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

How to Add an S3 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:
5. Select Create 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 '{
       "name": "<REGISTRY_NAME>",
       "type": "s3",
       "bucket": "<BUCKET_ADDRESS>",
       "accessKey": "<ACCESS_KEY>",
       "secretKey": "<SECRET_KEY>",
       "endpointUrl": "<BUCKET_ENDPOINT_URL>"
     }'

   Copy

How to Add an OpenLLM 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:
   • Name: The name of the registry within HPE Machine Learning Inferencing Software.
   • Bucket Endpoint URL: https://huggingface.co
   • HuggingFace Token: The access token obtained from your Hugging Face account.
5. Select Create registry.

Via the CLI #

aioli registry create <REGISTRY_NAME> \
--type openllm \
--secret-key <ACCESS_TOKEN>