- 3.52.0 (latest)
- 3.50.0
- 3.49.0
- 3.48.0
- 3.47.0
- 3.46.0
- 3.45.0
- 3.44.0
- 3.43.0
- 3.42.0
- 3.41.0
- 3.40.0
- 3.38.0
- 3.37.0
- 3.36.0
- 3.35.0
- 3.34.0
- 3.33.0
- 3.32.0
- 3.31.0
- 3.30.0
- 3.29.0
- 3.28.0
- 3.25.0
- 3.24.0
- 3.23.0
- 3.22.0
- 3.21.0
- 3.20.0
- 3.19.0
- 3.18.0
- 3.17.0
- 3.16.0
- 3.15.0
- 3.14.0
- 3.13.0
- 3.12.0
- 3.11.0
- 3.10.0
- 3.9.0
- 3.8.0
- 3.7.0
- 3.6.0
- 3.5.0
- 3.4.2
- 3.3.0
- 3.2.0
- 3.0.0
- 2.9.8
- 2.8.9
- 2.7.4
- 2.5.3
- 2.4.0
public static final class ModelContainerSpec.Builder extends GeneratedMessageV3.Builder<ModelContainerSpec.Builder> implements ModelContainerSpecOrBuilder
Specification of a container for serving predictions. Some fields in this message correspond to fields in the Kubernetes Container v1 core specification.
Protobuf type google.cloud.aiplatform.v1.ModelContainerSpec
Inheritance
Object > AbstractMessageLite.Builder<MessageType,BuilderType> > AbstractMessage.Builder<BuilderType> > GeneratedMessageV3.Builder > ModelContainerSpec.BuilderImplements
ModelContainerSpecOrBuilderStatic Methods
getDescriptor()
public static final Descriptors.Descriptor getDescriptor()
Returns | |
---|---|
Type | Description |
Descriptor |
Methods
addAllArgs(Iterable<String> values)
public ModelContainerSpec.Builder addAllArgs(Iterable<String> values)
Immutable. Specifies arguments for the command that runs when the container
starts. This overrides the container's
CMD
. Specify
this field as an array of executable and arguments, similar to a Docker
CMD
's "default parameters" form.
If you don't specify this field but do specify the
command field,
then the command from the command
field runs without any additional
arguments. See the Kubernetes documentation about how the command
and
args
fields interact with a container's ENTRYPOINT
and
CMD
.
If you don't specify this field and don't specify the command
field,
then the container's
ENTRYPOINT
and
CMD
determine what runs based on their default behavior. See the Docker
documentation about how CMD
and ENTRYPOINT
interact.
In this field, you can reference environment variables
set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the args
field of the Kubernetes Containers v1 core
API.
repeated string args = 3 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
values |
Iterable<String> The args to add. |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
addAllCommand(Iterable<String> values)
public ModelContainerSpec.Builder addAllCommand(Iterable<String> values)
Immutable. Specifies the command that runs when the container starts. This
overrides the container's
ENTRYPOINT.
Specify this field as an array of executable and arguments, similar to a
Docker ENTRYPOINT
's "exec" form, not its "shell" form.
If you do not specify this field, then the container's ENTRYPOINT
runs,
in conjunction with the
args field or the
container's CMD
,
if either exists. If this field is not specified and the container does not
have an ENTRYPOINT
, then refer to the Docker documentation about how
CMD
and ENTRYPOINT
interact.
If you specify this field, then you can also specify the args
field to
provide additional arguments for this command. However, if you specify this
field, then the container's CMD
is ignored. See the
Kubernetes documentation about how the
command
and args
fields interact with a container's ENTRYPOINT
and
CMD
.
In this field, you can reference environment variables set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the command
field of the Kubernetes Containers v1 core
API.
repeated string command = 2 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
values |
Iterable<String> The command to add. |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
addAllEnv(Iterable<? extends EnvVar> values)
public ModelContainerSpec.Builder addAllEnv(Iterable<? extends EnvVar> values)
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
values |
Iterable<? extends com.google.cloud.aiplatform.v1.EnvVar> |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
addAllGrpcPorts(Iterable<? extends Port> values)
public ModelContainerSpec.Builder addAllGrpcPorts(Iterable<? extends Port> values)
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
values |
Iterable<? extends com.google.cloud.aiplatform.v1.Port> |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
addAllPorts(Iterable<? extends Port> values)
public ModelContainerSpec.Builder addAllPorts(Iterable<? extends Port> values)
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
values |
Iterable<? extends com.google.cloud.aiplatform.v1.Port> |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
addArgs(String value)
public ModelContainerSpec.Builder addArgs(String value)
Immutable. Specifies arguments for the command that runs when the container
starts. This overrides the container's
CMD
. Specify
this field as an array of executable and arguments, similar to a Docker
CMD
's "default parameters" form.
If you don't specify this field but do specify the
command field,
then the command from the command
field runs without any additional
arguments. See the Kubernetes documentation about how the command
and
args
fields interact with a container's ENTRYPOINT
and
CMD
.
If you don't specify this field and don't specify the command
field,
then the container's
ENTRYPOINT
and
CMD
determine what runs based on their default behavior. See the Docker
documentation about how CMD
and ENTRYPOINT
interact.
In this field, you can reference environment variables
set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the args
field of the Kubernetes Containers v1 core
API.
repeated string args = 3 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
String The args to add. |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
addArgsBytes(ByteString value)
public ModelContainerSpec.Builder addArgsBytes(ByteString value)
Immutable. Specifies arguments for the command that runs when the container
starts. This overrides the container's
CMD
. Specify
this field as an array of executable and arguments, similar to a Docker
CMD
's "default parameters" form.
If you don't specify this field but do specify the
command field,
then the command from the command
field runs without any additional
arguments. See the Kubernetes documentation about how the command
and
args
fields interact with a container's ENTRYPOINT
and
CMD
.
If you don't specify this field and don't specify the command
field,
then the container's
ENTRYPOINT
and
CMD
determine what runs based on their default behavior. See the Docker
documentation about how CMD
and ENTRYPOINT
interact.
In this field, you can reference environment variables
set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the args
field of the Kubernetes Containers v1 core
API.
repeated string args = 3 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
ByteString The bytes of the args to add. |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
addCommand(String value)
public ModelContainerSpec.Builder addCommand(String value)
Immutable. Specifies the command that runs when the container starts. This
overrides the container's
ENTRYPOINT.
Specify this field as an array of executable and arguments, similar to a
Docker ENTRYPOINT
's "exec" form, not its "shell" form.
If you do not specify this field, then the container's ENTRYPOINT
runs,
in conjunction with the
args field or the
container's CMD
,
if either exists. If this field is not specified and the container does not
have an ENTRYPOINT
, then refer to the Docker documentation about how
CMD
and ENTRYPOINT
interact.
If you specify this field, then you can also specify the args
field to
provide additional arguments for this command. However, if you specify this
field, then the container's CMD
is ignored. See the
Kubernetes documentation about how the
command
and args
fields interact with a container's ENTRYPOINT
and
CMD
.
In this field, you can reference environment variables set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the command
field of the Kubernetes Containers v1 core
API.
repeated string command = 2 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
String The command to add. |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
addCommandBytes(ByteString value)
public ModelContainerSpec.Builder addCommandBytes(ByteString value)
Immutable. Specifies the command that runs when the container starts. This
overrides the container's
ENTRYPOINT.
Specify this field as an array of executable and arguments, similar to a
Docker ENTRYPOINT
's "exec" form, not its "shell" form.
If you do not specify this field, then the container's ENTRYPOINT
runs,
in conjunction with the
args field or the
container's CMD
,
if either exists. If this field is not specified and the container does not
have an ENTRYPOINT
, then refer to the Docker documentation about how
CMD
and ENTRYPOINT
interact.
If you specify this field, then you can also specify the args
field to
provide additional arguments for this command. However, if you specify this
field, then the container's CMD
is ignored. See the
Kubernetes documentation about how the
command
and args
fields interact with a container's ENTRYPOINT
and
CMD
.
In this field, you can reference environment variables set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the command
field of the Kubernetes Containers v1 core
API.
repeated string command = 2 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
ByteString The bytes of the command to add. |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
addEnv(EnvVar value)
public ModelContainerSpec.Builder addEnv(EnvVar value)
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
EnvVar |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
addEnv(EnvVar.Builder builderForValue)
public ModelContainerSpec.Builder addEnv(EnvVar.Builder builderForValue)
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
builderForValue |
EnvVar.Builder |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
addEnv(int index, EnvVar value)
public ModelContainerSpec.Builder addEnv(int index, EnvVar value)
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Parameters | |
---|---|
Name | Description |
index |
int |
value |
EnvVar |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
addEnv(int index, EnvVar.Builder builderForValue)
public ModelContainerSpec.Builder addEnv(int index, EnvVar.Builder builderForValue)
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Parameters | |
---|---|
Name | Description |
index |
int |
builderForValue |
EnvVar.Builder |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
addEnvBuilder()
public EnvVar.Builder addEnvBuilder()
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
EnvVar.Builder |
addEnvBuilder(int index)
public EnvVar.Builder addEnvBuilder(int index)
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int |
Returns | |
---|---|
Type | Description |
EnvVar.Builder |
addGrpcPorts(Port value)
public ModelContainerSpec.Builder addGrpcPorts(Port value)
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
Port |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
addGrpcPorts(Port.Builder builderForValue)
public ModelContainerSpec.Builder addGrpcPorts(Port.Builder builderForValue)
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
builderForValue |
Port.Builder |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
addGrpcPorts(int index, Port value)
public ModelContainerSpec.Builder addGrpcPorts(int index, Port value)
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Parameters | |
---|---|
Name | Description |
index |
int |
value |
Port |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
addGrpcPorts(int index, Port.Builder builderForValue)
public ModelContainerSpec.Builder addGrpcPorts(int index, Port.Builder builderForValue)
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Parameters | |
---|---|
Name | Description |
index |
int |
builderForValue |
Port.Builder |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
addGrpcPortsBuilder()
public Port.Builder addGrpcPortsBuilder()
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
Port.Builder |
addGrpcPortsBuilder(int index)
public Port.Builder addGrpcPortsBuilder(int index)
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int |
Returns | |
---|---|
Type | Description |
Port.Builder |
addPorts(Port value)
public ModelContainerSpec.Builder addPorts(Port value)
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
Port |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
addPorts(Port.Builder builderForValue)
public ModelContainerSpec.Builder addPorts(Port.Builder builderForValue)
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
builderForValue |
Port.Builder |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
addPorts(int index, Port value)
public ModelContainerSpec.Builder addPorts(int index, Port value)
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Parameters | |
---|---|
Name | Description |
index |
int |
value |
Port |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
addPorts(int index, Port.Builder builderForValue)
public ModelContainerSpec.Builder addPorts(int index, Port.Builder builderForValue)
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Parameters | |
---|---|
Name | Description |
index |
int |
builderForValue |
Port.Builder |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
addPortsBuilder()
public Port.Builder addPortsBuilder()
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
Port.Builder |
addPortsBuilder(int index)
public Port.Builder addPortsBuilder(int index)
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int |
Returns | |
---|---|
Type | Description |
Port.Builder |
addRepeatedField(Descriptors.FieldDescriptor field, Object value)
public ModelContainerSpec.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Parameters | |
---|---|
Name | Description |
field |
FieldDescriptor |
value |
Object |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
build()
public ModelContainerSpec build()
Returns | |
---|---|
Type | Description |
ModelContainerSpec |
buildPartial()
public ModelContainerSpec buildPartial()
Returns | |
---|---|
Type | Description |
ModelContainerSpec |
clear()
public ModelContainerSpec.Builder clear()
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
clearArgs()
public ModelContainerSpec.Builder clearArgs()
Immutable. Specifies arguments for the command that runs when the container
starts. This overrides the container's
CMD
. Specify
this field as an array of executable and arguments, similar to a Docker
CMD
's "default parameters" form.
If you don't specify this field but do specify the
command field,
then the command from the command
field runs without any additional
arguments. See the Kubernetes documentation about how the command
and
args
fields interact with a container's ENTRYPOINT
and
CMD
.
If you don't specify this field and don't specify the command
field,
then the container's
ENTRYPOINT
and
CMD
determine what runs based on their default behavior. See the Docker
documentation about how CMD
and ENTRYPOINT
interact.
In this field, you can reference environment variables
set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the args
field of the Kubernetes Containers v1 core
API.
repeated string args = 3 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
clearCommand()
public ModelContainerSpec.Builder clearCommand()
Immutable. Specifies the command that runs when the container starts. This
overrides the container's
ENTRYPOINT.
Specify this field as an array of executable and arguments, similar to a
Docker ENTRYPOINT
's "exec" form, not its "shell" form.
If you do not specify this field, then the container's ENTRYPOINT
runs,
in conjunction with the
args field or the
container's CMD
,
if either exists. If this field is not specified and the container does not
have an ENTRYPOINT
, then refer to the Docker documentation about how
CMD
and ENTRYPOINT
interact.
If you specify this field, then you can also specify the args
field to
provide additional arguments for this command. However, if you specify this
field, then the container's CMD
is ignored. See the
Kubernetes documentation about how the
command
and args
fields interact with a container's ENTRYPOINT
and
CMD
.
In this field, you can reference environment variables set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the command
field of the Kubernetes Containers v1 core
API.
repeated string command = 2 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
clearDeploymentTimeout()
public ModelContainerSpec.Builder clearDeploymentTimeout()
Immutable. Deployment timeout. Limit for deployment timeout is 2 hours.
.google.protobuf.Duration deployment_timeout = 10 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
clearEnv()
public ModelContainerSpec.Builder clearEnv()
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
clearField(Descriptors.FieldDescriptor field)
public ModelContainerSpec.Builder clearField(Descriptors.FieldDescriptor field)
Parameter | |
---|---|
Name | Description |
field |
FieldDescriptor |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
clearGrpcPorts()
public ModelContainerSpec.Builder clearGrpcPorts()
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
clearHealthProbe()
public ModelContainerSpec.Builder clearHealthProbe()
Immutable. Specification for Kubernetes readiness probe.
.google.cloud.aiplatform.v1.Probe health_probe = 13 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
clearHealthRoute()
public ModelContainerSpec.Builder clearHealthRoute()
Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks.
For example, if you set this field to /bar
, then Vertex AI
intermittently sends a GET request to the /bar
path on the port of your
container specified by the first value of this ModelContainerSpec
's
ports field.
If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: <code>/v1/endpoints/<var>ENDPOINT</var>/deployedModels/<var>DEPLOYED_MODEL</var>:predict</code> The placeholders in this value are replaced as follows:
<var>ENDPOINT</var>: The last segment (following
endpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.)<var>DEPLOYED_MODEL</var>: DeployedModel.id of the
DeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.)
string health_route = 7 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
clearImageUri()
public ModelContainerSpec.Builder clearImageUri()
Required. Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent.
The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used.
To learn about the requirements for the Docker image itself, see Custom container requirements.
You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
string image_uri = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
clearOneof(Descriptors.OneofDescriptor oneof)
public ModelContainerSpec.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Parameter | |
---|---|
Name | Description |
oneof |
OneofDescriptor |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
clearPorts()
public ModelContainerSpec.Builder clearPorts()
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
clearPredictRoute()
public ModelContainerSpec.Builder clearPredictRoute()
Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response.
For example, if you set this field to /foo
, then when Vertex AI
receives a prediction request, it forwards the request body in a POST
request to the /foo
path on the port of your container specified by the
first value of this ModelContainerSpec
's
ports field.
If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: <code>/v1/endpoints/<var>ENDPOINT</var>/deployedModels/<var>DEPLOYED_MODEL</var>:predict</code> The placeholders in this value are replaced as follows:
<var>ENDPOINT</var>: The last segment (following
endpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.)<var>DEPLOYED_MODEL</var>: DeployedModel.id of the
DeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.)
string predict_route = 6 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
clearSharedMemorySizeMb()
public ModelContainerSpec.Builder clearSharedMemorySizeMb()
Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes.
int64 shared_memory_size_mb = 11 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
clearStartupProbe()
public ModelContainerSpec.Builder clearStartupProbe()
Immutable. Specification for Kubernetes startup probe.
.google.cloud.aiplatform.v1.Probe startup_probe = 12 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
clone()
public ModelContainerSpec.Builder clone()
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
getArgs(int index)
public String getArgs(int index)
Immutable. Specifies arguments for the command that runs when the container
starts. This overrides the container's
CMD
. Specify
this field as an array of executable and arguments, similar to a Docker
CMD
's "default parameters" form.
If you don't specify this field but do specify the
command field,
then the command from the command
field runs without any additional
arguments. See the Kubernetes documentation about how the command
and
args
fields interact with a container's ENTRYPOINT
and
CMD
.
If you don't specify this field and don't specify the command
field,
then the container's
ENTRYPOINT
and
CMD
determine what runs based on their default behavior. See the Docker
documentation about how CMD
and ENTRYPOINT
interact.
In this field, you can reference environment variables
set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the args
field of the Kubernetes Containers v1 core
API.
repeated string args = 3 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int The index of the element to return. |
Returns | |
---|---|
Type | Description |
String |
The args at the given index. |
getArgsBytes(int index)
public ByteString getArgsBytes(int index)
Immutable. Specifies arguments for the command that runs when the container
starts. This overrides the container's
CMD
. Specify
this field as an array of executable and arguments, similar to a Docker
CMD
's "default parameters" form.
If you don't specify this field but do specify the
command field,
then the command from the command
field runs without any additional
arguments. See the Kubernetes documentation about how the command
and
args
fields interact with a container's ENTRYPOINT
and
CMD
.
If you don't specify this field and don't specify the command
field,
then the container's
ENTRYPOINT
and
CMD
determine what runs based on their default behavior. See the Docker
documentation about how CMD
and ENTRYPOINT
interact.
In this field, you can reference environment variables
set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the args
field of the Kubernetes Containers v1 core
API.
repeated string args = 3 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int The index of the value to return. |
Returns | |
---|---|
Type | Description |
ByteString |
The bytes of the args at the given index. |
getArgsCount()
public int getArgsCount()
Immutable. Specifies arguments for the command that runs when the container
starts. This overrides the container's
CMD
. Specify
this field as an array of executable and arguments, similar to a Docker
CMD
's "default parameters" form.
If you don't specify this field but do specify the
command field,
then the command from the command
field runs without any additional
arguments. See the Kubernetes documentation about how the command
and
args
fields interact with a container's ENTRYPOINT
and
CMD
.
If you don't specify this field and don't specify the command
field,
then the container's
ENTRYPOINT
and
CMD
determine what runs based on their default behavior. See the Docker
documentation about how CMD
and ENTRYPOINT
interact.
In this field, you can reference environment variables
set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the args
field of the Kubernetes Containers v1 core
API.
repeated string args = 3 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
int |
The count of args. |
getArgsList()
public ProtocolStringList getArgsList()
Immutable. Specifies arguments for the command that runs when the container
starts. This overrides the container's
CMD
. Specify
this field as an array of executable and arguments, similar to a Docker
CMD
's "default parameters" form.
If you don't specify this field but do specify the
command field,
then the command from the command
field runs without any additional
arguments. See the Kubernetes documentation about how the command
and
args
fields interact with a container's ENTRYPOINT
and
CMD
.
If you don't specify this field and don't specify the command
field,
then the container's
ENTRYPOINT
and
CMD
determine what runs based on their default behavior. See the Docker
documentation about how CMD
and ENTRYPOINT
interact.
In this field, you can reference environment variables
set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the args
field of the Kubernetes Containers v1 core
API.
repeated string args = 3 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ProtocolStringList |
A list containing the args. |
getCommand(int index)
public String getCommand(int index)
Immutable. Specifies the command that runs when the container starts. This
overrides the container's
ENTRYPOINT.
Specify this field as an array of executable and arguments, similar to a
Docker ENTRYPOINT
's "exec" form, not its "shell" form.
If you do not specify this field, then the container's ENTRYPOINT
runs,
in conjunction with the
args field or the
container's CMD
,
if either exists. If this field is not specified and the container does not
have an ENTRYPOINT
, then refer to the Docker documentation about how
CMD
and ENTRYPOINT
interact.
If you specify this field, then you can also specify the args
field to
provide additional arguments for this command. However, if you specify this
field, then the container's CMD
is ignored. See the
Kubernetes documentation about how the
command
and args
fields interact with a container's ENTRYPOINT
and
CMD
.
In this field, you can reference environment variables set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the command
field of the Kubernetes Containers v1 core
API.
repeated string command = 2 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int The index of the element to return. |
Returns | |
---|---|
Type | Description |
String |
The command at the given index. |
getCommandBytes(int index)
public ByteString getCommandBytes(int index)
Immutable. Specifies the command that runs when the container starts. This
overrides the container's
ENTRYPOINT.
Specify this field as an array of executable and arguments, similar to a
Docker ENTRYPOINT
's "exec" form, not its "shell" form.
If you do not specify this field, then the container's ENTRYPOINT
runs,
in conjunction with the
args field or the
container's CMD
,
if either exists. If this field is not specified and the container does not
have an ENTRYPOINT
, then refer to the Docker documentation about how
CMD
and ENTRYPOINT
interact.
If you specify this field, then you can also specify the args
field to
provide additional arguments for this command. However, if you specify this
field, then the container's CMD
is ignored. See the
Kubernetes documentation about how the
command
and args
fields interact with a container's ENTRYPOINT
and
CMD
.
In this field, you can reference environment variables set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the command
field of the Kubernetes Containers v1 core
API.
repeated string command = 2 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int The index of the value to return. |
Returns | |
---|---|
Type | Description |
ByteString |
The bytes of the command at the given index. |
getCommandCount()
public int getCommandCount()
Immutable. Specifies the command that runs when the container starts. This
overrides the container's
ENTRYPOINT.
Specify this field as an array of executable and arguments, similar to a
Docker ENTRYPOINT
's "exec" form, not its "shell" form.
If you do not specify this field, then the container's ENTRYPOINT
runs,
in conjunction with the
args field or the
container's CMD
,
if either exists. If this field is not specified and the container does not
have an ENTRYPOINT
, then refer to the Docker documentation about how
CMD
and ENTRYPOINT
interact.
If you specify this field, then you can also specify the args
field to
provide additional arguments for this command. However, if you specify this
field, then the container's CMD
is ignored. See the
Kubernetes documentation about how the
command
and args
fields interact with a container's ENTRYPOINT
and
CMD
.
In this field, you can reference environment variables set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the command
field of the Kubernetes Containers v1 core
API.
repeated string command = 2 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
int |
The count of command. |
getCommandList()
public ProtocolStringList getCommandList()
Immutable. Specifies the command that runs when the container starts. This
overrides the container's
ENTRYPOINT.
Specify this field as an array of executable and arguments, similar to a
Docker ENTRYPOINT
's "exec" form, not its "shell" form.
If you do not specify this field, then the container's ENTRYPOINT
runs,
in conjunction with the
args field or the
container's CMD
,
if either exists. If this field is not specified and the container does not
have an ENTRYPOINT
, then refer to the Docker documentation about how
CMD
and ENTRYPOINT
interact.
If you specify this field, then you can also specify the args
field to
provide additional arguments for this command. However, if you specify this
field, then the container's CMD
is ignored. See the
Kubernetes documentation about how the
command
and args
fields interact with a container's ENTRYPOINT
and
CMD
.
In this field, you can reference environment variables set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the command
field of the Kubernetes Containers v1 core
API.
repeated string command = 2 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ProtocolStringList |
A list containing the command. |
getDefaultInstanceForType()
public ModelContainerSpec getDefaultInstanceForType()
Returns | |
---|---|
Type | Description |
ModelContainerSpec |
getDeploymentTimeout()
public Duration getDeploymentTimeout()
Immutable. Deployment timeout. Limit for deployment timeout is 2 hours.
.google.protobuf.Duration deployment_timeout = 10 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
Duration |
The deploymentTimeout. |
getDeploymentTimeoutBuilder()
public Duration.Builder getDeploymentTimeoutBuilder()
Immutable. Deployment timeout. Limit for deployment timeout is 2 hours.
.google.protobuf.Duration deployment_timeout = 10 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
Builder |
getDeploymentTimeoutOrBuilder()
public DurationOrBuilder getDeploymentTimeoutOrBuilder()
Immutable. Deployment timeout. Limit for deployment timeout is 2 hours.
.google.protobuf.Duration deployment_timeout = 10 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
DurationOrBuilder |
getDescriptorForType()
public Descriptors.Descriptor getDescriptorForType()
Returns | |
---|---|
Type | Description |
Descriptor |
getEnv(int index)
public EnvVar getEnv(int index)
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int |
Returns | |
---|---|
Type | Description |
EnvVar |
getEnvBuilder(int index)
public EnvVar.Builder getEnvBuilder(int index)
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int |
Returns | |
---|---|
Type | Description |
EnvVar.Builder |
getEnvBuilderList()
public List<EnvVar.Builder> getEnvBuilderList()
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
List<Builder> |
getEnvCount()
public int getEnvCount()
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
int |
getEnvList()
public List<EnvVar> getEnvList()
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
List<EnvVar> |
getEnvOrBuilder(int index)
public EnvVarOrBuilder getEnvOrBuilder(int index)
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int |
Returns | |
---|---|
Type | Description |
EnvVarOrBuilder |
getEnvOrBuilderList()
public List<? extends EnvVarOrBuilder> getEnvOrBuilderList()
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
List<? extends com.google.cloud.aiplatform.v1.EnvVarOrBuilder> |
getGrpcPorts(int index)
public Port getGrpcPorts(int index)
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int |
Returns | |
---|---|
Type | Description |
Port |
getGrpcPortsBuilder(int index)
public Port.Builder getGrpcPortsBuilder(int index)
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int |
Returns | |
---|---|
Type | Description |
Port.Builder |
getGrpcPortsBuilderList()
public List<Port.Builder> getGrpcPortsBuilderList()
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
List<Builder> |
getGrpcPortsCount()
public int getGrpcPortsCount()
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
int |
getGrpcPortsList()
public List<Port> getGrpcPortsList()
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
List<Port> |
getGrpcPortsOrBuilder(int index)
public PortOrBuilder getGrpcPortsOrBuilder(int index)
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int |
Returns | |
---|---|
Type | Description |
PortOrBuilder |
getGrpcPortsOrBuilderList()
public List<? extends PortOrBuilder> getGrpcPortsOrBuilderList()
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
List<? extends com.google.cloud.aiplatform.v1.PortOrBuilder> |
getHealthProbe()
public Probe getHealthProbe()
Immutable. Specification for Kubernetes readiness probe.
.google.cloud.aiplatform.v1.Probe health_probe = 13 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
Probe |
The healthProbe. |
getHealthProbeBuilder()
public Probe.Builder getHealthProbeBuilder()
Immutable. Specification for Kubernetes readiness probe.
.google.cloud.aiplatform.v1.Probe health_probe = 13 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
Probe.Builder |
getHealthProbeOrBuilder()
public ProbeOrBuilder getHealthProbeOrBuilder()
Immutable. Specification for Kubernetes readiness probe.
.google.cloud.aiplatform.v1.Probe health_probe = 13 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ProbeOrBuilder |
getHealthRoute()
public String getHealthRoute()
Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks.
For example, if you set this field to /bar
, then Vertex AI
intermittently sends a GET request to the /bar
path on the port of your
container specified by the first value of this ModelContainerSpec
's
ports field.
If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: <code>/v1/endpoints/<var>ENDPOINT</var>/deployedModels/<var>DEPLOYED_MODEL</var>:predict</code> The placeholders in this value are replaced as follows:
<var>ENDPOINT</var>: The last segment (following
endpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.)<var>DEPLOYED_MODEL</var>: DeployedModel.id of the
DeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.)
string health_route = 7 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
String |
The healthRoute. |
getHealthRouteBytes()
public ByteString getHealthRouteBytes()
Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks.
For example, if you set this field to /bar
, then Vertex AI
intermittently sends a GET request to the /bar
path on the port of your
container specified by the first value of this ModelContainerSpec
's
ports field.
If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: <code>/v1/endpoints/<var>ENDPOINT</var>/deployedModels/<var>DEPLOYED_MODEL</var>:predict</code> The placeholders in this value are replaced as follows:
<var>ENDPOINT</var>: The last segment (following
endpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.)<var>DEPLOYED_MODEL</var>: DeployedModel.id of the
DeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.)
string health_route = 7 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ByteString |
The bytes for healthRoute. |
getImageUri()
public String getImageUri()
Required. Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent.
The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used.
To learn about the requirements for the Docker image itself, see Custom container requirements.
You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
string image_uri = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
String |
The imageUri. |
getImageUriBytes()
public ByteString getImageUriBytes()
Required. Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent.
The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used.
To learn about the requirements for the Docker image itself, see Custom container requirements.
You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
string image_uri = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ByteString |
The bytes for imageUri. |
getPorts(int index)
public Port getPorts(int index)
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int |
Returns | |
---|---|
Type | Description |
Port |
getPortsBuilder(int index)
public Port.Builder getPortsBuilder(int index)
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int |
Returns | |
---|---|
Type | Description |
Port.Builder |
getPortsBuilderList()
public List<Port.Builder> getPortsBuilderList()
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
List<Builder> |
getPortsCount()
public int getPortsCount()
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
int |
getPortsList()
public List<Port> getPortsList()
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
List<Port> |
getPortsOrBuilder(int index)
public PortOrBuilder getPortsOrBuilder(int index)
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int |
Returns | |
---|---|
Type | Description |
PortOrBuilder |
getPortsOrBuilderList()
public List<? extends PortOrBuilder> getPortsOrBuilderList()
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
List<? extends com.google.cloud.aiplatform.v1.PortOrBuilder> |
getPredictRoute()
public String getPredictRoute()
Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response.
For example, if you set this field to /foo
, then when Vertex AI
receives a prediction request, it forwards the request body in a POST
request to the /foo
path on the port of your container specified by the
first value of this ModelContainerSpec
's
ports field.
If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: <code>/v1/endpoints/<var>ENDPOINT</var>/deployedModels/<var>DEPLOYED_MODEL</var>:predict</code> The placeholders in this value are replaced as follows:
<var>ENDPOINT</var>: The last segment (following
endpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.)<var>DEPLOYED_MODEL</var>: DeployedModel.id of the
DeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.)
string predict_route = 6 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
String |
The predictRoute. |
getPredictRouteBytes()
public ByteString getPredictRouteBytes()
Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response.
For example, if you set this field to /foo
, then when Vertex AI
receives a prediction request, it forwards the request body in a POST
request to the /foo
path on the port of your container specified by the
first value of this ModelContainerSpec
's
ports field.
If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: <code>/v1/endpoints/<var>ENDPOINT</var>/deployedModels/<var>DEPLOYED_MODEL</var>:predict</code> The placeholders in this value are replaced as follows:
<var>ENDPOINT</var>: The last segment (following
endpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.)<var>DEPLOYED_MODEL</var>: DeployedModel.id of the
DeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.)
string predict_route = 6 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ByteString |
The bytes for predictRoute. |
getSharedMemorySizeMb()
public long getSharedMemorySizeMb()
Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes.
int64 shared_memory_size_mb = 11 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
long |
The sharedMemorySizeMb. |
getStartupProbe()
public Probe getStartupProbe()
Immutable. Specification for Kubernetes startup probe.
.google.cloud.aiplatform.v1.Probe startup_probe = 12 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
Probe |
The startupProbe. |
getStartupProbeBuilder()
public Probe.Builder getStartupProbeBuilder()
Immutable. Specification for Kubernetes startup probe.
.google.cloud.aiplatform.v1.Probe startup_probe = 12 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
Probe.Builder |
getStartupProbeOrBuilder()
public ProbeOrBuilder getStartupProbeOrBuilder()
Immutable. Specification for Kubernetes startup probe.
.google.cloud.aiplatform.v1.Probe startup_probe = 12 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
ProbeOrBuilder |
hasDeploymentTimeout()
public boolean hasDeploymentTimeout()
Immutable. Deployment timeout. Limit for deployment timeout is 2 hours.
.google.protobuf.Duration deployment_timeout = 10 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
boolean |
Whether the deploymentTimeout field is set. |
hasHealthProbe()
public boolean hasHealthProbe()
Immutable. Specification for Kubernetes readiness probe.
.google.cloud.aiplatform.v1.Probe health_probe = 13 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
boolean |
Whether the healthProbe field is set. |
hasStartupProbe()
public boolean hasStartupProbe()
Immutable. Specification for Kubernetes startup probe.
.google.cloud.aiplatform.v1.Probe startup_probe = 12 [(.google.api.field_behavior) = IMMUTABLE];
Returns | |
---|---|
Type | Description |
boolean |
Whether the startupProbe field is set. |
internalGetFieldAccessorTable()
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns | |
---|---|
Type | Description |
FieldAccessorTable |
isInitialized()
public final boolean isInitialized()
Returns | |
---|---|
Type | Description |
boolean |
mergeDeploymentTimeout(Duration value)
public ModelContainerSpec.Builder mergeDeploymentTimeout(Duration value)
Immutable. Deployment timeout. Limit for deployment timeout is 2 hours.
.google.protobuf.Duration deployment_timeout = 10 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
Duration |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
mergeFrom(ModelContainerSpec other)
public ModelContainerSpec.Builder mergeFrom(ModelContainerSpec other)
Parameter | |
---|---|
Name | Description |
other |
ModelContainerSpec |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
public ModelContainerSpec.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters | |
---|---|
Name | Description |
input |
CodedInputStream |
extensionRegistry |
ExtensionRegistryLite |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
Exceptions | |
---|---|
Type | Description |
IOException |
mergeFrom(Message other)
public ModelContainerSpec.Builder mergeFrom(Message other)
Parameter | |
---|---|
Name | Description |
other |
Message |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
mergeHealthProbe(Probe value)
public ModelContainerSpec.Builder mergeHealthProbe(Probe value)
Immutable. Specification for Kubernetes readiness probe.
.google.cloud.aiplatform.v1.Probe health_probe = 13 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
Probe |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
mergeStartupProbe(Probe value)
public ModelContainerSpec.Builder mergeStartupProbe(Probe value)
Immutable. Specification for Kubernetes startup probe.
.google.cloud.aiplatform.v1.Probe startup_probe = 12 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
Probe |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
mergeUnknownFields(UnknownFieldSet unknownFields)
public final ModelContainerSpec.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Parameter | |
---|---|
Name | Description |
unknownFields |
UnknownFieldSet |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
removeEnv(int index)
public ModelContainerSpec.Builder removeEnv(int index)
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
removeGrpcPorts(int index)
public ModelContainerSpec.Builder removeGrpcPorts(int index)
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
removePorts(int index)
public ModelContainerSpec.Builder removePorts(int index)
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
index |
int |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
setArgs(int index, String value)
public ModelContainerSpec.Builder setArgs(int index, String value)
Immutable. Specifies arguments for the command that runs when the container
starts. This overrides the container's
CMD
. Specify
this field as an array of executable and arguments, similar to a Docker
CMD
's "default parameters" form.
If you don't specify this field but do specify the
command field,
then the command from the command
field runs without any additional
arguments. See the Kubernetes documentation about how the command
and
args
fields interact with a container's ENTRYPOINT
and
CMD
.
If you don't specify this field and don't specify the command
field,
then the container's
ENTRYPOINT
and
CMD
determine what runs based on their default behavior. See the Docker
documentation about how CMD
and ENTRYPOINT
interact.
In this field, you can reference environment variables
set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the args
field of the Kubernetes Containers v1 core
API.
repeated string args = 3 [(.google.api.field_behavior) = IMMUTABLE];
Parameters | |
---|---|
Name | Description |
index |
int The index to set the value at. |
value |
String The args to set. |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
setCommand(int index, String value)
public ModelContainerSpec.Builder setCommand(int index, String value)
Immutable. Specifies the command that runs when the container starts. This
overrides the container's
ENTRYPOINT.
Specify this field as an array of executable and arguments, similar to a
Docker ENTRYPOINT
's "exec" form, not its "shell" form.
If you do not specify this field, then the container's ENTRYPOINT
runs,
in conjunction with the
args field or the
container's CMD
,
if either exists. If this field is not specified and the container does not
have an ENTRYPOINT
, then refer to the Docker documentation about how
CMD
and ENTRYPOINT
interact.
If you specify this field, then you can also specify the args
field to
provide additional arguments for this command. However, if you specify this
field, then the container's CMD
is ignored. See the
Kubernetes documentation about how the
command
and args
fields interact with a container's ENTRYPOINT
and
CMD
.
In this field, you can reference environment variables set by Vertex
AI
and environment variables set in the
env field. You cannot
reference environment variables set in the Docker image. In order for
environment variables to be expanded, reference them by using the following
syntax: <code>$(<var>VARIABLE_NAME</var>)</code> Note that this differs
from Bash variable expansion, which does not use parentheses. If a variable
cannot be resolved, the reference in the input string is used unchanged. To
avoid variable expansion, you can escape this syntax with $$
; for
example: <code>$$(<var>VARIABLE_NAME</var>)</code> This field corresponds
to the command
field of the Kubernetes Containers v1 core
API.
repeated string command = 2 [(.google.api.field_behavior) = IMMUTABLE];
Parameters | |
---|---|
Name | Description |
index |
int The index to set the value at. |
value |
String The command to set. |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
setDeploymentTimeout(Duration value)
public ModelContainerSpec.Builder setDeploymentTimeout(Duration value)
Immutable. Deployment timeout. Limit for deployment timeout is 2 hours.
.google.protobuf.Duration deployment_timeout = 10 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
Duration |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
setDeploymentTimeout(Duration.Builder builderForValue)
public ModelContainerSpec.Builder setDeploymentTimeout(Duration.Builder builderForValue)
Immutable. Deployment timeout. Limit for deployment timeout is 2 hours.
.google.protobuf.Duration deployment_timeout = 10 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
builderForValue |
Builder |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
setEnv(int index, EnvVar value)
public ModelContainerSpec.Builder setEnv(int index, EnvVar value)
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Parameters | |
---|---|
Name | Description |
index |
int |
value |
EnvVar |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
setEnv(int index, EnvVar.Builder builderForValue)
public ModelContainerSpec.Builder setEnv(int index, EnvVar.Builder builderForValue)
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables.
Additionally, the
command and
args fields can
reference these variables. Later entries in this list can also reference
earlier entries. For example, the following example sets the variable
VAR_2
to have the value foo bar
:
`json
[
{
"name": "VAR_1",
"value": "foo"
},
{
"name": "VAR_2",
"value": "$(VAR_1) bar"
}
]
If you switch the order of the variables in the example, then the expansion
does not occur.
This field corresponds to the
env` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.EnvVar env = 4 [(.google.api.field_behavior) = IMMUTABLE];
Parameters | |
---|---|
Name | Description |
index |
int |
builderForValue |
EnvVar.Builder |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
setField(Descriptors.FieldDescriptor field, Object value)
public ModelContainerSpec.Builder setField(Descriptors.FieldDescriptor field, Object value)
Parameters | |
---|---|
Name | Description |
field |
FieldDescriptor |
value |
Object |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
setGrpcPorts(int index, Port value)
public ModelContainerSpec.Builder setGrpcPorts(int index, Port value)
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Parameters | |
---|---|
Name | Description |
index |
int |
value |
Port |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
setGrpcPorts(int index, Port.Builder builderForValue)
public ModelContainerSpec.Builder setGrpcPorts(int index, Port.Builder builderForValue)
Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, gRPC requests to the container will be disabled.
Vertex AI does not use ports other than the first one listed. This field
corresponds to the ports
field of the Kubernetes Containers v1 core API.
repeated .google.cloud.aiplatform.v1.Port grpc_ports = 9 [(.google.api.field_behavior) = IMMUTABLE];
Parameters | |
---|---|
Name | Description |
index |
int |
builderForValue |
Port.Builder |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
setHealthProbe(Probe value)
public ModelContainerSpec.Builder setHealthProbe(Probe value)
Immutable. Specification for Kubernetes readiness probe.
.google.cloud.aiplatform.v1.Probe health_probe = 13 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
Probe |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
setHealthProbe(Probe.Builder builderForValue)
public ModelContainerSpec.Builder setHealthProbe(Probe.Builder builderForValue)
Immutable. Specification for Kubernetes readiness probe.
.google.cloud.aiplatform.v1.Probe health_probe = 13 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
builderForValue |
Probe.Builder |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
setHealthRoute(String value)
public ModelContainerSpec.Builder setHealthRoute(String value)
Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks.
For example, if you set this field to /bar
, then Vertex AI
intermittently sends a GET request to the /bar
path on the port of your
container specified by the first value of this ModelContainerSpec
's
ports field.
If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: <code>/v1/endpoints/<var>ENDPOINT</var>/deployedModels/<var>DEPLOYED_MODEL</var>:predict</code> The placeholders in this value are replaced as follows:
<var>ENDPOINT</var>: The last segment (following
endpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.)<var>DEPLOYED_MODEL</var>: DeployedModel.id of the
DeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.)
string health_route = 7 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
String The healthRoute to set. |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
setHealthRouteBytes(ByteString value)
public ModelContainerSpec.Builder setHealthRouteBytes(ByteString value)
Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks.
For example, if you set this field to /bar
, then Vertex AI
intermittently sends a GET request to the /bar
path on the port of your
container specified by the first value of this ModelContainerSpec
's
ports field.
If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: <code>/v1/endpoints/<var>ENDPOINT</var>/deployedModels/<var>DEPLOYED_MODEL</var>:predict</code> The placeholders in this value are replaced as follows:
<var>ENDPOINT</var>: The last segment (following
endpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.)<var>DEPLOYED_MODEL</var>: DeployedModel.id of the
DeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.)
string health_route = 7 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
ByteString The bytes for healthRoute to set. |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
setImageUri(String value)
public ModelContainerSpec.Builder setImageUri(String value)
Required. Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent.
The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used.
To learn about the requirements for the Docker image itself, see Custom container requirements.
You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
string image_uri = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
String The imageUri to set. |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
setImageUriBytes(ByteString value)
public ModelContainerSpec.Builder setImageUriBytes(ByteString value)
Required. Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent.
The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used.
To learn about the requirements for the Docker image itself, see Custom container requirements.
You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
string image_uri = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
ByteString The bytes for imageUri to set. |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
setPorts(int index, Port value)
public ModelContainerSpec.Builder setPorts(int index, Port value)
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Parameters | |
---|---|
Name | Description |
index |
int |
value |
Port |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
setPorts(int index, Port.Builder builderForValue)
public ModelContainerSpec.Builder setPorts(int index, Port.Builder builderForValue)
Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port.
If you do not specify this field, it defaults to following value:
`json
[
{
"containerPort": 8080
}
]
Vertex AI does not use ports other than the first one listed. This field
corresponds to the
ports` field of the Kubernetes Containers
v1 core
API.
repeated .google.cloud.aiplatform.v1.Port ports = 5 [(.google.api.field_behavior) = IMMUTABLE];
Parameters | |
---|---|
Name | Description |
index |
int |
builderForValue |
Port.Builder |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
setPredictRoute(String value)
public ModelContainerSpec.Builder setPredictRoute(String value)
Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response.
For example, if you set this field to /foo
, then when Vertex AI
receives a prediction request, it forwards the request body in a POST
request to the /foo
path on the port of your container specified by the
first value of this ModelContainerSpec
's
ports field.
If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: <code>/v1/endpoints/<var>ENDPOINT</var>/deployedModels/<var>DEPLOYED_MODEL</var>:predict</code> The placeholders in this value are replaced as follows:
<var>ENDPOINT</var>: The last segment (following
endpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.)<var>DEPLOYED_MODEL</var>: DeployedModel.id of the
DeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.)
string predict_route = 6 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
String The predictRoute to set. |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
setPredictRouteBytes(ByteString value)
public ModelContainerSpec.Builder setPredictRouteBytes(ByteString value)
Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response.
For example, if you set this field to /foo
, then when Vertex AI
receives a prediction request, it forwards the request body in a POST
request to the /foo
path on the port of your container specified by the
first value of this ModelContainerSpec
's
ports field.
If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: <code>/v1/endpoints/<var>ENDPOINT</var>/deployedModels/<var>DEPLOYED_MODEL</var>:predict</code> The placeholders in this value are replaced as follows:
<var>ENDPOINT</var>: The last segment (following
endpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.)<var>DEPLOYED_MODEL</var>: DeployedModel.id of the
DeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.)
string predict_route = 6 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
ByteString The bytes for predictRoute to set. |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
public ModelContainerSpec.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Parameters | |
---|---|
Name | Description |
field |
FieldDescriptor |
index |
int |
value |
Object |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
setSharedMemorySizeMb(long value)
public ModelContainerSpec.Builder setSharedMemorySizeMb(long value)
Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes.
int64 shared_memory_size_mb = 11 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
long The sharedMemorySizeMb to set. |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
This builder for chaining. |
setStartupProbe(Probe value)
public ModelContainerSpec.Builder setStartupProbe(Probe value)
Immutable. Specification for Kubernetes startup probe.
.google.cloud.aiplatform.v1.Probe startup_probe = 12 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
value |
Probe |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
setStartupProbe(Probe.Builder builderForValue)
public ModelContainerSpec.Builder setStartupProbe(Probe.Builder builderForValue)
Immutable. Specification for Kubernetes startup probe.
.google.cloud.aiplatform.v1.Probe startup_probe = 12 [(.google.api.field_behavior) = IMMUTABLE];
Parameter | |
---|---|
Name | Description |
builderForValue |
Probe.Builder |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |
setUnknownFields(UnknownFieldSet unknownFields)
public final ModelContainerSpec.Builder setUnknownFields(UnknownFieldSet unknownFields)
Parameter | |
---|---|
Name | Description |
unknownFields |
UnknownFieldSet |
Returns | |
---|---|
Type | Description |
ModelContainerSpec.Builder |