Install with HTTP/SSL with Models and Advanced Options

This configuration combines an SSL configuration with additional embedding models and the configuration file. For a more advanced configuration, you can optionally choose to specify the HTTP port, container version, and or container name.

In this example, your desired ONNX Pipeline models are in /home/opc/models and your config file is /home/opc/config/config.json.

1. Configure and start the container with the models provided in the configuration file. Notice the file locations specified when running the configSetup script.

   Note:

   If a container is already running and you try to start a new container with the same configuration, then the old container will automatically be stopped and replaced with the new container.

   If you try to start a new container with a different configuration than that of the running container, then the container start will likely fail, and you will need to stop the existing container.

   mkdir /home/opc/privateai
   mkdir /home/opc/secrets
   mkdir /home/opc/models
   export PRIVATE_DIR=/home/opc/privateai
   export SECRETS_DIR=/home/opc/secrets
   ./secretsSetup.sh -s $SECRETS_DIR
   ./configSetup.sh -d $PRIVATE_DIR -s $SECRETS_DIR -m /home/opc/models -c /home/opc/config/config.json 
   ./containerSetup.sh -d $PRIVATE_DIR

   You can optionally specify the port, version, and container name when running the containerSetup script by replacing the last line, as in the following:

   podman stop privateai
   ./containerSetup.sh -d $PRIVATE_DIR -p 9443 -v 25.1.2.0.0 -n everything4
   podman ps

2. Define the value of the API_KEY to make the curl SSL commands easier and define the API_KEY value:

   export PORT=9443
   export API_KEY=$(cat $SECRETS_DIR/api-key)

3. Provide the digital certificate as a parameter.

   The same SSL curl commands work for both local and remote client machines.

   curl -i --cacert $SECRETS_DIR/cert.pem https://$HOST:$PORT/health
   
   curl --header "Authorization: Bearer $API_KEY" --cacert $SECRETS_DIR/cert.pem  https://$HOST:$PORT/v1/models
   
   curl -X POST --header "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" -d '{"model": "tinybert", "input":["This is a phrase to vectorize"]}' --cacert $SECRETS_DIR/cert.pem https://$HOST:$PORT/v1/embeddings
   
   curl --header "Authorization: Bearer $API_KEY" --cacert $SECRETS_DIR/cert.pem https://$HOST:$PORT/metrics/embeddings_call_latency