chore(ollama): set longer timeout to deploy Ollama

CLAUDE.md

@@ -429,6 +429,7 @@ When writing Markdown documentation:
    ```
 
 2. **Always validate with markdownlint-cli2**:
-   - Run `markdownlint-cli2 <file>` before committing any Markdown files
+   - Run from the project root directory to use `.markdownlint.yaml` config:
+     `cd <top-dir> && markdownlint-cli2 <relative-path>`
    - Fix all linting errors to ensure consistent formatting
    - Pay attention to code block language specifications (MD040) and list formatting (MD029)

README.md

@@ -63,6 +63,7 @@ A remotely accessible Kubernetes home lab with OIDC authentication. Build a mode
 ### LLM & AI Applications (Optional)
 
 - **[Ollama](https://ollama.com/)**: Local LLM inference server with GPU acceleration
+- **[LiteLLM](https://litellm.ai/)**: Unified LLM gateway for accessing multiple providers through OpenAI-compatible API
 - **[LibreChat](https://www.librechat.ai/)**: Web-based chat interface with multi-model support and MCP integration
 - **[Langfuse](https://langfuse.com/)**: LLM observability and analytics platform for tracking and debugging AI applications
 
@@ -346,6 +347,18 @@ LLM observability and analytics platform:
 
 [📖 See Langfuse Documentation](./langfuse/README.md)
 
+### LiteLLM
+
+Unified LLM gateway and proxy:
+
+- **Multi-Provider Support**: Anthropic, OpenAI, Ollama, Mistral, Groq, and more through single API
+- **OpenAI-Compatible**: Drop-in replacement for OpenAI SDK
+- **Virtual Keys**: Generate scoped API keys for users with usage tracking
+- **Cost Tracking**: Monitor spending across all LLM providers
+- **Keycloak Authentication**: OAuth2 for Admin UI with role-based access
+
+[📖 See LiteLLM Documentation](./litellm/README.md)
+
 ### Dagster
 
 Modern data orchestration platform:
@@ -485,6 +498,7 @@ kubectl --context yourpc-oidc get nodes
 # JupyterHub: https://jupyter.yourdomain.com
 # MLflow: https://mlflow.yourdomain.com
 # Langfuse: https://langfuse.yourdomain.com
+# LiteLLM: https://litellm.yourdomain.com
 # LibreChat: https://chat.yourdomain.com
 ```
 

clickhouse/.gitignore

@@ -2,4 +2,5 @@ clickhouse-credentials-external-secret.yaml
 clickhouse-ingress.yaml
 clickhouse-installation-template.yaml
 clickhouse-operator-values.yaml
+clickhouse-servicemonitor.yaml
 clickhouse.yaml

clickhouse/README.md

@@ -44,3 +44,31 @@ ClickHouse can use the following Linux capabilities for enhanced performance, bu
 | `SYS_NICE` | Thread priority control via `os_thread_priority` | Setting has no effect                         |
 
 These capabilities are disabled by default to comply with baseline Pod Security Standards. To enable them, the namespace must allow privileged pods, and you need to uncomment the `add` line in `clickhouse-installation-template.yaml`.
+
+## Monitoring
+
+ClickHouse exposes Prometheus metrics on port 9363. When Prometheus (kube-prometheus-stack) is installed, monitoring can be enabled during installation or manually.
+
+### Enable Monitoring
+
+```bash
+just clickhouse::setup-monitoring
+```
+
+This creates a ServiceMonitor and a metrics Service for Prometheus to scrape.
+
+### Grafana Dashboard
+
+Import the ClickHouse dashboard from Grafana.com:
+
+1. Open Grafana → **Dashboards** → **New** → **Import**
+2. Enter Dashboard ID: `14192`
+3. Click **Load**, select **Prometheus** data source, then **Import**
+
+The dashboard includes panels for memory, connections, queries, I/O, replication, merge operations, cache, and ZooKeeper metrics.
+
+### Remove Monitoring
+
+```bash
+just clickhouse::remove-monitoring
+```

clickhouse/clickhouse-installation-template.gomplate.yaml

@@ -20,6 +20,10 @@ spec:
           containers:
             - name: clickhouse
               image: {{ .Env.CLICKHOUSE_IMAGE }}
+              ports:
+                - name: prometheus
+                  containerPort: 9363
+                  protocol: TCP
               resources:
                 requests:
                   cpu: {{ .Env.CLICKHOUSE_CPU_REQUEST }}

clickhouse/clickhouse-servicemonitor.gomplate.yaml

@@ -0,0 +1,67 @@
+{{- if .Env.MONITORING_ENABLED }}
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: clickhouse-metrics
+  namespace: {{ .Env.CLICKHOUSE_NAMESPACE }}
+  labels:
+    app: clickhouse
+    clickhouse.altinity.com/chi: clickhouse
+spec:
+  type: ClusterIP
+  ports:
+    - name: prometheus
+      port: 9363
+      targetPort: 9363
+      protocol: TCP
+  selector:
+    clickhouse.altinity.com/chi: clickhouse
+---
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: clickhouse
+  namespace: {{ .Env.CLICKHOUSE_NAMESPACE }}
+  labels:
+    app: clickhouse
+    release: kube-prometheus-stack
+spec:
+  selector:
+    matchLabels:
+      app: clickhouse
+      clickhouse.altinity.com/chi: clickhouse
+  namespaceSelector:
+    matchNames:
+      - {{ .Env.CLICKHOUSE_NAMESPACE }}
+  endpoints:
+    - port: prometheus
+      path: /metrics
+      interval: 30s
+      scrapeTimeout: 10s
+---
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: clickhouse-operator
+  namespace: {{ .Env.CLICKHOUSE_NAMESPACE }}
+  labels:
+    app: clickhouse-operator
+    release: kube-prometheus-stack
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: altinity-clickhouse-operator
+  namespaceSelector:
+    matchNames:
+      - {{ .Env.CLICKHOUSE_NAMESPACE }}
+  endpoints:
+    - port: ch-metrics
+      path: /metrics
+      interval: 30s
+      scrapeTimeout: 10s
+    - port: op-metrics
+      path: /metrics
+      interval: 30s
+      scrapeTimeout: 10s
+{{- end }}

clickhouse/clickhouse.gomplate.yaml

@@ -29,6 +29,17 @@ spec:
             <schema_type>transposed</schema_type>
           </asynchronous_metric_log>
         </clickhouse>
+      # Enable Prometheus metrics endpoint
+      prometheus.xml: |
+        <clickhouse>
+          <prometheus>
+            <endpoint>/metrics</endpoint>
+            <port>9363</port>
+            <metrics>true</metrics>
+            <events>true</events>
+            <asynchronous_metrics>true</asynchronous_metrics>
+          </prometheus>
+        </clickhouse>
     users:
       admin/k8s_secret_password: clickhouse-credentials/admin
       admin/networks/ip: "::/0"

clickhouse/justfile

@@ -5,6 +5,8 @@ export CLICKHOUSE_HOST := env("CLICKHOUSE_HOST", "")
 export CLICKHOUSE_CHART_VERSION := env("CLICKHOUSE_CHART_VERSION", "0.25.5")
 export CLICKHOUSE_IMAGE := env("CLICKHOUSE_IMAGE", "clickhouse/clickhouse-server:25.10")
 export EXTERNAL_SECRETS_NAMESPACE := env("EXTERNAL_SECRETS_NAMESPACE", "external-secrets")
+export PROMETHEUS_NAMESPACE := env("PROMETHEUS_NAMESPACE", "monitoring")
+export MONITORING_ENABLED := env("MONITORING_ENABLED", "")
 
 # ClickHouse resource settings
 export CLICKHOUSE_MEMORY_REQUEST := env("CLICKHOUSE_MEMORY_REQUEST", "1Gi")
@@ -107,6 +109,16 @@ install:
             --placeholder="e.g., clickhouse.example.com"
         )
     done
+    # Check if Prometheus is available and ask about monitoring
+    if helm status kube-prometheus-stack -n ${PROMETHEUS_NAMESPACE} &>/dev/null; then
+        if [ -z "${MONITORING_ENABLED}" ]; then
+            if gum confirm "Enable Prometheus monitoring?"; then
+                MONITORING_ENABLED="true"
+            else
+                MONITORING_ENABLED="false"
+            fi
+        fi
+    fi
     echo "Installing ClickHouse..."
     just create-namespace
     just install-zookeeper
@@ -124,6 +136,10 @@ install:
     kubectl wait --for=jsonpath='{.status.status}'=Completed \
         clickhouseinstallation/clickhouse -n ${CLICKHOUSE_NAMESPACE} --timeout=600s
     just setup-ingress ${CLICKHOUSE_HOST}
+    # Setup monitoring if enabled
+    if [ "${MONITORING_ENABLED}" = "true" ]; then
+        just setup-monitoring
+    fi
     echo "ClickHouse installation completed successfully"
     echo "ClickHouse API at: https://${CLICKHOUSE_HOST}"
 
@@ -137,6 +153,27 @@ setup-ingress host:
     kubectl apply -n ${CLICKHOUSE_NAMESPACE} -f clickhouse-ingress.yaml
     echo "ClickHouse Ingress configured successfully"
 
+# Setup Prometheus monitoring for ClickHouse
+setup-monitoring:
+    #!/bin/bash
+    set -euo pipefail
+    echo "Setting up Prometheus monitoring for ClickHouse..."
+    kubectl label namespace ${CLICKHOUSE_NAMESPACE} buun.channel/enable-monitoring=true --overwrite
+    MONITORING_ENABLED="true" gomplate -f clickhouse-servicemonitor.gomplate.yaml \
+        -o clickhouse-servicemonitor.yaml
+    kubectl apply -f clickhouse-servicemonitor.yaml
+    echo "Prometheus monitoring configured successfully"
+
+# Remove Prometheus monitoring for ClickHouse
+remove-monitoring:
+    #!/bin/bash
+    set -euo pipefail
+    echo "Removing Prometheus monitoring for ClickHouse..."
+    kubectl delete servicemonitor clickhouse clickhouse-operator -n ${CLICKHOUSE_NAMESPACE} --ignore-not-found
+    kubectl delete service clickhouse-metrics -n ${CLICKHOUSE_NAMESPACE} --ignore-not-found
+    kubectl label namespace ${CLICKHOUSE_NAMESPACE} buun.channel/enable-monitoring- --ignore-not-found
+    echo "Prometheus monitoring removed"
+
 # Uninstall ClickHouse (delete_volumes='false' to preserve PVCs and namespace)
 uninstall delete-volumes='true':
     #!/bin/bash

jupyterhub/jupyterhub-values.gomplate.yaml

@@ -445,6 +445,10 @@ ingress:
   annotations:
     kubernetes.io/ingress.class: traefik
     traefik.ingress.kubernetes.io/router.entrypoints: websecure
+    # Enable sticky sessions for WebSocket connections (required for Jupyter RTC/MCP)
+    traefik.ingress.kubernetes.io/service.sticky.cookie: "true"
+    traefik.ingress.kubernetes.io/service.sticky.cookie.name: jupyter-session
+    traefik.ingress.kubernetes.io/service.sticky.cookie.secure: "true"
   ingressClassName: traefik
   hosts:
     - {{ .Env.JUPYTERHUB_HOST }}

justfile

@@ -23,10 +23,12 @@ mod kserve
 mod langfuse
 mod lakekeeper
 mod librechat
+mod litellm
 mod longhorn
 mod metabase
 mod mlflow
 mod minio
+mod nats
 mod nvidia-device-plugin
 mod fairwinds-polaris
 mod oauth2-proxy

langfuse/justfile

@@ -98,8 +98,8 @@ install:
         --version ${LANGFUSE_CHART_VERSION} -n ${LANGFUSE_NAMESPACE} --wait \
         -f langfuse-values.yaml
 
-# Uninstall Langfuse
-uninstall:
+# Uninstall Langfuse (delete-data: true to delete database and storage)
+uninstall delete-data='false':
     #!/bin/bash
     set -euo pipefail
     helm uninstall langfuse -n ${LANGFUSE_NAMESPACE} --wait --ignore-not-found
@@ -108,19 +108,29 @@ uninstall:
     # Clean up Keycloak client and Vault secrets to avoid stale credentials
     just delete-keycloak-client || true
 
-    echo "Langfuse uninstalled successfully"
-    echo ""
-    echo "Note: The following resources were NOT deleted:"
-    echo "  - PostgreSQL user and database (langfuse)"
-    echo "  - ClickHouse user and database (langfuse)"
-    echo "  - MinIO user and bucket (langfuse)"
-    echo "  - Keycloak user (langfuse)"
-    echo ""
-    echo "To delete these resources, run:"
-    echo "  just langfuse::delete-postgres-user-and-db"
-    echo "  just langfuse::delete-clickhouse-user"
-    echo "  just langfuse::delete-minio-user"
-    echo "  just langfuse::delete-keycloak-user"
+    if [ "{{ delete-data }}" = "true" ]; then
+        echo "Deleting database and storage..."
+        just delete-postgres-user-and-db || true
+        just delete-clickhouse-user || true
+        just delete-minio-user || true
+        just delete-keycloak-user || true
+        just delete-salt || true
+        just delete-nextauth-secret || true
+        just delete-redis-password || true
+        echo "Langfuse uninstalled with all data deleted."
+    else
+        echo "Langfuse uninstalled successfully"
+        echo ""
+        echo "Note: The following resources were NOT deleted:"
+        echo "  - PostgreSQL user and database (langfuse)"
+        echo "  - ClickHouse user and database (langfuse)"
+        echo "  - MinIO user and bucket (langfuse)"
+        echo "  - Keycloak user (langfuse)"
+        echo "  - Vault secrets (langfuse/*)"
+        echo ""
+        echo "To delete all data, run:"
+        echo "  just langfuse::uninstall true"
+    fi
 
 # Create all secrets (PostgreSQL, Keycloak, MinIO, Redis)
 create-secrets:

langfuse/langfuse-values.gomplate.yaml

@@ -69,13 +69,13 @@ langfuse:
     tls:
       enabled: true
 
-  # Resource configuration based on Goldilocks/VPA recommendations
-  # CPU limits increased to handle startup spikes
+  # Resource recommendations from Goldilocks VPA
+  # web target: cpu=15m, memory=717Mi
   web:
     resources:
       requests:
-        cpu: 15m
-        memory: 704Mi
+        cpu: 25m
+        memory: 768Mi
       limits:
         cpu: 100m
         memory: 1.5Gi
@@ -89,10 +89,12 @@ langfuse:
       timeoutSeconds: 30
       failureThreshold: 5
 
+  # Resource recommendations from Goldilocks VPA
+  # worker target: cpu=15m, memory=380Mi
   worker:
     resources:
       requests:
-        cpu: 15m
+        cpu: 25m
         memory: 512Mi
       limits:
         cpu: 100m
@@ -113,6 +115,16 @@ redis:
     username: "default"
     existingSecret: redis-auth
     existingSecretPasswordKey: secret
+  # Resource recommendations from Goldilocks VPA
+  # valkey target: cpu=15m, memory=100Mi
+  master:
+    resources:
+      requests:
+        cpu: 25m
+        memory: 128Mi
+      limits:
+        cpu: 100m
+        memory: 256Mi
 
 clickhouse:
   deploy: false

librechat/values.gomplate.yaml

@@ -94,10 +94,10 @@ ingress:
 
 resources:
   requests:
-    cpu: 100m
+    cpu: 25m
     memory: 512Mi
   limits:
-    cpu: 1000m
+    cpu: 100m
     memory: 1Gi
 
 mongodb:
@@ -110,6 +110,13 @@ mongodb:
     tag: "latest"
   persistence:
     size: 8Gi
+  resources:
+    requests:
+      cpu: 75m
+      memory: 512Mi
+    limits:
+      cpu: 500m
+      memory: 2Gi
   podSecurityContext:
     fsGroup: 1001
     seccompProfile:
@@ -132,6 +139,13 @@ meilisearch:
     tag: "v1.7.3"
   auth:
     existingMasterKeySecret: "librechat-credentials-env"
+  resources:
+    requests:
+      cpu: 25m
+      memory: 256Mi
+    limits:
+      cpu: 100m
+      memory: 1Gi
   podSecurityContext:
     fsGroup: 1000
     seccompProfile:

litellm/.gitignore

@@ -0,0 +1,3 @@
+litellm-values.yaml
+apikey-external-secret.yaml
+models.yaml

litellm/README.md

@@ -0,0 +1,547 @@
+# LiteLLM
+
+Unified LLM gateway and proxy for accessing multiple LLM providers through a single OpenAI-compatible API:
+
+- **Multi-Provider Support**: Anthropic, OpenAI, Ollama, Mistral, Groq, Cohere, Azure, Bedrock, Vertex AI
+- **OpenAI-Compatible API**: Drop-in replacement for OpenAI SDK
+- **Load Balancing & Fallback**: Automatic failover between providers
+- **Virtual Keys**: Generate API keys for users with usage tracking
+- **Cost Tracking**: Monitor spending across providers
+- **Rate Limiting**: Control usage per key/user
+
+## Prerequisites
+
+- Kubernetes cluster (k3s)
+- External Secrets Operator (required)
+- PostgreSQL cluster (CloudNativePG)
+- Vault for secrets management
+
+## Configuration Overview
+
+LiteLLM requires two types of configuration:
+
+1. **Environment variables** (`.env.local`): Host, namespace, chart version
+2. **Model definitions** (`models.yaml`): LLM providers and models to expose
+
+This separation allows flexible model configuration without modifying environment files.
+
+## Installation
+
+### Step 1: Create Model Configuration
+
+Copy the example configuration and customize:
+
+```bash
+cp litellm/models.example.yaml litellm/models.yaml
+```
+
+Edit `litellm/models.yaml` to configure your models:
+
+```yaml
+# Anthropic Claude
+- model_name: claude-sonnet
+  litellm_params:
+    model: anthropic/claude-3-7-sonnet-latest
+    api_key: os.environ/ANTHROPIC_API_KEY
+
+# OpenAI
+- model_name: gpt-4o
+  litellm_params:
+    model: openai/gpt-4o
+    api_key: os.environ/OPENAI_API_KEY
+
+# Ollama (local models - no API key required)
+- model_name: llama3
+  litellm_params:
+    model: ollama/llama3.2
+    api_base: http://ollama.ollama:11434
+```
+
+### Step 2: Set API Keys
+
+For each provider that requires an API key:
+
+```bash
+just litellm::set-api-key anthropic
+just litellm::set-api-key openai
+```
+
+Or interactively select the provider:
+
+```bash
+just litellm::set-api-key
+```
+
+API keys are stored in Vault and synced to Kubernetes via External Secrets Operator.
+
+### Step 3: Install LiteLLM
+
+```bash
+just litellm::install
+```
+
+You will be prompted for:
+
+- **LiteLLM host (FQDN)**: e.g., `litellm.example.com`
+- **Enable Prometheus monitoring**: If kube-prometheus-stack is installed
+
+## Model Management
+
+### Add a Model Interactively
+
+```bash
+just litellm::add-model
+```
+
+This guides you through:
+
+1. Selecting a provider
+2. Choosing a model
+3. Setting a model alias
+
+### Remove a Model
+
+```bash
+just litellm::remove-model
+```
+
+### List Configured Models
+
+```bash
+just litellm::list-models
+```
+
+### Example Output
+
+```text
+Configured models:
+  - claude-sonnet: anthropic/claude-3-7-sonnet-latest
+  - claude-haiku: anthropic/claude-3-5-haiku-latest
+  - llama3: ollama/llama3.2
+```
+
+## API Key Management
+
+### Set API Key for a Provider
+
+```bash
+just litellm::set-api-key anthropic
+```
+
+### Get API Key (from Vault)
+
+```bash
+just litellm::get-api-key anthropic
+```
+
+### Verify All Required Keys
+
+```bash
+just litellm::verify-api-keys
+```
+
+## Environment Variables
+
+| Variable | Default | Description |
+| -------- | ------- | ----------- |
+| `LITELLM_NAMESPACE` | `litellm` | Kubernetes namespace |
+| `LITELLM_CHART_VERSION` | `0.1.825` | Helm chart version |
+| `LITELLM_HOST` | (prompt) | External hostname (FQDN) |
+| `OLLAMA_NAMESPACE` | `ollama` | Ollama namespace for local models |
+| `MONITORING_ENABLED` | (prompt) | Enable Prometheus ServiceMonitor |
+
+## Authentication
+
+LiteLLM has two types of authentication:
+
+1. **API Access**: Uses Master Key or Virtual Keys for programmatic access
+2. **Admin UI**: Uses Keycloak SSO for browser-based access
+
+### Enable SSO for Admin UI
+
+After installing LiteLLM, enable Keycloak authentication for the Admin UI:
+
+```bash
+just litellm::setup-oidc
+```
+
+This will:
+
+- Create a Keycloak client for LiteLLM
+- Store the client secret in Vault
+- Configure LiteLLM with OIDC environment variables
+- Upgrade the deployment with SSO enabled
+
+### Disable SSO
+
+To disable SSO and return to unauthenticated Admin UI access:
+
+```bash
+just litellm::disable-oidc
+```
+
+### SSO Configuration Details
+
+| Setting | Value |
+| ------- | ----- |
+| Callback URL | `https://<litellm-host>/sso/callback` |
+| Authorization Endpoint | `https://<keycloak-host>/realms/<realm>/protocol/openid-connect/auth` |
+| Token Endpoint | `https://<keycloak-host>/realms/<realm>/protocol/openid-connect/token` |
+| Userinfo Endpoint | `https://<keycloak-host>/realms/<realm>/protocol/openid-connect/userinfo` |
+| Scope | `openid email profile` |
+
+## User Management
+
+SSO users are automatically created in LiteLLM when they first log in. By default, new users are assigned the `internal_user_viewer` role (read-only access).
+
+### List Users
+
+```bash
+just litellm::list-users
+```
+
+### Assign Role to User
+
+Interactively select user and role:
+
+```bash
+just litellm::assign-role
+```
+
+Or specify directly:
+
+```bash
+just litellm::assign-role buun proxy_admin
+```
+
+### User Roles
+
+| Role | Description |
+| ---- | ----------- |
+| `proxy_admin` | Full admin access (manage keys, users, models, settings) |
+| `proxy_admin_viewer` | Admin read-only access |
+| `internal_user` | Can create and manage own API keys |
+| `internal_user_viewer` | Read-only access (default for SSO users) |
+
+**Note**: To manage API keys in the Admin UI, users need at least `internal_user` or `proxy_admin` role.
+
+## API Usage
+
+LiteLLM exposes an OpenAI-compatible API at `https://your-litellm-host/`.
+
+### Get Master Key
+
+```bash
+just litellm::master-key
+```
+
+### Generate Virtual Key for a User
+
+```bash
+just litellm::generate-virtual-key buun
+```
+
+This will prompt for a model selection and generate an API key for the specified user. Select `all` to grant access to all models.
+
+### OpenAI SDK Example
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    base_url="https://litellm.example.com",
+    api_key="sk-..."  # Virtual key or master key
+)
+
+response = client.chat.completions.create(
+    model="claude-sonnet",  # Use your model alias
+    messages=[{"role": "user", "content": "Hello!"}]
+)
+print(response.choices[0].message.content)
+```
+
+### curl Example
+
+```bash
+curl https://litellm.example.com/v1/chat/completions \
+  -H "Authorization: Bearer sk-..." \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "claude-sonnet",
+    "messages": [{"role": "user", "content": "Hello!"}]
+  }'
+```
+
+## Team Management
+
+Teams allow you to group users and configure team-specific settings such as Langfuse projects for observability.
+
+### Create a Team
+
+```bash
+just litellm::create-team
+```
+
+Or with a name directly:
+
+```bash
+just litellm::create-team name="project-alpha"
+```
+
+### List Teams
+
+```bash
+just litellm::list-teams
+```
+
+### Get Team Info
+
+```bash
+just litellm::get-team team_id=<team-id>
+```
+
+### Delete a Team
+
+```bash
+just litellm::delete-team team_id=<team-id>
+```
+
+### Generate Virtual Key for a Team
+
+```bash
+just litellm::generate-team-key
+```
+
+This will prompt for team selection and username. The generated key inherits the team's settings (including Langfuse project configuration).
+
+## Langfuse Integration
+
+[Langfuse](https://langfuse.com/) provides LLM observability with tracing, monitoring, and analytics. LiteLLM can send traces to Langfuse for every API call.
+
+### Enable Langfuse Integration
+
+During installation (`just litellm::install`) or upgrade (`just litellm::upgrade`), you will be prompted to enable Langfuse integration. Alternatively:
+
+```bash
+just litellm::setup-langfuse
+```
+
+You will need Langfuse API keys (Public Key and Secret Key) from the Langfuse UI: **Settings > API Keys**.
+
+### Set Langfuse API Keys
+
+```bash
+just litellm::set-langfuse-keys
+```
+
+### Disable Langfuse Integration
+
+```bash
+just litellm::disable-langfuse
+```
+
+### Per-Team Langfuse Projects
+
+Each team can have its own Langfuse project for isolated observability. This is useful when different projects or departments need separate trace data.
+
+#### Setup Flow
+
+1. Create a team:
+
+   ```bash
+   just litellm::create-team name="project-alpha"
+   ```
+
+2. Create a Langfuse project for the team and get API keys from Langfuse UI
+
+3. Configure the team's Langfuse project:
+
+   ```bash
+   just litellm::set-team-langfuse-project
+   ```
+
+   This will prompt for team selection and Langfuse API keys.
+
+4. Generate a key for the team:
+
+   ```bash
+   just litellm::generate-team-key
+   ```
+
+5. Use the team key for API calls - traces will be sent to the team's Langfuse project
+
+#### Architecture
+
+```plain
+LiteLLM Proxy
+  |
+  +-- Default Langfuse Project (for keys without team)
+  |
+  +-- Team A --> Langfuse Project A
+  |
+  +-- Team B --> Langfuse Project B
+```
+
+### Environment Variables
+
+| Variable | Default | Description |
+| -------- | ------- | ----------- |
+| `LITELLM_LANGFUSE_INTEGRATION_ENABLED` | (prompt) | Enable Langfuse integration |
+| `LANGFUSE_HOST` | (prompt) | Langfuse instance hostname |
+
+## Supported Providers
+
+| Provider | Model Prefix | API Key Required |
+| -------- | ------------ | ---------------- |
+| Anthropic | `anthropic/` | Yes |
+| OpenAI | `openai/` | Yes |
+| Ollama | `ollama/` | No (uses `api_base`) |
+| Mistral | `mistral/` | Yes |
+| Groq | `groq/` | Yes |
+| Cohere | `cohere/` | Yes |
+| Azure OpenAI | `azure/` | Yes |
+| AWS Bedrock | `bedrock/` | Yes |
+| Google Vertex AI | `vertexai/` | Yes |
+
+## Architecture
+
+```plain
+External Users/Applications
+      |
+Cloudflare Tunnel (HTTPS)
+      |
+Traefik Ingress (HTTPS)
+      |
+LiteLLM Proxy (HTTP inside cluster)
+  |-- PostgreSQL (usage tracking, virtual keys)
+  |-- Redis (caching, rate limiting)
+  |-- External Secrets (API keys from Vault)
+      |
+      +-- Anthropic API
+      +-- OpenAI API
+      +-- Ollama (local)
+      +-- Other providers...
+```
+
+## Upgrade
+
+After modifying `models.yaml` or updating API keys:
+
+```bash
+just litellm::upgrade
+```
+
+## Uninstall
+
+```bash
+just litellm::uninstall
+```
+
+This removes:
+
+- Helm release and all Kubernetes resources
+- Namespace
+- External Secrets
+
+**Note**: The following resources are NOT deleted:
+
+- PostgreSQL database (use `just postgres::delete-db litellm`)
+- API keys in Vault
+
+### Full Cleanup
+
+To remove everything including database and Vault secrets:
+
+```bash
+just litellm::cleanup
+```
+
+## Troubleshooting
+
+### Check Pod Status
+
+```bash
+kubectl get pods -n litellm
+```
+
+Expected pods:
+
+- `litellm-*` - LiteLLM proxy
+- `litellm-redis-master-0` - Redis instance
+
+### View Logs
+
+```bash
+kubectl logs -n litellm deployment/litellm --tail=100
+```
+
+### API Key Not Working
+
+Verify the ExternalSecret is synced:
+
+```bash
+kubectl get externalsecret -n litellm
+kubectl get secret apikey -n litellm -o yaml
+```
+
+### Model Not Found
+
+Ensure the model is configured in `models.yaml` and the deployment is updated:
+
+```bash
+just litellm::list-models
+just litellm::upgrade
+```
+
+### Provider API Errors
+
+Check if the API key is set correctly:
+
+```bash
+just litellm::get-api-key anthropic
+```
+
+If empty, set the API key:
+
+```bash
+just litellm::set-api-key anthropic
+```
+
+### Database Connection Issues
+
+Check PostgreSQL connectivity:
+
+```bash
+kubectl exec -n litellm deployment/litellm -- \
+  psql -h postgres-cluster-rw.postgres -U litellm -d litellm -c "SELECT 1"
+```
+
+## Configuration Files
+
+| File | Description |
+| ---- | ----------- |
+| `models.yaml` | Model definitions (user-created, gitignored) |
+| `models.example.yaml` | Example model configuration |
+| `litellm-values.gomplate.yaml` | Helm values template |
+| `apikey-external-secret.gomplate.yaml` | ExternalSecret for API keys |
+| `keycloak-auth-external-secret.gomplate.yaml` | ExternalSecret for Keycloak OIDC |
+| `langfuse-auth-external-secret.gomplate.yaml` | ExternalSecret for Langfuse API keys |
+
+## Security Considerations
+
+- **Pod Security Standards**: Namespace configured with **baseline** enforcement
+  (LiteLLM's Prisma requires write access to `/.cache`, which prevents `restricted` level)
+- **Secrets Management**: API keys stored in Vault, synced via External Secrets Operator
+- **Virtual Keys**: Generate scoped API keys for users instead of sharing master key
+- **TLS/HTTPS**: All external traffic encrypted via Traefik Ingress
+- **Database Credentials**: Unique PostgreSQL user with minimal privileges
+
+## References
+
+- [LiteLLM Documentation](https://docs.litellm.ai/)
+- [LiteLLM GitHub](https://github.com/BerriAI/litellm)
+- [LiteLLM Helm Chart](https://github.com/BerriAI/litellm/tree/main/deploy/charts/litellm-helm)
+- [Supported Models](https://docs.litellm.ai/docs/providers)
+- [Virtual Keys](https://docs.litellm.ai/docs/proxy/virtual_keys)
+- [Langfuse Integration](https://docs.litellm.ai/docs/proxy/logging#langfuse)
+- [Team-based Logging](https://docs.litellm.ai/docs/proxy/team_logging)

litellm/apikey-external-secret.gomplate.yaml

@@ -0,0 +1,29 @@
+{{- $models := (datasource "models") -}}
+{{- $providerMap := dict -}}
+{{- range $models -}}
+{{- if has .litellm_params "api_key" -}}
+{{- $parts := strings.Split "/" .litellm_params.model -}}
+{{- $provider := index $parts 0 -}}
+{{- $providerMap = merge $providerMap (dict $provider true) -}}
+{{- end -}}
+{{- end -}}
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: apikey-external-secret
+  namespace: {{ .Env.LITELLM_NAMESPACE }}
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    name: vault-secret-store
+    kind: ClusterSecretStore
+  target:
+    name: apikey
+    creationPolicy: Owner
+  data:
+{{- range $provider, $_ := $providerMap }}
+  - secretKey: {{ $provider | strings.ToUpper }}_API_KEY
+    remoteRef:
+      key: litellm/{{ $provider }}
+      property: apikey
+{{- end }}

litellm/keycloak-auth-external-secret.gomplate.yaml

@@ -0,0 +1,22 @@
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: keycloak-auth-external-secret
+  namespace: {{ .Env.LITELLM_NAMESPACE }}
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    name: vault-secret-store
+    kind: ClusterSecretStore
+  target:
+    name: keycloak-auth
+    creationPolicy: Owner
+  data:
+  - secretKey: GENERIC_CLIENT_ID
+    remoteRef:
+      key: keycloak/client/litellm
+      property: client_id
+  - secretKey: GENERIC_CLIENT_SECRET
+    remoteRef:
+      key: keycloak/client/litellm
+      property: client_secret

litellm/langfuse-auth-external-secret.gomplate.yaml

@@ -0,0 +1,22 @@
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: langfuse-auth-external-secret
+  namespace: {{ .Env.LITELLM_NAMESPACE }}
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    name: vault-secret-store
+    kind: ClusterSecretStore
+  target:
+    name: langfuse-auth
+    creationPolicy: Owner
+  data:
+  - secretKey: LANGFUSE_PUBLIC_KEY
+    remoteRef:
+      key: litellm/langfuse
+      property: public_key
+  - secretKey: LANGFUSE_SECRET_KEY
+    remoteRef:
+      key: litellm/langfuse
+      property: secret_key

litellm/litellm-values.gomplate.yaml

@@ -0,0 +1,114 @@
+# https://github.com/BerriAI/litellm/tree/main/deploy/charts/litellm-helm
+# https://github.com/BerriAI/litellm/tree/main/litellm/proxy/example_config_yaml
+
+masterkeySecretName: ""
+masterkeySecretKey: ""
+
+# Note: LiteLLM image requires write access to /.cache for Prisma
+# Pod Security Standards must be set to "baseline" for this namespace
+podSecurityContext: {}
+
+securityContext: {}
+
+# Resource recommendations from Goldilocks VPA
+# litellm target: cpu=11m, memory=549Mi
+resources:
+  requests:
+    cpu: 25m
+    memory: 512Mi
+  limits:
+    cpu: 100m
+    memory: 1Gi
+
+migrationJob:
+  resources:
+    requests:
+      cpu: 100m
+      memory: 512Mi
+    limits:
+      memory: 1Gi
+
+environmentSecrets:
+  - apikey
+{{- if .Env.LITELLM_OIDC_ENABLED }}
+  - keycloak-auth
+{{- end }}
+{{- if .Env.LITELLM_LANGFUSE_INTEGRATION_ENABLED }}
+  - langfuse-auth
+{{- end }}
+
+extraEnvVars:
+{{- if .Env.LITELLM_OIDC_ENABLED }}
+  - name: PROXY_BASE_URL
+    value: "https://{{ .Env.LITELLM_HOST }}"
+  - name: GENERIC_AUTHORIZATION_ENDPOINT
+    value: "https://{{ .Env.KEYCLOAK_HOST }}/realms/{{ .Env.KEYCLOAK_REALM }}/protocol/openid-connect/auth"
+  - name: GENERIC_TOKEN_ENDPOINT
+    value: "https://{{ .Env.KEYCLOAK_HOST }}/realms/{{ .Env.KEYCLOAK_REALM }}/protocol/openid-connect/token"
+  - name: GENERIC_USERINFO_ENDPOINT
+    value: "https://{{ .Env.KEYCLOAK_HOST }}/realms/{{ .Env.KEYCLOAK_REALM }}/protocol/openid-connect/userinfo"
+  - name: GENERIC_SCOPE
+    value: "openid email profile"
+{{- end }}
+{{- if .Env.LITELLM_LANGFUSE_INTEGRATION_ENABLED }}
+  - name: LANGFUSE_HOST
+    value: "https://{{ .Env.LANGFUSE_HOST }}"
+{{- end }}
+
+proxy_config:
+  model_list:
+{{ file.Read "models.yaml" | indent 4 }}
+{{- if .Env.LITELLM_LANGFUSE_INTEGRATION_ENABLED }}
+  litellm_settings:
+    success_callback: ["langfuse"]
+    failure_callback: ["langfuse"]
+{{- end }}
+
+db:
+  useExisting: true
+
+  endpoint: postgres-cluster-rw.postgres
+  database: litellm
+  secret:
+    name: postgres-auth
+    usernameKey: username
+    passwordKey: password
+
+  deployStandalone: false
+
+redis:
+  enabled: true
+  # Resource recommendations from Goldilocks VPA
+  # redis target: cpu=15m, memory=100Mi
+  master:
+    resources:
+      requests:
+        cpu: 25m
+        memory: 128Mi
+      limits:
+        cpu: 100m
+        memory: 256Mi
+
+ingress:
+  enabled: true
+  className: traefik
+  annotations:
+    kubernetes.io/ingress.class: traefik
+    traefik.ingress.kubernetes.io/router.entrypoints: websecure
+  hosts:
+    - host: {{ .Env.LITELLM_HOST }}
+      paths:
+        - path: /
+          pathType: ImplementationSpecific
+  tls:
+    - hosts:
+      - {{ .Env.LITELLM_HOST }}
+
+{{- if .Env.MONITORING_ENABLED }}
+serviceMonitor:
+  enabled: true
+  labels:
+    release: kube-prometheus-stack
+  interval: 30s
+  scrapeTimeout: 10s
+{{- end }}

litellm/models.example.yaml

@@ -0,0 +1,106 @@
+# LiteLLM Model Configuration
+# Copy this file to models.yaml and customize for your environment.
+#
+# Usage:
+#   cp litellm/models.example.yaml litellm/models.yaml
+#   # Edit models.yaml to add/remove models
+#   just litellm::install
+#
+# API keys are stored in Vault and injected as environment variables.
+# Use: just litellm::set-api-key provider=<provider>
+#
+# Supported providers:
+#   - anthropic: Claude models (Opus, Sonnet, Haiku)
+#   - openai: GPT and o-series models
+#   - ollama: Local models (no API key required)
+#   - azure: Azure OpenAI
+#   - bedrock: AWS Bedrock
+#   - vertexai: Google Vertex AI
+#   - mistral: Mistral AI
+#   - groq: Groq (fast inference)
+#   - cohere: Cohere
+
+# Anthropic Claude (https://docs.anthropic.com/en/docs/about-claude/models/overview)
+- model_name: claude-sonnet
+  litellm_params:
+    model: anthropic/claude-sonnet-4-20250514
+    api_key: os.environ/ANTHROPIC_API_KEY
+
+- model_name: claude-haiku
+  litellm_params:
+    model: anthropic/claude-haiku-4-20251015
+    api_key: os.environ/ANTHROPIC_API_KEY
+
+# - model_name: claude-opus
+#   litellm_params:
+#     model: anthropic/claude-opus-4-20250514
+#     api_key: os.environ/ANTHROPIC_API_KEY
+
+# OpenAI (https://platform.openai.com/docs/models)
+# - model_name: gpt-4o
+#   litellm_params:
+#     model: openai/gpt-4o
+#     api_key: os.environ/OPENAI_API_KEY
+
+# - model_name: gpt-4o-mini
+#   litellm_params:
+#     model: openai/gpt-4o-mini
+#     api_key: os.environ/OPENAI_API_KEY
+
+# - model_name: o3
+#   litellm_params:
+#     model: openai/o3
+#     api_key: os.environ/OPENAI_API_KEY
+
+# - model_name: o4-mini
+#   litellm_params:
+#     model: openai/o4-mini
+#     api_key: os.environ/OPENAI_API_KEY
+
+# Ollama (local models - no API key required)
+# - model_name: llama4-scout
+#   litellm_params:
+#     model: ollama/llama4:scout
+#     api_base: http://ollama.ollama:11434
+
+# - model_name: qwen3
+#   litellm_params:
+#     model: ollama/qwen3:8b
+#     api_base: http://ollama.ollama:11434
+
+# - model_name: deepseek-r1
+#   litellm_params:
+#     model: ollama/deepseek-r1:8b
+#     api_base: http://ollama.ollama:11434
+
+# Mistral AI (https://docs.mistral.ai/getting-started/models/models_overview/)
+# - model_name: mistral-large
+#   litellm_params:
+#     model: mistral/mistral-large-latest
+#     api_key: os.environ/MISTRAL_API_KEY
+
+# - model_name: ministral-8b
+#   litellm_params:
+#     model: mistral/ministral-8b-latest
+#     api_key: os.environ/MISTRAL_API_KEY
+
+# - model_name: codestral
+#   litellm_params:
+#     model: mistral/codestral-latest
+#     api_key: os.environ/MISTRAL_API_KEY
+
+# Groq (fast inference - https://console.groq.com/docs/models)
+# - model_name: groq-llama4-scout
+#   litellm_params:
+#     model: groq/meta-llama/llama-4-scout-17b-16e-instruct
+#     api_key: os.environ/GROQ_API_KEY
+
+# - model_name: groq-llama3.3
+#   litellm_params:
+#     model: groq/llama-3.3-70b-versatile
+#     api_key: os.environ/GROQ_API_KEY
+
+# - model_name: groq-llama3.1
+#   litellm_params:
+#     model: groq/llama-3.1-8b-instant
+#     api_key: os.environ/GROQ_API_KEY

nats/justfile

@@ -0,0 +1,113 @@
+set fallback := true
+
+export NATS_NAMESPACE := env("NATS_NAMESPACE", "nats")
+export NATS_CHART_VERSION := env("NATS_CHART_VERSION", "2.12.2")
+export NATS_REPLICAS := env("NATS_REPLICAS", "1")
+export NATS_JETSTREAM_ENABLED := env("NATS_JETSTREAM_ENABLED", "true")
+export NATS_JETSTREAM_STORAGE_SIZE := env("NATS_JETSTREAM_STORAGE_SIZE", "10Gi")
+export NATS_JETSTREAM_MEMORY_SIZE := env("NATS_JETSTREAM_MEMORY_SIZE", "256Mi")
+
+[private]
+default:
+    @just --list --unsorted --list-submodules
+
+# Add Helm repository
+add-helm-repo:
+    helm repo add nats https://nats-io.github.io/k8s/helm/charts/
+    helm repo update nats
+
+# Remove Helm repository
+remove-helm-repo:
+    helm repo remove nats
+
+# Create NATS namespace
+create-namespace:
+    #!/bin/bash
+    set -euo pipefail
+    if ! kubectl get namespace ${NATS_NAMESPACE} &>/dev/null; then
+        kubectl create namespace ${NATS_NAMESPACE}
+    fi
+    kubectl label namespace ${NATS_NAMESPACE} \
+        pod-security.kubernetes.io/enforce=restricted \
+        pod-security.kubernetes.io/enforce-version=latest \
+        pod-security.kubernetes.io/warn=restricted \
+        pod-security.kubernetes.io/warn-version=latest \
+        --overwrite
+
+# Delete NATS namespace
+delete-namespace:
+    kubectl delete namespace ${NATS_NAMESPACE} --ignore-not-found
+
+# Install NATS
+install:
+    #!/bin/bash
+    set -euo pipefail
+
+    just create-namespace
+    just add-helm-repo
+
+    gomplate -f values.gomplate.yaml -o values.yaml
+    helm upgrade --install nats nats/nats \
+        --version ${NATS_CHART_VERSION} \
+        -n ${NATS_NAMESPACE} \
+        -f values.yaml \
+        --wait
+
+    echo ""
+    echo "NATS installed successfully"
+    echo "Namespace: ${NATS_NAMESPACE}"
+    echo "Replicas: ${NATS_REPLICAS}"
+    echo "JetStream enabled: ${NATS_JETSTREAM_ENABLED}"
+    echo ""
+    echo "Internal URL: nats://nats.${NATS_NAMESPACE}.svc:4222"
+
+# Upgrade NATS
+upgrade:
+    #!/bin/bash
+    set -euo pipefail
+
+    gomplate -f values.gomplate.yaml -o values.yaml
+    helm upgrade nats nats/nats \
+        --version ${NATS_CHART_VERSION} \
+        -n ${NATS_NAMESPACE} \
+        -f values.yaml \
+        --wait
+
+    echo "NATS upgraded successfully"
+
+# Uninstall NATS
+uninstall:
+    #!/bin/bash
+    set -euo pipefail
+    if ! gum confirm "Are you sure you want to uninstall NATS?"; then
+        echo "Aborted"
+        exit 0
+    fi
+    helm uninstall nats -n ${NATS_NAMESPACE} --wait --ignore-not-found
+    just delete-namespace
+    echo "NATS uninstalled"
+
+# Show NATS status
+status:
+    kubectl get pods -n ${NATS_NAMESPACE}
+    kubectl get svc -n ${NATS_NAMESPACE}
+
+# Show NATS logs
+logs:
+    kubectl logs -n ${NATS_NAMESPACE} -l app.kubernetes.io/name=nats -f
+
+# Show server info via monitoring endpoint
+server-info:
+    kubectl exec -n ${NATS_NAMESPACE} nats-0 -c nats -- \
+        wget -qO- http://localhost:8222/varz | head -50
+
+# Show JetStream info via monitoring endpoint
+js-info:
+    kubectl exec -n ${NATS_NAMESPACE} nats-0 -c nats -- \
+        wget -qO- http://localhost:8222/jsz
+
+# Port forward for local testing
+port-forward:
+    @echo "NATS available at localhost:4222"
+    @echo "Monitor available at http://localhost:8222"
+    kubectl port-forward -n ${NATS_NAMESPACE} svc/nats 4222:4222 8222:8222

nats/values.gomplate.yaml

@@ -0,0 +1,64 @@
+config:
+  cluster:
+    enabled: {{ if gt (conv.ToInt .Env.NATS_REPLICAS) 1 }}true{{ else }}false{{ end }}
+    replicas: {{ .Env.NATS_REPLICAS }}
+
+  jetstream:
+    enabled: {{ .Env.NATS_JETSTREAM_ENABLED }}
+    fileStore:
+      enabled: true
+      dir: /data
+      pvc:
+        enabled: true
+        size: {{ .Env.NATS_JETSTREAM_STORAGE_SIZE }}
+    memoryStore:
+      enabled: true
+      maxSize: {{ .Env.NATS_JETSTREAM_MEMORY_SIZE }}
+
+  monitor:
+    enabled: true
+    port: 8222
+
+container:
+  resources:
+    requests:
+      cpu: 50m
+      memory: 64Mi
+    limits:
+      cpu: 500m
+      memory: 512Mi
+
+  merge:
+    securityContext:
+      runAsUser: 1000
+      runAsNonRoot: true
+      allowPrivilegeEscalation: false
+      seccompProfile:
+        type: RuntimeDefault
+      capabilities:
+        drop:
+          - ALL
+
+reloader:
+  enabled: true
+  merge:
+    securityContext:
+      runAsUser: 1000
+      runAsNonRoot: true
+      allowPrivilegeEscalation: false
+      seccompProfile:
+        type: RuntimeDefault
+      capabilities:
+        drop:
+          - ALL
+
+podTemplate:
+  merge:
+    spec:
+      securityContext:
+        fsGroup: 1000
+        seccompProfile:
+          type: RuntimeDefault
+
+natsBox:
+  enabled: false

nats/values.yaml

@@ -0,0 +1,64 @@
+config:
+  cluster:
+    enabled: false
+    replicas: 1
+
+  jetstream:
+    enabled: true
+    fileStore:
+      enabled: true
+      dir: /data
+      pvc:
+        enabled: true
+        size: 10Gi
+    memoryStore:
+      enabled: true
+      maxSize: 256Mi
+
+  monitor:
+    enabled: true
+    port: 8222
+
+container:
+  resources:
+    requests:
+      cpu: 50m
+      memory: 64Mi
+    limits:
+      cpu: 500m
+      memory: 512Mi
+
+  merge:
+    securityContext:
+      runAsUser: 1000
+      runAsNonRoot: true
+      allowPrivilegeEscalation: false
+      seccompProfile:
+        type: RuntimeDefault
+      capabilities:
+        drop:
+          - ALL
+
+reloader:
+  enabled: true
+  merge:
+    securityContext:
+      runAsUser: 1000
+      runAsNonRoot: true
+      allowPrivilegeEscalation: false
+      seccompProfile:
+        type: RuntimeDefault
+      capabilities:
+        drop:
+          - ALL
+
+podTemplate:
+  merge:
+    spec:
+      securityContext:
+        fsGroup: 1000
+        seccompProfile:
+          type: RuntimeDefault
+
+natsBox:
+  enabled: false

ollama/justfile

@@ -8,6 +8,7 @@ export OLLAMA_GPU_TYPE := env("OLLAMA_GPU_TYPE", "nvidia")
 export OLLAMA_GPU_COUNT := env("OLLAMA_GPU_COUNT", "1")
 export OLLAMA_MODELS := env("OLLAMA_MODELS", "")
 export OLLAMA_STORAGE_SIZE := env("OLLAMA_STORAGE_SIZE", "30Gi")
+export OLLAMA_HELM_TIMEOUT := env("OLLAMA_HELM_TIMEOUT", "10m")
 
 [private]
 default:
@@ -66,7 +67,8 @@ install:
 
     gomplate -f values.gomplate.yaml -o values.yaml
     helm upgrade --install ollama ollama/ollama \
-        --version ${OLLAMA_CHART_VERSION} -n ${OLLAMA_NAMESPACE} --wait \
+        --version ${OLLAMA_CHART_VERSION} -n ${OLLAMA_NAMESPACE} \
+        --wait --timeout ${OLLAMA_HELM_TIMEOUT} \
         -f values.yaml
 
     echo ""
@@ -97,7 +99,8 @@ upgrade:
 
     gomplate -f values.gomplate.yaml -o values.yaml
     helm upgrade ollama ollama/ollama \
-        --version ${OLLAMA_CHART_VERSION} -n ${OLLAMA_NAMESPACE} --wait \
+        --version ${OLLAMA_CHART_VERSION} -n ${OLLAMA_NAMESPACE} \
+        --wait --timeout ${OLLAMA_HELM_TIMEOUT} \
         -f values.yaml
 
     echo "Ollama upgraded successfully"