Fix some argo lint errors in examples folder (#1244)

**Pull Request Checklist** - [ ] ~~Fixes~~ #1163 - [ ] ~~Tests added~~ - [ ] ~~Documentation/examples added~~ - [x] [Good commit messages](https://cbea.ms/git-commit/) and/or PR title **Description of PR** Fixed argo lint errors in following dirs: - examples/workflows/use-case - examples/workflows/scripts - examples/workflows/misc --------- Signed-off-by: Ukjae Jeong <[email protected]>
argoproj-labs · Oct 21, 2024 · 3266a5b · 3266a5b
1 parent e7ed95b
commit 3266a5b
Show file tree

Hide file tree

Showing 33 changed files with 110 additions and 76 deletions.
diff --git a/docs/examples/workflows/misc/data.md b/docs/examples/workflows/misc/data.md
@@ -16,7 +16,7 @@
         Workflow,
     )
 
-    with Workflow(generate_name="data-") as w:
+    with Workflow(generate_name="data-", entrypoint="list-log-files") as w:
         Data(
             name="list-log-files",
             source=S3Artifact(name="test-bucket", bucket="my-bucket"),
@@ -33,6 +33,7 @@
     metadata:
       generateName: data-
     spec:
+      entrypoint: list-log-files
       templates:
       - data:
           source:

diff --git a/docs/examples/workflows/misc/env.md b/docs/examples/workflows/misc/env.md
@@ -21,6 +21,7 @@
 
     with Workflow(generate_name="secret-env-from-", entrypoint="whalesay") as w:
         whalesay = Container(
+            name="whalesay",
             image="docker/whalesay:latest",
             command=["cowsay"],
             env_from=[
@@ -76,5 +77,6 @@
               optional: false
             prefix: abc
           image: docker/whalesay:latest
+        name: whalesay
     ```
 
diff --git a/docs/examples/workflows/misc/env_from.md b/docs/examples/workflows/misc/env_from.md
@@ -12,6 +12,7 @@
 
     with Workflow(generate_name="secret-env-from-", entrypoint="whalesay") as w:
         whalesay = Container(
+            name="whalesay",
             image="docker/whalesay:latest",
             command=["cowsay"],
             env_from=[
@@ -44,5 +45,6 @@
               optional: false
             prefix: abc
           image: docker/whalesay:latest
+        name: whalesay
     ```
 
diff --git a/docs/examples/workflows/misc/http.md b/docs/examples/workflows/misc/http.md
@@ -11,10 +11,10 @@
     from hera.expr import g
     from hera.workflows import HTTP, Parameter, Workflow
 
-    with Workflow(generate_name="http-") as w:
+    with Workflow(generate_name="http-", entrypoint="http") as w:
         HTTP(
             name="http",
-            inputs=[Parameter(name="url")],
+            inputs=[Parameter(name="url", value="https://example.com")],
             timeout_seconds=20,
             url=f"{g.inputs.parameters.url:$}",
             method="GET",
@@ -32,6 +32,7 @@
     metadata:
       generateName: http-
     spec:
+      entrypoint: http
       templates:
       - http:
           body: test body
@@ -45,6 +46,7 @@
         inputs:
           parameters:
           - name: url
+            value: https://example.com
         name: http
     ```
 
diff --git a/docs/examples/workflows/misc/suspend.md b/docs/examples/workflows/misc/suspend.md
@@ -10,7 +10,7 @@
     ```python linenums="1"
     from hera.workflows import Parameter, Suspend, Workflow
 
-    with Workflow(generate_name="suspend-") as w:
+    with Workflow(generate_name="suspend-", entrypoint="suspend-without-duration") as w:
         Suspend(name="suspend-without-duration")
         Suspend(name="suspend-with-duration", duration=30)
         Suspend(
@@ -31,6 +31,7 @@
     metadata:
       generateName: suspend-
     spec:
+      entrypoint: suspend-without-duration
       templates:
       - name: suspend-without-duration
         suspend: {}

diff --git a/docs/examples/workflows/scripts/callable_script.md b/docs/examples/workflows/scripts/callable_script.md
@@ -92,7 +92,7 @@
         return Output(output=[annotated_input_value])
 
 
-    with Workflow(name="my-workflow") as w:
+    with Workflow(name="my-workflow", entrypoint="my-steps") as w:
         with Steps(name="my-steps") as s:
             my_function(arguments={"input": Input(a=2, b="bar", c=42)})
             str_function(arguments={"input": serialize(Input(a=2, b="bar", c=42))})
@@ -109,6 +109,7 @@
     metadata:
       name: my-workflow
     spec:
+      entrypoint: my-steps
       templates:
       - name: my-steps
         steps:

diff --git a/docs/examples/workflows/scripts/callable_script_v1.md b/docs/examples/workflows/scripts/callable_script_v1.md
@@ -95,7 +95,7 @@
         return Output(output=[annotated_input_value])
 
 
-    with Workflow(name="my-workflow") as w:
+    with Workflow(name="my-workflow", entrypoint="my-steps") as w:
         with Steps(name="my-steps") as s:
             my_function(arguments={"input": Input(a=2, b="bar", c=42)})
             str_function(arguments={"input": serialize(Input(a=2, b="bar", c=42))})
@@ -112,6 +112,7 @@
     metadata:
       name: my-workflow
     spec:
+      entrypoint: my-steps
       templates:
       - name: my-steps
         steps:

diff --git a/docs/examples/workflows/use-cases/fine_tune_llama.md b/docs/examples/workflows/use-cases/fine_tune_llama.md
@@ -39,10 +39,10 @@ There are several implicit dependencies in this script:
     NUM_NODES = 4
 
     """`create_ssd_storage_class` defines the K8s storage class required for an ssd that's created dynamically.
- 
+
     K8s will create the necessary PersistentVolumeClaim and PersistentVolume resources when a pod requests a volume
-    rather than when the PVC/PV are _defined_. This helps avoid the risk of pod + volume zone mismatches. Note that this 
-    was tested in GCP / GKE specifically. If you have a different cloud provider you have to change the `provisioner` 
+    rather than when the PVC/PV are _defined_. This helps avoid the risk of pod + volume zone mismatches. Note that this
+    was tested in GCP / GKE specifically. If you have a different cloud provider you have to change the `provisioner`
     field.
     """
     create_ssd_storage_class = Resource(
@@ -144,7 +144,7 @@ There are several implicit dependencies in this script:
 
     """The delete resource removes the etcd client load balancer and the stateful set.
 
-    Useful for cases when you want to dynamically spin up an etcd cluster and then delete it after the client application 
+    Useful for cases when you want to dynamically spin up an etcd cluster and then delete it after the client application
     is done.
     """
     delete_etcd_resources = Resource(
@@ -244,8 +244,6 @@ There are several implicit dependencies in this script:
                 mount_path="/kubecon_na_23_llama2_finetune/finetune",
                 name="{{inputs.parameters.node-vol}}",
             ),
-            # in addition, we set a volume mount for the empty dir volume that we use for communication between GPUs
-            m.VolumeMount(mount_path="/dev/shm", name="gpu-comm"),
         ],
     )
 
@@ -540,8 +538,6 @@ There are several implicit dependencies in this script:
             name: '{{inputs.parameters.node-vol}}'
           - mountPath: /dev/shm
             name: gpu-comm
-          - mountPath: /dev/shm
-            name: gpu-comm
         inputs:
           parameters:
           - name: rdvz-id

diff --git a/docs/examples/workflows/use-cases/map_reduce.md b/docs/examples/workflows/use-cases/map_reduce.md
@@ -34,7 +34,10 @@ See the upstream example [here](https://github.com/argoproj/argo-workflows/blob/
 
     @script(
         image="python:alpine3.6",
-        inputs=Artifact(name="part", path="/mnt/in/part.json"),
+        inputs=[
+            Parameter(name="part_id"),
+            Artifact(name="part", path="/mnt/in/part.json"),
+        ],
         outputs=S3Artifact(
             name="part",
             path="/mnt/out/part.json",
@@ -76,10 +79,13 @@ See the upstream example [here](https://github.com/argoproj/argo-workflows/blob/
 
     with Workflow(generate_name="map-reduce-", entrypoint="main", arguments=Parameter(name="num_parts", value="4")) as w:
         with DAG(name="main"):
-            s = split(arguments=Parameter(name="num_parts", value="{{workflow.parameters.numParts}}"))
+            s = split(arguments=Parameter(name="num_parts", value="{{workflow.parameters.num_parts}}"))
             m = map_(
                 with_param=s.result,
-                arguments=S3Artifact(name="part", key="{{workflow.name}}/parts/{{item}}.json"),
+                arguments=[
+                    Parameter(name="part_id", value="{{item}}"),
+                    S3Artifact(name="part", key="{{workflow.name}}/parts/{{item}}.json"),
+                ],
             )
             s >> m >> reduce()
     ```
@@ -103,14 +109,17 @@ See the upstream example [here](https://github.com/argoproj/argo-workflows/blob/
           - arguments:
               parameters:
               - name: num_parts
-                value: '{{workflow.parameters.numParts}}'
+                value: '{{workflow.parameters.num_parts}}'
             name: split
             template: split
           - arguments:
               artifacts:
               - name: part
                 s3:
                   key: '{{workflow.name}}/parts/{{item}}.json'
+              parameters:
+              - name: part_id
+                value: '{{item}}'
             depends: split
             name: map-
             template: map-
@@ -156,6 +165,8 @@ See the upstream example [here](https://github.com/argoproj/argo-workflows/blob/
           artifacts:
           - name: part
             path: /mnt/in/part.json
+          parameters:
+          - name: part_id
         name: map-
         outputs:
           artifacts:

diff --git a/docs/examples/workflows/use-cases/spacy_inference_pipeline.md b/docs/examples/workflows/use-cases/spacy_inference_pipeline.md
@@ -111,13 +111,13 @@ Step 2: Performs inference on the dataset in the volume path /mnt/data using Spa
 
 
     with Workflow(
-        generate_name="spacy_inference_pipeline-",
-        entrypoint="spacy_inference_pipeline",
+        generate_name="spacy-inference-pipeline-",
+        entrypoint="spacy-inference-pipeline",
         volumes=[Volume(name="data-dir", size="1Gi", mount_path="/mnt/data")],
         service_account_name="hera",
         namespace="argo",
     ) as w:
-        with Steps(name="spacy_inference_pipeline") as steps:
+        with Steps(name="spacy-inference-pipeline") as steps:
             data_prep(name="data-prep")
             inference_spacy(name="inference-spacy")
     ```
@@ -128,13 +128,13 @@ Step 2: Performs inference on the dataset in the volume path /mnt/data using Spa
     apiVersion: argoproj.io/v1alpha1
     kind: Workflow
     metadata:
-      generateName: spacy_inference_pipeline-
+      generateName: spacy-inference-pipeline-
       namespace: argo
     spec:
-      entrypoint: spacy_inference_pipeline
+      entrypoint: spacy-inference-pipeline
       serviceAccountName: hera
       templates:
-      - name: spacy_inference_pipeline
+      - name: spacy-inference-pipeline
         steps:
         - - name: data-prep
             template: data-prep

diff --git a/docs/examples/workflows/use-cases/spark.md b/docs/examples/workflows/use-cases/spark.md
@@ -15,7 +15,7 @@ compares a regular Pandas dataframe with a Spark dataframe. Inspired by: https:/
 
 
     @script(image="jupyter/pyspark-notebook:latest", resources=Resources(cpu_request=4, memory_request="8Gi"))
-    def spark(n: int) -> None:
+    def spark(num_data: int) -> None:
         import random
         import subprocess
         import time
@@ -33,7 +33,7 @@ compares a regular Pandas dataframe with a Spark dataframe. Inspired by: https:/
         spark = SparkSession.builder.master("local[1]").appName("my-spark-example-running-in-hera.com").getOrCreate()
 
         # let's compare a regular dataframe vs a spark dataframe! First, we define the data to use
-        data, columns = [random.randint(0, n) for _ in range(n)], ["value"]
+        data, columns = [random.randint(0, num_data) for _ in range(num_data)], ["value"]
 
         # as a very simple and naive comparison, let's print out the average, min, and max of both dataframes
         # and now let's create a regular Pandas dataframe
@@ -58,8 +58,8 @@ compares a regular Pandas dataframe with a Spark dataframe. Inspired by: https:/
 
     with Workflow(generate_name="spark-", entrypoint="d") as w:
         with DAG(name="d"):
-            for i, n in enumerate([1_000, 10_000, 100_000, 1_000_000, 10_000_000, 100_000_000]):
-                spark(name="spark-{i}".format(i=i), arguments={"n": n})
+            for i, num_data in enumerate([1_000, 10_000, 100_000, 1_000_000, 10_000_000, 100_000_000]):
+                spark(name="spark-{i}".format(i=i), arguments={"num_data": num_data})
     ```
 
 === "YAML"
@@ -76,44 +76,44 @@ compares a regular Pandas dataframe with a Spark dataframe. Inspired by: https:/
           tasks:
           - arguments:
               parameters:
-              - name: n
+              - name: num_data
                 value: '1000'
             name: spark-0
             template: spark
           - arguments:
               parameters:
-              - name: n
+              - name: num_data
                 value: '10000'
             name: spark-1
             template: spark
           - arguments:
               parameters:
-              - name: n
+              - name: num_data
                 value: '100000'
             name: spark-2
             template: spark
           - arguments:
               parameters:
-              - name: n
+              - name: num_data
                 value: '1000000'
             name: spark-3
             template: spark
           - arguments:
               parameters:
-              - name: n
+              - name: num_data
                 value: '10000000'
             name: spark-4
             template: spark
           - arguments:
               parameters:
-              - name: n
+              - name: num_data
                 value: '100000000'
             name: spark-5
             template: spark
         name: d
       - inputs:
           parameters:
-          - name: n
+          - name: num_data
         name: spark
         script:
           command:
@@ -128,8 +128,8 @@ compares a regular Pandas dataframe with a Spark dataframe. Inspired by: https:/
             import sys
             sys.path.append(os.getcwd())
             import json
-            try: n = json.loads(r'''{{inputs.parameters.n}}''')
-            except: n = r'''{{inputs.parameters.n}}'''
+            try: num_data = json.loads(r'''{{inputs.parameters.num_data}}''')
+            except: num_data = r'''{{inputs.parameters.num_data}}'''
 
             import random
             import subprocess
@@ -138,7 +138,7 @@ compares a regular Pandas dataframe with a Spark dataframe. Inspired by: https:/
             import pandas as pd
             from pyspark.sql import SparkSession
             spark = SparkSession.builder.master('local[1]').appName('my-spark-example-running-in-hera.com').getOrCreate()
-            (data, columns) = ([random.randint(0, n) for _ in range(n)], ['value'])
+            (data, columns) = ([random.randint(0, num_data) for _ in range(num_data)], ['value'])
             pandas_df = pd.DataFrame(data=data, columns=columns)
             start = time.time()
             pandas_result = pandas_df.describe()

diff --git a/examples/workflows/misc/data.py b/examples/workflows/misc/data.py
@@ -6,7 +6,7 @@
     Workflow,
 )
 
-with Workflow(generate_name="data-") as w:
+with Workflow(generate_name="data-", entrypoint="list-log-files") as w:
     Data(
         name="list-log-files",
         source=S3Artifact(name="test-bucket", bucket="my-bucket"),

diff --git a/examples/workflows/misc/data.yaml b/examples/workflows/misc/data.yaml
@@ -3,6 +3,7 @@ kind: Workflow
 metadata:
   generateName: data-
 spec:
+  entrypoint: list-log-files
   templates:
   - data:
       source:

diff --git a/examples/workflows/misc/env-from.yaml b/examples/workflows/misc/env-from.yaml
@@ -18,3 +18,4 @@ spec:
           optional: false
         prefix: abc
       image: docker/whalesay:latest
+    name: whalesay
diff --git a/examples/workflows/misc/env.py b/examples/workflows/misc/env.py
@@ -11,6 +11,7 @@
 
 with Workflow(generate_name="secret-env-from-", entrypoint="whalesay") as w:
     whalesay = Container(
+        name="whalesay",
         image="docker/whalesay:latest",
         command=["cowsay"],
         env_from=[

diff --git a/examples/workflows/misc/env.yaml b/examples/workflows/misc/env.yaml
@@ -35,3 +35,4 @@ spec:
           optional: false
         prefix: abc
       image: docker/whalesay:latest
+    name: whalesay