Deployment for AIDR using a Helm file requires creating a config.yaml file, then downloading and deploying as a container to a Kubernetes cluster.
For prerequisites, including licenses, see Resource Requirements.
To deploy AIDR, a config.yaml file must be generated with the appropriate settings. Use the following example and modify as needed.
Select your provider to view installation instructions.
aidr_genai:
platform:
api-connection:
base-url: "https://<HiddenLayer Platform Hostname>"
max-retry-count: 3
## Set type: disabled to install AIDR without a connection to the Platform.
## If AIDR is deployed and you want to change the type, update this yaml file, then run a helm upgrade command.
type: "hybrid"
proxy:
log-level: "info"
provider:
timeout-in-seconds: 600
aws:
region: # "us-east-1"
enable-instance-profile-credentials: false
credential-provider: "instance" # container
sagemaker:
base-url: # "https://runtime.sagemaker.{region}.amazonaws.com"
bedrock:
base-url: # "https://bedrock-runtime.{region}.amazonaws.com"
credentials:
#- name:
# access-key-id:
# secret-access-key:
# session-token:
# region:
# sagemaker-base-url:
# bedrock-base-url:The following is required to log in to the HiddenLayer helm registry.
Run the following command in a terminal to log in to the HiddenLayer registry.
- The
usernameis your Registry username. - The
passwordis your License ID. - For more information, see Resource Requirements.
helm registry login registry.hiddenlayer.ai --username <email specified for registry> --password <License ID>- The
Use the following instructions to install AIDR.
Create a config.yaml file to customize installation
- See above for an example config.yaml file.
Run the following command to deploy AIDR.
helm install oci://registry.hiddenlayer.ai/aidr-genai/stable/distro-enterprise-aidr-genai-installer --version 2.1.0 -f config.yaml
There is a known issue for where provider credentials for AWS are not utilized when using the config.yaml file.
Environment variables cannot be used with the installer to set AWS credentials.
Work around: Add an Authorization header in the request to the LLM Proxy.
#Example Authorization: Credential=AWSAccessKeyId#Example curl -XPOST http://localhost:8000/api/v1/proxy/bedrock/model/meta.llama2-13b-chat-v1 \ -H "Content-Type: application/json" \ -H "Authorization: Credential=AWSAccessKeyId" \ -d '{ "prompt": "Hello, how are you?", "max_tokens_to_sample": 300 }'