Spaces:
Paused
Paused
| AWSTemplateFormatVersion: '2010-09-09' | |
| Transform: AWS::Serverless-2016-10-31 | |
| Description: > | |
| llmlite-service | |
| SAM Template for llmlite-service | |
| # More info about Globals: https://github.com/awslabs/serverless-application-model/blob/master/docs/globals.rst | |
| Globals: | |
| Function: | |
| Timeout: 600 | |
| MemorySize: 128 | |
| Environment: | |
| Variables: | |
| WORKER_CONFIG: !Ref WorkerConfigParameter | |
| Parameters: | |
| AliasParameter: | |
| Type: String | |
| Default: live | |
| WorkerConfigParameter: | |
| Type: String | |
| Description: Sample environment variable | |
| Default: '{"model": null, "alias": null, "api_base": null, "api_version": "2023-07-01-preview", "debug": false, "temperature": null, "max_tokens": null, "request_timeout": 600, "max_budget": null, "telemetry": true, "drop_params": false, "add_function_to_prompt": false, "headers": null, "save": false, "config": null, "use_queue": false}' | |
| Resources: | |
| MyUrlFunctionPermissions: | |
| Type: AWS::Lambda::Permission | |
| Properties: | |
| FunctionName: !Ref URL | |
| Action: lambda:InvokeFunctionUrl | |
| Principal: "*" | |
| FunctionUrlAuthType: NONE | |
| Function: | |
| Type: AWS::Serverless::Function | |
| Properties: | |
| FunctionName: !Sub "${AWS::StackName}-function" | |
| CodeUri: "./litellm" | |
| Handler: proxy/lambda.handler | |
| Runtime: python3.11 | |
| AutoPublishAlias: !Ref AliasParameter | |
| Architectures: | |
| - x86_64 | |
| DeploymentPreference: | |
| Type: AllAtOnce | |
| Alarms: | |
| - !Ref NewVersionErrorMetricGreaterThanZeroAlarm | |
| NewVersionErrorMetricGreaterThanZeroAlarm: | |
| Type: "AWS::CloudWatch::Alarm" | |
| Properties: | |
| AlarmDescription: Lambda Function Error > 0 | |
| ComparisonOperator: GreaterThanThreshold | |
| Dimensions: | |
| - Name: Resource | |
| Value: !Sub "${Function}:live" | |
| - Name: FunctionName | |
| Value: !Ref Function | |
| - Name: ExecutedVersion | |
| Value: !GetAtt Function.Version.Version | |
| EvaluationPeriods: 1 | |
| Unit: Count | |
| MetricName: Errors | |
| Namespace: AWS/Lambda | |
| Period: 60 | |
| Statistic: Sum | |
| Threshold: 0 | |
| URL: | |
| Type: AWS::Lambda::Url | |
| DependsOn: FunctionAliaslive | |
| Properties: | |
| AuthType: NONE | |
| Qualifier: live | |
| TargetFunctionArn: !GetAtt Function.Arn | |
| Outputs: | |
| FunctionARN: | |
| Description: "Lambda Function ARN" | |
| Value: !GetAtt Function.Arn | |
| FunctionUrl: | |
| Description: "Lambda Function URL Endpoint" | |
| Value: | |
| Fn::GetAtt: URL.FunctionUrl | |
| FunctionVersion: | |
| Description: "Lambda Function Version" | |
| Value: !GetAtt Function.Version.Version | |
| FunctionNewAlarmARN: | |
| Description: "Lambda Function New Alarm ARN" | |
| Value: !GetAtt NewVersionErrorMetricGreaterThanZeroAlarm.Arn | |