scaleway_async.inference.v1beta1 package

Submodules

scaleway_async.inference.v1beta1.api module

class scaleway_async.inference.v1beta1.api.InferenceV1Beta1API(client: Client, *, bypass_validation: bool = False)

Bases: API

This API allows you to manage your Inference services.

async add_deployment_acl_rules(*, deployment_id: str, region: Optional[str] = None, acls: Optional[List[ACLRuleRequest]] = None) → AddDeploymentACLRulesResponse

Add new ACLs. Add new ACL rules for a specific deployment. :param deployment_id: ID of the deployment to add ACL rules to. :param region: Region to target. If none is passed will use default region from the config. :param acls: List of ACL rules to add. :return: AddDeploymentACLRulesResponse

Usage:

result = await api.add_deployment_acl_rules(
    deployment_id="example",
)

async create_deployment(*, model_name: str, node_type: str, endpoints: List[EndpointSpec], region: Optional[str] = None, name: Optional[str] = None, project_id: Optional[str] = None, accept_eula: Optional[bool] = None, tags: Optional[List[str]] = None, min_size: Optional[int] = None, max_size: Optional[int] = None) → Deployment

Create a deployment. Create a new inference deployment related to a specific model. :param model_name: Name of the model to use. :param node_type: Name of the node type to use. :param endpoints: List of endpoints to create. :param region: Region to target. If none is passed will use default region from the config. :param name: Name of the deployment. :param project_id: ID of the Project to create the deployment in. :param accept_eula: If the model has an EULA, you must accept it before proceeding. The terms of the EULA can be retrieved using the GetModelEula API call. :param tags: List of tags to apply to the deployment. :param min_size: Defines the minimum size of the pool. :param max_size: Defines the maximum size of the pool. :return: Deployment

Usage:

result = await api.create_deployment(
    model_name="example",
    node_type="example",
    endpoints=[],
)

async create_endpoint(*, deployment_id: str, endpoint: EndpointSpec, region: Optional[str] = None) → Endpoint

Create an endpoint. Create a new Endpoint related to a specific deployment. :param deployment_id: ID of the deployment to create the endpoint for. :param endpoint: Specification of the endpoint. :param region: Region to target. If none is passed will use default region from the config. :return: Endpoint

Usage:

result = await api.create_endpoint(
    deployment_id="example",
    endpoint=EndpointSpec(),
)

async delete_deployment(*, deployment_id: str, region: Optional[str] = None) → Deployment

Delete a deployment. Delete an existing inference deployment. :param deployment_id: ID of the deployment to delete. :param region: Region to target. If none is passed will use default region from the config. :return: Deployment

Usage:

result = await api.delete_deployment(
    deployment_id="example",
)

async delete_deployment_acl_rule(*, acl_id: str, region: Optional[str] = None) → None

Delete an exising ACL. :param acl_id: ID of the ACL rule to delete. :param region: Region to target. If none is passed will use default region from the config.

Usage:

result = await api.delete_deployment_acl_rule(
    acl_id="example",
)

async delete_endpoint(*, endpoint_id: str, region: Optional[str] = None) → None

Delete an endpoint. Delete an existing Endpoint. :param endpoint_id: ID of the endpoint to delete. :param region: Region to target. If none is passed will use default region from the config.

Usage:

result = await api.delete_endpoint(
    endpoint_id="example",
)

async get_deployment(*, deployment_id: str, region: Optional[str] = None) → Deployment

Get a deployment. Get the deployment for the given ID. :param deployment_id: ID of the deployment to get. :param region: Region to target. If none is passed will use default region from the config. :return: Deployment

Usage:

result = await api.get_deployment(
    deployment_id="example",
)

async get_deployment_certificate(*, deployment_id: str, region: Optional[str] = None) → ScwFile

Get the CA certificate. Get the CA certificate used for the deployment of private endpoints. The CA certificate will be returned as a PEM file. :param deployment_id: :param region: Region to target. If none is passed will use default region from the config. :return: ScwFile

Usage:

result = await api.get_deployment_certificate(
    deployment_id="example",
)

async get_model(*, model_id: str, region: Optional[str] = None) → Model

Get a model. Get the model for the given ID. :param model_id: ID of the model to get. :param region: Region to target. If none is passed will use default region from the config. :return: Model

Usage:

result = await api.get_model(
    model_id="example",
)

async get_model_eula(*, model_id: str, region: Optional[str] = None) → Eula

Parameters:

model_id –
region – Region to target. If none is passed will use default region from the config.

Returns:

Eula

Usage:

result = await api.get_model_eula(
    model_id="example",
)

async list_deployment_acl_rules(*, deployment_id: str, region: Optional[str] = None, page: Optional[int] = None, page_size: Optional[int] = None) → ListDeploymentACLRulesResponse

List your ACLs. List ACLs for a specific deployment. :param deployment_id: ID of the deployment to list ACL rules for. :param region: Region to target. If none is passed will use default region from the config. :param page: Page number to return. :param page_size: Maximum number of ACL rules to return per page. :return: ListDeploymentACLRulesResponse

Usage:

result = await api.list_deployment_acl_rules(
    deployment_id="example",
)

async list_deployment_acl_rules_all(*, deployment_id: str, region: Optional[str] = None, page: Optional[int] = None, page_size: Optional[int] = None) → List[ACLRule]

List your ACLs. List ACLs for a specific deployment. :param deployment_id: ID of the deployment to list ACL rules for. :param region: Region to target. If none is passed will use default region from the config. :param page: Page number to return. :param page_size: Maximum number of ACL rules to return per page. :return: List[ACLRule]

Usage:

result = await api.list_deployment_acl_rules_all(
    deployment_id="example",
)

async list_deployments(*, region: Optional[str] = None, page: Optional[int] = None, page_size: Optional[int] = None, order_by: Optional[ListDeploymentsRequestOrderBy] = None, project_id: Optional[str] = None, organization_id: Optional[str] = None, name: Optional[str] = None, tags: Optional[List[str]] = None) → ListDeploymentsResponse

List inference deployments. List all your inference deployments. :param region: Region to target. If none is passed will use default region from the config. :param page: Page number to return. :param page_size: Maximum number of deployments to return per page. :param order_by: Order in which to return results. :param project_id: Filter by Project ID. :param organization_id: Filter by Organization ID. :param name: Filter by deployment name. :param tags: Filter by tags. :return: ListDeploymentsResponse

Usage:

result = await api.list_deployments()

async list_deployments_all(*, region: Optional[str] = None, page: Optional[int] = None, page_size: Optional[int] = None, order_by: Optional[ListDeploymentsRequestOrderBy] = None, project_id: Optional[str] = None, organization_id: Optional[str] = None, name: Optional[str] = None, tags: Optional[List[str]] = None) → List[Deployment]

List inference deployments. List all your inference deployments. :param region: Region to target. If none is passed will use default region from the config. :param page: Page number to return. :param page_size: Maximum number of deployments to return per page. :param order_by: Order in which to return results. :param project_id: Filter by Project ID. :param organization_id: Filter by Organization ID. :param name: Filter by deployment name. :param tags: Filter by tags. :return: List[Deployment]

Usage:

result = await api.list_deployments_all()

async list_models(*, region: Optional[str] = None, order_by: Optional[ListModelsRequestOrderBy] = None, page: Optional[int] = None, page_size: Optional[int] = None, project_id: Optional[str] = None, name: Optional[str] = None, tags: Optional[List[str]] = None) → ListModelsResponse

List models. List all available models. :param region: Region to target. If none is passed will use default region from the config. :param order_by: Order in which to return results. :param page: Page number to return. :param page_size: Maximum number of models to return per page. :param project_id: Filter by Project ID. :param name: Filter by model name. :param tags: Filter by tags. :return: ListModelsResponse

Usage:

result = await api.list_models()

async list_models_all(*, region: Optional[str] = None, order_by: Optional[ListModelsRequestOrderBy] = None, page: Optional[int] = None, page_size: Optional[int] = None, project_id: Optional[str] = None, name: Optional[str] = None, tags: Optional[List[str]] = None) → List[Model]

List models. List all available models. :param region: Region to target. If none is passed will use default region from the config. :param order_by: Order in which to return results. :param page: Page number to return. :param page_size: Maximum number of models to return per page. :param project_id: Filter by Project ID. :param name: Filter by model name. :param tags: Filter by tags. :return: List[Model]

Usage:

result = await api.list_models_all()

async list_node_types(*, include_disabled_types: bool, region: Optional[str] = None, page: Optional[int] = None, page_size: Optional[int] = None) → ListNodeTypesResponse

List available node types. List all available node types. By default, the node types returned in the list are ordered by creation date in ascending order, though this can be modified via the order_by field. :param include_disabled_types: Include disabled node types in the response. :param region: Region to target. If none is passed will use default region from the config. :param page: Page number to return. :param page_size: Maximum number of node types to return per page. :return: ListNodeTypesResponse

Usage:

result = await api.list_node_types(
    include_disabled_types=False,
)

async list_node_types_all(*, include_disabled_types: bool, region: Optional[str] = None, page: Optional[int] = None, page_size: Optional[int] = None) → List[NodeType]

List available node types. List all available node types. By default, the node types returned in the list are ordered by creation date in ascending order, though this can be modified via the order_by field. :param include_disabled_types: Include disabled node types in the response. :param region: Region to target. If none is passed will use default region from the config. :param page: Page number to return. :param page_size: Maximum number of node types to return per page. :return: List[NodeType]

Usage:

result = await api.list_node_types_all(
    include_disabled_types=False,
)

async set_deployment_acl_rules(*, deployment_id: str, region: Optional[str] = None, acls: Optional[List[ACLRuleRequest]] = None) → SetDeploymentACLRulesResponse

Set new ACL. Set new ACL rules for a specific deployment. :param deployment_id: ID of the deployment to set ACL rules for. :param region: Region to target. If none is passed will use default region from the config. :param acls: All existing ACL rules will be replaced by the new ones. :return: SetDeploymentACLRulesResponse

Usage:

result = await api.set_deployment_acl_rules(
    deployment_id="example",
)

async update_deployment(*, deployment_id: str, region: Optional[str] = None, name: Optional[str] = None, tags: Optional[List[str]] = None, min_size: Optional[int] = None, max_size: Optional[int] = None) → Deployment

Update a deployment. Update an existing inference deployment. :param deployment_id: ID of the deployment to update. :param region: Region to target. If none is passed will use default region from the config. :param name: Name of the deployment. :param tags: List of tags to apply to the deployment. :param min_size: Defines the new minimum size of the pool. :param max_size: Defines the new maximum size of the pool. :return: Deployment

Usage:

result = await api.update_deployment(
    deployment_id="example",
)

async update_endpoint(*, endpoint_id: str, region: Optional[str] = None, disable_auth: Optional[bool] = None) → Endpoint

Update an endpoint. Update an existing Endpoint. :param endpoint_id: ID of the endpoint to update. :param region: Region to target. If none is passed will use default region from the config. :param disable_auth: By default, deployments are protected by IAM authentication. When setting this field to true, the authentication will be disabled. :return: Endpoint

Usage:

result = await api.update_endpoint(
    endpoint_id="example",
)

async wait_for_deployment(*, deployment_id: str, region: Optional[str] = None, options: Optional[WaitForOptions[Deployment, Union[bool, Awaitable[bool]]]] = None) → Deployment

Get a deployment. Get the deployment for the given ID. :param deployment_id: ID of the deployment to get. :param region: Region to target. If none is passed will use default region from the config. :return: Deployment

Usage:

result = await api.get_deployment(
    deployment_id="example",
)

scaleway_async.inference.v1beta1.content module

scaleway_async.inference.v1beta1.content.DEPLOYMENT_TRANSIENT_STATUSES: List[DeploymentStatus] = [<DeploymentStatus.CREATING: 'creating'>, <DeploymentStatus.DEPLOYING: 'deploying'>, <DeploymentStatus.DELETING: 'deleting'>]: Lists transient statutes of the enum DeploymentStatus.

scaleway_async.inference.v1beta1.marshalling module

scaleway_async.inference.v1beta1.marshalling.marshal_ACLRuleRequest(request: ACLRuleRequest, defaults: ProfileDefaults) → Dict[str, Any]

scaleway_async.inference.v1beta1.marshalling.marshal_AddDeploymentACLRulesRequest(request: AddDeploymentACLRulesRequest, defaults: ProfileDefaults) → Dict[str, Any]

scaleway_async.inference.v1beta1.marshalling.marshal_CreateDeploymentRequest(request: CreateDeploymentRequest, defaults: ProfileDefaults) → Dict[str, Any]

scaleway_async.inference.v1beta1.marshalling.marshal_CreateEndpointRequest(request: CreateEndpointRequest, defaults: ProfileDefaults) → Dict[str, Any]

scaleway_async.inference.v1beta1.marshalling.marshal_EndpointSpec(request: EndpointSpec, defaults: ProfileDefaults) → Dict[str, Any]

scaleway_async.inference.v1beta1.marshalling.marshal_EndpointSpecPrivateNetwork(request: EndpointSpecPrivateNetwork, defaults: ProfileDefaults) → Dict[str, Any]

scaleway_async.inference.v1beta1.marshalling.marshal_EndpointSpecPublic(request: EndpointSpecPublic, defaults: ProfileDefaults) → Dict[str, Any]

scaleway_async.inference.v1beta1.marshalling.marshal_SetDeploymentACLRulesRequest(request: SetDeploymentACLRulesRequest, defaults: ProfileDefaults) → Dict[str, Any]

scaleway_async.inference.v1beta1.marshalling.marshal_UpdateDeploymentRequest(request: UpdateDeploymentRequest, defaults: ProfileDefaults) → Dict[str, Any]

scaleway_async.inference.v1beta1.marshalling.marshal_UpdateEndpointRequest(request: UpdateEndpointRequest, defaults: ProfileDefaults) → Dict[str, Any]

scaleway_async.inference.v1beta1.marshalling.unmarshal_ACLRule(data: Any) → ACLRule

scaleway_async.inference.v1beta1.marshalling.unmarshal_AddDeploymentACLRulesResponse(data: Any) → AddDeploymentACLRulesResponse

scaleway_async.inference.v1beta1.marshalling.unmarshal_Deployment(data: Any) → Deployment

scaleway_async.inference.v1beta1.marshalling.unmarshal_Endpoint(data: Any) → Endpoint

scaleway_async.inference.v1beta1.marshalling.unmarshal_EndpointPrivateNetworkDetails(data: Any) → EndpointPrivateNetworkDetails

scaleway_async.inference.v1beta1.marshalling.unmarshal_EndpointPublicAccessDetails(data: Any) → EndpointPublicAccessDetails

scaleway_async.inference.v1beta1.marshalling.unmarshal_Eula(data: Any) → Eula

scaleway_async.inference.v1beta1.marshalling.unmarshal_ListDeploymentACLRulesResponse(data: Any) → ListDeploymentACLRulesResponse

scaleway_async.inference.v1beta1.marshalling.unmarshal_ListDeploymentsResponse(data: Any) → ListDeploymentsResponse

scaleway_async.inference.v1beta1.marshalling.unmarshal_ListModelsResponse(data: Any) → ListModelsResponse

scaleway_async.inference.v1beta1.marshalling.unmarshal_ListNodeTypesResponse(data: Any) → ListNodeTypesResponse

scaleway_async.inference.v1beta1.marshalling.unmarshal_Model(data: Any) → Model

scaleway_async.inference.v1beta1.marshalling.unmarshal_ModelS3Model(data: Any) → ModelS3Model

scaleway_async.inference.v1beta1.marshalling.unmarshal_NodeType(data: Any) → NodeType

scaleway_async.inference.v1beta1.marshalling.unmarshal_SetDeploymentACLRulesResponse(data: Any) → SetDeploymentACLRulesResponse

scaleway_async.inference.v1beta1.types module

class scaleway_async.inference.v1beta1.types.ACLRule(id: 'str', ip: 'str', description: 'str')

Bases: object

description: str: Description of the ACL rule.

id: str: Unique identifier.

ip: str: Allowed IP address or CIDR range.

class scaleway_async.inference.v1beta1.types.ACLRuleRequest(ip: 'str', description: 'str')

Bases: object

description: str: Description of the ACL rule.

ip: str: It can be specified as a single IP address or a range of IP addresses in CIDR notation.

class scaleway_async.inference.v1beta1.types.AddDeploymentACLRulesRequest(deployment_id: 'str', region: 'Optional[ScwRegion]', acls: 'Optional[List[ACLRuleRequest]]')

Bases: object

acls: Optional[List[ACLRuleRequest]]: List of ACL rules to add.

deployment_id: str: ID of the deployment to add ACL rules to.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.types.AddDeploymentACLRulesResponse(rules: 'List[ACLRule]')

Bases: object

rules: List[ACLRule]: List of ACL rules added.

class scaleway_async.inference.v1beta1.types.CreateDeploymentRequest(model_name: 'str', node_type: 'str', endpoints: 'List[EndpointSpec]', region: 'Optional[ScwRegion]', name: 'Optional[str]', project_id: 'Optional[str]', accept_eula: 'Optional[bool]', tags: 'Optional[List[str]]', min_size: 'Optional[int]', max_size: 'Optional[int]')

Bases: object

accept_eula: Optional[bool]: If the model has an EULA, you must accept it before proceeding.

The terms of the EULA can be retrieved using the GetModelEula API call.

endpoints: List[EndpointSpec]: List of endpoints to create.

max_size: Optional[int]: Defines the maximum size of the pool.

min_size: Optional[int]: Defines the minimum size of the pool.

model_name: str: Name of the model to use.

name: Optional[str]: Name of the deployment.

node_type: str: Name of the node type to use.

project_id: Optional[str]: ID of the Project to create the deployment in.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

tags: Optional[List[str]]: List of tags to apply to the deployment.

class scaleway_async.inference.v1beta1.types.CreateEndpointRequest(deployment_id: 'str', endpoint: 'EndpointSpec', region: 'Optional[ScwRegion]')

Bases: object

deployment_id: str: ID of the deployment to create the endpoint for.

endpoint: EndpointSpec: Specification of the endpoint.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.types.DeleteDeploymentACLRuleRequest(acl_id: 'str', region: 'Optional[ScwRegion]')

Bases: object

acl_id: str: ID of the ACL rule to delete.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.types.DeleteDeploymentRequest(deployment_id: 'str', region: 'Optional[ScwRegion]')

Bases: object

deployment_id: str: ID of the deployment to delete.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.types.DeleteEndpointRequest(endpoint_id: 'str', region: 'Optional[ScwRegion]')

Bases: object

endpoint_id: str: ID of the endpoint to delete.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.types.Deployment(id: 'str', name: 'str', project_id: 'str', status: 'DeploymentStatus', tags: 'List[str]', node_type: 'str', endpoints: 'List[Endpoint]', size: 'int', min_size: 'int', max_size: 'int', model_name: 'str', model_id: 'str', region: 'ScwRegion', error_message: 'Optional[str]', created_at: 'Optional[datetime]', updated_at: 'Optional[datetime]')

Bases: object

created_at: Optional[datetime]: Creation date of the deployment.

endpoints: List[Endpoint]: List of endpoints.

error_message: Optional[str]: Displays information if your deployment is in error state.

id: str: Unique identifier.

max_size: int: Defines the maximum size of the pool.

min_size: int: Defines the minimum size of the pool.

model_id: str: ID of the model used for the deployment.

model_name: str: The inference model used for the deployment.

name: str: Name of the deployment.

node_type: str: Node type of the deployment.

project_id: str: Project ID.

region: str: Region of the deployment.

size: int: Current size of the pool.

status: DeploymentStatus: Status of the deployment.

tags: List[str]: List of tags applied to the deployment.

updated_at: Optional[datetime]: Last modification date of the deployment.

class scaleway_async.inference.v1beta1.types.DeploymentStatus(value: str, names: Optional[Any] = None, *args: Any, **kwargs: Any)

Bases: str, Enum

An enumeration.

CREATING = 'creating'

DELETING = 'deleting'

DEPLOYING = 'deploying'

ERROR = 'error'

LOCKED = 'locked'

READY = 'ready'

UNKNOWN_STATUS = 'unknown_status'

class scaleway_async.inference.v1beta1.types.Endpoint(id: 'str', url: 'str', disable_auth: 'bool', public_access: 'Optional[EndpointPublicAccessDetails]', private_network: 'Optional[EndpointPrivateNetworkDetails]')

Bases: object

disable_auth: bool: Defines whether the authentication is disabled.

id: str: Unique identifier.

private_network: Optional[EndpointPrivateNetworkDetails]

public_access: Optional[EndpointPublicAccessDetails]

url: str: For private endpoints, the URL will be accessible only from the Private Network.

In addition, private endpoints will expose a CA certificate that can be used to verify the server’s identity. This CA certificate can be retrieved using the GetDeploymentCertificate API call.

class scaleway_async.inference.v1beta1.types.EndpointPrivateNetworkDetails(private_network_id: 'str')

Bases: object

private_network_id: str: ID of the Private Network.

class scaleway_async.inference.v1beta1.types.EndpointPublicAccessDetails: Bases: object

class scaleway_async.inference.v1beta1.types.EndpointSpec(disable_auth: 'bool', public: 'Optional[EndpointSpecPublic]', private_network: 'Optional[EndpointSpecPrivateNetwork]')

Bases: object

disable_auth: bool: By default, deployments are protected by IAM authentication.

When setting this field to true, the authentication will be disabled.

private_network: Optional[EndpointSpecPrivateNetwork]

public: Optional[EndpointSpecPublic]

class scaleway_async.inference.v1beta1.types.EndpointSpecPrivateNetwork(private_network_id: 'str')

Bases: object

private_network_id: str: ID of the Private Network.

class scaleway_async.inference.v1beta1.types.EndpointSpecPublic: Bases: object

class scaleway_async.inference.v1beta1.types.Eula(content: 'str')

Bases: object

content: str: Content of the end user license agreement.

class scaleway_async.inference.v1beta1.types.GetDeploymentCertificateRequest(deployment_id: 'str', region: 'Optional[ScwRegion]')

Bases: object

deployment_id: str

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.types.GetDeploymentRequest(deployment_id: 'str', region: 'Optional[ScwRegion]')

Bases: object

deployment_id: str: ID of the deployment to get.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.types.GetModelEulaRequest(model_id: 'str', region: 'Optional[ScwRegion]')

Bases: object

model_id: str

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.types.GetModelRequest(model_id: 'str', region: 'Optional[ScwRegion]')

Bases: object

model_id: str: ID of the model to get.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.types.ListDeploymentACLRulesRequest(deployment_id: 'str', region: 'Optional[ScwRegion]', page: 'Optional[int]', page_size: 'Optional[int]')

Bases: object

deployment_id: str: ID of the deployment to list ACL rules for.

page: Optional[int]: Page number to return.

page_size: Optional[int]: Maximum number of ACL rules to return per page.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.types.ListDeploymentACLRulesResponse(rules: 'List[ACLRule]', total_count: 'int')

Bases: object

rules: List[ACLRule]: List of ACL rules on the current page.

total_count: int: Total number of ACL rules.

class scaleway_async.inference.v1beta1.types.ListDeploymentsRequest(region: 'Optional[ScwRegion]', page: 'Optional[int]', page_size: 'Optional[int]', order_by: 'Optional[ListDeploymentsRequestOrderBy]', project_id: 'Optional[str]', organization_id: 'Optional[str]', name: 'Optional[str]', tags: 'Optional[List[str]]')

Bases: object

name: Optional[str]: Filter by deployment name.

order_by: Optional[ListDeploymentsRequestOrderBy]: Order in which to return results.

organization_id: Optional[str]: Filter by Organization ID.

page: Optional[int]: Page number to return.

page_size: Optional[int]: Maximum number of deployments to return per page.

project_id: Optional[str]: Filter by Project ID.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

tags: Optional[List[str]]: Filter by tags.

class scaleway_async.inference.v1beta1.types.ListDeploymentsRequestOrderBy(value: str, names: Optional[Any] = None, *args: Any, **kwargs: Any)

Bases: str, Enum

An enumeration.

CREATED_AT_ASC = 'created_at_asc'

CREATED_AT_DESC = 'created_at_desc'

NAME_ASC = 'name_asc'

NAME_DESC = 'name_desc'

class scaleway_async.inference.v1beta1.types.ListDeploymentsResponse(deployments: 'List[Deployment]', total_count: 'int')

Bases: object

deployments: List[Deployment]: List of deployments on the current page.

total_count: int: Total number of deployments.

class scaleway_async.inference.v1beta1.types.ListModelsRequest(region: 'Optional[ScwRegion]', order_by: 'Optional[ListModelsRequestOrderBy]', page: 'Optional[int]', page_size: 'Optional[int]', project_id: 'Optional[str]', name: 'Optional[str]', tags: 'Optional[List[str]]')

Bases: object

name: Optional[str]: Filter by model name.

order_by: Optional[ListModelsRequestOrderBy]: Order in which to return results.

page: Optional[int]: Page number to return.

page_size: Optional[int]: Maximum number of models to return per page.

project_id: Optional[str]: Filter by Project ID.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

tags: Optional[List[str]]: Filter by tags.

class scaleway_async.inference.v1beta1.types.ListModelsRequestOrderBy(value: str, names: Optional[Any] = None, *args: Any, **kwargs: Any)

Bases: str, Enum

An enumeration.

CREATED_AT_ASC = 'created_at_asc'

CREATED_AT_DESC = 'created_at_desc'

DISPLAY_RANK_ASC = 'display_rank_asc'

NAME_ASC = 'name_asc'

NAME_DESC = 'name_desc'

class scaleway_async.inference.v1beta1.types.ListModelsResponse(models: 'List[Model]', total_count: 'int')

Bases: object

models: List[Model]: List of models on the current page.

total_count: int: Total number of models.

class scaleway_async.inference.v1beta1.types.ListNodeTypesRequest(include_disabled_types: 'bool', region: 'Optional[ScwRegion]', page: 'Optional[int]', page_size: 'Optional[int]')

Bases: object

include_disabled_types: bool: Include disabled node types in the response.

page: Optional[int]: Page number to return.

page_size: Optional[int]: Maximum number of node types to return per page.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.types.ListNodeTypesResponse(node_types: 'List[NodeType]', total_count: 'int')

Bases: object

node_types: List[NodeType]: List of node types.

total_count: int: Total number of node types.

class scaleway_async.inference.v1beta1.types.Model(id: 'str', name: 'str', project_id: 'str', provider: 'str', tags: 'List[str]', description: 'str', has_eula: 'bool', region: 'ScwRegion', is_public: 'bool', compatible_node_types: 'List[str]', quantization_level: 'str', created_at: 'Optional[datetime]', updated_at: 'Optional[datetime]', s3_model: 'Optional[ModelS3Model]')

Bases: object

compatible_node_types: List[str]: Names of the node types compatible with the model.

created_at: Optional[datetime]: Creation date of the model.

description: str: Purpose of the model.

has_eula: bool: Defines whether the model has an end user license agreement.

id: str: Unique identifier.

is_public: bool: Defines whether the model is public or not.

name: str: Unique Name identifier.

project_id: str: Project ID.

provider: str: Name of the model provider.

quantization_level: str: Quantization level of the model.

region: str: Region of the model.

s3_model: Optional[ModelS3Model]

tags: List[str]: List of tags applied to the model.

updated_at: Optional[datetime]: Last modification date of the model.

class scaleway_async.inference.v1beta1.types.ModelS3Model(s3_url: 'str', python_dependencies: 'Dict[str, str]', node_type: 'Optional[str]', triton_server_version: 'Optional[str]')

Bases: object

node_type: Optional[str]

python_dependencies: Dict[str, str]

s3_url: str

triton_server_version: Optional[str]

class scaleway_async.inference.v1beta1.types.NodeType(name: 'str', stock_status: 'NodeTypeStock', description: 'str', vcpus: 'int', memory: 'int', vram: 'int', disabled: 'bool', beta: 'bool', gpus: 'int', region: 'ScwRegion', created_at: 'Optional[datetime]', updated_at: 'Optional[datetime]')

Bases: object

beta: bool: The node type is currently in beta.

created_at: Optional[datetime]: Creation date of the node type.

description: str: Current specs of the offer.

disabled: bool: The node type is currently disabled.

gpus: int: Number of GPUs.

memory: int: Quantity of RAM.

name: str: Name of the node type.

region: str: Region of the node type.

stock_status: NodeTypeStock: Current stock status for the node type.

updated_at: Optional[datetime]: Last modification date of the node type.

vcpus: int: Number of virtual CPUs.

vram: int: Quantity of GPU RAM.

class scaleway_async.inference.v1beta1.types.NodeTypeStock(value: str, names: Optional[Any] = None, *args: Any, **kwargs: Any)

Bases: str, Enum

An enumeration.

AVAILABLE = 'available'

LOW_STOCK = 'low_stock'

OUT_OF_STOCK = 'out_of_stock'

UNKNOWN_STOCK = 'unknown_stock'

class scaleway_async.inference.v1beta1.types.SetDeploymentACLRulesRequest(deployment_id: 'str', region: 'Optional[ScwRegion]', acls: 'Optional[List[ACLRuleRequest]]')

Bases: object

acls: Optional[List[ACLRuleRequest]]: All existing ACL rules will be replaced by the new ones.

deployment_id: str: ID of the deployment to set ACL rules for.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.types.SetDeploymentACLRulesResponse(rules: 'List[ACLRule]')

Bases: object

rules: List[ACLRule]: List of ACL rules that were set.

class scaleway_async.inference.v1beta1.types.UpdateDeploymentRequest(deployment_id: 'str', region: 'Optional[ScwRegion]', name: 'Optional[str]', tags: 'Optional[List[str]]', min_size: 'Optional[int]', max_size: 'Optional[int]')

Bases: object

deployment_id: str: ID of the deployment to update.

max_size: Optional[int]: Defines the new maximum size of the pool.

min_size: Optional[int]: Defines the new minimum size of the pool.

name: Optional[str]: Name of the deployment.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

tags: Optional[List[str]]: List of tags to apply to the deployment.

class scaleway_async.inference.v1beta1.types.UpdateEndpointRequest(endpoint_id: 'str', region: 'Optional[ScwRegion]', disable_auth: 'Optional[bool]')

Bases: object

disable_auth: Optional[bool]: By default, deployments are protected by IAM authentication.

When setting this field to true, the authentication will be disabled.

endpoint_id: str: ID of the endpoint to update.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

Module contents

class scaleway_async.inference.v1beta1.ACLRule(id: 'str', ip: 'str', description: 'str')

Bases: object

description: str: Description of the ACL rule.

id: str: Unique identifier.

ip: str: Allowed IP address or CIDR range.

class scaleway_async.inference.v1beta1.ACLRuleRequest(ip: 'str', description: 'str')

Bases: object

description: str: Description of the ACL rule.

ip: str: It can be specified as a single IP address or a range of IP addresses in CIDR notation.

class scaleway_async.inference.v1beta1.AddDeploymentACLRulesRequest(deployment_id: 'str', region: 'Optional[ScwRegion]', acls: 'Optional[List[ACLRuleRequest]]')

Bases: object

acls: Optional[List[ACLRuleRequest]]: List of ACL rules to add.

deployment_id: str: ID of the deployment to add ACL rules to.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.AddDeploymentACLRulesResponse(rules: 'List[ACLRule]')

Bases: object

rules: List[ACLRule]: List of ACL rules added.

class scaleway_async.inference.v1beta1.CreateDeploymentRequest(model_name: 'str', node_type: 'str', endpoints: 'List[EndpointSpec]', region: 'Optional[ScwRegion]', name: 'Optional[str]', project_id: 'Optional[str]', accept_eula: 'Optional[bool]', tags: 'Optional[List[str]]', min_size: 'Optional[int]', max_size: 'Optional[int]')

Bases: object

accept_eula: Optional[bool]: If the model has an EULA, you must accept it before proceeding.

The terms of the EULA can be retrieved using the GetModelEula API call.

endpoints: List[EndpointSpec]: List of endpoints to create.

max_size: Optional[int]: Defines the maximum size of the pool.

min_size: Optional[int]: Defines the minimum size of the pool.

model_name: str: Name of the model to use.

name: Optional[str]: Name of the deployment.

node_type: str: Name of the node type to use.

project_id: Optional[str]: ID of the Project to create the deployment in.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

tags: Optional[List[str]]: List of tags to apply to the deployment.

class scaleway_async.inference.v1beta1.CreateEndpointRequest(deployment_id: 'str', endpoint: 'EndpointSpec', region: 'Optional[ScwRegion]')

Bases: object

deployment_id: str: ID of the deployment to create the endpoint for.

endpoint: EndpointSpec: Specification of the endpoint.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.DeleteDeploymentACLRuleRequest(acl_id: 'str', region: 'Optional[ScwRegion]')

Bases: object

acl_id: str: ID of the ACL rule to delete.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.DeleteDeploymentRequest(deployment_id: 'str', region: 'Optional[ScwRegion]')

Bases: object

deployment_id: str: ID of the deployment to delete.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.DeleteEndpointRequest(endpoint_id: 'str', region: 'Optional[ScwRegion]')

Bases: object

endpoint_id: str: ID of the endpoint to delete.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.Deployment(id: 'str', name: 'str', project_id: 'str', status: 'DeploymentStatus', tags: 'List[str]', node_type: 'str', endpoints: 'List[Endpoint]', size: 'int', min_size: 'int', max_size: 'int', model_name: 'str', model_id: 'str', region: 'ScwRegion', error_message: 'Optional[str]', created_at: 'Optional[datetime]', updated_at: 'Optional[datetime]')

Bases: object

created_at: Optional[datetime]: Creation date of the deployment.

endpoints: List[Endpoint]: List of endpoints.

error_message: Optional[str]: Displays information if your deployment is in error state.

id: str: Unique identifier.

max_size: int: Defines the maximum size of the pool.

min_size: int: Defines the minimum size of the pool.

model_id: str: ID of the model used for the deployment.

model_name: str: The inference model used for the deployment.

name: str: Name of the deployment.

node_type: str: Node type of the deployment.

project_id: str: Project ID.

region: str: Region of the deployment.

size: int: Current size of the pool.

status: DeploymentStatus: Status of the deployment.

tags: List[str]: List of tags applied to the deployment.

updated_at: Optional[datetime]: Last modification date of the deployment.

class scaleway_async.inference.v1beta1.DeploymentStatus(value: str, names: Optional[Any] = None, *args: Any, **kwargs: Any)

Bases: str, Enum

An enumeration.

CREATING = 'creating'

DELETING = 'deleting'

DEPLOYING = 'deploying'

ERROR = 'error'

LOCKED = 'locked'

READY = 'ready'

UNKNOWN_STATUS = 'unknown_status'

class scaleway_async.inference.v1beta1.Endpoint(id: 'str', url: 'str', disable_auth: 'bool', public_access: 'Optional[EndpointPublicAccessDetails]', private_network: 'Optional[EndpointPrivateNetworkDetails]')

Bases: object

disable_auth: bool: Defines whether the authentication is disabled.

id: str: Unique identifier.

private_network: Optional[EndpointPrivateNetworkDetails]

public_access: Optional[EndpointPublicAccessDetails]

url: str: For private endpoints, the URL will be accessible only from the Private Network.

In addition, private endpoints will expose a CA certificate that can be used to verify the server’s identity. This CA certificate can be retrieved using the GetDeploymentCertificate API call.

class scaleway_async.inference.v1beta1.EndpointPrivateNetworkDetails(private_network_id: 'str')

Bases: object

private_network_id: str: ID of the Private Network.

class scaleway_async.inference.v1beta1.EndpointPublicAccessDetails: Bases: object

class scaleway_async.inference.v1beta1.EndpointSpec(disable_auth: 'bool', public: 'Optional[EndpointSpecPublic]', private_network: 'Optional[EndpointSpecPrivateNetwork]')

Bases: object

disable_auth: bool: By default, deployments are protected by IAM authentication.

When setting this field to true, the authentication will be disabled.

private_network: Optional[EndpointSpecPrivateNetwork]

public: Optional[EndpointSpecPublic]

class scaleway_async.inference.v1beta1.EndpointSpecPrivateNetwork(private_network_id: 'str')

Bases: object

private_network_id: str: ID of the Private Network.

class scaleway_async.inference.v1beta1.EndpointSpecPublic: Bases: object

class scaleway_async.inference.v1beta1.Eula(content: 'str')

Bases: object

content: str: Content of the end user license agreement.

class scaleway_async.inference.v1beta1.GetDeploymentCertificateRequest(deployment_id: 'str', region: 'Optional[ScwRegion]')

Bases: object

deployment_id: str

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.GetDeploymentRequest(deployment_id: 'str', region: 'Optional[ScwRegion]')

Bases: object

deployment_id: str: ID of the deployment to get.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.GetModelEulaRequest(model_id: 'str', region: 'Optional[ScwRegion]')

Bases: object

model_id: str

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.GetModelRequest(model_id: 'str', region: 'Optional[ScwRegion]')

Bases: object

model_id: str: ID of the model to get.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.InferenceV1Beta1API(client: Client, *, bypass_validation: bool = False)

Bases: API

This API allows you to manage your Inference services.

async add_deployment_acl_rules(*, deployment_id: str, region: Optional[str] = None, acls: Optional[List[ACLRuleRequest]] = None) → AddDeploymentACLRulesResponse

Add new ACLs. Add new ACL rules for a specific deployment. :param deployment_id: ID of the deployment to add ACL rules to. :param region: Region to target. If none is passed will use default region from the config. :param acls: List of ACL rules to add. :return: AddDeploymentACLRulesResponse

Usage:

result = await api.add_deployment_acl_rules(
    deployment_id="example",
)

async create_deployment(*, model_name: str, node_type: str, endpoints: List[EndpointSpec], region: Optional[str] = None, name: Optional[str] = None, project_id: Optional[str] = None, accept_eula: Optional[bool] = None, tags: Optional[List[str]] = None, min_size: Optional[int] = None, max_size: Optional[int] = None) → Deployment

Create a deployment. Create a new inference deployment related to a specific model. :param model_name: Name of the model to use. :param node_type: Name of the node type to use. :param endpoints: List of endpoints to create. :param region: Region to target. If none is passed will use default region from the config. :param name: Name of the deployment. :param project_id: ID of the Project to create the deployment in. :param accept_eula: If the model has an EULA, you must accept it before proceeding. The terms of the EULA can be retrieved using the GetModelEula API call. :param tags: List of tags to apply to the deployment. :param min_size: Defines the minimum size of the pool. :param max_size: Defines the maximum size of the pool. :return: Deployment

Usage:

result = await api.create_deployment(
    model_name="example",
    node_type="example",
    endpoints=[],
)

async create_endpoint(*, deployment_id: str, endpoint: EndpointSpec, region: Optional[str] = None) → Endpoint

Create an endpoint. Create a new Endpoint related to a specific deployment. :param deployment_id: ID of the deployment to create the endpoint for. :param endpoint: Specification of the endpoint. :param region: Region to target. If none is passed will use default region from the config. :return: Endpoint

Usage:

result = await api.create_endpoint(
    deployment_id="example",
    endpoint=EndpointSpec(),
)

async delete_deployment(*, deployment_id: str, region: Optional[str] = None) → Deployment

Delete a deployment. Delete an existing inference deployment. :param deployment_id: ID of the deployment to delete. :param region: Region to target. If none is passed will use default region from the config. :return: Deployment

Usage:

result = await api.delete_deployment(
    deployment_id="example",
)

async delete_deployment_acl_rule(*, acl_id: str, region: Optional[str] = None) → None

Delete an exising ACL. :param acl_id: ID of the ACL rule to delete. :param region: Region to target. If none is passed will use default region from the config.

Usage:

result = await api.delete_deployment_acl_rule(
    acl_id="example",
)

async delete_endpoint(*, endpoint_id: str, region: Optional[str] = None) → None

Delete an endpoint. Delete an existing Endpoint. :param endpoint_id: ID of the endpoint to delete. :param region: Region to target. If none is passed will use default region from the config.

Usage:

result = await api.delete_endpoint(
    endpoint_id="example",
)

async get_deployment(*, deployment_id: str, region: Optional[str] = None) → Deployment

Get a deployment. Get the deployment for the given ID. :param deployment_id: ID of the deployment to get. :param region: Region to target. If none is passed will use default region from the config. :return: Deployment

Usage:

result = await api.get_deployment(
    deployment_id="example",
)

async get_deployment_certificate(*, deployment_id: str, region: Optional[str] = None) → ScwFile

Get the CA certificate. Get the CA certificate used for the deployment of private endpoints. The CA certificate will be returned as a PEM file. :param deployment_id: :param region: Region to target. If none is passed will use default region from the config. :return: ScwFile

Usage:

result = await api.get_deployment_certificate(
    deployment_id="example",
)

async get_model(*, model_id: str, region: Optional[str] = None) → Model

Get a model. Get the model for the given ID. :param model_id: ID of the model to get. :param region: Region to target. If none is passed will use default region from the config. :return: Model

Usage:

result = await api.get_model(
    model_id="example",
)

async get_model_eula(*, model_id: str, region: Optional[str] = None) → Eula

Parameters:

model_id –
region – Region to target. If none is passed will use default region from the config.

Returns:

Eula

Usage:

result = await api.get_model_eula(
    model_id="example",
)

async list_deployment_acl_rules(*, deployment_id: str, region: Optional[str] = None, page: Optional[int] = None, page_size: Optional[int] = None) → ListDeploymentACLRulesResponse

List your ACLs. List ACLs for a specific deployment. :param deployment_id: ID of the deployment to list ACL rules for. :param region: Region to target. If none is passed will use default region from the config. :param page: Page number to return. :param page_size: Maximum number of ACL rules to return per page. :return: ListDeploymentACLRulesResponse

Usage:

result = await api.list_deployment_acl_rules(
    deployment_id="example",
)

async list_deployment_acl_rules_all(*, deployment_id: str, region: Optional[str] = None, page: Optional[int] = None, page_size: Optional[int] = None) → List[ACLRule]

List your ACLs. List ACLs for a specific deployment. :param deployment_id: ID of the deployment to list ACL rules for. :param region: Region to target. If none is passed will use default region from the config. :param page: Page number to return. :param page_size: Maximum number of ACL rules to return per page. :return: List[ACLRule]

Usage:

result = await api.list_deployment_acl_rules_all(
    deployment_id="example",
)

async list_deployments(*, region: Optional[str] = None, page: Optional[int] = None, page_size: Optional[int] = None, order_by: Optional[ListDeploymentsRequestOrderBy] = None, project_id: Optional[str] = None, organization_id: Optional[str] = None, name: Optional[str] = None, tags: Optional[List[str]] = None) → ListDeploymentsResponse

List inference deployments. List all your inference deployments. :param region: Region to target. If none is passed will use default region from the config. :param page: Page number to return. :param page_size: Maximum number of deployments to return per page. :param order_by: Order in which to return results. :param project_id: Filter by Project ID. :param organization_id: Filter by Organization ID. :param name: Filter by deployment name. :param tags: Filter by tags. :return: ListDeploymentsResponse

Usage:

result = await api.list_deployments()

async list_deployments_all(*, region: Optional[str] = None, page: Optional[int] = None, page_size: Optional[int] = None, order_by: Optional[ListDeploymentsRequestOrderBy] = None, project_id: Optional[str] = None, organization_id: Optional[str] = None, name: Optional[str] = None, tags: Optional[List[str]] = None) → List[Deployment]

List inference deployments. List all your inference deployments. :param region: Region to target. If none is passed will use default region from the config. :param page: Page number to return. :param page_size: Maximum number of deployments to return per page. :param order_by: Order in which to return results. :param project_id: Filter by Project ID. :param organization_id: Filter by Organization ID. :param name: Filter by deployment name. :param tags: Filter by tags. :return: List[Deployment]

Usage:

result = await api.list_deployments_all()

async list_models(*, region: Optional[str] = None, order_by: Optional[ListModelsRequestOrderBy] = None, page: Optional[int] = None, page_size: Optional[int] = None, project_id: Optional[str] = None, name: Optional[str] = None, tags: Optional[List[str]] = None) → ListModelsResponse

List models. List all available models. :param region: Region to target. If none is passed will use default region from the config. :param order_by: Order in which to return results. :param page: Page number to return. :param page_size: Maximum number of models to return per page. :param project_id: Filter by Project ID. :param name: Filter by model name. :param tags: Filter by tags. :return: ListModelsResponse

Usage:

result = await api.list_models()

async list_models_all(*, region: Optional[str] = None, order_by: Optional[ListModelsRequestOrderBy] = None, page: Optional[int] = None, page_size: Optional[int] = None, project_id: Optional[str] = None, name: Optional[str] = None, tags: Optional[List[str]] = None) → List[Model]

List models. List all available models. :param region: Region to target. If none is passed will use default region from the config. :param order_by: Order in which to return results. :param page: Page number to return. :param page_size: Maximum number of models to return per page. :param project_id: Filter by Project ID. :param name: Filter by model name. :param tags: Filter by tags. :return: List[Model]

Usage:

result = await api.list_models_all()

async list_node_types(*, include_disabled_types: bool, region: Optional[str] = None, page: Optional[int] = None, page_size: Optional[int] = None) → ListNodeTypesResponse

List available node types. List all available node types. By default, the node types returned in the list are ordered by creation date in ascending order, though this can be modified via the order_by field. :param include_disabled_types: Include disabled node types in the response. :param region: Region to target. If none is passed will use default region from the config. :param page: Page number to return. :param page_size: Maximum number of node types to return per page. :return: ListNodeTypesResponse

Usage:

result = await api.list_node_types(
    include_disabled_types=False,
)

async list_node_types_all(*, include_disabled_types: bool, region: Optional[str] = None, page: Optional[int] = None, page_size: Optional[int] = None) → List[NodeType]

List available node types. List all available node types. By default, the node types returned in the list are ordered by creation date in ascending order, though this can be modified via the order_by field. :param include_disabled_types: Include disabled node types in the response. :param region: Region to target. If none is passed will use default region from the config. :param page: Page number to return. :param page_size: Maximum number of node types to return per page. :return: List[NodeType]

Usage:

result = await api.list_node_types_all(
    include_disabled_types=False,
)

async set_deployment_acl_rules(*, deployment_id: str, region: Optional[str] = None, acls: Optional[List[ACLRuleRequest]] = None) → SetDeploymentACLRulesResponse

Set new ACL. Set new ACL rules for a specific deployment. :param deployment_id: ID of the deployment to set ACL rules for. :param region: Region to target. If none is passed will use default region from the config. :param acls: All existing ACL rules will be replaced by the new ones. :return: SetDeploymentACLRulesResponse

Usage:

result = await api.set_deployment_acl_rules(
    deployment_id="example",
)

async update_deployment(*, deployment_id: str, region: Optional[str] = None, name: Optional[str] = None, tags: Optional[List[str]] = None, min_size: Optional[int] = None, max_size: Optional[int] = None) → Deployment

Update a deployment. Update an existing inference deployment. :param deployment_id: ID of the deployment to update. :param region: Region to target. If none is passed will use default region from the config. :param name: Name of the deployment. :param tags: List of tags to apply to the deployment. :param min_size: Defines the new minimum size of the pool. :param max_size: Defines the new maximum size of the pool. :return: Deployment

Usage:

result = await api.update_deployment(
    deployment_id="example",
)

async update_endpoint(*, endpoint_id: str, region: Optional[str] = None, disable_auth: Optional[bool] = None) → Endpoint

Update an endpoint. Update an existing Endpoint. :param endpoint_id: ID of the endpoint to update. :param region: Region to target. If none is passed will use default region from the config. :param disable_auth: By default, deployments are protected by IAM authentication. When setting this field to true, the authentication will be disabled. :return: Endpoint

Usage:

result = await api.update_endpoint(
    endpoint_id="example",
)

async wait_for_deployment(*, deployment_id: str, region: Optional[str] = None, options: Optional[WaitForOptions[Deployment, Union[bool, Awaitable[bool]]]] = None) → Deployment

Get a deployment. Get the deployment for the given ID. :param deployment_id: ID of the deployment to get. :param region: Region to target. If none is passed will use default region from the config. :return: Deployment

Usage:

result = await api.get_deployment(
    deployment_id="example",
)

class scaleway_async.inference.v1beta1.ListDeploymentACLRulesRequest(deployment_id: 'str', region: 'Optional[ScwRegion]', page: 'Optional[int]', page_size: 'Optional[int]')

Bases: object

deployment_id: str: ID of the deployment to list ACL rules for.

page: Optional[int]: Page number to return.

page_size: Optional[int]: Maximum number of ACL rules to return per page.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.ListDeploymentACLRulesResponse(rules: 'List[ACLRule]', total_count: 'int')

Bases: object

rules: List[ACLRule]: List of ACL rules on the current page.

total_count: int: Total number of ACL rules.

class scaleway_async.inference.v1beta1.ListDeploymentsRequest(region: 'Optional[ScwRegion]', page: 'Optional[int]', page_size: 'Optional[int]', order_by: 'Optional[ListDeploymentsRequestOrderBy]', project_id: 'Optional[str]', organization_id: 'Optional[str]', name: 'Optional[str]', tags: 'Optional[List[str]]')

Bases: object

name: Optional[str]: Filter by deployment name.

order_by: Optional[ListDeploymentsRequestOrderBy]: Order in which to return results.

organization_id: Optional[str]: Filter by Organization ID.

page: Optional[int]: Page number to return.

page_size: Optional[int]: Maximum number of deployments to return per page.

project_id: Optional[str]: Filter by Project ID.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

tags: Optional[List[str]]: Filter by tags.

class scaleway_async.inference.v1beta1.ListDeploymentsRequestOrderBy(value: str, names: Optional[Any] = None, *args: Any, **kwargs: Any)

Bases: str, Enum

An enumeration.

CREATED_AT_ASC = 'created_at_asc'

CREATED_AT_DESC = 'created_at_desc'

NAME_ASC = 'name_asc'

NAME_DESC = 'name_desc'

class scaleway_async.inference.v1beta1.ListDeploymentsResponse(deployments: 'List[Deployment]', total_count: 'int')

Bases: object

deployments: List[Deployment]: List of deployments on the current page.

total_count: int: Total number of deployments.

class scaleway_async.inference.v1beta1.ListModelsRequest(region: 'Optional[ScwRegion]', order_by: 'Optional[ListModelsRequestOrderBy]', page: 'Optional[int]', page_size: 'Optional[int]', project_id: 'Optional[str]', name: 'Optional[str]', tags: 'Optional[List[str]]')

Bases: object

name: Optional[str]: Filter by model name.

order_by: Optional[ListModelsRequestOrderBy]: Order in which to return results.

page: Optional[int]: Page number to return.

page_size: Optional[int]: Maximum number of models to return per page.

project_id: Optional[str]: Filter by Project ID.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

tags: Optional[List[str]]: Filter by tags.

class scaleway_async.inference.v1beta1.ListModelsRequestOrderBy(value: str, names: Optional[Any] = None, *args: Any, **kwargs: Any)

Bases: str, Enum

An enumeration.

CREATED_AT_ASC = 'created_at_asc'

CREATED_AT_DESC = 'created_at_desc'

DISPLAY_RANK_ASC = 'display_rank_asc'

NAME_ASC = 'name_asc'

NAME_DESC = 'name_desc'

class scaleway_async.inference.v1beta1.ListModelsResponse(models: 'List[Model]', total_count: 'int')

Bases: object

models: List[Model]: List of models on the current page.

total_count: int: Total number of models.

class scaleway_async.inference.v1beta1.ListNodeTypesRequest(include_disabled_types: 'bool', region: 'Optional[ScwRegion]', page: 'Optional[int]', page_size: 'Optional[int]')

Bases: object

include_disabled_types: bool: Include disabled node types in the response.

page: Optional[int]: Page number to return.

page_size: Optional[int]: Maximum number of node types to return per page.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.ListNodeTypesResponse(node_types: 'List[NodeType]', total_count: 'int')

Bases: object

node_types: List[NodeType]: List of node types.

total_count: int: Total number of node types.

class scaleway_async.inference.v1beta1.Model(id: 'str', name: 'str', project_id: 'str', provider: 'str', tags: 'List[str]', description: 'str', has_eula: 'bool', region: 'ScwRegion', is_public: 'bool', compatible_node_types: 'List[str]', quantization_level: 'str', created_at: 'Optional[datetime]', updated_at: 'Optional[datetime]', s3_model: 'Optional[ModelS3Model]')

Bases: object

compatible_node_types: List[str]: Names of the node types compatible with the model.

created_at: Optional[datetime]: Creation date of the model.

description: str: Purpose of the model.

has_eula: bool: Defines whether the model has an end user license agreement.

id: str: Unique identifier.

is_public: bool: Defines whether the model is public or not.

name: str: Unique Name identifier.

project_id: str: Project ID.

provider: str: Name of the model provider.

quantization_level: str: Quantization level of the model.

region: str: Region of the model.

s3_model: Optional[ModelS3Model]

tags: List[str]: List of tags applied to the model.

updated_at: Optional[datetime]: Last modification date of the model.

class scaleway_async.inference.v1beta1.ModelS3Model(s3_url: 'str', python_dependencies: 'Dict[str, str]', node_type: 'Optional[str]', triton_server_version: 'Optional[str]')

Bases: object

node_type: Optional[str]

python_dependencies: Dict[str, str]

s3_url: str

triton_server_version: Optional[str]

class scaleway_async.inference.v1beta1.NodeType(name: 'str', stock_status: 'NodeTypeStock', description: 'str', vcpus: 'int', memory: 'int', vram: 'int', disabled: 'bool', beta: 'bool', gpus: 'int', region: 'ScwRegion', created_at: 'Optional[datetime]', updated_at: 'Optional[datetime]')

Bases: object

beta: bool: The node type is currently in beta.

created_at: Optional[datetime]: Creation date of the node type.

description: str: Current specs of the offer.

disabled: bool: The node type is currently disabled.

gpus: int: Number of GPUs.

memory: int: Quantity of RAM.

name: str: Name of the node type.

region: str: Region of the node type.

stock_status: NodeTypeStock: Current stock status for the node type.

updated_at: Optional[datetime]: Last modification date of the node type.

vcpus: int: Number of virtual CPUs.

vram: int: Quantity of GPU RAM.

class scaleway_async.inference.v1beta1.NodeTypeStock(value: str, names: Optional[Any] = None, *args: Any, **kwargs: Any)

Bases: str, Enum

An enumeration.

AVAILABLE = 'available'

LOW_STOCK = 'low_stock'

OUT_OF_STOCK = 'out_of_stock'

UNKNOWN_STOCK = 'unknown_stock'

class scaleway_async.inference.v1beta1.SetDeploymentACLRulesRequest(deployment_id: 'str', region: 'Optional[ScwRegion]', acls: 'Optional[List[ACLRuleRequest]]')

Bases: object

acls: Optional[List[ACLRuleRequest]]: All existing ACL rules will be replaced by the new ones.

deployment_id: str: ID of the deployment to set ACL rules for.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

class scaleway_async.inference.v1beta1.SetDeploymentACLRulesResponse(rules: 'List[ACLRule]')

Bases: object

rules: List[ACLRule]: List of ACL rules that were set.

class scaleway_async.inference.v1beta1.UpdateDeploymentRequest(deployment_id: 'str', region: 'Optional[ScwRegion]', name: 'Optional[str]', tags: 'Optional[List[str]]', min_size: 'Optional[int]', max_size: 'Optional[int]')

Bases: object

deployment_id: str: ID of the deployment to update.

max_size: Optional[int]: Defines the new maximum size of the pool.

min_size: Optional[int]: Defines the new minimum size of the pool.

name: Optional[str]: Name of the deployment.

region: Optional[str]: Region to target. If none is passed will use default region from the config.

tags: Optional[List[str]]: List of tags to apply to the deployment.

class scaleway_async.inference.v1beta1.UpdateEndpointRequest(endpoint_id: 'str', region: 'Optional[ScwRegion]', disable_auth: 'Optional[bool]')

Bases: object

disable_auth: Optional[bool]: By default, deployments are protected by IAM authentication.

When setting this field to true, the authentication will be disabled.

endpoint_id: str: ID of the endpoint to update.

region: Optional[str]: Region to target. If none is passed will use default region from the config.