ENH: Add a "hello world" test script (#948)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-08-13 10:59:20 +01:00 · 2024-08-13 10:59:20 +01:00 · ca7a4d8f15
--- a/create_and_lock_environment.sh
+++ b/create_and_lock_environment.sh
@ -1,5 +1,17 @@
 #!/bin/bash

+# Read input file from argument 1, default to primary_deps.yml
+input_file="primary_deps.yml"
+output_file="environment.yml"
+if [ "$#" -gt 0 ]; then
+    input_file=$1
+    echo "Using input file: $input_file"
+fi
+if [ "$#" -gt 1 ]; then
+    output_file=$2
+    echo "Using output file: $output_file"
+fi
+
 os_name=$(uname)
 if [[ ! $os_name == *"Linux"* ]]; then
    echo "ERROR: cannot run environment locking in non-linux environment. Windows users can do this using WSL - https://docs.microsoft.com/en-us/windows/wsl/install"
@ -9,7 +21,7 @@ else
 fi

 # get environment name from primary dependencies YAML file
-name_line="$(cat primary_deps.yml | grep 'name:')"
+name_line="$(cat $input_file | grep 'name:')"
 IFS=':' read -ra name_arr <<< "$name_line"
 env_name="${name_arr[1]}"

@ -19,7 +31,7 @@ echo "Building Conda environment: $env_name"
 export CONDA_ALWAYS_YES="true"
 conda activate base
 conda env remove --name $env_name
-conda env create --file primary_deps.yml
+conda env create --file $input_file

 # export new environment to environment.yml
 echo "Exporting environment $env_name to environment.tmp1"
@ -39,7 +51,7 @@ while IFS='' read -r line; do
    fi
 done < environment.tmp1 > environment.tmp2
 echo "Creating final environment.yml with warning line"
-echo "# WARNING - DO NOT EDIT THIS FILE MANUALLY" > environment.yml
-echo "# To update, please modify 'primary_deps.yml' and then run the locking script 'create_and_lock_environment.sh'">> environment.yml
-cat environment.tmp2 >> environment.yml
+echo "# WARNING - DO NOT EDIT THIS FILE MANUALLY" > $output_file
+echo "# To update, please modify '$input_file' and then run the locking script 'create_and_lock_environment.sh'">> $output_file
+cat environment.tmp2 >> $output_file
 rm environment.tmp1 environment.tmp2
--- a/hi-ml-azure/Makefile
+++ b/hi-ml-azure/Makefile
@ -87,3 +87,22 @@ test_all: pip_test call_flake8 call_mypy call_pytest_and_coverage
 example: pip_local
 	echo 'edit src/health/azure/examples/elevate_this.py to reference your compute_cluster_name'
 	cd src/health/azure/examples; python elevate_this.py --azureml --message 'running example from makefile'
+
+# Create a local Conda environment
+env:
+	conda env create --file environment.yml
+
+# Install Conda from scratch
+conda:
+	wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
+	bash Miniconda3-latest-Linux-x86_64.sh -b
+	rm Miniconda3-latest-Linux-x86_64.sh
+	conda update -y -n base conda
+	conda install -y -n base conda-libmamba-solver
+	conda config --set solver libmamba
+
+env_hello_world_lock:
+	../create_and_lock_environment.sh primary_deps_hello_world.yml environment_hello_world.yml
+
+env_hello_world:
+	conda env create --file environment_hello_world.yml
--- a/hi-ml-azure/README.md
+++ b/hi-ml-azure/README.md
@ -0,0 +1,68 @@
+# HI-ML-Azure
+
+This folder contains the source code for PyPI package `hi-ml-azure`.
+
+## Testing an AzureML setup
+
+To test if your AzureML setup is correct, follow these steps to setup up Python on your local machine:
+
+- Change the working directory to `<repo_root>/hi-ml-azure`
+- Run `make conda` to install MiniConda
+- Run `make env_hello_world` to build a simple Python environment with the necessary packages
+- Run `conda activate hello_world` to activate the environment
+
+Then follow these steps to test the AzureML setup:
+
+- Download the `config.json` file from your AzureML workspace and place it in folder `<repo_root>/hi-ml-azure`
+  There is a `Download config.json` button once you expand the dropdown menu on the top-right of your AzureML workspace.
+  This is not in the core Azure portal, but only visible once you open `AzureML Studio` from the portal.
+  The file `config.json` should look like this:
+
+  ```json
+  {
+    "subscription_id": "your-subscription-id",
+    "resource_group": "your-resource-group",
+    "workspace_name": "your-workspace-name"
+  }
+  ```
+
+- To run the test script, you must have created a compute cluster in your AzureML workspace.
+  You can do this by clicking on `Compute` in the left-hand menu, selecting the "Compute clusters" tab, and
+  then `+ New` to create a new compute cluster. To run the test script, it is sufficient to use a cheap CPU-only VM
+  type, like `STANDARD_DS3_V2`. Give the cluster a name, and use the same name in the script below.
+- Log into Azure by running `az login` in the terminal.
+- Start the test script via `python hello_world.py --cluster <your_compute_cluster_name>`.
+  If successful, this will print out "Successfully queued run..." at the end, and a "Run URL" that points to your job.
+- Open the "Run URL" that was printed on the console in the browser to monitor the run.
+
+## Testing access to OpenAI from an AzureML job
+
+Requirements:
+
+- Your compute cluster has a managed identity assigned.
+- You have an OpenAI deployment URL and model name.
+- The managed identity has "Cognitive Services OpenAI User" access to the OpenAI deployment.
+
+Run the following script to test access to OpenAI from an AzureML job:
+
+```python
+python hello_world.py --cluster <your_compute_cluster_name> --openai_url <URL> --openai_model <Model>
+```
+
+If successful, this will print out the response from OpenAI.
+
+## Testing access to datasets
+
+Requirements:
+
+- You have a datastore registered in your AzureML workspace
+- You have a dataset registered in your AzureML workspace. For example, upload an empty file to a folder `hello_world`
+  in your storage account, and register this folder as a dataset called `hello_world` in your AzureML workspace.
+- You have a folder in your storage account for an output dataset. For that, upload an empty file to a folder
+  `hello_world_output` and register this folder as a dataset `hello_world_output` in your AzureML workspace.
+
+Then run the following script to test access to datasets:
+
+```python
+python hello_world.py --cluster <your_compute_cluster_name> --input_dataset hello_world --output_dataset hello_world_output
+```
--- a/hi-ml-azure/environment_hello_world.yml
+++ b/hi-ml-azure/environment_hello_world.yml
@ -0,0 +1,283 @@
+# WARNING - DO NOT EDIT THIS FILE MANUALLY
+# To update, please modify 'primary_deps_openai.yml' and then run the locking script 'create_and_lock_environment.sh'
+name: hello_world
+channels:
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - _openmp_mutex=5.1=1_gnu
+  - ca-certificates=2024.3.11=h06a4308_0
+  - ld_impl_linux-64=2.38=h1181459_1
+  - libffi=3.4.4=h6a678d5_1
+  - libgcc-ng=11.2.0=h1234567_1
+  - libgomp=11.2.0=h1234567_1
+  - libstdcxx-ng=11.2.0=h1234567_1
+  - ncurses=6.4=h6a678d5_0
+  - openssl=3.0.14=h5eee18b_0
+  - pip=23.3.1=py39h06a4308_0
+  - python=3.9.18
+  - readline=8.2=h5eee18b_0
+  - setuptools=69.5.1=py39h06a4308_0
+  - sqlite=3.45.3=h5eee18b_0
+  - tk=8.6.14=h39e8969_0
+  - wheel=0.43.0=py39h06a4308_0
+  - xz=5.4.6=h5eee18b_1
+  - zlib=1.2.13=h5eee18b_1
+  - pip:
+      - absl-py==2.1.0
+      - adal==1.2.7
+      - alembic==1.13.2
+      - aniso8601==9.0.1
+      - annotated-types==0.7.0
+      - antlr4-python3-runtime==4.13.1
+      - anyio==4.4.0
+      - applicationinsights==0.11.10
+      - argcomplete==3.3.0
+      - attrs==23.2.0
+      - azure-ai-ml==1.17.0
+      - azure-appconfiguration==1.1.1
+      - azure-batch==14.2.0
+      - azure-cli==2.61.0
+      - azure-cli-core==2.61.0
+      - azure-cli-telemetry==1.1.0
+      - azure-common==1.1.28
+      - azure-core==1.30.2
+      - azure-cosmos==3.2.0
+      - azure-data-tables==12.4.0
+      - azure-datalake-store==0.0.53
+      - azure-graphrbac==0.60.0
+      - azure-identity==1.17.1
+      - azure-keyvault-administration==4.4.0b2
+      - azure-keyvault-certificates==4.7.0
+      - azure-keyvault-keys==4.9.0b3
+      - azure-keyvault-secrets==4.7.0
+      - azure-mgmt-advisor==9.0.0
+      - azure-mgmt-apimanagement==4.0.0
+      - azure-mgmt-appconfiguration==3.0.0
+      - azure-mgmt-appcontainers==2.0.0
+      - azure-mgmt-applicationinsights==1.0.0
+      - azure-mgmt-authorization==4.0.0
+      - azure-mgmt-batch==17.3.0
+      - azure-mgmt-batchai==7.0.0b1
+      - azure-mgmt-billing==6.0.0
+      - azure-mgmt-botservice==2.0.0
+      - azure-mgmt-cdn==12.0.0
+      - azure-mgmt-cognitiveservices==13.5.0
+      - azure-mgmt-compute==31.0.0
+      - azure-mgmt-containerinstance==10.1.0
+      - azure-mgmt-containerregistry==10.3.0
+      - azure-mgmt-containerservice==30.0.0
+      - azure-mgmt-core==1.4.0
+      - azure-mgmt-cosmosdb==9.4.0
+      - azure-mgmt-databoxedge==1.0.0
+      - azure-mgmt-datalake-nspkg==3.0.1
+      - azure-mgmt-datalake-store==0.5.0
+      - azure-mgmt-datamigration==10.0.0
+      - azure-mgmt-devtestlabs==4.0.0
+      - azure-mgmt-dns==8.0.0
+      - azure-mgmt-eventgrid==10.2.0b2
+      - azure-mgmt-eventhub==10.1.0
+      - azure-mgmt-extendedlocation==1.0.0b2
+      - azure-mgmt-hdinsight==9.0.0
+      - azure-mgmt-imagebuilder==1.3.0
+      - azure-mgmt-iotcentral==10.0.0b2
+      - azure-mgmt-iothub==3.0.0
+      - azure-mgmt-iothubprovisioningservices==1.1.0
+      - azure-mgmt-keyvault==10.3.0
+      - azure-mgmt-kusto==0.3.0
+      - azure-mgmt-loganalytics==13.0.0b4
+      - azure-mgmt-managedservices==1.0.0
+      - azure-mgmt-managementgroups==1.0.0
+      - azure-mgmt-maps==2.0.0
+      - azure-mgmt-marketplaceordering==1.1.0
+      - azure-mgmt-media==9.0.0
+      - azure-mgmt-monitor==5.0.1
+      - azure-mgmt-msi==7.0.0
+      - azure-mgmt-netapp==10.1.0
+      - azure-mgmt-network==25.4.0
+      - azure-mgmt-nspkg==3.0.2
+      - azure-mgmt-policyinsights==1.1.0b4
+      - azure-mgmt-privatedns==1.0.0
+      - azure-mgmt-rdbms==10.2.0b17
+      - azure-mgmt-recoveryservices==3.0.0
+      - azure-mgmt-recoveryservicesbackup==9.1.0
+      - azure-mgmt-redhatopenshift==1.4.0
+      - azure-mgmt-redis==14.3.0
+      - azure-mgmt-resource==23.1.1
+      - azure-mgmt-search==9.1.0
+      - azure-mgmt-security==6.0.0
+      - azure-mgmt-servicebus==8.2.0
+      - azure-mgmt-servicefabric==2.1.0
+      - azure-mgmt-servicefabricmanagedclusters==2.0.0b6
+      - azure-mgmt-servicelinker==1.2.0b2
+      - azure-mgmt-signalr==2.0.0b1
+      - azure-mgmt-sql==4.0.0b16
+      - azure-mgmt-sqlvirtualmachine==1.0.0b5
+      - azure-mgmt-storage==21.1.0
+      - azure-mgmt-synapse==2.1.0b5
+      - azure-mgmt-trafficmanager==1.0.0
+      - azure-mgmt-web==7.2.0
+      - azure-monitor-query==1.2.0
+      - azure-multiapi-storage==1.2.0
+      - azure-nspkg==3.0.2
+      - azure-storage-blob==12.19.0
+      - azure-storage-common==1.4.2
+      - azure-storage-file-datalake==12.14.0
+      - azure-storage-file-share==12.16.0
+      - azure-synapse-accesscontrol==0.5.0
+      - azure-synapse-artifacts==0.18.0
+      - azure-synapse-managedprivateendpoints==0.4.0
+      - azure-synapse-spark==0.2.0
+      - azureml-core==1.56.0
+      - azureml-dataprep==5.1.6
+      - azureml-dataprep-native==41.0.0
+      - azureml-dataprep-rslex==2.22.2
+      - azureml-dataset-runtime==1.56.0
+      - azureml-mlflow==1.56.0
+      - azureml-telemetry==1.56.0
+      - azureml-tensorboard==1.56.0
+      - azureml-train-core==1.56.0
+      - azureml-train-restclients-hyperdrive==1.56.0
+      - backports-tempfile==1.0
+      - backports-weakref==1.0.post1
+      - bcrypt==4.1.3
+      - blinker==1.8.2
+      - cachetools==5.3.3
+      - certifi==2024.6.2
+      - cffi==1.16.0
+      - chardet==5.2.0
+      - charset-normalizer==3.3.2
+      - click==8.1.7
+      - cloudpickle==2.2.1
+      - colorama==0.4.6
+      - conda-merge==0.2.0
+      - contextlib2==21.6.0
+      - contourpy==1.2.1
+      - cryptography==42.0.8
+      - cycler==0.12.1
+      - decorator==5.1.1
+      - deprecated==1.2.14
+      - distro==1.9.0
+      - docker==7.1.0
+      - entrypoints==0.4
+      - exceptiongroup==1.2.1
+      - fabric==3.2.2
+      - flask==3.0.3
+      - fonttools==4.53.0
+      - fusepy==3.0.1
+      - gitdb==4.0.11
+      - gitpython==3.1.43
+      - google-api-core==2.19.1
+      - google-auth==2.30.0
+      - googleapis-common-protos==1.63.2
+      - graphene==3.3
+      - graphql-core==3.2.3
+      - graphql-relay==3.2.0
+      - greenlet==3.0.3
+      - grpcio==1.64.1
+      - gunicorn==22.0.0
+      - h11==0.14.0
+      - httpcore==1.0.5
+      - httpx==0.27.0
+      - humanfriendly==10.0
+      - idna==3.7
+      - importlib-metadata==7.1.0
+      - importlib-resources==6.4.0
+      - invoke==2.2.0
+      - isodate==0.6.1
+      - itsdangerous==2.2.0
+      - javaproperties==0.5.2
+      - jeepney==0.8.0
+      - jinja2==3.1.4
+      - jmespath==1.0.1
+      - joblib==1.4.2
+      - jsondiff==2.0.0
+      - jsonpickle==3.2.2
+      - jsonschema==4.22.0
+      - jsonschema-specifications==2023.12.1
+      - kiwisolver==1.4.5
+      - knack==0.11.0
+      - mako==1.3.5
+      - markdown==3.6
+      - markupsafe==2.1.5
+      - marshmallow==3.21.3
+      - matplotlib==3.9.0
+      - mlflow==2.14.1
+      - mlflow-skinny==2.14.1
+      - msal==1.28.0
+      - msal-extensions==1.2.0b1
+      - msrest==0.7.1
+      - msrestazure==0.6.4
+      - ndg-httpsclient==0.5.1
+      - numpy==1.23.5
+      - oauthlib==3.2.2
+      - openai==1.35.5
+      - opencensus==0.11.4
+      - opencensus-context==0.1.3
+      - opencensus-ext-azure==1.1.13
+      - opencensus-ext-logging==0.1.1
+      - opentelemetry-api==1.25.0
+      - opentelemetry-sdk==1.25.0
+      - opentelemetry-semantic-conventions==0.46b0
+      - packaging==24.1
+      - pandas==2.2.2
+      - param==1.13.0
+      - paramiko==3.4.0
+      - pathspec==0.12.1
+      - pillow==10.3.0
+      - pkginfo==1.11.1
+      - portalocker==2.10.0
+      - proto-plus==1.24.0
+      - protobuf==3.20.3
+      - psutil==5.9.8
+      - pyarrow==15.0.2
+      - pyasn1==0.6.0
+      - pyasn1-modules==0.4.0
+      - pycomposefile==0.0.31
+      - pycparser==2.22
+      - pydantic==2.7.4
+      - pydantic-core==2.18.4
+      - pydash==8.0.1
+      - pygithub==1.59.1
+      - pygments==2.18.0
+      - pyjwt==2.8.0
+      - pynacl==1.5.0
+      - pyopenssl==24.1.0
+      - pyparsing==3.1.2
+      - pysocks==1.7.1
+      - python-dateutil==2.9.0.post0
+      - pytz==2024.1
+      - pyyaml==6.0.1
+      - querystring-parser==1.2.4
+      - referencing==0.35.1
+      - requests==2.32.3
+      - requests-oauthlib==2.0.0
+      - rpds-py==0.18.1
+      - rsa==4.9
+      - ruamel-yaml==0.18.6
+      - ruamel-yaml-clib==0.2.8
+      - scikit-learn==1.5.0
+      - scipy==1.13.1
+      - scp==0.13.6
+      - secretstorage==3.3.3
+      - semver==2.13.0
+      - six==1.16.0
+      - smmap==5.0.1
+      - sniffio==1.3.1
+      - sqlalchemy==2.0.31
+      - sqlparse==0.5.0
+      - sshtunnel==0.1.5
+      - strictyaml==1.7.3
+      - tabulate==0.9.0
+      - tensorboard==2.17.0
+      - tensorboard-data-server==0.7.2
+      - threadpoolctl==3.5.0
+      - tqdm==4.66.4
+      - typing-extensions==4.12.2
+      - tzdata==2024.1
+      - urllib3==2.2.2
+      - websocket-client==1.3.3
+      - werkzeug==3.0.3
+      - wrapt==1.16.0
+      - xmltodict==0.13.0
+      - zipp==3.19.2
--- a/hi-ml-azure/hello_world.py
+++ b/hi-ml-azure/hello_world.py
@ -0,0 +1,146 @@
+#  ------------------------------------------------------------------------------------------
+#  Copyright (c) Microsoft Corporation. All rights reserved.
+#  Licensed under the MIT License (MIT). See LICENSE in the repo root for license information.
+#  ------------------------------------------------------------------------------------------
+"""
+Simple 'hello world' script to elevate to AML using our `submit_to_azure_if_needed` function.
+
+Invoke like this:
+    python hello_world.py --cluster <name_of_compute_cluster>
+
+"""
+import os
+import sys
+from argparse import ArgumentParser
+from typing import Callable, Union
+from pathlib import Path
+from datetime import datetime
+
+from azure.identity import get_bearer_token_provider, AzureCliCredential, ManagedIdentityCredential
+import openai
+
+# Add hi-ml packages to sys.path so that AML can find them
+himl_azure_root = Path(__file__).resolve().parent
+folders_to_add = [himl_azure_root / "src"]
+for folder in folders_to_add:
+    if folder.is_dir():
+        sys.path.insert(0, str(folder))
+
+from health_azure import submit_to_azure_if_needed, DatasetConfig, is_running_in_azure_ml
+from health_azure.logging import logging_to_stdout
+
+# The default scope for the Azure Cognitive Services. Tokens are retrieve from this page, and later used instead
+# of the API key.
+AZURE_COGNITIVE_SERVICES = "https://cognitiveservices.azure.com"
+
+ENV_AZUREML_IDENTITY_ID = "DEFAULT_IDENTITY_CLIENT_ID"
+
+
+def get_credential() -> Union[AzureCliCredential, ManagedIdentityCredential]:
+    """Get the appropriate Azure credential based on the environment. The credential is a managed identity when running
+    in AzureML, otherwise Azure CLI credential."""
+    if is_running_in_azure_ml():
+        return ManagedIdentityCredential(client_id=os.environ[ENV_AZUREML_IDENTITY_ID])
+    return AzureCliCredential()
+
+
+def get_azure_token_provider() -> Callable[[], str]:
+    """Get a token provider for Azure Cognitive Services. The bearer token provider gets authentication tokens and
+    refreshes them automatically upon expiry.
+    """
+    credential = get_credential()
+    credential.get_token(AZURE_COGNITIVE_SERVICES)
+    return get_bearer_token_provider(credential, AZURE_COGNITIVE_SERVICES)
+
+
+def main() -> None:
+    """
+    Write out the given message, in an AzureML 'experiment' if required.
+
+    First call submit_to_azure_if_needed.
+    """
+    parser = ArgumentParser()
+    parser.add_argument("-c", "--cluster", type=str, required=True, help="The name of the compute cluster to run on")
+    parser.add_argument("--openai_url", type=str, required=False, help="The URL of the OpenAI endpoint to use")
+    parser.add_argument("--openai_model", type=str, required=False, help="The OpenAI deployment to use")
+    parser.add_argument("--input_dataset", type=str, required=False, help="The name of the input dataset to enumerate")
+    parser.add_argument("--output_dataset", type=str, required=False, help="The name of the output dataset")
+    args = parser.parse_args()
+    input_datasets: list[DatasetConfig] = []
+    output_datasets: list[DatasetConfig] = []
+    if args.input_dataset:
+        input_datasets.append(DatasetConfig(name=args.input_dataset, use_mounting=True))
+    if args.output_dataset:
+        output_datasets.append(DatasetConfig(name=args.output_dataset, use_mounting=True))
+    logging_to_stdout
+    run_info = submit_to_azure_if_needed(
+        compute_cluster_name=args.cluster,
+        strictly_aml_v1=True,
+        submit_to_azureml=True,
+        workspace_config_file=himl_azure_root / "config.json",
+        snapshot_root_directory=himl_azure_root,
+        input_datasets=input_datasets,
+        output_datasets=output_datasets,
+        conda_environment_file=himl_azure_root / "environment_hello_world.yml",
+    )
+    print("Hello Chris! This is your first successful AzureML run :-)")
+    any_error = False
+    if args.input_dataset:
+        try:
+            input_dataset = run_info.input_datasets[0]
+            assert input_dataset is not None
+            if input_dataset.is_file():
+                print(f"Input dataset is a single file: {input_dataset}")
+            elif input_dataset.is_dir():
+                print(f"Files in input dataset folder {input_dataset}:")
+                for file in input_dataset.glob("*"):
+                    print(file)
+            else:
+                print(f"Input dataset is neither a file nor a folder: {input_dataset}")
+                any_error = True
+        except Exception as e:
+            print(f"Failed to read input dataset: {e}")
+            any_error = True
+    else:
+        print("No input dataset was specified.")
+    if args.output_dataset:
+        try:
+            output_dataset = run_info.output_datasets[0]
+            assert output_dataset is not None
+            timestamp = datetime.utcnow().strftime("%Y-%m-%dT%H%M%S")
+            output_file = output_dataset / f"hello_world_{timestamp}.txt"
+            output_text = f"Calling all dentists, the private song group starts at {timestamp}!"
+            print(f"Writing to output file: {output_text}")
+            output_file.write_text(output_text)
+        except Exception as e:
+            print(f"Failed to write output dataset: {e}")
+            any_error = True
+    else:
+        print("No output dataset was specified..")
+    if args.openai_url and args.openai_model:
+        try:
+            print(f"OpenAI URL: {args.openai_url}")
+            token_provider = get_azure_token_provider()
+            openai.api_version = "2023-12-01-preview"
+            openai.azure_endpoint = args.openai_url
+            openai.azure_ad_token_provider = token_provider
+            prompt = "Write a 4 line poem using the words 'private', 'dentist', 'song' and 'group'. "
+            print(f"Prompt: {prompt}")
+            response = openai.chat.completions.create(
+                model=args.openai_model,
+                messages=[{"role": "user", "content": prompt}],
+                max_tokens=50,
+                temperature=0.8,
+            )
+            content = response.choices[0].message.content
+            print(f"Response from OpenAI: {content}")
+        except Exception as e:
+            print(f"Failed to connect to OpenAI: {e}")
+            any_error = True
+
+    if any_error:
+        raise RuntimeError("There were errors during the run.")
+
+
+if __name__ == "__main__":
+    main()
--- a/hi-ml-azure/primary_deps_hello_world.yml
+++ b/hi-ml-azure/primary_deps_hello_world.yml
@ -0,0 +1,10 @@
+# This environment definition contains all packages required to run the hello_world script
+name: hello_world
+channels:
+  - defaults
+dependencies:
+  - pip=23.3
+  - python=3.9.18
+  - pip:
+      - -r run_requirements.txt
+      - openai