add ollama [ci skip]

modules/kubernetes/ollama/main.tf

@@ -46,16 +46,113 @@ resource "kubernetes_persistent_volume" "ollama-pv" {
   }
 }
 
-resource "helm_release" "ollama" {
+# resource "helm_release" "ollama" {
-  namespace = "ollama"
+#   namespace = "ollama"
-  name      = "ollama"
+#   name      = "ollama"
 
-  repository = "https://otwld.github.io/ollama-helm/"
+#   repository = "https://otwld.github.io/ollama-helm/"
-  chart      = "ollama"
+#   chart      = "ollama"
-  atomic     = true
+#   atomic     = true
 
-  values  = [templatefile("${path.module}/values.yaml", {})]
+#   values  = [templatefile("${path.module}/values.yaml", {})]
-  timeout = 2400
+#   timeout = 2400
+# }
+
+
+resource "kubernetes_deployment" "ollama" {
+  metadata {
+    name      = "ollama"
+    namespace = "ollama"
+    labels = {
+      app = "ollama"
+    }
+  }
+  spec {
+    replicas = 1
+    selector {
+      match_labels = {
+        app = "ollama"
+      }
+    }
+    template {
+      metadata {
+        labels = {
+          app = "ollama"
+        }
+      }
+      spec {
+        container {
+          image = "ollama/ollama:latest"
+          name  = "ollama"
+          env {
+            name  = "OLLAMA_HOST"
+            value = "0.0.0.0:11434"
+          }
+          env {
+            name  = "PATH"
+            value = "/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
+          }
+          env {
+            name  = "OLLAMA_KEEP_ALIVE"
+            value = "1h"
+          }
+
+          port {
+            container_port = 11434
+          }
+          volume_mount {
+            name       = "ollama-data"
+            mount_path = "/root/.ollama"
+          }
+          resources {
+            limits = {
+              "nvidia.com/gpu" = "1"
+            }
+          }
+        }
+        volume {
+          name = "ollama-data"
+          nfs {
+            path   = "/mnt/main/ollama"
+            server = "10.0.10.15"
+          }
+        }
+      }
+    }
+  }
+}
+
+resource "kubernetes_service" "ollama" {
+  metadata {
+    name      = "ollama"
+    namespace = "ollama"
+    labels = {
+      app = "ollama"
+    }
+  }
+
+  spec {
+    selector = {
+      app = "ollama"
+    }
+    port {
+      name = "http"
+      port = 11434
+    }
+  }
+}
+
+# Allow ollama to be connected to from external apps
+module "ollama-ingress" {
+  source                  = "../ingress_factory"
+  namespace               = "ollama"
+  name                    = "ollama-server"
+  service_name            = "ollama"
+  root_domain             = "viktorbarzin.lan"
+  tls_secret_name         = var.tls_secret_name
+  allow_local_access_only = true
+  ssl_redirect            = false
+  port                    = 11434
 }
 
 # Web UI
@@ -86,7 +183,7 @@ resource "kubernetes_deployment" "ollama-ui" {
           name  = "ollama-ui"
           env {
             name  = "OLLAMA_BASE_URL"
-            value = "http://ollama:11434"
+            value = "http://ollama.ollama.svc.cluster.local:11434"
           }
 
           port {

modules/kubernetes/ollama/values.yaml

@@ -1,7 +1,7 @@
 ollama:
   gpu:
     # -- Enable GPU integration
-    enabled: false
+    enabled: true
 
     # -- GPU type: 'nvidia' or 'amd'
     type: "nvidia"