Viante installation guide

Viante installation guide

https://cloud.znotes.ru/public.php/dav/files/vcloud/Platform_4-lic.zip
https://cloud.znotes.ru/public.php/dav/files/vcloudai/CluebaseVMS.zip
https://drive.google.com/file/d/1x2HiTNweSBRE1tzionbT7wdtT8pkEETP/view

 

Check if port is open: netstat -tulnp | grep 8000

If multiple ports:

ports="8080 80 554 15672 2379 40000 5180 9100 4001 3000 3307 8565 8095 10000 8081"
for port in $ports; do
  if nc -z localhost $port >/dev/null 2>&1; then
    echo "Port $port is in use"
  else
    echo "Port $port is free"
  fi
done

ports="3478 5349 49152-65535"
for port in $ports; do
  if nc -z localhost $port >/dev/null 2>&1; then
    echo "Port $port is in use"
  else
    echo "Port $port is free"
  fi
done

If VM check for avx2:

grep "flags" /proc/cpuinfo | grep "avx2"

# -=== Installing the NVIDIA Container Toolkit 1.19 ===-

sudo apt-get update && sudo apt-get install -y --no-install-recommends ca-certificates curl gnupg2 docker-compose-plugin
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
  && curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
    sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
    sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
sudo apt-get update
export NVIDIA_CONTAINER_TOOLKIT_VERSION=1.19.0-1
  sudo apt-get install -y \
      nvidia-container-toolkit=${NVIDIA_CONTAINER_TOOLKIT_VERSION} \
      nvidia-container-toolkit-base=${NVIDIA_CONTAINER_TOOLKIT_VERSION} \
      libnvidia-container-tools=${NVIDIA_CONTAINER_TOOLKIT_VERSION} \
      libnvidia-container1=${NVIDIA_CONTAINER_TOOLKIT_VERSION}
sudo nvidia-ctk runtime configure --runtime=docker
nano /etc/docker/daemon.json


Add "min-api-version": "1.24", in file /etc/docker/daemon.json

sudo systemctl restart docker
sysctl fs.aio-max-nr
nano /etc/sysctl.d/99-aio.conf
fs.aio-max-nr = 1048576
sysctl --system
chmod a+x \
./install.py \
./uninstall.py \
./restart.sh \
./start.sh \
./stop.sh \
./collect_logs.sh
  vms-phpmyadmin:
    image: phpmyadmin:latest
    container_name: vms-phpmyadmin
    restart: always
    ports:
      - 18080:80
    environment:
      PMA_HOST: vms-db
      PMA_PORT: 3306
      MYSQL_ROOT_PASSWORD: ${MYSQL_PASSWORD}
    depends_on:
      vms-db:
        condition: service_healthy
      NVIDIA_VISIBLE_DEVICES: all
      NVIDIA_DRIVER_CAPABILITIES: all
    runtime: nvidia
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]


======= ollama ===============================================================

docker run -d \
--gpus=all \
--name ollama \
--restart=always \
-e OLLAMA_SCHED_SPREAD=1 \
-v ollama:/root/.ollama \
-p 11434:11434 \
--health-cmd='curl -fsS http://0.0.0.0:11434/api/tags || exit 1' \
--health-interval=30s \
--health-timeout=5s \
--health-retries=3 \
--health-start-period=20s \
ollama/ollama


=========platform 4 CPU ============================

./install.py \
--ecm-rabbitmq-management-port=15673 \
--ecm-port=8081 \
--skip-docker-images-load \
--im-fr-algorithm alg2 \
--im-enroll-hardware-type cpu \
--fd-hardware-type cpu \
--ecm-data-storage-period-in-days 30 \
--ecm-data-index-period-in-days 30 \
--ecm-webhook-url http://118.107.96.20/api/event/addTevianEvent \
--ecm-admin-password a10@2025 \
--ecm-rabbitmq-password a10@2025

 

--ecm-webhook-url http://127.0.0.1/api/event/addTevianEvent \
--ecm-no-webhook
=========platform 4 GPU ============================

./install.py \
--ecm-rabbitmq-management-port=15673 \
--ecm-port=8081 \
--im-fr-algorithm alg2 \
--im-enroll-hardware-type gpu \
--im-enroll-gpu-device-id 1 \
--fd-hardware-type gpu \
--fd-gpu-device-id 1 \
--with-silhouette \
--silhouette-with-classifiers \
--silhouette-gpu-device-id 1 \
--ecm-data-storage-period-in-days 30 \
--ecm-data-index-period-in-days 30 \
--ecm-webhook-url http://192.168.69.2:8000/api/event/addTevianEvent \
--ecm-admin-password admin \
--ecm-rabbitmq-password admin


--with-silhouette \
--silhouette-with-classifiers \
--silhouette-gpu-device-id 0 \
--im-api-port 40001 \

--im-scylla-skip-schema-load \
--skip-docker-images-load \

=========platform 5 CPU ============================

./install.py \
--ecm-rabbitmq-management-port=15673 \
--ecm-port=8081 \
--im-fr-algorithm alg2 \
--im-enroll-hardware-type cpu \
--fd-hardware-type cpu \
--ecm-data-storage-period-in-days 30 \
--ecm-data-index-period-in-days 30 \
--with-silhouette \
--silhouette-hardware-type cpu \
--silhouette-with-classifiers \
--ecm-webhook-url http://192.168.0.72/api/event/addTevianEvent \
--ecm-admin-password admin \
--ecm-rabbitmq-password admin

=========platform 5 GPU ============================

./install.py \
--ecm-rabbitmq-management-port=15673 \
--ecm-port=8081 \
--im-fr-algorithm alg5 \
--im-enroll-hardware-type gpu \
--im-enroll-gpu-device-id 0 \
--fd-hardware-type gpu \
--fd-gpu-device-id 0 \
--ecm-data-storage-period-in-days 30 \
--ecm-data-index-period-in-days 30 \
--with-silhouette \
--silhouette-hardware-type gpu \
--silhouette-gpu-device-id 1 \
--silhouette-with-classifiers \
--ecm-webhook-url http://192.168.73.2/api/event/addTevianEvent \
--ecm-admin-password admin \
--ecm-rabbitmq-password admin

 

Viante installation guide minimal

1. Check if port is open: netstat -tulnp | grep 8081

If multiple ports:

ports="8080 80 554 15672 2379 40000 5180 9100 4001 3000 3307 8565 8095 10000 8081"
for port in $ports; do
  if nc -z localhost $port >/dev/null 2>&1; then
    echo "Port $port is in use"
  else
    echo "Port $port is free"
  fi
done

2. Checking the processor for avx2 support:

grep "flags" /proc/cpuinfo | grep "avx2"

3. Add "min-api-version": "1.24", in file /etc/docker/daemon.json

sudo nano /etc/docker/daemon.json
sudo systemctl restart docker
sudo sysctl fs.aio-max-nr

4. Add "fs.aio-max-nr = 1048576" in file /etc/sysctl.d/99-aio.conf

sudo nano /etc/sysctl.d/99-aio.conf
fs.aio-max-nr = 1048576
sudo sysctl --system

Go to the folder where the archive is unpacked (for example, /opt/Platform-4-lic)

sudo chmod a+x \
./install.py \
./uninstall.py \
./restart.sh \
./start.sh \
./stop.sh \
./collect_logs.sh

=========platform 4 CPU ============================

./install.py \
--ecm-rabbitmq-management-port=15673 \
--ecm-port=8081 \
--im-fr-algorithm alg2 \
--im-enroll-hardware-type cpu \
--fd-hardware-type cpu \
--ecm-data-storage-period-in-days 30 \
--ecm-data-index-period-in-days 30 \
--ecm-webhook-url http://vms-server-ip:port/api/event/addTevianEvent \
--ecm-admin-password admin \
--ecm-rabbitmq-password admin

=========platform 4 GPU ============================

./install.py \
--ecm-rabbitmq-management-port=15673 \
--ecm-port=8081 \
--im-fr-algorithm alg2 \
--im-enroll-hardware-type gpu \
--im-enroll-gpu-device-id 0 \
--fd-hardware-type gpu \
--fd-gpu-device-id 0 \
--ecm-data-storage-period-in-days 30 \
--ecm-data-index-period-in-days 30 \
--ecm-webhook-url http://vms-server-ip:port/api/event/addTevianEvent \
--ecm-admin-password admin \
--ecm-rabbitmq-password admin

--ecm-no-webhook  \

--with-silhouette \
--silhouette-with-classifiers \
--silhouette-gpu-device-id 0 \

--im-api-port 40001 \

--im-scylla-skip-schema-load \

--skip-docker-images-load \