Deploy an agent

To deploy an agent on Vertex AI Agent Engine, use the following steps:

Complete prerequisites.
(Optional) Configure your agent for deployment.
Create an AgentEngine instance.
(Optional) Get the agent resource ID.
(Optional) List the supported operations.
(Optional) Grant the deployed agent permissions.

You can also use Agent Starter Pack templates for deployment.

Prerequisites

Before you deploy an agent, make sure you have completed the following tasks:

(Optional) Configure your agent for deployment

You can make the following optional configurations for your agent:

Define the package requirements

Provide the set of packages required by the agent for deployment. The set of packages can either be a list of items to be installed by pip, or the path to a file that follows the Requirements File Format. Use the following best practices:

Pin your package versions for reproducible builds. Common packages to keep track of include the following: google-cloud-aiplatform, cloudpickle, langchain, langchain-core, langchain-google-vertexai, and pydantic.
Minimize the number of dependencies in your agent. This reduces the number of breaking changes when updating your dependencies and agent.

If the agent doesn't have any dependencies, you can set requirements to None:

requirements = None

If the agent uses a framework-specific template, you should specify the SDK version that is imported (such as 1.112.0) when developing the agent.

ADK

requirements = [
    "google-cloud-aiplatform[agent_engines,adk]",
    # any other dependencies
]

A2A

requirements = [
    "google-cloud-aiplatform[agent_engines]",
    "a2a-sdk>=0.3.4"
    # any other dependencies
]

LangChain

requirements = [
    "google-cloud-aiplatform[agent_engines,langchain]",
    # any other dependencies
]

LangGraph

requirements = [
    "google-cloud-aiplatform[agent_engines,langgraph]",
    # any other dependencies
]

AG2

requirements = [
    "google-cloud-aiplatform[agent_engines,ag2]",
    # any other dependencies
]

LlamaIndex

The following instructions are for LlamaIndex Query Pipeline:

requirements = [
    "google-cloud-aiplatform[agent_engines,llama_index]",
    # any other dependencies
]

You can also do the following with package requirements:

Upper-bound or pin the version of a given package (such as google-cloud-aiplatform):

  requirements = [
      # See https://pypi.org/project/google-cloud-aiplatform for the latest version.
      "google-cloud-aiplatform[agent_engines,adk]==1.112.0",
  ]

Add additional packages and constraints:

  requirements = [
      "google-cloud-aiplatform[agent_engines,adk]==1.112.0",
      "cloudpickle==3.0", # new
  ]

Point to the version of a package on a GitHub branch or pull request:

  requirements = [
      "google-cloud-aiplatform[agent_engines,adk] @ git+https://github.com/googleapis/python-aiplatform.git@BRANCH_NAME", # new
  ]

Maintain the list of requirements in a file (such as path/to/requirements.txt):
```
  requirements = "path/to/requirements.txt"
  
```
where path/to/requirements.txt is a text file that follows the Requirements File Format. For example:
```
  google-cloud-aiplatform[agent_engines,adk]
  cloudpickle==3.0
  
```

Define additional packages

You can include local files or directories that contain local required Python source files. Compared to package requirements, this lets you use private utilities you have developed that aren't otherwise available on PyPI or GitHub.

If the agent does not require any extra packages, you can set extra_packages to None:

extra_packages = None

You can also do the following with extra_packages:

Include a single file (such as agents/agent.py):

  extra_packages = ["agents/agent.py"]

Include the set of files in an entire directory (for example, agents/):

  extra_packages = ["agents"] # directory that includes agents/agent.py

Specify Python wheel binaries (for example, path/to/python_package.whl):

  requirements = [
      "google-cloud-aiplatform[agent_engines,adk]",
      "cloudpickle==3.0",
      "python_package.whl",  # install from the whl file that was uploaded
  ]
  extra_packages = ["path/to/python_package.whl"]  # bundle the whl file for uploading

Define environment variables

If there are environment variables that your agent depends on, you can specify them in the env_vars= argument. If the agent does not depend on any environment variables, you can set it to None:

env_vars = None

Warning: You shouldn't set the following environment variables: GOOGLE_CLOUD_PROJECT, GOOGLE_CLOUD_QUOTA_PROJECT, GOOGLE_CLOUD_LOCATION, PORT, K_SERVICE, K_REVISION, K_CONFIGURATION, and GOOGLE_APPLICATION_CREDENTIALS. Also, you should avoid the prefix GOOGLE_CLOUD_AGENT_ENGINE to avoid naming conflicts with Vertex AI Agent Engine environment variables.

To specify the environment variables, there are a few different options available:

Dictionary

env_vars = {
  "VARIABLE_1": "VALUE_1",
  "VARIABLE_2": "VALUE_2",
}
# These environment variables will become available in Vertex AI Agent Engine
# through `os.environ`, e.g.
#
#   import os
#   os.environ["VARIABLE_1"] # will have the value "VALUE_1"
#
# and
#
#   os.environ["VARIABLE_2"] # will have the value "VALUE_2"
#

To reference a secret in Secret Manager and have it be available as an environment variable (for example, CLOUD_SQL_CREDENTIALS_SECRET), first follow the instructions to Create a secret for CLOUD_SQL_CREDENTIALS_SECRET in your project, before specifying the environment variables as:

env_vars = {
  # ... (other environment variables and their values)
  "CLOUD_SQL_CREDENTIALS_SECRET": {"secret": SECRET_ID, "version": SECRET_VERSION_ID},
}

where

SECRET_VERSION_ID is the ID of the secret version.
SECRET_ID is the ID of the secret.

In your agent code, you can then reference the secret like so:

secret = os.environ.get("CLOUD_SQL_CREDENTIALS_SECRET")
if secret:
  # Secrets are stored as strings, so use json.loads to parse JSON
  # payloads.
  return json.loads(secret)

List

env_vars = ["VARIABLE_1", "VARIABLE_2"]
# This corresponds to the following code snippet:
#
#   import os
#
#   env_vars = {
#     "VARIABLE_1": os.environ["VARIABLE_1"],
#     "VARIABLE_2": os.environ["VARIABLE_2"],
#   }

You also need to follow the instructions in Set up the identity and permissions for your agent to grant your agent the Secret Manager Secret Accessor (roles/secretmanager.secretAccessor) permission.

Define customized resource controls

You can specify runtime resource controls for the agent, such as the minimum and maximum number of application instances, resource limits for each container, and concurrency for each container.

min_instances: The minimum number of application instances to keep running at all times, with a range of [0, 10]. The default value is 1.

Note: While this feature is in Preview, even if you configure a higher number of minimum instances, you won't be billed for time when an agent is idle. This billing behavior is subject to change in the future.
max_instances: The maximum number of application instances that can be launched to handle increased traffic, with a range of [1, 1000]. The default value is 100. If VPC-SC or PSC-I is enabled, the acceptable range is [1, 100].
resource_limits: Resource limits for each container. Only cpu and memory keys are supported. The default value is {"cpu": "4", "memory": "4Gi"}.
- The only supported values for cpu are 1, 2, 4, 6 and 8. For more information, see Configure CPU allocation.
- The only supported values for memory are 1Gi, 2Gi, ... 32Gi.
- For required CPU on different memory values, see Configure memory limits.
container_concurrency: Concurrency for each container and agent server. The recommended value is 2 * cpu + 1. The default value is 9.

remote_agent = client.agent_engines.create(
    agent=local_agent,
    config={
        "min_instances": 1,
        "max_instances": 10,
        "resource_limits": {"cpu": "4", "memory": "8Gi"},
        "container_concurrency": 9,
        # ... other configs
    }
)

Define build options

You can specify build options for the agent, such as installation scripts to run when building the agent's container image. This is useful for installing system dependencies (for example, gcloud cli, npx) or other custom setups. The scripts are run with root permissions.

To use installation scripts, create a directory named installation_scripts and place your shell scripts inside the directory:

.
├── ...
└── installation_scripts/
    └── install.sh

Next, specify the installation_scripts directory in extra_packages and the script paths in build_options:

extra_packages = [..., "installation_scripts/install.sh"]
build_options = {"installation_scripts": ["installation_scripts/install.sh"]}

You can use one of the following common installation scripts:

install_npx.sh

#!/bin/bash

# Exit immediately if a command exits with a non-zero status.
set -e

echo "--- Installing System-Wide Node.js v20.x ---"

# 1. Install prerequisites
apt-get update
apt-get install -y ca-certificates curl gnupg

# 2. Add the NodeSource repository GPG key
mkdir -p /etc/apt/keyrings
curl -fsSL https://deb.nodesource.com/gpgkey/nodesource-repo.gpg.key | gpg --dearmor -o /etc/apt/keyrings/nodesource.gpg

# 3. Add the NodeSource repository for Node.js v20
NODE_MAJOR=20
echo "deb [signed-by=/etc/apt/keyrings/nodesource.gpg] https://deb.nodesource.com/node_$NODE_MAJOR.x nodistro main" | tee /etc/apt/sources.list.d/nodesource.list

# 4. Update package lists again and install Node.js
apt-get update
apt-get install nodejs -y

echo "--- System-wide Node.js installation complete ---"
echo "Verifying versions:"

# These commands will now work for ANY user because node and npx
# are installed in /usr/bin/ which is in everyone's default PATH.
node -v
npm -v
npx -v

install_uvx.sh

#!/bin/bash

# Exit immediately if a command exits with a non-zero status.
set -e

echo "Starting setup..."

# Install uv
apt-get update
apt-get install -y curl
curl -LsSf https://astral.sh/uv/install.sh | env UV_INSTALL_DIR="/usr/local/bin" sh

# These commands will now work for ANY user because uv and uvx
# are installed in /usr/local/bin/ which is in everyone's default PATH.
uv --version
uvx --version

install_gcloud_cli.sh

#!/bin/bash

# Exit immediately if a command exits with a non-zero status.
set -e

apt-get install -y curl gpg
curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | gpg --dearmor -o /usr/share/keyrings/cloud.google.gpg
echo "deb [signed-by=/usr/share/keyrings/cloud.google.gpg] https://packages.cloud.google.com/apt cloud-sdk main" | tee -a /etc/apt/sources.list.d/google-cloud-sdk.list
apt-get update -y && apt-get install google-cloud-cli -y

gcloud --version

Define a Cloud Storage folder

Staging artifacts are overwritten if they correspond to an existing folder in a Cloud Storage bucket. If necessary, you can specify the Cloud Storage folder for the staging artifacts. You can set gcs_dir_name to None if you don't mind potentially overwriting the files in the default folder:

gcs_dir_name = None

To avoid overwriting the files (such as for different environments such as development, staging, and production), you can set up corresponding folder, and specify the folder to stage the artifact under:

gcs_dir_name = "dev" # or "staging" or "prod"

If you want or need to avoid collisions, you can generate a random uuid:

import uuid
gcs_dir_name = str(uuid.uuid4())

Configure resource metadata

You can set metadata on the ReasoningEngine resource:

display_name = "Currency Exchange Rate Agent (Staging)"

description = """
An agent that has access to tools for looking up the exchange rate.

If you run into any issues, please contact the dev team.
"""

For a full set of the parameters, see the API reference.

Configure a custom service account

You can configure a custom service account as the identity of your deployed agent, instead of the default identity.

To do so, specify the email of your custom service account as the service_account when creating or updating the Agent Engine instance, for example:

# Create a new instance
client.agent_engines.create(
    agent=local_agent,
    config={
        "service_account": "my-custom-service-account@my-project.iam.gserviceaccount.com",
        # ...
    },
)

# Update an existing instance
resource_name = "projects/{project_id}/locations/{location}/reasoningEngines/{reasoning_engine_id}"
client.agent_engines.update(
    name=resource_name,
    agent=local_agent,
    config={
        "service_account": "my-new-custom-service-account@my-project.iam.gserviceaccount.com",
        # ...
    },
)

Note: Specify only the service account email, not the full resource URI, such as projects/{project_id}/serviceAccounts/{service_account_email}.

Configure Private Service Connect interface

If you have Private Service Connect interface and DNS peering set up, you can specify your network attachment and private DNS peering while deploying your agent:

remote_agent = client.agent_engines.create(
    agent=local_agent,
    config={
        "psc_interface_config": {
            "network_attachment": "NETWORK_ATTACHMENT",
            "dns_peering_configs": [
                {
                    "domain": "DOMAIN_SUFFIX",
                    "target_project": "TARGET_PROJECT",
                    "target_network": "TARGET_NETWORK",
                },
            ],
        },
    },
)

where

NETWORK_ATTACHMENT is the name or full path of your network attachment. If the network attachment is created in a project (such as the Shared VPC host project) different from where you use Agent Engine, you need to pass the full path of your network attachment.
DOMAIN_SUFFIX is the DNS name of the private Cloud DNS zone that you created when setting up the private DNS Peering.
TARGET_PROJECT is the project that hosts the VPC network.
TARGET_NETWORK is the VPC network name.

You can configure multiple agents to use either a single, shared network attachment or unique, dedicated network attachments. To use a shared network attachment, provide the same network attachment in the psc_interface_config for each agent you create.

Configure customer-managed encryption keys

You can use a custom key to encrypt your agent's data at rest. See Agent Engine Customer-managed encryption keys (CMEK) for more details.

To configure the custom key (CMEK) for your agent, you need to provide the key resource name to the encryption_spec parameter when creating the Agent Engine instance.

# The fully qualified key name
kms_key_name = "projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY_NAME"

remote_agent = client.agent_engines.create(
    agent=local_agent,
    config={
        "encryption_spec": {"kms_key_name": kms_key_name},
        # ... other parameters
    },
)

Create an `AgentEngine` instance

To deploy the agent on Vertex AI, use client.agent_engines.create to pass in the local_agent object along with any optional configurations:

remote_agent = client.agent_engines.create(
    agent=local_agent,                                  # Optional.
    config={
        "requirements": requirements,                   # Optional.
        "extra_packages": extra_packages,               # Optional.
        "gcs_dir_name": gcs_dir_name,                   # Optional.
        "display_name": display_name,                   # Optional.
        "description": description,                     # Optional.
        "env_vars": env_vars,                           # Optional.
        "build_options": build_options,                 # Optional.
        "service_account": service_account,             # Optional.
        "min_instances": min_instances,                 # Optional.
        "max_instances": max_instances,                 # Optional.
        "resource_limits": resource_limits,             # Optional.
        "container_concurrency": container_concurrency, # Optional
        "encryption_spec": encryption_spec,             # Optional.
    },
)

Deployment takes a few minutes, during which the following steps happen in the background:

A bundle of the following artifacts are generated locally:
- *.pkl a pickle file corresponding to local_agent.
- requirements.txt a text file containing the package requirements.
- dependencies.tar.gz a tar file containing any extra packages.
The bundle is uploaded to Cloud Storage (under the corresponding folder) for staging the artifacts.
The Cloud Storage URIs for the respective artifacts are specified in the PackageSpec.
The Vertex AI Agent Engine service receives the request and builds containers and starts HTTP servers on the backend.

Deployment latency depends on the total time it takes to install required packages. Once deployed, remote_agent corresponds to an instance of local_agent that is running on Vertex AI and can be queried or deleted. It is separate from local instances of the agent.

The remote_agent object corresponds to an AgentEngine class that contains the following attributes:

a remote_agent.api_resource with information about the deployed agent. You can also call agent.operation_schemas() to return the list of operations that the agent supports. See List the supported operations for details.
a remote_agent.api_client that allows for synchronous service interactions.
a remote_agent.async_api_client that allows for asynchronous service interactions.

(Optional) Get the agent resource ID

Each deployed agent has a unique identifier. You can run the following command to get the resource name for your deployed agent:

remote_agent.api_resource.name

The response should look like the following string:

"projects/PROJECT_NUMBER/locations/LOCATION/reasoningEngines/RESOURCE_ID"

where

PROJECT_ID is the Google Cloud project ID where the deployed agent runs.
LOCATION is the region where the deployed agent runs.
RESOURCE_ID is the ID of the deployed agent as a reasoningEngine resource.

(Optional) List the supported operations

Each deployed agent has a list of supported operations. You can run the following command to get the list of operations supported by the deployed agent:

remote_agent.operation_schemas()

The schema for each operation is a dictionary that documents the information of a method for the agent that you can call. The set of supported operations depends on the framework you used to develop your agent:

(Optional) Grant the deployed agent permissions

If the deployed agent needs to be granted any additional permissions, follow the instructions in Set up the identity and permissions for your agent.

Deploy an agent Stay organized with collections Save and categorize content based on your preferences.

Prerequisites

(Optional) Configure your agent for deployment

Define the package requirements

ADK

A2A

LangChain

LangGraph

AG2

LlamaIndex

Define additional packages

Define environment variables

Dictionary

List

Define customized resource controls

Define build options

install_npx.sh

install_uvx.sh

install_gcloud_cli.sh

Define a Cloud Storage folder

Configure resource metadata

Configure a custom service account

Configure Private Service Connect interface

Configure customer-managed encryption keys

Create an AgentEngine instance

(Optional) Get the agent resource ID

(Optional) List the supported operations

(Optional) Grant the deployed agent permissions

What's next

Deploy an agent

Create an `AgentEngine` instance