From 6efffb3b9a8b1b58877c8d6d83005f872cee4cd2 Mon Sep 17 00:00:00 2001
From: cindyz <cindyz@anyscale.com>
Date: Thu, 7 Sep 2023 18:48:05 +0000
Subject: [PATCH] add yaml

Signed-off-by: cindyz <cindyz@anyscale.com>
---
 .../config/samples/ray-service.text-ml.yaml   | 94 +++++++++++++++++++
 1 file changed, 94 insertions(+)
 create mode 100644 ray-operator/config/samples/ray-service.text-ml.yaml

diff --git a/ray-operator/config/samples/ray-service.text-ml.yaml b/ray-operator/config/samples/ray-service.text-ml.yaml
new file mode 100644
index 00000000000..ea034cdf09c
--- /dev/null
+++ b/ray-operator/config/samples/ray-service.text-ml.yaml
@@ -0,0 +1,94 @@
+# Make sure to increase resource requests and limits before using this example in production.
+# For examples with more realistic resource configuration, see
+# ray-cluster.complete.large.yaml and
+# ray-cluster.autoscaler.large.yaml.
+apiVersion: ray.io/v1alpha1
+kind: RayService
+metadata:
+  name: rayservice-sample
+spec:
+  serviceUnhealthySecondThreshold: 900 # Config for the health check threshold for Ray Serve applications. Default value is 900.
+  deploymentUnhealthySecondThreshold: 300 # Config for the health check threshold for Ray dashboard agent. Default value is 300.
+  # serveConfigV2 takes a yaml multi-line scalar, which should be a Ray Serve multi-application config. See https://docs.ray.io/en/latest/serve/multi-app.html.
+  # Only one of serveConfig and serveConfigV2 should be used.
+  serveConfigV2: |
+    applications:
+      - name: text_ml_app
+        import_path: text_ml.app
+        route_prefix: /summarize_translate
+        runtime_env:
+          working_dir: "https://github.com/ray-project/serve_config_examples/archive/36862c251615e258a58285934c7c41cffd1ee3b7.zip"
+          pip:
+            - torch
+            - transformers
+        deployments:
+          - name: Translator
+            num_replicas: 1
+            ray_actor_options:
+              num_cpus: 0.2
+            user_config:
+              language: german
+          - name: Summarizer
+            num_replicas: 1
+            ray_actor_options:
+              num_cpus: 0.2
+  rayClusterConfig:
+    rayVersion: '2.6.3' # should match the Ray version in the image of the containers
+    ######################headGroupSpecs#################################
+    # Ray head pod template.
+    headGroupSpec:
+      # The `rayStartParams` are used to configure the `ray start` command.
+      # See https://github.com/ray-project/kuberay/blob/master/docs/guidance/rayStartParams.md for the default settings of `rayStartParams` in KubeRay.
+      # See https://docs.ray.io/en/latest/cluster/cli.html#ray-start for all available options in `rayStartParams`.
+      rayStartParams:
+        dashboard-host: '0.0.0.0'
+      #pod template
+      template:
+        spec:
+          containers:
+            - name: ray-head
+              image: rayproject/ray:2.6.3
+              resources:
+                limits:
+                  cpu: 2
+                  memory: 2Gi
+                requests:
+                  cpu: 2
+                  memory: 2Gi
+              ports:
+                - containerPort: 6379
+                  name: gcs-server
+                - containerPort: 8265 # Ray dashboard
+                  name: dashboard
+                - containerPort: 10001
+                  name: client
+                - containerPort: 8000
+                  name: serve
+    workerGroupSpecs:
+      # the pod replicas in this group typed worker
+      - replicas: 1
+        minReplicas: 1
+        maxReplicas: 5
+        # logical group name, for this called small-group, also can be functional
+        groupName: small-group
+        # The `rayStartParams` are used to configure the `ray start` command.
+        # See https://github.com/ray-project/kuberay/blob/master/docs/guidance/rayStartParams.md for the default settings of `rayStartParams` in KubeRay.
+        # See https://docs.ray.io/en/latest/cluster/cli.html#ray-start for all available options in `rayStartParams`.
+        rayStartParams: {}
+        #pod template
+        template:
+          spec:
+            containers:
+              - name: ray-worker # must consist of lower case alphanumeric characters or '-', and must start and end with an alphanumeric character (e.g. 'my-name',  or '123-abc'
+                image: rayproject/ray:2.6.3
+                lifecycle:
+                  preStop:
+                    exec:
+                      command: ["/bin/sh","-c","ray stop"]
+                resources:
+                  limits:
+                    cpu: "1"
+                    memory: "2Gi"
+                  requests:
+                    cpu: "500m"
+                    memory: "2Gi"