Class API

constructor

• new API(client): LLMInference.v1beta1.API

• Parameters

  • client: Client

  Returns LLMInference.v1beta1.API

Static ReadonlyLOCALITIES

addDeploymentACLRules

• addDeploymentACLRules(request): Promise<LLMInference.v1beta1.AddDeploymentACLRulesResponse>

• Add new ACLs. Add new ACL rules for a specific deployment.

  Parameters

  • request: Readonly<LLMInference.v1beta1.AddDeploymentACLRulesRequest>

    The request AddDeploymentACLRulesRequest

  Returns Promise<LLMInference.v1beta1.AddDeploymentACLRulesResponse>

  A Promise of AddDeploymentACLRulesResponse

createDeployment

• createDeployment(request): Promise<LLMInference.v1beta1.Deployment>

• Create a deployment. Create a new inference deployment related to a specific model.

  Parameters

  • request: Readonly<LLMInference.v1beta1.CreateDeploymentRequest>

    The request CreateDeploymentRequest

  Returns Promise<LLMInference.v1beta1.Deployment>

  A Promise of Deployment

createEndpoint

• createEndpoint(request): Promise<LLMInference.v1beta1.Endpoint>

• Create an endpoint. Create a new Endpoint related to a specific deployment.

  Parameters

  • request: Readonly<LLMInference.v1beta1.CreateEndpointRequest>

    The request CreateEndpointRequest

  Returns Promise<LLMInference.v1beta1.Endpoint>

  A Promise of Endpoint

deleteDeployment

• deleteDeployment(request): Promise<LLMInference.v1beta1.Deployment>

• Delete a deployment. Delete an existing inference deployment.

  Parameters

  • request: Readonly<LLMInference.v1beta1.DeleteDeploymentRequest>

    The request DeleteDeploymentRequest

  Returns Promise<LLMInference.v1beta1.Deployment>

  A Promise of Deployment

deleteDeploymentACLRule

• deleteDeploymentACLRule(request): Promise<void>

• Delete an exising ACL.

  Parameters

  • request: Readonly<LLMInference.v1beta1.DeleteDeploymentACLRuleRequest>

    The request DeleteDeploymentACLRuleRequest

  Returns Promise<void>

deleteEndpoint

• deleteEndpoint(request): Promise<void>

• Delete an endpoint. Delete an existing Endpoint.

  Parameters

  • request: Readonly<LLMInference.v1beta1.DeleteEndpointRequest>

    The request DeleteEndpointRequest

  Returns Promise<void>

getDeployment

• getDeployment(request): Promise<LLMInference.v1beta1.Deployment>

• Get a deployment. Get the deployment for the given ID.

  Parameters

  • request: Readonly<LLMInference.v1beta1.GetDeploymentRequest>

    The request GetDeploymentRequest

  Returns Promise<LLMInference.v1beta1.Deployment>

  A Promise of Deployment

getDeploymentCertificate

• getDeploymentCertificate(request): Promise<Blob>

• 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.

  Parameters

  • request: Readonly<LLMInference.v1beta1.GetDeploymentCertificateRequest>

    The request GetDeploymentCertificateRequest

  Returns Promise<Blob>

  A Promise of Blob

getModel

• getModel(request): Promise<LLMInference.v1beta1.Model>

• Get a model. Get the model for the given ID.

  Parameters

  • request: Readonly<LLMInference.v1beta1.GetModelRequest>

    The request GetModelRequest

  Returns Promise<LLMInference.v1beta1.Model>

  A Promise of Model

getModelEula

• getModelEula(request): Promise<LLMInference.v1beta1.Eula>

• Parameters

  • request: Readonly<LLMInference.v1beta1.GetModelEulaRequest>

  Returns Promise<LLMInference.v1beta1.Eula>

listDeploymentACLRules

• listDeploymentACLRules(request): Promise<LLMInference.v1beta1.ListDeploymentACLRulesResponse> & {
      [asyncIterator]: (() => AsyncGenerator<LLMInference.v1beta1.ACLRule[], void, void>);
      all: (() => Promise<LLMInference.v1beta1.ACLRule[]>);
  }

• List your ACLs. List ACLs for a specific deployment.

  Parameters

  • request: Readonly<LLMInference.v1beta1.ListDeploymentACLRulesRequest>

    The request ListDeploymentACLRulesRequest

  Returns Promise<LLMInference.v1beta1.ListDeploymentACLRulesResponse> & {
      [asyncIterator]: (() => AsyncGenerator<LLMInference.v1beta1.ACLRule[], void, void>);
      all: (() => Promise<LLMInference.v1beta1.ACLRule[]>);
  }

  A Promise of ListDeploymentACLRulesResponse

listDeployments

• listDeployments(request?): Promise<LLMInference.v1beta1.ListDeploymentsResponse> & {
      [asyncIterator]: (() => AsyncGenerator<LLMInference.v1beta1.Deployment[], void, void>);
      all: (() => Promise<LLMInference.v1beta1.Deployment[]>);
  }

• List inference deployments. List all your inference deployments.

  Parameters

  • request: Readonly<LLMInference.v1beta1.ListDeploymentsRequest> = {}

    The request ListDeploymentsRequest

  Returns Promise<LLMInference.v1beta1.ListDeploymentsResponse> & {
      [asyncIterator]: (() => AsyncGenerator<LLMInference.v1beta1.Deployment[], void, void>);
      all: (() => Promise<LLMInference.v1beta1.Deployment[]>);
  }

  A Promise of ListDeploymentsResponse

listModels

• listModels(request?): Promise<LLMInference.v1beta1.ListModelsResponse> & {
      [asyncIterator]: (() => AsyncGenerator<LLMInference.v1beta1.Model[], void, void>);
      all: (() => Promise<LLMInference.v1beta1.Model[]>);
  }

• List models. List all available models.

  Parameters

  • request: Readonly<LLMInference.v1beta1.ListModelsRequest> = {}

    The request ListModelsRequest

  Returns Promise<LLMInference.v1beta1.ListModelsResponse> & {
      [asyncIterator]: (() => AsyncGenerator<LLMInference.v1beta1.Model[], void, void>);
      all: (() => Promise<LLMInference.v1beta1.Model[]>);
  }

  A Promise of ListModelsResponse

listNodeTypes

• listNodeTypes(request): Promise<LLMInference.v1beta1.ListNodeTypesResponse> & {
      [asyncIterator]: (() => AsyncGenerator<LLMInference.v1beta1.NodeType[], void, void>);
      all: (() => Promise<LLMInference.v1beta1.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.

  Parameters

  • request: Readonly<LLMInference.v1beta1.ListNodeTypesRequest>

    The request ListNodeTypesRequest

  Returns Promise<LLMInference.v1beta1.ListNodeTypesResponse> & {
      [asyncIterator]: (() => AsyncGenerator<LLMInference.v1beta1.NodeType[], void, void>);
      all: (() => Promise<LLMInference.v1beta1.NodeType[]>);
  }

  A Promise of ListNodeTypesResponse

setDeploymentACLRules

• setDeploymentACLRules(request): Promise<LLMInference.v1beta1.SetDeploymentACLRulesResponse>

• Set new ACL. Set new ACL rules for a specific deployment.

  Parameters

  • request: Readonly<LLMInference.v1beta1.SetDeploymentACLRulesRequest>

    The request SetDeploymentACLRulesRequest

  Returns Promise<LLMInference.v1beta1.SetDeploymentACLRulesResponse>

  A Promise of SetDeploymentACLRulesResponse

updateDeployment

• updateDeployment(request): Promise<LLMInference.v1beta1.Deployment>

• Update a deployment. Update an existing inference deployment.

  Parameters

  • request: Readonly<LLMInference.v1beta1.UpdateDeploymentRequest>

    The request UpdateDeploymentRequest

  Returns Promise<LLMInference.v1beta1.Deployment>

  A Promise of Deployment

updateEndpoint

• updateEndpoint(request): Promise<LLMInference.v1beta1.Endpoint>

• Update an endpoint. Update an existing Endpoint.

  Parameters

  • request: Readonly<LLMInference.v1beta1.UpdateEndpointRequest>

    The request UpdateEndpointRequest

  Returns Promise<LLMInference.v1beta1.Endpoint>

  A Promise of Endpoint

waitForDeployment

• waitForDeployment(request, options?): Promise<LLMInference.v1beta1.Deployment>

• Waits for Deployment to be in a final state.

  Parameters

  • request: Readonly<LLMInference.v1beta1.GetDeploymentRequest>

    The request GetDeploymentRequest
  • Optionaloptions: Readonly<WaitForOptions<LLMInference.v1beta1.Deployment>>

    The waiting options

  Returns Promise<LLMInference.v1beta1.Deployment>

  A Promise of Deployment