install-embeddings

Need

• eksctl (min. version 0.190.0)
• aws cli
• helm cli
• kubectl
• glasskube

Check AWS quota

Ensure you have quotas for

• ${gpu_count}*4 for On-Demand G and VT instances in the region of choice
• At least 1 load-balancer per each model you want. (Not per server running)

Create eks cluster and install needed plugins

Modify the following lines in create_cluster.sh

To get your account id run

aws sts get-caller-identity

install-embeddings/create_cluster.sh

Lines 7 to 12 in d55047e

	account_id=555555555555
	region=us-east-2
	cluster_name=trieve-gpu
	main_instance_type=t3.small
	gpu_instance_type=g4dn.xlarge
	gpu_count=1

Run ./create_cluster.sh to generate the cluster

2. Specify your embedding models

Modify embedding_models.yaml for the models that you want to use

3. Install the helm chart

helm upgrade -i embedding-release oci://registry-1.docker.io/trieve/embeddings-helm -f embedding_models.yaml

4. Get your model endpoints

kubectl get ing

Cleanup

helm uninstall embedding-release
./delete_cluster.sh