gz format.

pickle_object_gcs_uri

string

The Cloud Storage URI of the pickled python object.

python_version

string

The Python version.

Currently support 3.8, 3.9, 3.10, 3.11, 3.12, 3.13.

If not specified, default value is 3.10.

requirements_gcs_uri

string

The Cloud Storage URI of the requirements.txtfile.

service_account

string

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.

source_code_spec

dictionary

Specification for deploying from source code.

agent_config_source

dictionary

Specification for the deploying from agent config.

adk_config

dictionary

Configuration for the Agent Development Kit (ADK).

json_config

string / required

The value of the ADK config in JSON format.

inline_source

dictionary

Any additional files needed to interpret the config.

source_archive

string / required

Input only.

The application source code archive, provided as a compressed tarball (.tar.gz) file.

developer_connect_source

dictionary

Specification for source code to be fetched from a Git repository managed through the Developer Connect service.

config

dictionary / required

The Developer Connect configuration that defines the specific repository, revision, and directory to use as the source code root.

dir

string / required

Directory, relative to the source root, in which to run the build.

string / required

The Developer Connect Git repository link, formatted as projects/*/locations/*/connections/*/gitRepositoryLink/*.

revision

string / required

The revision to fetch from the Git repository such as a branch, a tag, a commit SHA, or any Git ref.

image_spec

dictionary

Configuration for building an image with custom config file.

build_args

dictionary

Build arguments to be used.

They will be passed through --build-arg flags.

inline_source

dictionary

Source code is provided directly in the request.

source_archive

string

Input only.

The application source code archive, provided as a compressed tarball (.tar.gz) file.

A base64-encoded string.

python_spec

dictionary

Specification for running a Python application from source.

entrypoint_module

string

The Python module to load as the entrypoint, specified as a fully qualified module name.

For example: path.to.agent.

If not specified, defaults to “agent”.

The project root will be added to Python sys.path, allowing imports to be specified relative to the root.

entrypoint_object

string

The name of the callable object within the entrypointModule to use as the application If not specified, defaults to “root_agent”.

requirements_file

string

The path to the requirements file, relative to the source root.

If not specified, defaults to “requirements.txt”.

version

string

The version of Python to use.

Support version includes 3.9, 3.10, 3.11, 3.12, 3.13.

If not specified, default value is 3.10.

state

string

Whether the resource should exist.

Choices:

  • "present" ← (default)

  • "absent"

traffic_config

dictionary

Traffic distribution configuration for the Reasoning Engine.

~> **Note:** Because revision IDs do not exist before the resource is created, the best practice for initial deployment is to set `traffic_split_always_latest {}`.

Once the resource is created, you can update the configuration to a manual split using newly generated revision IDs, short names (e.g.

`rev-1`), or keywords such as `LATEST` and `PREVIOUS`.

traffic_split_always_latest

dictionary

Traffic distribution configuration, where all traffic is sent to the latest Runtime Revision.

traffic_split_manual

dictionary

Manual traffic distribution configuration, where the user specifies the Runtime Revision IDs and the percentage of traffic to send to each.

targets

list / elements=dictionary

A list of traffic targets for the Runtimes Revisions.

The sum of percentages must equal to 100.

percent

integer / required

Specifies percent of the traffic to this Runtime Revision.

runtime_revision_name

string / required

The Runtime Revision name to which to send this portion of traffic.

Accepts revision IDs, short names (e.g.

`rev-1`), or keywords such as `LATEST` and `PREVIOUS`.

Note: Keywords like `LATEST` and `PREVIOUS` resolve at apply time to the concrete underlying revision ID and remain pinned until `traffic_config` is updated in Terraform.

Notes

Note

Examples

- name: Create Basic Reasoning Engine
  google.cloud.gcp_vertexai_reasoning_engine:
    state: present
    display_name: basic-reasoning-engine
    description: A Basic Reasoning Engine
    region: us-central1

################################################################################

- name: Create Source Based Deployment Reasoning Engine
  google.cloud.gcp_vertexai_reasoning_engine:
    state: present
    display_name: source-based-deployment-reasoning-engine
    description: A Source Based Deployment Reasoning Engine
    region: us-central1
    spec:
      source_code_spec:
        inline_source:
          source_archive: "{{ slurped_tarball.content }}"  # slurp already returns b64
          # source_archive: "{{ some_other_b64_encoded_string }}"
        python_spec:
          entrypoint_module: my_agent
          entrypoint_object: name_generator
          requirements_file: prod-requirements.txt  # defaults to requirements.txt
          version: "3.11"

Return Values

Common return values are documented here, the following are the fields unique to this module:

Key

Description

changed

boolean

Whether the resource was changed.

Returned: always

createTime

string

The timestamp of when the Index was created in RFC3339 UTC “Zulu” format, with nanosecond resolution and up to nine fractional digits.

Returned: success

name

string

The generated name of the ReasoningEngine, in the format projects/{project}/locations/{location}/reasoningEngines/{reasoningEngine}.

Returned: success

state

string

The current state of the resource.

Returned: always

updateTime

string

The timestamp of when the Index was last updated in RFC3339 UTC “Zulu” format, with nanosecond resolution and up to nine fractional digits.

Returned: success

url

string

Output only.

The URL of the reasoning engine.

Returned: success

Authors

  • Google Inc. (@googlecloudplatform)