Skip to content
Qdrant Vector Database - AI Stack product logo
  • AWS· soonComing soon on Amazon Web Services
  • Azure· nextMicrosoft Azure is next on the roadmap
  • GCP· nextGoogle Cloud is next on the roadmap
Coming soon

Qdrant Vector Database - AI Stack

A ready-to-use vector search and AI workbench: Qdrant 1.19.1 with JupyterLab, MinIO object storage and a CPU PyTorch environment with sentence-transformers. Embed, index and search on the instance the moment it boots - no API keys, no external services - with a quickstart notebook that runs clean out of the box.

Version
v1.19.1
Operating system
Ubuntu 24.04 LTS
Architecture
x86_64
Support
Community

What's installed

Every package and version on the image. Nothing else is installed.

  • Qdrant 1.19.1
  • JupyterLab 4.6.3
  • MinIO RELEASE.2025-09-07
  • PyTorch 2.14.0 (CPU)
  • sentence-transformers 6.0.1
  • qdrant-client 1.19.0
  • nginx 1.24.0

Licensing — Open source (Qdrant Apache-2.0, MinIO AGPL-3.0), no licence key required

Deploy anywhere

Qdrant Vector Database - AI Stack on AWS.

Microsoft Azure and Google Cloud are next on the roadmap. One clean-room build, one first-boot credential model, one patch cadence — identical on every cloud you run. Every identifier below is the real one; copy it and launch.

  1. AWS

    Amazon Web Services

    AMI · v1.19.1

    Coming soon

    AWS AMI ID

    ami-003eb6d70c45b28f8
    Released
    September 12, 2026
    Root volume
    gp3 · 30 GiB

    Instance types

    • t3a.large
    • t3.large
    • t3a.xlarge
    • m6a.xlarge

    Regions

    • us-east-1
    AWS launch steps

Getting started

From launch to signed in, step by step.

  1. Launch in us-east-1 with TCP 22, 80, 8888 and 9001 open (and 9000 if you will use the S3 API from outside); wait two to three minutes.

  2. Open http://<instance-public-ip>/ for the stack home page with a live status light per service. Qdrant dashboard: /dashboard. REST API at the root, no authentication.

  3. JupyterLab: http://<instance-public-ip>:8888, password = your EC2 Instance ID (for example i-0123456789abcdef0). MinIO console: port 9001, admin / minioadmin123.

  4. Change the MinIO credential before storing real data - it is published and identical on every copy of this image: sudo bash /home/ubuntu/iscripts/pass_minio.sh.

  5. The quickstart notebook 01-quickstart.ipynb opens automatically. From your own code, point any Qdrant client at http://<instance-public-ip> (or localhost:6333 on the instance).

  6. The Qdrant API has no authentication: restrict port 80 to the addresses that need it. qdrant-status reports the whole stack.

Security posture

What this image does and does not ship with, one fact per line.

  • Clean-room build on Canonical's official Ubuntu 24.04 LTS image: every component comes from its own official repository or release, nothing is copied from any third-party image, and the finished image was scanned for third-party vendor strings before capture.

  • No usable credential ships in the image; passwords are set on your instance at first boot from EC2 instance metadata (IMDSv2) and the scripts that set them delete themselves afterwards.

  • SSH is key-only, root login over SSH is refused, and build-time SSH keys, shell history and logs were removed before imaging.

  • Two things to act on before real data: the Qdrant API on port 80 has no authentication, so restrict that port to the addresses that need it or put your own auth in front, and the MinIO root credential is a documented default that pass_minio.sh replaces in one step (it rolls back automatically if MinIO fails to restart).

  • JupyterLab is already unique to your instance, its password set from the Instance ID at first boot.

  • Qdrant's own ports (6333/6334) are bound to 127.0.0.1 and published only through nginx.

  • Qdrant and MinIO run as dedicated nologin accounts under hardened systemd units and restart on failure; checksums were verified for every release binary.

  • The bundled password tools enforce at least 10 characters with upper- and lower-case letters, a number and a symbol, and verify the new credential with a real sign-in before reporting success.

  • The image is HTTP-only by design so it works at a bare IP with no certificate warnings: terminate TLS at a load balancer or add a certificate before exposing it publicly, and restrict port 22 and any admin ports to trusted IP ranges in your security group.