Dell Technologies Dell Deskside Agentic AI Solutions
Home / solutions / agentic-vss / landscape-fleet-deploy

Fleet deployment via Canonical Landscape (Agentic Video Search & Summarization)

Roll Agentic Video Search & Summarization out to a fleet of enrolled Ubuntu systems (Dell deskside systems powered by NVIDIA) from Canonical Landscape, with no SSH, logged in the Landscape activity feed and repeatable from CI. The enrolment, script-execution, verification and close-out steps are the same for every solution and are described once in Fleet Deploy via Landscape (Agentic Coding); this page adds what is specific here.

Steps

  1. Enable script execution on the target devices (Step 1 of the common guide, root, once per rollout window).
  2. Stage this repository on each device at /opt/deskside-agentic-ai-solutions-for-nvidia (file transfer only).
  3. Deploy with the solution payload:
export SOLUTION=vss
python3 scripts/landscape/landscape_client.py runscript \
  --file scripts/landscape/deploy-solution.sh --ids "$ID" --user root --limit 3000
python3 scripts/landscape/landscape_client.py pollscript --group <group-id> --timeout 3200

The payload runs the serving recipe first (nvidia runtime self-heal, pinned image, readiness contract), then the solution step, and exits non-zero unless the solution is actually up. Variables: VSS_COMPOSE_FILE (the VSS blueprint compose project already staged on the device), VSS_HEALTH_URL (default http://localhost:7777). 4. Verify (Step 3 of the common guide, scripts/landscape/verify-serving.sh) and confirm the Agent UI answers on :7777, the serving endpoint lists its model on :8000 (start recipes with DESKSIDE_BASE_PORT=8100 when VSS owns :8000), and docker compose ps shows every VSS service running. 5. Close root script execution (Step 4 of the common guide, scripts/landscape/disable-script-execution.sh) once the fleet is healthy.

Notes

  • VSS needs NGC credentials and the blueprint compose project on the device. Stage them as files (not on the command line) and point VSS_COMPOSE_FILE at them.
  • The blueprint runs its own LLM and VLM; budget GPU memory with the co-tenancy rules in Operations.
  • The Docker engine must be inside the version window the blueprint supports; check it before the rollout.

Rollback and teardown

Re-run the deploy with the previous image digest from recipes/versions.lock, or remove the containers with a one-line payload (docker rm -f <container>; docker compose down -v for compose-based solutions). Re-enable script execution first if it has been closed.