Evaluation Deployment Guide

1. VM Preparation

   • Launch a Virtual Machine (VM) using your organization's standard protocol

   • Ensure the VM meets all system requirements. System Requirements

   • Ensure VM meets the Software Requirements & Network Validation. Software Requirements

   • If needed, consult cloud-specific documentation for VM setup or run our sample terraform templates to launch VM in your cloud

   • Install nginx on the VM - and ensure that it is accessible from the developer machine. HTTP or HTTPS(if required) is already setup.

2. Installation Execution

   • SSH into the instance

   • Run the provided bash script on your prepared VM

3. Verify Installation

System Requirements

Architecture	ARM	AMD
CPU	8 vCPU	16 vCPU
Memory	32 GB	64 GB
Disk Space	128 GB	128 GB

• Disk where /var is mounted should have 80GB as available disk space.

• Linux user must have sudo access

Inbound Ports

• 22 (SSH)

  • Required to access the terminal to run the script.

• 80 (HTTP)

  • Required to access the APIs and UI.

Outbound Ports

• 443 (HTTPS)

  • Required to pull images from docker hub.

  • Required to connect to hosted LLMs (e.g. OpenAPI, Anthropic)

• 587 [Optional] (SMTP)

  • Only needed if email functionality is required.

• 80 (HTTP)

  • Required only during initial setup. This is required to install few packages like (unizp, jq)

  • We should close port 80 after installing Raga Catalyst.

Software Requirements

• Operating System: Ubuntu Noble 24.04 (LTS) or RHEL 9

• Docker 27.2.0+ (Install Docker)
• Minikube V1.33.0+ (Install Minikube)
• Nginx (Install Nginx)

Validating Installation & Network Accessibility

Verify Docker Installation & Networking

• Run a Docker container:

  docker run --rm nginx sh -c "curl -o /dev/null -s -w '%{http_code}\n' https://www.google.com"

• If it prints 200, the installation is successful, and the networking is compatible.

Verify Minikube Installation

• Check the installation by executing:

  minikube version

Verify Nginx Installation

• Check the Nginx status by executing:

  sudo systctl status nginx

  It should be running.

• Execute the command:

  curl -o /dev/null -s -w '%{http_code}\n' localhost

  If should print 200

• Access the default Nginx page from a browser outside the VM using its IP http://:80/

Sample Terraform Templates to Launch VM

Azure

Prerequisites

• Install terraform CLI command
• Ensure that your system supports Bash commands

• Active Azure account with a valid subscription

• Owner or Contributor role on the subscription

• Registered namespaces:

  • Microsoft.Network

  • Microsoft.Compute

• Ensure at least 16 vCPUs are available within your subscription and region to deploy the Standard Ds v3 Family instance type.

• Azure CLI installed

Azure login using CLI

az login

• Open the web link and input the code

• Select the desired subscription

Execute the following command in your terminal:

curl -sL https://raga-catalyst-aws.s3.ap-south-1.amazonaws.com/create_vm.sh | bash -s -- 'azure' '<region>' '<vm_type>'

Replace placeholders:

• <region>: Deployment region

• <vm_type>: public | private

Output:

• Get the IP and password of the Instance

SSH into the instance:

ssh -i ubuntu@<VM-IP>

Install Azure Monitor Agent (Optional)

Get the VM ID:

az vm show --name RagaCatalystVM --resource-group RagaCatalystRG --query "id" --output tsv

Example output:

/subscriptions/<tenant_id>/resourceGroups/RAGA-AMI/providers/Microsoft.Compute/virtualMachines/RagaCatalyst

This is the VM ID, which can be used in other Azure commands to reference the virtual machine

Install the Azure Monitor Agent on VM:

az vm extension set --name AzureMonitorLinuxAgent --publisher Microsoft.Azure.Monitor --enable-auto-upgrade true --ids <replace-id>

Remove Port 80 Outbound Rule after installing Raga Catalyst on VM

az network nsg rule delete \
    --resource-group RagaCatalystRG \
    --nsg-name RagaCatalyst-NSG \
    --name Allow-80-Outbound

AWS

Prerequisites

• Install terraform CLI command
• Ensure that your system supports Bash commands

• AWS account:

  • You must have an AWS account with 8 vCPUs available and Ec2 FullAccess in that region in the region where the instance will be created. The AWS user must have programmatic access.

• AWS user with programmatic access

• AWS CLI installed

AWS login using CLI

Option A: Using aws configure

aws configure

Provide:

• Access Key ID

• Secret Access Key

• Default Region (e.g., us-east-1)

• Output Format (json, text, table)

Option B: Using AWS Keys Export

export AWS_ACCESS_KEY_ID=your-access-key-id
export AWS_SECRET_ACCESS_KEY=your-secret-access-key

Validate aws cli Login:

aws sts get-caller-identity

Execute the following command to Launch Raga Catalyst VM:

curl -sL https://raga-catalyst-aws.s3.ap-south-1.amazonaws.com/create_vm.sh | bash -s -- 'aws' '<region>' '<vm_type>'

Replace placeholders:

• <region>: Deployment region

• <vm_type>: public | private

Output:

• Retrieve the PEM file raga-catalyst.pem from the current path. Copy the PEM file to another location as a precaution. If the PEM file is lost, you will not be able to SSH into the instances in the future

• Save the security_group_id, as it will be required in the next steps.

• Get the IP of the Instance

SSH into the instance:

ssh -i raga-catalyst.pem ubuntu@<VM-IP>

Remove Port 80 Outbound Rule after installing Raga Catalyst on VM

• Get the security group ID from the step 2 command output and replace that ID in the following command security-group-id

• replace your-region with your region

aws ec2 revoke-security-group-egress \
    --group-id <security-group-id> \
    --protocol tcp \
    --port 80 \
    --region <your-region> \
    --cidr 0.0.0.0/0

GCP

GCP Account Requirements

• GCP Account , Project and Quotas

  • Ensure you have a Google Cloud account with an active project.

  • Ensure you have a Google Cloud project with a sufficient quota to launch an instance with the t2a-standard-8 machine type (8 vCPUs and 32 GiB Memory).

  • Confirm the availability of the required resources (such as VPCs, subnets, and public IP addresses) in your chosen region. Use This Command

    gcloud services enable compute.googleapis.com

  • Alternatively, enable it via the Google Cloud Console: Navigate to APIs & Services > Library, search for "Compute Engine API," and click Enable. Navigate to APIs & Services > Library, search for "Compute Engine API," and click Enable:

  • The Gcloud user or service account used must have the following permissions:

    • Compute Admin: To create and manage instances, networks, and firewall rules.

    • Storage Admin: If additional storage operations are required.

    • Service Account User: To assign the service account to the instance.

• Programmatic Access

  • Set up programmatic access using either gcloud auth or service account credentials.

  • Refer to the Authentication Setup section below for details.
• Google Cloud CLI Installed

  • Ensure the Google Cloud CLI (gcloud) is installed on your local system.

  • Installation guide: Install Google Cloud CLI.

GCP login using CLI

Option A: Using gcloud Auth

• Authenticate with The Google Cloud SDK.

  gcloud auth application-default login

• Authenticate using gcloud auth.

  gcloud auth login

• Set the active project and region:

  gcloud config set project <PROJECT_ID>
  gcloud config set compute/region <REGION>

• Export the Project ID in The Environment.

  export GOOGLE_PROJECT=$(gcloud config get-value project)

• Verify your configuration:

  gcloud config list

Option B: Using a Service Account Key File

• Obtain a service account key file (JSON format) with the necessary permissions.

  gcloud auth activate-service-account --key-file=<PATH_TO_KEY_FILE>

• Set the active project and region:

  gcloud config set project <PROJECT_ID>
  gcloud config set compute/region <REGION>

• Export the Project ID in The Environment.

  export GOOGLE_PROJECT=$(gcloud config get-value project)

• Verify your configuration:

  gcloud config list

Execute the following command to Launch Raga Catalyst VM:

curl -sL https://raga-catalyst-aws.s3.ap-south-1.amazonaws.com/create_vm.sh | bash -s -- 'gcp' '<region>' '<vm_type>'

Replace placeholders:

• <region>: Deployment region

• <vm_type>: public | private

Output:

• Retrieve the PEM file raga_ssh_private_key.pem from the current path. Copy the PEM file to another location as a precaution. If the PEM file is lost, you will not be able to SSH into the instances in the future

• Get the IP of the Instance

SSH into the instance:

ssh -i raga_ssh_private_key.pem ubuntu@<VM-IP>

Install Raga Catalyst on VM

Install Raga Catalyst:

• SSH into the instance and run the installation command.

• Run the script received from inside the VM from user home directory.

Access Raga Catalyst

• Wait 30 minutes after command execution

• Portal: http://<vm_ip>

• API: http://<vm_ip>/api

• If you face any issues accessing Raga Catalyst, run the command cat /var/log/ragastartup.log and share the output with the Raga team for quick assistance