Add ContainerConfig example comment to ir notebooks (#3600)

* Add ContainerConfig example comment to ir notebooks * adding containerConfig md to rest of the notebooks * add containerConfig md and handle missing variantName * rerun pr tests * rerun pr tests * rerun pr tests * rerun pr tests Co-authored-by: Gary Wang <[email protected]>
aws · Oct 3, 2022 · ed1b78c · ed1b78c
1 parent 413abd0
commit ed1b78c
Show file tree

Hide file tree

Showing 5 changed files with 308 additions and 12 deletions.
diff --git a/...nce-recommender/huggingface-inference-recommender/huggingface-inference-recommender.ipynb b/...nce-recommender/huggingface-inference-recommender/huggingface-inference-recommender.ipynb
@@ -513,6 +513,79 @@
     "print(model_package_version_response)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Alternative Option: ContainerConfig\n",
+    "\n",
+    "If you are missing mandatory fields to create an inference recommender job in your model package version like so (this `create_model_package` is missing `Domain`, `Task`, and `SamplePayloadUrl`):\n",
+    "\n",
+    "```\n",
+    "client.create_model_package(\n",
+    "    ModelPackageGroupName=str(model_package_group_name),\n",
+    "    ModelPackageDescription=\"HuggingFace PyTorch Inference Recommender Demo\",\n",
+    "    InferenceSpecification={\n",
+    "        \"Containers\": [\n",
+    "            {\n",
+    "                \"ContainerHostname\": \"huggingface-pytorch\",\n",
+    "                \"Image\": inference_image,\n",
+    "                \"ModelDataUrl\": model_url,\n",
+    "                \"Framework\": ml_framework,\n",
+    "                \"NearestModelName\": model,\n",
+    "                \"Environment\": {\n",
+    "                    \"SAGEMAKER_CONTAINER_LOG_LEVEL\": \"20\",\n",
+    "                    \"SAGEMAKER_PROGRAM\": \"inference.py\",\n",
+    "                    \"SAGEMAKER_REGION\": region,\n",
+    "                    \"SAGEMAKER_SUBMIT_DIRECTORY\": model_url,\n",
+    "                },\n",
+    "            },\n",
+    "        ],\n",
+    "        \"SupportedRealtimeInferenceInstanceTypes\": [\n",
+    "            \"ml.c5.large\",\n",
+    "            \"ml.c5.xlarge\",\n",
+    "            \"ml.c5.2xlarge\",\n",
+    "            \"ml.m5.xlarge\",\n",
+    "            \"ml.m5.2xlarge\",\n",
+    "        ],\n",
+    "        \"SupportedContentTypes\": [\"text/csv\"],\n",
+    "        \"SupportedResponseMIMETypes\": [\"text/csv\"],\n",
+    "    },\n",
+    ")\n",
+    "```\n",
+    "\n",
+    "You may define the fields `Domain`, `Task`, and `SamplePayloadUrl` in the optional field `ContainerConfig` like so:\n",
+    "\n",
+    "```\n",
+    "payload_config = {\n",
+    "    \"SamplePayloadUrl\": sample_payload_url,\n",
+    "}\n",
+    "\n",
+    "container_config = {\n",
+    "    \"Domain\": ml_domain,\n",
+    "    \"Task\": ml_task,\n",
+    "    \"PayloadConfig\": payload_config,\n",
+    "}\n",
+    "```\n",
+    "\n",
+    "And then provide it directly within `create_inference_recommendations_job()` API like so:\n",
+    "\n",
+    "```\n",
+    "default_response = client.create_inference_recommendations_job(\n",
+    "    JobName=str(default_job),\n",
+    "    JobDescription=\"\",\n",
+    "    JobType=\"Default\",\n",
+    "    RoleArn=role,\n",
+    "    InputConfig={\n",
+    "        \"ModelPackageVersionArn\": model_package_arn,\n",
+    "        \"ContainerConfig\": container_config\n",
+    "    },\n",
+    ")\n",
+    "```\n",
+    "\n",
+    "For more information on what else can be provided via `ContainerConfig` please refer to the `CreateInferenceRecommendationsJob` doc here: [CreateInferenceRecommendationsJob](https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateInferenceRecommendationsJob.html)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -621,7 +694,8 @@
     "    for x in inference_recommender_job[\"InferenceRecommendations\"]\n",
     "]\n",
     "df = pd.DataFrame(data)\n",
-    "df.drop(\"VariantName\", inplace=True, axis=1)\n",
+    "dropFilter = df.filter([\"VariantName\"])\n",
+    "df.drop(dropFilter, inplace=True, axis=1)\n",
     "pd.set_option(\"max_colwidth\", 400)"
    ]
   },

diff --git a/sagemaker-inference-recommender/inference-recommender.ipynb b/sagemaker-inference-recommender/inference-recommender.ipynb
@@ -607,6 +607,54 @@
     "sm_client.describe_model_package(ModelPackageName=model_package_arn)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Alternative Option: ContainerConfig\n",
+    "\n",
+    "If you are missing mandatory fields to create an inference recommender job in your model package version like so (this `create_model_package_input_dict` is missing `Domain`, `Task`, and `SamplePayloadUrl`):\n",
+    "\n",
+    "```\n",
+    "create_model_package_input_dict = {\n",
+    "    \"ModelPackageGroupName\": model_package_group_name,\n",
+    "    \"ModelPackageDescription\": model_package_description,\n",
+    "    \"ModelApprovalStatus\": model_approval_status,\n",
+    "}\n",
+    "```\n",
+    "\n",
+    "You may define the fields `Domain`, `Task`, and `SamplePayloadUrl` in the optional field `ContainerConfig` like so:\n",
+    "\n",
+    "```\n",
+    "payload_config = {\n",
+    "    \"SamplePayloadUrl\": sample_payload_url,\n",
+    "}\n",
+    "\n",
+    "container_config = {\n",
+    "    \"Domain\": ml_domain.upper(),\n",
+    "    \"Task\": ml_task.upper(),\n",
+    "    \"PayloadConfig\": payload_config,\n",
+    "}\n",
+    "```\n",
+    "\n",
+    "And then provide it directly within `create_inference_recommendations_job()` API like so:\n",
+    "\n",
+    "```\n",
+    "default_response = client.create_inference_recommendations_job(\n",
+    "    JobName=str(default_job),\n",
+    "    JobDescription=\"\",\n",
+    "    JobType=\"Default\",\n",
+    "    RoleArn=role,\n",
+    "    InputConfig={\n",
+    "        \"ModelPackageVersionArn\": model_package_arn,\n",
+    "        \"ContainerConfig\": container_config\n",
+    "    },\n",
+    ")\n",
+    "```\n",
+    "\n",
+    "For more information on what else can be provided via `ContainerConfig` please refer to the `CreateInferenceRecommendationsJob` doc here: [CreateInferenceRecommendationsJob](https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateInferenceRecommendationsJob.html)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -709,7 +757,8 @@
     "    for x in inference_recommender_job[\"InferenceRecommendations\"]\n",
     "]\n",
     "df = pd.DataFrame(data)\n",
-    "df.drop(\"VariantName\", inplace=True, axis=1)\n",
+    "dropFilter = df.filter([\"VariantName\"])\n",
+    "df.drop(dropFilter, inplace=True, axis=1)\n",
     "pd.set_option(\"max_colwidth\", 400)\n",
     "df.head()"
    ]
@@ -828,7 +877,8 @@
     "    for x in inference_recommender_job[\"InferenceRecommendations\"]\n",
     "]\n",
     "df = pd.DataFrame(data)\n",
-    "df.drop(\"VariantName\", inplace=True, axis=1)\n",
+    "dropFilter = df.filter([\"VariantName\"])\n",
+    "df.drop(dropFilter, inplace=True, axis=1)\n",
     "pd.set_option(\"max_colwidth\", 400)\n",
     "df.head()"
    ]

diff --git a/...r-inference-recommender/sklearn-inference-recommender/sklearn-inference-recommender.ipynb b/...r-inference-recommender/sklearn-inference-recommender/sklearn-inference-recommender.ipynb
@@ -40,8 +40,7 @@
    "execution_count": null,
    "metadata": {
     "collapsed": false,
-    "jupyter": {
-    },
+    "jupyter": {},
     "pycharm": {
      "name": "#%%\n"
     }
@@ -56,8 +55,7 @@
    "execution_count": null,
    "metadata": {
     "collapsed": false,
-    "jupyter": {
-    },
+    "jupyter": {},
     "pycharm": {
      "name": "#%%\n"
     }
@@ -459,6 +457,79 @@
     "print(model_package_version_response)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Alternative Option: ContainerConfig\n",
+    "\n",
+    "If you are missing mandatory fields to create an inference recommender job in your model package version like so (this `create_model_package` is missing `Domain`, `Task`, and `SamplePayloadUrl`):\n",
+    "\n",
+    "```\n",
+    "client.create_model_package(\n",
+    "    ModelPackageGroupName=str(model_package_group_name),\n",
+    "    ModelPackageDescription=\"scikit-learn Inference Recommender Demo\",\n",
+    "    InferenceSpecification={\n",
+    "        \"Containers\": [\n",
+    "            {\n",
+    "                \"ContainerHostname\": \"scikit-learn\",\n",
+    "                \"Image\": inference_image,\n",
+    "                \"ModelDataUrl\": model_url,\n",
+    "                \"Framework\": ml_framework,\n",
+    "                \"NearestModelName\": model,\n",
+    "                \"Environment\": {\n",
+    "                    \"SAGEMAKER_CONTAINER_LOG_LEVEL\": \"20\",\n",
+    "                    \"SAGEMAKER_PROGRAM\": sagemaker_program,\n",
+    "                    \"SAGEMAKER_REGION\": region,\n",
+    "                    \"SAGEMAKER_SUBMIT_DIRECTORY\": sourcedir_url,\n",
+    "                },\n",
+    "            },\n",
+    "        ],\n",
+    "        \"SupportedRealtimeInferenceInstanceTypes\": [\n",
+    "            \"ml.c5.large\",\n",
+    "            \"ml.c5.xlarge\",\n",
+    "            \"ml.c5.2xlarge\",\n",
+    "            \"ml.m5.xlarge\",\n",
+    "            \"ml.m5.2xlarge\",\n",
+    "        ],\n",
+    "        \"SupportedContentTypes\": [\"text/csv\"],\n",
+    "        \"SupportedResponseMIMETypes\": [\"text/csv\"],\n",
+    "    },\n",
+    ")\n",
+    "```\n",
+    "\n",
+    "You may define the fields `Domain`, `Task`, and `SamplePayloadUrl` in the optional field `ContainerConfig` like so:\n",
+    "\n",
+    "```\n",
+    "payload_config = {\n",
+    "    \"SamplePayloadUrl\": sample_payload_url,\n",
+    "}\n",
+    "\n",
+    "container_config = {\n",
+    "    \"Domain\": ml_domain,\n",
+    "    \"Task\": ml_task,\n",
+    "    \"PayloadConfig\": payload_config,\n",
+    "}\n",
+    "```\n",
+    "\n",
+    "And then provide it directly within `create_inference_recommendations_job()` API like so:\n",
+    "\n",
+    "```\n",
+    "default_response = client.create_inference_recommendations_job(\n",
+    "    JobName=str(default_job),\n",
+    "    JobDescription=\"\",\n",
+    "    JobType=\"Default\",\n",
+    "    RoleArn=role,\n",
+    "    InputConfig={\n",
+    "        \"ModelPackageVersionArn\": model_package_arn,\n",
+    "        \"ContainerConfig\": container_config\n",
+    "    },\n",
+    ")\n",
+    "```\n",
+    "\n",
+    "For more information on what else can be provided via `ContainerConfig` please refer to the `CreateInferenceRecommendationsJob` doc here: [CreateInferenceRecommendationsJob](https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateInferenceRecommendationsJob.html)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -567,7 +638,8 @@
     "    for x in inference_recommender_job[\"InferenceRecommendations\"]\n",
     "]\n",
     "df = pd.DataFrame(data)\n",
-    "df.drop(\"VariantName\", inplace=True, axis=1)\n",
+    "dropFilter = df.filter([\"VariantName\"])\n",
+    "df.drop(dropFilter, inplace=True, axis=1)\n",
     "pd.set_option(\"max_colwidth\", 400)"
    ]
   },
@@ -717,7 +789,8 @@
     "    for x in inference_recommender_job[\"InferenceRecommendations\"]\n",
     "]\n",
     "df = pd.DataFrame(data)\n",
-    "df.drop(\"VariantName\", inplace=True, axis=1)\n",
+    "dropFilter = df.filter([\"VariantName\"])\n",
+    "df.drop(dropFilter, inplace=True, axis=1)\n",
     "pd.set_option(\"max_colwidth\", 400)\n",
     "df.head()"
    ]

diff --git a/...ker-inference-recommender/tensorflow-cloudwatch/tf-cloudwatch-inference-recommender.ipynb b/...ker-inference-recommender/tensorflow-cloudwatch/tf-cloudwatch-inference-recommender.ipynb
@@ -484,6 +484,54 @@
     "print(\"ModelPackage Version ARN : {}\".format(model_package_arn))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Alternative Option: ContainerConfig\n",
+    "\n",
+    "If you are missing mandatory fields to create an inference recommender job in your model package version like so (this `create_model_package_input_dict` is missing `Domain`, `Task`, and `SamplePayloadUrl`):\n",
+    "\n",
+    "```\n",
+    "create_model_package_input_dict = {\n",
+    "    \"ModelPackageGroupName\": model_package_group_name,\n",
+    "    \"ModelPackageDescription\": model_package_description,\n",
+    "    \"ModelApprovalStatus\": model_approval_status,\n",
+    "}\n",
+    "```\n",
+    "\n",
+    "You may define the fields `Domain`, `Task`, and `SamplePayloadUrl` in the optional field `ContainerConfig` like so:\n",
+    "\n",
+    "```\n",
+    "payload_config = {\n",
+    "    \"SamplePayloadUrl\": sample_payload_url,\n",
+    "}\n",
+    "\n",
+    "container_config = {\n",
+    "    \"Domain\": ml_domain.upper(),\n",
+    "    \"Task\": ml_task.upper(),\n",
+    "    \"PayloadConfig\": payload_config,\n",
+    "}\n",
+    "```\n",
+    "\n",
+    "And then provide it directly within `create_inference_recommendations_job()` API like so:\n",
+    "\n",
+    "```\n",
+    "default_response = client.create_inference_recommendations_job(\n",
+    "    JobName=str(default_job),\n",
+    "    JobDescription=\"\",\n",
+    "    JobType=\"Default\",\n",
+    "    RoleArn=role,\n",
+    "    InputConfig={\n",
+    "        \"ModelPackageVersionArn\": model_package_arn,\n",
+    "        \"ContainerConfig\": container_config\n",
+    "    },\n",
+    ")\n",
+    "```\n",
+    "\n",
+    "For more information on what else can be provided via `ContainerConfig` please refer to the `CreateInferenceRecommendationsJob` doc here: [CreateInferenceRecommendationsJob](https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateInferenceRecommendationsJob.html)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -583,7 +631,8 @@
     "    for x in inference_recommender_job[\"InferenceRecommendations\"]\n",
     "]\n",
     "df = pd.DataFrame(data)\n",
-    "df.drop(\"VariantName\", inplace=True, axis=1)\n",
+    "dropFilter = df.filter([\"VariantName\"])\n",
+    "df.drop(dropFilter, inplace=True, axis=1)\n",
     "pd.set_option(\"max_colwidth\", 400)\n",
     "df.head()"
    ]
@@ -778,7 +827,8 @@
     "    for x in inference_recommender_job[\"InferenceRecommendations\"]\n",
     "]\n",
     "df = pd.DataFrame(data)\n",
-    "df.drop(\"VariantName\", inplace=True, axis=1)\n",
+    "dropFilter = df.filter([\"VariantName\"])\n",
+    "df.drop(dropFilter, inplace=True, axis=1)\n",
     "pd.set_option(\"max_colwidth\", 400)\n",
     "df.head()"
    ]