Deploying on Kubernetes
The Helm chart simplifies Text Embedding NIM deployment on Kubernetes. It aims to support deployment with a variety of possible cluster, GPU and storage confurations. The Helm chart downloads the model and spin up the service to begin running.
NIMs are intended to be run on a system with NVIDIA GPUs, with the type and number of GPUs depending on the model. To use helm, you must have a Kubernetes cluster with appropriate GPU nodes and the GPU Operator installed.
Using a helm chart:
Enables using Kubernetes Nodes and horizontally scaling the service
Encapsulates the complexity of running Docker commands directly
Enables monitoring metrics from the NIM
If you haven’t set up your NGC API key and do not know exactly which NIM you want to download and deploy, see the information in the User Guide.
This helm chart requires that you have a secret with your NGC API key configured for downloading private images, and one with your NGC API key (below named ngc-api). These will likely have the same key in it, but they will have different formats (dockerconfig.json vs opaque). See Creating Secrets below.
These instructions will assume that you have your NGC_API_KEY exported in the environment.
export NGC_API_KEY="<YOUR NGC API KEY>"
In the event that model assets must be pre-fetched (e.g. in an air-gapped system), the NIM container supports downloading these assets to the NIM cache without starting the server.
# Choose a container name for bookkeeping
export NIM_MODEL_NAME=nvidia/nv-embedqa-e5-v5
export CONTAINER_NAME=$(basename $NIM_MODEL_NAME)
# Choose a NIM Image from NGC
export IMG_NAME="nvcr.io/nim/$NIM_MODEL_NAME:1.0.0"
# Choose a path on your system to cache the downloaded models
export LOCAL_NIM_CACHE=~/.cache/nim
mkdir -p "$LOCAL_NIM_CACHE"
# Start the NIM
docker run -it --rm --name=$CONTAINER_NAME \
--runtime=nvidia \
--gpus all \
--shm-size=16GB \
-e NGC_API_KEY \
-v "$LOCAL_NIM_CACHE:/opt/nim/.cache" \
-u $(id -u) \
-p 8000:8000 \
$IMG_NAME download-to-cache
You can fetch the helm chart from NGC by executing the following command:
helm fetch https://helm.ngc.nvidia.com/nim/nvidia/charts/text-embedding-nim-1.0.0.tgz --username='$oauthtoken' --password=$NGC_API_KEY
You can use OpenTelemetry for monitoring your container. See OpenTelemetry parameters for details.
You can choose to deploy to whichever namespace is appropriate, but for documentation purposes we will deploy to a namespace named embedding-nim.
kubectl create namespace embedding-nim
Use the following script to create the expected secrets for this helm chart.
DOCKER_CONFIG='{"auths":{"nvcr.io":{"username":"$oauthtoken", "password":"'${NGC_API_KEY}'" }}}'
echo -n $DOCKER_CONFIG | base64 -w0
NGC_REGISTRY_PASSWORD=$(echo -n $DOCKER_CONFIG | base64 -w0 )
cat <<EOF > imagepull.yaml
apiVersion: v1
kind: Secret
metadata:
name: nvcrimagepullsecret
type: kubernetes.io/dockerconfigjson
data:
.dockerconfigjson: ${NGC_REGISTRY_PASSWORD}
EOF
kubectl apply -n embedding-nim -f imagepull.yaml
kubectl create -n embedding-nim secret generic ngc-api-2 --from-literal=NGC_CLI_API_KEY=${NGC_API_KEY}
The following deployment commands will by default create a single deployment with one replica using the NV-EmbedQA-E5-V5 model. The following options can be used to make modifications to the behavior. See Parameters for a description of the Helm parameters.
image.repository– The container (Text Embedding NIM) to deployimage.tag– The version of that container (Text Embedding NIM)Storage options, based on the environment and cluster in use
resources– Use this option when a model requires more than the default of one GPU. See below for support matrix and resource requirements.env– Which is an array of environment variables presented to the container, if advanced configuration is needed
This NIM uses persistent storage for storing downloaded models. These instructions require that you have a local-nfs storage class provisioner installed in your cluster.
helm repo add nfs-ganesha-server-and-external-provisioner https://kubernetes-sigs.github.io/nfs-ganesha-server-and-external-provisioner/
helm install nfs-server nfs-ganesha-server-and-external-provisioner/nfs-server-provisioner --set storageClass.name=local-nfs
Advanced Storage Configuration
Storage is a particular concern when setting up NIMs. Models can be quite large, and you can fill a disk downloading things to emptyDirs or other locations around your pod image. We recommend that you mount persistent storage of some kind on your pod.
This chart supports two general categories:
Persistent Volume Claims (enabled with
persistence.enabled)hostPath (enabled with
persistences.hostPath)
By default, the chart uses the standard storage class and creates a PersistentVolume and a PersistentVolumeClaim.
If you do not have a Storage Class Provisioner that creates PersistentVolumes automatically, set the value persistence.createPV=true. This is also necessary when you use persistence.hostPath on minikube.
If you have an existing PersistentVolumeClaim where you’d like the models to be stored at, pass that value in at persistence.exsitingClaimName.
See the Helm options in Parameters.
Use the following bash command to create a basic deploymnet.
helm upgrade --install \
--namespace embedding-nim \
nemo-embedder \
--set persistence.class="local-nfs" \
text-embedding-nim-1.0.0.tgz
You can also change the version of the model in use by adding the following after --namespace
--set image.tag=1.0.0 \
After deploying check the pods to ensure that it is running, initial image pull and model download can take upwards of 15 minutes.
kubectl get pods -n embedding-nim
The pod should eventually end up in the running state.
NAME READY STATUS RESTARTS AGE
text-embedding-nim-0 1/1 Running 0 8m44s
Check events for failures:
kubectl get events --field-selector involvedObject.name=text-embedding-nim -n embedding-nim
Minikube will create a hostPath based PV and PVC by default with this chart. We recommend that you add the following to your helm commands.
--set persistence.class=standard
Run the helm command with the following parameters, update your version in image.tag:
helm upgrade --install \
--namespace embedding-nim \
--set image.repository=nvcr.io/nim/snowflake/arctic-embed-l \
--set image.tag=1.0.0 \
--set persistence.class="local-nfs" \
nemo-embedder \
text-embedding-nim-1.0.0.tgz
Create a values files for the resource requirements of the 7B Model:
# values-mistral.yaml
resources:
limits:
ephemeral-storage: 28Gi
nvidia.com/gpu: 1
memory: 32Gi
cpu: "16000m"
requests:
ephemeral-storage: 28Gi
nvidia.com/gpu: 1
memory: 16Gi
cpu: "4000m"
Then deploy the model:
helm upgrade --install \
--namespace embedding-nim \
-f values-mistral.yaml \
--set image.repository=nvcr.io/nim/nvidia/nv-embedqa-mistral-7b-v2 \
--set image.tag=1.0.0 \
--set persistence.class="local-nfs" \
nemo-embedder \
text-embedding-nim-1.0.0.tgz
In the previous example the API endpoint is exposed on port 8080 through the Kubernetes service of the default type with no ingress, since authentication is not handled by the NIM itself. The following commands assume the NV-EmbedQA-E5-V5 model was deployed.
Adjust the “model” value in the request JSON body to use a different model.
Use the following command to port-forward the service to your local machine to test inference.
kubectl port-forward -n embedding-nim service/text-embedding-nim 8080:8080
Then try a request:
curl -X 'POST' \
'http://localhost:8080/v1/embeddings' \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"input": "hello world",
"model": "nvidia/nv-embedqa-e5-v5",
"input_type": "passage"
}'
Use the following command to view the container log messages in the docker logs.
docker logs $CONTAINER_NAME -f