Skip to content
Vane Search AI Platform & Data · Vane 1.12.2 Launch on AWS

Getting started

Launch Vane Search, run the walkthrough, and open port 3000 through Session Manager.

You need: an AWS account that can subscribe on AWS Marketplace, launch EC2, and start Session Manager. Install the AWS CLI and the Session Manager plugin on your workstation. You also need an OpenAI-compatible chat and embedding endpoint. No key is included on the image.

Watch on YouTube.

1. Subscribe

Open the Vane Search listing, choose View purchase options, review the terms, and subscribe. When the subscription is active, choose Launch your software.

2. Launch the instance

  1. Choose t3.large with at least 8 GiB of memory.
  2. Use an encrypted gp3 root volume of at least 40 GiB.
  3. Require IMDSv2.
  4. Attach an instance profile that includes AmazonSSMManagedInstanceCore.
  5. Allow outbound HTTPS. Leave inbound application ports closed.
  6. Choose Launch instance.

3. Connect and run the walkthrough

Wait for cloud-init, then:

sudo -iu ubuntu bash /opt/sushi/docs/demo.sh

Read /opt/sushi/docs/README.md on the instance for the package notes (less /opt/sushi/docs/README.md).

4. Open port 3000

On your computer, leave a port-forwarding session open. Replace <instance-id> with the instance ID:

aws ssm start-session --target <instance-id> \
  --document-name AWS-StartPortForwardingSession \
  --parameters '{"portNumber":["3000"],"localPortNumber":["3000"]}'

5. Add your models

Write the OpenAI-compatible chat and embedding endpoint into a file with mode 0600. Import that file the way /opt/sushi/docs/README.md describes. Do not put the key in user data, command arguments, or logs.

The per-instance access file belongs to this instance. The helper on the image reads it. Do not paste it into a ticket.

Next, see Configuration.

Last updated November 1, 2026 · Suggest an improvement