ollama upgrade ctx size

apps/kube-prometheus-stack/release-alloy.yaml

@@ -0,0 +1,145 @@
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: alloy
+  namespace: kube-prometheus-stack
+spec:
+  chart:
+    spec:
+      chart: alloy
+      version: 1.x
+      sourceRef:
+        kind: HelmRepository
+        name: grafana
+  interval: 15m
+  releaseName: alloy
+  values:
+    alloy:
+      configMap:
+        content: |-
+          // Write your Alloy config here:
+          loki.write "default" {
+            endpoint {
+              url = "http://loki:3100/loki/api/v1/push"
+            }
+          }
+
+          // discovery.kubernetes allows you to find scrape targets from Kubernetes resources.
+          // It watches cluster state and ensures targets are continually synced with what is currently running in your cluster.
+          discovery.kubernetes "pod" {
+            role = "pod"
+            // Restrict to pods on the node to reduce cpu & memory usage
+            selectors {
+              role = "pod"
+              field = "spec.nodeName=" + coalesce(sys.env("HOSTNAME"), constants.hostname)
+            }
+          }
+
+          // discovery.relabel rewrites the label set of the input targets by applying one or more relabeling rules.
+          // If no rules are defined, then the input targets are exported as-is.
+          discovery.relabel "pod_logs" {
+            targets = discovery.kubernetes.pod.targets
+
+            // Label creation - "namespace" field from "__meta_kubernetes_namespace"
+            rule {
+              source_labels = ["__meta_kubernetes_namespace"]
+              action = "replace"
+              target_label = "namespace"
+            }
+
+            // Label creation - "pod" field from "__meta_kubernetes_pod_name"
+            rule {
+              source_labels = ["__meta_kubernetes_pod_name"]
+              action = "replace"
+              target_label = "pod"
+            }
+
+            // Label creation - "container" field from "__meta_kubernetes_pod_container_name"
+            rule {
+              source_labels = ["__meta_kubernetes_pod_container_name"]
+              action = "replace"
+              target_label = "container"
+            }
+
+            // Label creation -  "app" field from "__meta_kubernetes_pod_label_app_kubernetes_io_name"
+            rule {
+              source_labels = ["__meta_kubernetes_pod_label_app_kubernetes_io_name"]
+              action = "replace"
+              target_label = "app"
+            }
+
+            // Label creation -  "job" field from "__meta_kubernetes_namespace" and "__meta_kubernetes_pod_container_name"
+            // Concatenate values __meta_kubernetes_namespace/__meta_kubernetes_pod_container_name
+            rule {
+              source_labels = ["__meta_kubernetes_namespace", "__meta_kubernetes_pod_container_name"]
+              action = "replace"
+              target_label = "job"
+              separator = "/"
+              replacement = "$1"
+            }
+
+            // Label creation - "__path__" field from "__meta_kubernetes_pod_uid" and "__meta_kubernetes_pod_container_name"
+            // Concatenate values __meta_kubernetes_pod_uid/__meta_kubernetes_pod_container_name.log
+            rule {
+              source_labels = ["__meta_kubernetes_pod_uid", "__meta_kubernetes_pod_container_name"]
+              action = "replace"
+              target_label = "__path__"
+              separator = "/"
+              replacement = "/var/log/pods/*$1/*.log"
+            }
+
+            // Label creation -  "container_runtime" field from "__meta_kubernetes_pod_container_id"
+            rule {
+              source_labels = ["__meta_kubernetes_pod_container_id"]
+              action = "replace"
+              target_label = "container_runtime"
+              regex = `^(\S+):\/\/.+$`
+              replacement = "$1"
+            }
+          }
+
+          // loki.source.kubernetes tails logs from Kubernetes containers using the Kubernetes API.
+          loki.source.kubernetes "pod_logs" {
+            targets    = discovery.relabel.pod_logs.output
+            forward_to = [loki.process.pod_logs.receiver]
+          }
+
+          // loki.process receives log entries from other Loki components, applies one or more processing stages,
+          // and forwards the results to the list of receivers in the component's arguments.
+          loki.process "pod_logs" {
+            stage.static_labels {
+                values = {
+                  cluster = "server",
+                }
+            }
+
+            forward_to = [loki.write.default.receiver]
+          }
+
+          // loki.source.kubernetes_events tails events from the Kubernetes API and converts them
+          // into log lines to forward to other Loki components.
+          loki.source.kubernetes_events "cluster_events" {
+            job_name   = "integrations/kubernetes/eventhandler"
+            log_format = "logfmt"
+            forward_to = [
+              loki.process.cluster_events.receiver,
+            ]
+          }
+
+          // loki.process receives log entries from other loki components, applies one or more processing stages,
+          // and forwards the results to the list of receivers in the component's arguments.
+          loki.process "cluster_events" {
+            forward_to = [loki.write.default.receiver]
+
+            stage.static_labels {
+              values = {
+                cluster = "server",
+              }
+            }
+
+            stage.labels {
+              values = {
+                kubernetes_cluster_events = "job",
+              }
+            }
+          }

apps/kube-prometheus-stack/release-loki.yaml

@@ -0,0 +1,71 @@
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: loki
+  namespace: kube-prometheus-stack
+spec:
+  chart:
+    spec:
+      chart: loki
+      version: 6.x
+      sourceRef:
+        kind: HelmRepository
+        name: grafana-community
+  interval: 15m
+  releaseName: loki
+  values:
+    loki:
+      auth_enabled: false
+      commonConfig:
+        replication_factor: 3
+      schemaConfig:
+        configs:
+          - from: "2024-04-01"
+            store: tsdb
+            object_store: s3
+            schema: v13
+            index:
+              prefix: loki_index_
+              period: 24h
+      pattern_ingester:
+          enabled: true
+      limits_config:
+        allow_structured_metadata: true
+        volume_enabled: true
+      ruler:
+        enable_api: true
+
+    minio:
+      enabled: true
+          
+    deploymentMode: SingleBinary
+
+    singleBinary:
+      replicas: 3
+
+    # Zero out replica counts of other deployment modes
+    backend:
+      replicas: 0
+    read:
+      replicas: 0
+    write:
+      replicas: 0
+
+    ingester:
+      replicas: 0
+    querier:
+      replicas: 0
+    queryFrontend:
+      replicas: 0
+    queryScheduler:
+      replicas: 0
+    distributor:
+      replicas: 0
+    compactor:
+      replicas: 0
+    indexGateway:
+      replicas: 0
+    bloomCompactor:
+      replicas: 0
+    bloomGateway:
+      replicas: 0

apps/kube-prometheus-stack/repository-grafana-community.yaml

@@ -0,0 +1,8 @@
+apiVersion: source.toolkit.fluxcd.io/v1
+kind: HelmRepository
+metadata:
+  name: grafana-community
+  namespace: kube-prometheus-stack
+spec:
+  interval: 15m
+  url: https://grafana-community.github.io/helm-charts

apps/kube-prometheus-stack/repository-grafana.yaml

@@ -0,0 +1,8 @@
+apiVersion: source.toolkit.fluxcd.io/v1
+kind: HelmRepository
+metadata:
+  name: grafana
+  namespace: kube-prometheus-stack
+spec:
+  interval: 15m
+  url: https://grafana.github.io/helm-charts

apps/ollama/release.yaml

@@ -0,0 +1,56 @@
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: ollama
+  namespace: ollama
+spec:
+  chart:
+    spec:
+      chart: ollama
+      version: 1.x
+      sourceRef:
+        kind: HelmRepository
+        name: otwld
+  interval: 15m
+  releaseName: ollama
+  values:
+    runtimeClassName: nvidia
+    ollama:
+      gpu:
+        # -- Enable GPU integration
+        enabled: true
+        
+        # -- GPU type: 'nvidia' or 'amd'
+        type: 'nvidia'
+        
+        # -- Specify the number of GPU to 1
+        number: 1
+
+        nvidiaResource: "nvidia.com/gpu-all"
+       
+      # -- List of models to pull at container startup
+      models:
+        create:
+          - name: qwen3.5:9b-ctx32768
+            template: |
+              FROM qwen3.5:9b
+              PARAMETER num_ctx 32768
+        run:
+          - qwen3.5:9b-ctx32768
+
+    ingress:
+      enabled: true
+      annotations:
+        cert-manager.io/cluster-issuer: "letsencrypt-prod"
+        traefik.ingress.kubernetes.io/router.tls: "true"
+        traefik.ingress.kubernetes.io/router.entrypoints: websecure
+      hosts:
+      - host: ollama.michaelthomson.dev
+        paths:
+          - path: /
+            pathType: Prefix
+      path: /
+      tls:
+        - secretName: ollama-tls
+          hosts:
+            - ollama.michaelthomson.dev

apps/ollama/repository.yaml

@@ -0,0 +1,8 @@
+apiVersion: source.toolkit.fluxcd.io/v1
+kind: HelmRepository
+metadata:
+  name: otwld
+  namespace: ollama
+spec:
+  interval: 15m
+  url: https://helm.otwld.com/

apps/open-webui/release.yaml

@@ -0,0 +1,27 @@
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: open-webui
+  namespace: open-webui
+spec:
+  chart:
+    spec:
+      chart: open-webui
+      version: 12.x
+      sourceRef:
+        kind: HelmRepository
+        name: open-webui
+  interval: 15m
+  releaseName: open-webui
+  values:
+    ollama:
+      enabled: false
+    ingress:
+      enabled: true
+      annotations:
+        cert-manager.io/cluster-issuer: "letsencrypt-prod"
+        traefik.ingress.kubernetes.io/router.tls: "true"
+        traefik.ingress.kubernetes.io/router.entrypoints: websecure
+      host: "chat.michaelthomson.dev" # update to your real domain
+      tls: true
+      existingSecret: open-webui-tls

apps/open-webui/repository.yaml

@@ -0,0 +1,8 @@
+apiVersion: source.toolkit.fluxcd.io/v1
+kind: HelmRepository
+metadata:
+  name: open-webui
+  namespace: open-webui
+spec:
+  interval: 15m
+  url: https://helm.openwebui.com/

bootstrap/apps/kustomization-ollama.yaml

@@ -0,0 +1,19 @@
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: ollama
+  namespace: flux-system
+spec:
+  interval: 1m
+  path: ./apps/ollama
+  prune: true # remove any elements later removed from the above path
+  wait: true
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+  decryption:
+    provider: sops
+    secretRef:
+      name: sops-age
+  dependsOn:
+    - name: infra-configs

bootstrap/apps/kustomization-open-webui.yaml

@@ -0,0 +1,19 @@
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: open-webui
+  namespace: flux-system
+spec:
+  interval: 1m
+  path: ./apps/open-webui
+  prune: true # remove any elements later removed from the above path
+  wait: true
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+  decryption:
+    provider: sops
+    secretRef:
+      name: sops-age
+  dependsOn:
+    - name: infra-configs

infrastructure/namespaces/namespace-ollama.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: ollama

infrastructure/namespaces/namespace-open-webui.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: open-webui