Skip to content

feat: Update Containers api schema #229

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mbrostami wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat: Update Containers api schema #229

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
120 changes: 61 additions & 59 deletions openapi.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12631,12 +12631,12 @@ components:
"target": 1.01} to scale based on queue backlog. Omit or set to null to
disable autoscaling'
oneOf:
- $ref: '#/components/schemas/HTTPAutoscalingConfig'
- $ref: '#/components/schemas/QueueAutoscalingConfig'
- $ref: '#/components/schemas/CustomMetricAutoscalingConfig'
- $ref: "#/components/schemas/HTTPAutoscalingConfig"
- $ref: "#/components/schemas/QueueAutoscalingConfig"
- $ref: "#/components/schemas/CustomMetricAutoscalingConfig"
command:
description: Command overrides the container's ENTRYPOINT. Provide as an array
(e.g., ["/bin/sh", "-c"])
description: Command overrides the container's ENTRYPOINT. Provide as an
array (e.g., ["/bin/sh", "-c"])
items:
type: string
type: array
Expand All @@ -12650,9 +12650,8 @@ components:
deployment
type: string
environment_variables:
description: EnvironmentVariables is a list of environment variables to set in
the container. Each must have a name and either a value or
value_from_secret
description: EnvironmentVariables is a list of environment variables to
set in the container. Each must have a name and either a value or value_from_secret
items:
$ref: "#/components/schemas/EnvironmentVariable"
type: array
Expand All @@ -12663,52 +12662,52 @@ components:
gpu_type:
description: GPUType specifies the GPU hardware to use (e.g., "h100-80gb").
enum:
- h100-80gb
- a100-80gb
- h100-80gb
type: string
health_check_path:
description: HealthCheckPath is the HTTP path for health checks (e.g.,
"/health"). If set, the platform will check this endpoint to
determine container health
description: HealthCheckPath is the HTTP path for health checks (e.g., "/health").
If set, the platform will check this endpoint to determine container health
type: string
image:
description: Image is the container image to deploy from registry.together.ai.
type: string
max_replicas:
description: MaxReplicas is the maximum number of container instances that can
be scaled up to. If not set, will be set to MinReplicas
description: MaxReplicas is the maximum number of container instances that
can be scaled up to. If not set, will be set to MinReplicas
type: integer
memory:
description: Memory is the amount of RAM to allocate per container instance in
GiB (e.g., 0.5 = 512MiB)
minimum: 0.1
description: Memory is the amount of RAM to allocate per container instance
in GiB (e.g., 0.5 = 512MiB)
maximum: 1000
type: number
min_replicas:
description: MinReplicas is the minimum number of container instances to run.
Defaults to 1 if not specified
description: MinReplicas is the minimum number of container instances to
run. Defaults to 1 if not specified
type: integer
name:
description: Name is the unique identifier for your deployment. Must contain
only alphanumeric characters, underscores, or hyphens (1-100
characters)
only alphanumeric characters, underscores, or hyphens (1-100 characters)
maxLength: 100
minLength: 1
type: string
port:
description: Port is the container port your application listens on (e.g., 8080
for web servers). Required if your application serves traffic
description: Port is the container port your application listens on (e.g.,
8080 for web servers). Required if your application serves traffic
maximum: 65535
minimum: 1
type: integer
storage:
description: Storage is the amount of ephemeral disk storage to allocate per
container instance (e.g., 10 = 10GiB)
description: Storage is the amount of ephemeral disk storage to allocate
per container instance (e.g., 10 = 10GiB)
maximum: 400
type: integer
termination_grace_period_seconds:
description: TerminationGracePeriodSeconds is the time in seconds to wait for
graceful shutdown before forcefully terminating the replica
description: TerminationGracePeriodSeconds is the time in seconds to wait
for graceful shutdown before forcefully terminating the replica
type: integer
volumes:
description: Volumes is a list of volume mounts to attach to the container. Each
mount must reference an existing volume by name
description: Volumes is a list of volume mounts to attach to the container.
Each mount must reference an existing volume by name
items:
$ref: "#/components/schemas/VolumeMount"
type: array
Expand Down Expand Up @@ -12806,6 +12805,7 @@ components:
created_at:
description: CreatedAt is the ISO8601 timestamp when this deployment was created
type: string
format: date-time
description:
description: Description provides a human-readable explanation of the
deployment's purpose or content
Expand Down Expand Up @@ -12890,6 +12890,7 @@ components:
description: UpdatedAt is the ISO8601 timestamp when this deployment was last
updated
type: string
format: date-time
volumes:
description: Volumes is a list of volume mounts for this deployment
items:
Expand Down Expand Up @@ -13105,15 +13106,15 @@ components:
type: string
type: array
autoscaling:
description: Autoscaling configuration for the deployment. Omit or set to
null to disable autoscaling
description: Autoscaling configuration for the deployment. Set to {} to
disable autoscaling
oneOf:
- $ref: '#/components/schemas/HTTPAutoscalingConfig'
- $ref: '#/components/schemas/QueueAutoscalingConfig'
- $ref: '#/components/schemas/CustomMetricAutoscalingConfig'
- $ref: "#/components/schemas/HTTPAutoscalingConfig"
- $ref: "#/components/schemas/QueueAutoscalingConfig"
- $ref: "#/components/schemas/CustomMetricAutoscalingConfig"
command:
description: Command overrides the container's ENTRYPOINT. Provide as an array
(e.g., ["/bin/sh", "-c"])
description: Command overrides the container's ENTRYPOINT. Provide as an
array (e.g., ["/bin/sh", "-c"])
items:
type: string
type: array
Expand All @@ -13127,8 +13128,8 @@ components:
deployment
type: string
environment_variables:
description: EnvironmentVariables is a list of environment variables to set in
the container. This will replace all existing environment variables
description: EnvironmentVariables is a list of environment variables to
set in the container. This will replace all existing environment variables
items:
$ref: "#/components/schemas/EnvironmentVariable"
type: array
Expand All @@ -13138,50 +13139,51 @@ components:
gpu_type:
description: GPUType specifies the GPU hardware to use (e.g., "h100-80gb")
enum:
- h100-80gb
- " a100-80gb"
- h100-80gb
type: string
health_check_path:
description: HealthCheckPath is the HTTP path for health checks (e.g.,
"/health"). Set to empty string to disable health checks
description: HealthCheckPath is the HTTP path for health checks (e.g., "/health").
Set to empty string to disable health checks
type: string
image:
description: Image is the container image to deploy from registry.together.ai.
type: string
max_replicas:
description: MaxReplicas is the maximum number of replicas that can be scaled up
to.
description: MaxReplicas is the maximum number of replicas that can be scaled
up to.
type: integer
memory:
description: Memory is the amount of RAM to allocate per container instance in
GiB (e.g., 0.5 = 512MiB)
minimum: 0.1
description: Memory is the amount of RAM to allocate per container instance
in GiB (e.g., 0.5 = 512MiB)
maximum: 1000
type: number
min_replicas:
description: MinReplicas is the minimum number of replicas to run
type: integer
name:
description: Name is the new unique identifier for your deployment. Must contain
only alphanumeric characters, underscores, or hyphens (1-100
characters)
description: Name is the new unique identifier for your deployment. Must
contain only alphanumeric characters, underscores, or hyphens (1-100 characters)
maxLength: 100
minLength: 1
type: string
port:
description: Port is the container port your application listens on (e.g., 8080
for web servers)
description: Port is the container port your application listens on (e.g.,
8080 for web servers)
maximum: 65535
minimum: 1
type: integer
storage:
description: Storage is the amount of ephemeral disk storage to allocate per
container instance (e.g., 10 = 10GiB)
description: Storage is the amount of ephemeral disk storage to allocate
per container instance (e.g., 10 = 10GiB)
maximum: 400
type: integer
termination_grace_period_seconds:
description: TerminationGracePeriodSeconds is the time in seconds to wait for
graceful shutdown before forcefully terminating the replica
description: TerminationGracePeriodSeconds is the time in seconds to wait
for graceful shutdown before forcefully terminating the replica
type: integer
volumes:
description: Volumes is a list of volume mounts to attach to the container. This
will replace all existing volumes
description: Volumes is a list of volume mounts to attach to the container.
This will replace all existing volumes
items:
$ref: "#/components/schemas/VolumeMount"
type: array
Expand Down
Loading