Quickstart - Hosted - SambaNova Documentation

This guide walks you through hosted SambaStack set up by preparing your configuration, setting up authentication, and verifying deployment to start managing your instance effectively.

Prerequisites

Install kubectl

Setup

Configure Kubeconfig Credentials

To interact with the cluster, you need valid kubeconfig credentials. SambaNova will provide both the kubeconfig file and the base64-encoded password.

Save the provided kubeconfig file securely (e.g.~/.sambastack/kubeconfig.yaml)
Decode the base64-encoded password and save it to a YAML file.
```
echo <PASSWORD> | base64 -d > <credentials-file-name>.yaml
```
Store both the password and kubeconfig file securely and do not share them with unauthorized users; the password is required to access cluster nodes.

Set the kubeconfig variable:

export KUBECONFIG=~/path/to/<credentials-file-name>.yaml

Your credentials file should resemble this example.

Configure and install `sambastack.yaml`

Configure a minimum viable sambastack.yaml file:

apiVersion: v1
kind: ConfigMap
metadata:
  annotations:
    serial: "1"
  name: sambastack
  labels:
    sambastack-installer: "true"
data:
  sambastack.yaml: |
    version: <NEW_VERSION>
    bundles:
      bundleSpecs:
      - name: gpt-oss-120b-8-32-64-128k
      bundleDeploymentSpecs:
      - name: gpt-oss-120b-8-32-64-128k
        groups:
        - name: "default"
          minReplicas: 1
          qosList:
          - "web"
          - "free"
    db-admin:
      admins:
        - abc@example.com

See the SambaStack.yaml Reference for a full example.

Update the version field to match the version provided by your SambaNova representative.

Apply the file

kubectl apply -f <path-to-sambastack.yaml>

If successful, you will see

configmap/sambastack configured

Verify success by running the following commands and observing expected outputs:

Check installer logs and retrieve UI/API domain names with:

kubectl -n sambastack-installer logs -l sambanova.ai/app=sambastack-installer -f

expected response:

NAME: sambastack
LAST DEPLOYED: Thu Sep 11 10:18:54 2025
NAMESPACE: default
STATUS: deployed
REVISION: 7
TEST SUITE: None
[INFO] (helm_upgrade_install) Upgraded/installed sambastack release
[INFO] (configure_default_ingress) UI Domain: ui-domain-example.sambanova.ai
[INFO] (configure_default_ingress) API Domain: api-domain-example.sambanova.ai

Verify cluster pods are running:

kubectl get pods

expected response:

NAME                                                     READY   STATUS      RESTARTS       AGE
alertmanager-sambastack-kube-prometheus-alertmanager-0   2/2     Running     0               1d
alertmanager-sambastack-kube-prometheus-alertmanager-1   2/2     Running     0               1d
auth-and-billing-6c75dd9459-pdfd4                        1/1     Running     0               1d
auth-and-billing-6c75dd9459-vpfrz                        1/1     Running     0               1d
cloud-ui-7646779bcb-mq295                                1/1     Running     0               1d
db-admin-59c6dc4958-rctmc                                2/2     Running     0               1d
gateway-95956579b-4gqsl                                  4/4     Running     0               1d
gateway-95956579b-bjltl                                  4/4     Running     0               1d
inf-gpt-oss-120b-8-32-64-128k-cache-0                    1/1     Running     0               1d
inf-gpt-oss-120b-8-32-64-128k-q-default-n-0              2/2     Running     1 (71d ago)     1d
inf-operator-0                                           1/1     Running     0               1d
inference-router-6f965555d8-wqf7t                        1/1     Running     0               1d
keycloak-0                                               1/1     Running     0               1d
keycloak-operator-8dc4bc4d9-gj2m9                        1/1     Running     5 (109d ago)    1d
opensearch-cluster-master-0                              1/1     Running     0               1d
opensearch-index-mgmt-job-skzw9                          0/1     Completed   0               1d
prometheus-sambastack-kube-prometheus-prometheus-0       2/2     Running     2 (109d ago)    1d
prometheus-sambastack-kube-prometheus-prometheus-1       2/2     Running     2 (109d ago)    1d
sambastack-cloudnative-pg-5bfd776f85-lwb74               1/1     Running     7 (25d ago)     1d
sambastack-fluent-bit-8vf55                              1/1     Running     0               1d
sambastack-global-queue-redis-master-0                   2/2     Running     0               1d
sambastack-grafana-7b6b8c899b-8r6gc                      3/3     Running     0               1d
sambastack-kube-prometheus-operator-65dddbc87f-2k84c     1/1     Running     0               1d
sambastack-kube-state-metrics-6fffcb5987-v6pfx           1/1     Running     0               1d
sambastack-localpv-provisioner-64f9fd84cd-h72zc          1/1     Running     7 (25d ago)     1d
sambastack-opensearch-dashboards-787695c54d-zgr4p        1/1     Running     0               1d
sambastack-postgres-1                                    1/1     Running     0               1d
sambastack-postgres-2                                    1/1     Running     0               1d
sambastack-postgres-3                                    1/1     Running     0               1d
sambastack-prometheus-node-exporter-fwzr6                1/1     Running     0               1d
sambastack-response-queue-redis-master-0                 2/2     Running     0               1d
sn-legacy-exporter-mlqg5                                 2/2     Running     0               1d

It usually takes about 5-10 minutes for all the pods to reach their desired Running state.

See the Pods reference table for more details.

Authentication Setup and User Management

For hosted SambaStack, SambaNova provides a default Keycloak instance for authentication. If you would like to set up a custom OIDC configuration, please refer to the Authentication Page.

Key considerations and common issues

Email is required: Users without an email cannot log in.
Unique usernames: Duplicate usernames are disallowed; keep username and email aligned.
Permanent passwords: Initial passwords should not be temporary unless a user reset is desired.
Browser tip: Use Chrome for Keycloak admin UI when port-forwarding to avoid session cookie issues.

Retrieve admin credentials:

kubectl get secret keycloak-initial-admin -o go-template='username: {{.data.username | base64decode}} password: {{.data.password | base64decode}}'

expected output:

username: admin
password: <random-password>

Port-forward Keycloak service

kubectl port-forward svc/keycloak-service 8080

Visit http://localhost:8080 and log in using retrieved credentials.
Manage users by following the Keycloak Server Administration Guide.

Log into SambaStack UI and Create API Key

Obtain the UI domain from the installer logs (see Step 2.3)
Access the UI domain using Google Chrome to avoid compatibility issues.
Log in using your credentials via the authentication flow.
Navigate to the API Keys page, create API key, and save securely!

Query Deployed Model Bundle

Set your API key:

export SAMBANOVA_API_KEY='<API key from step 4.3>'

Run a test query against the deployed model bundle with either cURL or a python script:

cURL
Python

Run the following cURL command, making sure to enter the correct domain:

curl https://<API DOMAIN from step 2.3>/v1/chat/completions \
  -H "Authorization: Bearer $SAMBANOVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-oss-120b",
    "messages": [
      {"role": "system", "content": "You are a concise assistant."},
      {"role": "user", "content": "Say hi in one sentence and comment on the weather."}
    ],
    "temperature": 0.2,
    "max_tokens": 128,
    "stream": false
  }'

Your response should resemble the following:

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "content": "Hi there, it's a sunny day today!",
		"reasoning": "The user wants a short response: \"Say hi in one sentence and comment on the weather.\" So we need to produce a single sentence that says hi and comments on the weather. Must be concise. So something like \"Hi there! It's a sunny day today.\" That's two sentences. Need one sentence. Could be \"Hi there—it's a sunny day today!\" That's one sentence with dash. Or \"Hi there, it's a sunny day today!\" That's one sentence with comma. That works. Provide that.",
        "role": "assistant"
      }
    }
  ],
  "created": 1770927918,
  "id": "c754b468-05e1-4fe4-8a28-f51ecc74f4f2",
  "model": "gpt-oss-120b",
  "object": "chat.completion",
  "system_fingerprint": "fastcoe",
  "usage": {
    "completion_tokens": 121,
	"completion_tokens_after_first_per_sec": 500.6027126944832,
    "completion_tokens_after_first_per_sec_first_ten": 502.05732024083596,
    "completion_tokens_after_first_per_sec_graph": 502.05732024083596,
    "completion_tokens_per_sec": 413.56225915094006,
    "end_time": 1770927918.2348678,
    "is_last_response": true,
    "prompt_tokens": 91,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "start_time": 1770927917.942288,
    "stop_reason": "stop",
    "time_to_first_token": 0.05286884307861328,
    "time_to_first_token_graph": 0.05082893371582031,
    "total_latency": 0.29257988929748535,
    "total_tokens": 212,
    "total_tokens_per_sec": 724.5884209917298
  }
}

Create a python script to run the following program. Make sure to insert your correct api domain name.

import os
from sambanova import SambaNova

api_key = os.environ.get("SAMBANOVA_API_KEY")

client = SambaNova(
    api_key=api_key,
    base_url="https://<API DOMAIN from step 2.3>/v1",
)

try:
    response = client.chat.completions.create(
        model="gpt-oss-120b",
        messages=[
            {"role": "system", "content": "You are a concise assistant."},
            {"role": "user", "content": "Say hi in one sentence and comment on the weather."}
        ],
        temperature=0.2,
    )
    print(response.choices[0].message.content)

except Exception as e:
    print(f"An error occurred: {e}")

Your response should resemble the following:

Hi, it's a sunny day today!

Next steps

Congrats! You’ve set up your SambaStack cluster to a baseline running state. At this point, what you configure next depends on your goals. The following is a list of common configurations you can set up next:

Appendix

Example kubeconfig structure

The following sample kubeconfig file shows how clusters, users, and contexts are defined for Kubernetes authentication and access.

    apiVersion: v1
    kind: Config
    clusters:
      - name: default
        cluster:
          certificate-authority-data: <redacted>
          server: https://<cluster-endpoint>
    users:
      - name: sambastack-admin
        user:
          token: <redacted>
    contexts:
      - name: default
        context:
          cluster: default
          user: sambastack-admin
          namespace: default
    current-context: default

Kubeconfig fields

Keyword	Description
apiVersion / kind	Defines the type of Kubernetes config.
clusters	Contains cluster names, endpoints, and certificate authority information.
users	Specifies users and their authentication method (e.g., token).
contexts	Maps a user to a cluster and may include a default namespace.
current-context	The active context used by `kubectl`.

Command reference table

Task	Example command
Set kubeconfig	`export KUBECONFIG=<Path for kubeconfig file>`
Check installer logs and get domain names	`kubectl -n sambastack-installer logs -l sambanova.ai/app=sambastack-installer -f`
Verify cluster pods	`kubectl get pods`
List nodes	`kubectl get nodes`
Apply / update manifest	`kubectl apply -f <sambastack.yaml>`
View applied manifest	`kubectl get configmap sambastack -o yaml`
Retrieve Keycloak admin credentials	`kubectl get secret keycloak-initial-admin -o go-template='username: {{.data.username \| base64decode}} password: {{.data.password \| base64decode}}'`
Access Keycloak as an admin	`kubectl port-forward svc/keycloak-service 8080`

Getting Started

Service Administration

Hardware Administration

Reference Architecture

Resources

Quickstart - hosted

Prerequisites

Setup

Configure Kubeconfig Credentials

Configure and install `sambastack.yaml`

Authentication Setup and User Management

Key considerations and common issues

Log into SambaStack UI and Create API Key

Query Deployed Model Bundle

Next steps

Appendix

Example kubeconfig structure

Kubeconfig fields

Command reference table

Getting Started

Service Administration

Hardware Administration

Reference Architecture

Resources

​Prerequisites

​Setup

Configure Kubeconfig Credentials

Configure and install `sambastack.yaml`

Authentication Setup and User Management

​Key considerations and common issues

Log into SambaStack UI and Create API Key

Query Deployed Model Bundle

​Next steps

​Appendix

​Example kubeconfig structure

​Kubeconfig fields

​Command reference table

Prerequisites

Setup

Key considerations and common issues

Next steps

Appendix

Example kubeconfig structure

Kubeconfig fields

Command reference table