Add Registry

By adding a registry to HPE Machine Learning Inferencing Software, you grant the platform read access to any models stored in that registry. Services can then be created and deployed in your Kubernetes cluster by pulling in these models and assigning the required resources.

Before You Start #

• S3: Ensure that you have set up a Registry (S3 bucket) and obtained the necessary access keys.

• OpenLLM: Sign up for a Hugging Face account and create an access token.

  • Profile > Settings > Access Tokens
  • New Token

• NGC: Sign up for an Nvidia NGC account and obtain the necessary API key.

  • Profile > Setup > Generate API Key

• PFS: Verify access to an HPE Machine Learning Data Management cluster and obtain the required authentication token. If your pachd installation uses HTTPS with a self-signed certificate, you may need to configure TLS for the external repository before adding it as a registry.

  • To obtain the authentication token for your HPE Machine Learning Data Management cluster, run the following commands:

    pachctl connect <PACHD_ADDRESS>:<PORT>
    pachctl auth login
    pachctl config get context <PACHD_ADDRESS>:<PORT> | jq -r '.session_token'

    Copy
    Example:

    AUTH_TOKEN_ENV=$(pachctl config get context http://34.44.25.160:80 | jq -r '.session_token')

    Copy

  ---

How to Add Registry #

Via the UI #

1. Sign in to HPE Machine Learning Inferencing Software.
2. Navigate to Registries.
3. Select Add new registry.
4. Input details for the following based on the registry type you are adding:
5. Select Create registry.

That’s it! You have successfully added a new registry to HPE Machine Learning Inferencing Software. You can now create a packaged model and associate it with this registry.

Via the CLI #

1. Sign in via the CLI.

   aioli user login <YOUR_USERNAME>

   Copy
2. Create a new registry with the following command:

   aioli registry create <REGISTRY_NAME> \
   --type s3 \
   --bucket <BUCKET_ADDRESS> \
   --access-key <ACCESS_KEY> \
   --secret-key <SECRET_KEY> \ 
   --endpoint-url <BUCKET_ENDPOINT_URL> \

   Copy

Via the API #

1. Sign in to HPE Machine Learning Inferencing Software.

   curl -X 'POST' \
     '<YOUR_EXT_CLUSTER_IP>/api/v1/login' \
     -H 'accept: application/json' \
     -H 'Content-Type: application/json' \
     -d '{
     "username": "<YOUR_USERNAME>",
     "password": "<YOUR_PASSWORD>"
   }'

   Copy
2. Obtain the Bearer token from the response.
3. Use the following cURL command to add a new registry.

   curl -X 'POST' \
     '<YOUR_EXT_CLUSTER_IP>/api/v1/registries' \
     -H 'accept: application/json' \
     -H 'Content-Type: application/json' \
     -H 'Authorization: Bearer <YOUR_ACCESS_TOKEN>' \ 
     -d '{
       "accessKey": "<ACCESS_KEY>",
       "bucket": "<BUCKET_ADDRESS>",
       "endpointUrl": "<BUCKET_ENDPOINT_URL>",
       "insecureHttps": true,
       "name": "<REGISTRY_NAME>",
       "secretKey": "<SECRET_KEY>",
       "type": "<TYPE>"
     }'

   Copy