[FEAT][Caluclate pricing]

requirements.txt

@@ -8,4 +8,6 @@ tensorrt
 torch 
 einops
 tiktoken
-uvicorn
+uvicorn
+loguru
+pydantic

scripts/hive.tf

@@ -0,0 +1,83 @@
+provider "aws" {
+  region = "us-west-2" # Choose an appropriate region
+}
+
+resource "aws_security_group" "allow_http" {
+  name        = "allow_http"
+  description = "Allow HTTP inbound traffic"
+
+  ingress {
+    from_port   = 80
+    to_port     = 80
+    protocol    = "tcp"
+    cidr_blocks = ["0.0.0.0/0"]
+  }
+
+  egress {
+    from_port   = 0
+    to_port     = 0
+    protocol    = "-1"
+    cidr_blocks = ["0.0.0.0/0"]
+  }
+}
+
+resource "aws_launch_template" "gpu_instance" {
+  name_prefix   = "gpu-instance-"
+  image_id      = "ami-123456" # Specify an appropriate AMI for your GPU instance
+  instance_type = "p3.2xlarge" # This is an example GPU instance type. Adjust based on your needs.
+
+  network_interfaces {
+    associate_public_ip_address = true
+    security_groups             = [aws_security_group.allow_http.id]
+  }
+
+  user_data = <<-EOF
+              #!/bin/bash
+              echo "Your setup script goes here. This could install Docker, your application, etc."
+              EOF
+}
+
+resource "aws_autoscaling_group" "gpu_asg" {
+  launch_template {
+    id      = aws_launch_template.gpu_instance.id
+    version = "$Latest"
+  }
+
+  min_size         = 1
+  max_size         = 3
+  desired_capacity = 2
+  vpc_zone_identifier = ["subnet-12345"] # Specify your subnet IDs
+
+  tag {
+    key                 = "Name"
+    value               = "GPUInstance"
+    propagate_at_launch = true
+  }
+}
+
+resource "aws_elb" "api_load_balancer" {
+  name               = "api-lb"
+  availability_zones = ["us-west-2a", "us-west-2b"] # Adjust based on your VPC and subnet setup
+
+  listener {
+    instance_port     = 80
+    instance_protocol = "HTTP"
+    lb_port           = 80
+    lb_protocol       = "HTTP"
+  }
+
+  health_check {
+    target              = "HTTP:80/"
+    interval            = 30
+    timeout             = 5
+    healthy_threshold   = 2
+    unhealthy_threshold = 2
+  }
+
+  instances                   = [aws_autoscaling_group.gpu_asg.*.id]
+  cross_zone_load_balancing   = true
+  idle_timeout                = 400
+  connection_draining         = true
+  connection_draining_timeout = 400
+}
+

scripts/hive2.tf

@@ -0,0 +1,104 @@
+provider "aws" {
+  region = "us-west-2"
+}
+
+# Define an Application Load Balancer
+resource "aws_lb" "example" {
+  name               = "example-lb"
+  internal           = false
+  load_balancer_type = "application"
+  security_groups    = [aws_security_group.lb_sg.id]
+  subnets            = [aws_subnet.example1.id, aws_subnet.example2.id]
+
+  enable_deletion_protection = false
+}
+
+# Define a target group for the ALB
+resource "aws_lb_target_group" "example" {
+  name     = "example-tg"
+  port     = 80
+  protocol = "HTTP"
+  vpc_id   = aws_vpc.example.id
+
+  health_check {
+    enabled = true
+    path    = "/"
+    protocol = "HTTP"
+    matcher = "200"
+  }
+}
+
+# Launch Template
+resource "aws_launch_template" "example" {
+  name_prefix   = "example-lt-"
+  image_id      = "ami-1234567890abcdef0"  # Replace with a valid AMI ID
+  instance_type = "t2.micro"
+
+  # Add other configurations as necessary, such as key name, security groups, etc.
+}
+
+# Auto Scaling Group
+resource "aws_autoscaling_group" "example" {
+  launch_template {
+    id      = aws_launch_template.example.id
+    version = "$Latest"
+  }
+
+  min_size         = 1
+  max_size         = 10
+  desired_capacity = 2
+  vpc_zone_identifier = [aws_subnet.example1.id, aws_subnet.example2.id]
+  target_group_arns   = [aws_lb_target_group.example.arn]
+}
+
+# CloudWatch Alarm for Scaling Out
+resource "aws_cloudwatch_metric_alarm" "high_cpu" {
+  alarm_name          = "high-cpu-usage"
+  comparison_operator = "GreaterThanThreshold"
+  evaluation_periods  = 2
+  metric_name         = "CPUUtilization"
+  namespace           = "AWS/EC2"
+  period              = 300
+  statistic           = "Average"
+  threshold           = 75
+  alarm_actions       = [aws_autoscaling_policy.scale_out.arn]
+
+  dimensions = {
+    AutoScalingGroupName = aws_autoscaling_group.example.name
+  }
+}
+
+# Scaling Policy for Out
+resource "aws_autoscaling_policy" "scale_out" {
+  name                   = "scale-out"
+  scaling_adjustment     = 1
+  adjustment_type        = "ChangeInCapacity"
+  autoscaling_group_name = aws_autoscaling_group.example.name
+  cooldown               = 300
+}
+
+# CloudWatch Alarm for Scaling In
+resource "aws_cloudwatch_metric_alarm" "low_cpu" {
+  alarm_name          = "low-cpu-usage"
+  comparison_operator = "LessThanThreshold"
+  evaluation_periods  = 2
+  metric_name         = "CPUUtilization"
+  namespace           = "AWS/EC2"
+  period              = 300
+  statistic           = "Average"
+  threshold           = 25
+  alarm_actions       = [aws_autoscaling_policy.scale_in.arn]
+
+  dimensions = {
+    AutoScalingGroupName = aws_autoscaling_group.example.name
+  }
+}
+
+# Scaling Policy for In
+resource "aws_autoscaling_policy" "scale_in" {
+  name                   = "scale-in"
+  scaling_adjustment     = -1
+  adjustment_type        = "ChangeInCapacity"
+  autoscaling_group_name = aws_autoscaling_group.example.name
+  cooldown               = 300
+}