{ "cells": [ { "cell_type": "markdown", "id": "b54f92ec", "metadata": {}, "source": [ "### This notebook shows how integration with AWS Sagemaker works\n", "- how to create endpoint using model saved in MLFlow\n", "- how to predict using Sagemaker endpoint\n", "- how to delete resources if inference setup is no more needed" ] }, { "cell_type": "markdown", "id": "f44544b2", "metadata": {}, "source": [ "NB! By running this notebook you will take responsibility for shutting down/deleting created Sagemaker resources." ] }, { "cell_type": "markdown", "id": "5680019b", "metadata": {}, "source": [ "Hopefully in the near future there will be availability for serverless endpoints also as it's currently in development: https://github.com/mlflow/mlflow/pull/9085/files" ] }, { "cell_type": "markdown", "id": "1ab8562f", "metadata": {}, "source": [ "Notebook setup" ] }, { "cell_type": "code", "execution_count": 1, "id": "feb761f8", "metadata": {}, "outputs": [], "source": [ "# import libraries and setup connection\n", "import mlflow\n", "import mlflow.deployments\n", "\n", "import random\n", "import pandas as pd\n", "import boto3\n", "import json\n", "from sklearn import datasets\n", "\n", "tracking_uri = 'https://dev-orch-mlflow-service.dev.theorchard.io'\n", "mlflow.set_tracking_uri(tracking_uri)" ] }, { "cell_type": "markdown", "id": "4313582e", "metadata": {}, "source": [ "Prerequisities:
\n", " In order to run next steps, MLFlow image repository must reside in the AWS ECR" ] }, { "cell_type": "markdown", "id": "9b236385", "metadata": {}, "source": [ "Deploy model" ] }, { "cell_type": "markdown", "id": "270b46fe", "metadata": {}, "source": [ "Make sure deployment name will be less than 35 characters because deployment will add random postfix like this at the end:
\n", " -model-borg4qqw1236zexafyvabcd
\n", "But maximum 64 characters are allowed.
\n", "This is used to distinquish deployment related objects." ] }, { "cell_type": "code", "execution_count": 4, "id": "3eda5ded", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Using deployment name: sagemaker-sk-randforest-94\n" ] } ], "source": [ "rand_id = random.randint(0, 100)\n", "run_id = '2695c2d819bc413a8ac3582a474cc95f' # rund id of the champion model chosen in the \"model_comparison\" notebook\n", "deployment_name = f'sagemaker-sk-randforest-{rand_id}'\n", "print(f'Using deployment name: {deployment_name}')\n", "image_ecr_url = \"103233932089.dkr.ecr.us-east-1.amazonaws.com/mlflow-base-venv:2.5.0\"\n", "region = \"us-east-1\"\n", "model_uri = \"runs:/\" + run_id + \"/model\"" ] }, { "cell_type": "code", "execution_count": 33, "id": "194d1269", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "2023/09/11 13:17:55 INFO mlflow.sagemaker: Using the python_function flavor for deployment!\n", "2023/09/11 13:17:55 INFO mlflow.sagemaker: tag response: {'ResponseMetadata': {'RequestId': 'F2GSERQX22D2EA0M', 'HostId': 'Q9YmBMNaDclD0QhE7Lyui5TyMrtEgNYL5Nc66l4v/DnwjyY/QZz8qXmR3nxlKYhIrabZFwWy6LY=', 'HTTPStatusCode': 200, 'HTTPHeaders': {'x-amz-id-2': 'Q9YmBMNaDclD0QhE7Lyui5TyMrtEgNYL5Nc66l4v/DnwjyY/QZz8qXmR3nxlKYhIrabZFwWy6LY=', 'x-amz-request-id': 'F2GSERQX22D2EA0M', 'date': 'Mon, 11 Sep 2023 13:17:56 GMT', 'x-amz-version-id': 'LdvzFZSIoJtSmjjjotUMRkWG9iYMTkiB', 'server': 'AmazonS3', 'content-length': '0'}, 'RetryAttempts': 0}, 'VersionId': 'LdvzFZSIoJtSmjjjotUMRkWG9iYMTkiB'}\n", "2023/09/11 13:17:55 INFO mlflow.sagemaker: Creating new endpoint with name: sagemaker-sk-randforest-94 ...\n", "2023/09/11 13:17:56 INFO mlflow.sagemaker: Created model with arn: arn:aws:sagemaker:us-east-1:103233932089:model/sagemaker-sk-randforest-94-model-borg4qqwqi6zeaafyvcqyg\n", "2023/09/11 13:17:57 INFO mlflow.sagemaker: Created endpoint configuration with arn: arn:aws:sagemaker:us-east-1:103233932089:endpoint-config/sagemaker-sk-randforest-94-config-vabt3jphabtt2wwwaxiqvd-q\n", "2023/09/11 13:17:57 INFO mlflow.sagemaker: Created endpoint with arn: arn:aws:sagemaker:us-east-1:103233932089:endpoint/sagemaker-sk-randforest-94\n", "2023/09/11 13:17:57 INFO mlflow.sagemaker: Waiting for the deployment operation to complete...\n", "2023/09/11 13:17:57 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:18:17 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:18:38 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:18:58 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:19:18 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:19:38 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:19:58 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:20:19 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:20:39 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:20:59 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:21:19 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:21:39 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:22:00 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:22:20 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:22:40 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:23:00 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:23:20 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:23:41 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:24:01 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:24:21 INFO mlflow.sagemaker: Waiting for endpoint to reach the \"InService\" state. Current endpoint status: \"Creating\"\n", "2023/09/11 13:24:41 INFO mlflow.sagemaker: The deployment operation completed successfully with message: \"The SageMaker endpoint was created successfully.\"\n" ] }, { "data": { "text/plain": [ "{'name': 'sagemaker-sk-randforest-94', 'flavor': 'python_function'}" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "deployment_client = mlflow.deployments.get_deploy_client(\"sagemaker:/\" + region)\n", "\n", "deployment_client.create_deployment(\n", " name=deployment_name,\n", " model_uri=model_uri,\n", " config={\n", " \"image_url\": image_ecr_url,\n", " \"bucket\": \"dev-cucumbers\",\n", " #\"execution_role_arn\": exec_role\n", " }\n", ")" ] }, { "cell_type": "markdown", "id": "9ec650a5", "metadata": {}, "source": [ "Check deployment status" ] }, { "cell_type": "code", "execution_count": 6, "id": "ade8ffea", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "MLflow SageMaker Deployment status is: InService\n" ] } ], "source": [ "deployment_info = deployment_client.get_deployment(name=deployment_name)\n", "print(f\"MLflow SageMaker Deployment status is: {deployment_info['EndpointStatus']}\")" ] }, { "cell_type": "markdown", "id": "d7ae7483", "metadata": {}, "source": [ "We also can see from AWS console that endpoint is running:" ] }, { "cell_type": "markdown", "id": "95b6fa06", "metadata": {}, "source": [ "![running_endpoint.png](attachment:running_endpoint.png)" ] }, { "cell_type": "markdown", "id": "7707315f", "metadata": {}, "source": [ "List all deployments" ] }, { "cell_type": "code", "execution_count": 39, "id": "477840b8", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "The following MLflow SageMaker Deployments exist in us-east-1: \n", " ['sagemaker-sk-randforest-94']\n" ] } ], "source": [ "deployments = deployment_client.list_deployments()\n", "\n", "deployment_names = [deployment['EndpointName'] for deployment in deployments]\n", "\n", "print(f\"The following MLflow SageMaker Deployments exist in {region}: \\n {deployment_names}\")" ] }, { "cell_type": "markdown", "id": "e55a88be", "metadata": {}, "source": [ "In overall this deplyoment created following objects:\n", "* model artifact - located in S3 dev-cucumbers bucket\n", "* model - located in Sagemaker -> models\n", "* model configuraiton - located in Sagemaker -> endpoint configurations\n", "* model endpoint - located in Sagemaker -> Endpoints" ] }, { "cell_type": "code", "execution_count": 8, "id": "b8813146", "metadata": {}, "outputs": [], "source": [ "iris = datasets.load_iris()" ] }, { "cell_type": "code", "execution_count": 9, "id": "9f659058", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[1.4 0.2]\n", " [3.5 1. ]\n", " [5.1 1.9]]\n", "[0 1 2]\n" ] } ], "source": [ "# Load some data for inference\n", "inference_df = iris.data[[0,60, 101], 2:]\n", "print(inference_df)\n", "\n", "targets = iris.target[[0,60, 101]]\n", "print(targets)" ] }, { "cell_type": "markdown", "id": "09fb8595", "metadata": {}, "source": [ "### Get inferences from Sagemaker endpoint" ] }, { "cell_type": "markdown", "id": "a88f6e76", "metadata": {}, "source": [ "Predict using Mlflow deployment reference:" ] }, { "cell_type": "code", "execution_count": 10, "id": "44e4cc0e", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Prediction response: {'predictions': [0.0, 1.0, 2.0]}\n" ] } ], "source": [ "predictions = deployment_client.predict(deployment_name, inference_df)\n", "\n", "print(f\"Prediction response: {predictions}\")" ] }, { "cell_type": "markdown", "id": "b5b4b60c", "metadata": {}, "source": [ "Predict using boto3 library:" ] }, { "cell_type": "code", "execution_count": 11, "id": "4c28c0c1", "metadata": {}, "outputs": [], "source": [ "endpoint=deployment_name\n", "client = boto3.client('sagemaker-runtime')" ] }, { "cell_type": "code", "execution_count": 12, "id": "9640b51e", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
column_acolumn_b
01.40.2
13.51.0
25.11.9
\n", "
" ], "text/plain": [ " column_a column_b\n", "0 1.4 0.2\n", "1 3.5 1.0\n", "2 5.1 1.9" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "query_df = pd.DataFrame(inference_df, columns = ['column_a','column_b'])\n", "query_df" ] }, { "cell_type": "code", "execution_count": 13, "id": "9b28a94e", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "{'dataframe_split': {'columns': ['column_a', 'column_b'], 'data': [[1.4, 0.2], [3.5, 1.0], [5.1, 1.9]]}}\n" ] } ], "source": [ "input_data = {\"dataframe_split\": {\"columns\": query_df.to_dict(orient=\"split\")['columns'], \"data\": query_df.to_dict(orient=\"split\")['data']}}\n", "print(input_data)" ] }, { "cell_type": "markdown", "id": "5b9f0284", "metadata": {}, "source": [ "Using json type of data for inference:" ] }, { "cell_type": "code", "execution_count": 14, "id": "b38a9f10", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "{\"predictions\": [0.0, 1.0, 2.0]}\n" ] } ], "source": [ "data = {\"dataframe_split\": {\"columns\": query_df.to_dict(orient=\"split\")['columns'], \"data\": query_df.to_dict(orient=\"split\")['data']}}\n", "\n", "prediction = client.invoke_endpoint(\n", " EndpointName=endpoint,\n", " Body=json.dumps(input_data),\n", " ContentType='application/json'\n", ")\n", "prediction = prediction['Body'].read().decode(\"ascii\")\n", "print(prediction)" ] }, { "cell_type": "markdown", "id": "3a9bd5b1", "metadata": {}, "source": [ "Manually constructing input for inference:" ] }, { "cell_type": "code", "execution_count": 15, "id": "25554596", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "{'predictions': [0.0, 1.0, 2.0]}\n" ] } ], "source": [ "prediction = client.invoke_endpoint(\n", " EndpointName=endpoint,\n", " Body=\"{\\\"dataframe_split\\\": {\\\"columns\\\":[\\\"column_a\\\", \\\"column_b\\\"],\\\"data\\\":[[1.4, 0.2], [3.5, 1.0], [5.1, 1.9]]}}\",\n", " ContentType='application/json'\n", ")\n", "\n", "print(str(json.loads(prediction['Body'].read())))" ] }, { "cell_type": "markdown", "id": "730d7c47", "metadata": {}, "source": [ "### Delete endpoint" ] }, { "cell_type": "markdown", "id": "13655b38", "metadata": {}, "source": [ "Command delete_deployment will delete endpoint, endpoint configuration, model and related S3 folder.
\n", "get_deployment command also fail and this is expected becaue the endpoint is not anymore available. " ] }, { "cell_type": "code", "execution_count": 16, "id": "a0116ffe", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "2023/09/11 13:25:40 INFO mlflow.sagemaker: Deleted endpoint with arn: arn:aws:sagemaker:us-east-1:103233932089:endpoint/sagemaker-sk-randforest-94\n", "2023/09/11 13:25:40 INFO mlflow.sagemaker: Waiting for the delete operation to complete...\n", "2023/09/11 13:25:40 INFO mlflow.sagemaker: Deletion is still in progress. Current endpoint status: Deleting\n", "2023/09/11 13:25:45 INFO mlflow.sagemaker: The deletion operation completed successfully with message: \"The SageMaker endpoint was deleted successfully.\"\n", "2023/09/11 13:25:45 INFO mlflow.sagemaker: Cleaning up unused resources...\n", "2023/09/11 13:25:45 INFO mlflow.sagemaker: Deleted associated endpoint configuration with arn: arn:aws:sagemaker:us-east-1:103233932089:endpoint-config/sagemaker-sk-randforest-94-config-vabt3jphabtt2wwwaxiqvd-q\n", "2023/09/11 13:25:46 INFO mlflow.sagemaker: Deleted associated model with arn: arn:aws:sagemaker:us-east-1:103233932089:model/sagemaker-sk-randforest-94-model-borg4qqwqi6zeaafyvcqyg\n" ] }, { "ename": "MlflowException", "evalue": "There was an error while retrieving the deployment: An error occurred (ValidationException) when calling the DescribeEndpoint operation: Could not find endpoint \"arn:aws:sagemaker:us-east-1:103233932089:endpoint/sagemaker-sk-randforest-94\".\n", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mClientError\u001b[0m Traceback (most recent call last)", "File \u001b[0;32m~/anaconda3/envs/python3/lib/python3.10/site-packages/mlflow/sagemaker/__init__.py:2657\u001b[0m, in \u001b[0;36mSageMakerDeploymentClient.get_deployment\u001b[0;34m(self, name, endpoint)\u001b[0m\n\u001b[1;32m 2654\u001b[0m sage_client \u001b[38;5;241m=\u001b[39m boto3\u001b[38;5;241m.\u001b[39mclient(\n\u001b[1;32m 2655\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msagemaker\u001b[39m\u001b[38;5;124m\"\u001b[39m, region_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mregion_name, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39massume_role_credentials\n\u001b[1;32m 2656\u001b[0m )\n\u001b[0;32m-> 2657\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43msage_client\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdescribe_endpoint\u001b[49m\u001b[43m(\u001b[49m\u001b[43mEndpointName\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mname\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2658\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m exc:\n", "File \u001b[0;32m~/anaconda3/envs/python3/lib/python3.10/site-packages/botocore/client.py:535\u001b[0m, in \u001b[0;36mClientCreator._create_api_method.._api_call\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 534\u001b[0m \u001b[38;5;66;03m# The \"self\" in this scope is referring to the BaseClient.\u001b[39;00m\n\u001b[0;32m--> 535\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_api_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43moperation_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/anaconda3/envs/python3/lib/python3.10/site-packages/botocore/client.py:980\u001b[0m, in \u001b[0;36mBaseClient._make_api_call\u001b[0;34m(self, operation_name, api_params)\u001b[0m\n\u001b[1;32m 979\u001b[0m error_class \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mexceptions\u001b[38;5;241m.\u001b[39mfrom_code(error_code)\n\u001b[0;32m--> 980\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m error_class(parsed_response, operation_name)\n\u001b[1;32m 981\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n", "\u001b[0;31mClientError\u001b[0m: An error occurred (ValidationException) when calling the DescribeEndpoint operation: Could not find endpoint \"arn:aws:sagemaker:us-east-1:103233932089:endpoint/sagemaker-sk-randforest-94\".", "\nDuring handling of the above exception, another exception occurred:\n", "\u001b[0;31mMlflowException\u001b[0m Traceback (most recent call last)", "Cell \u001b[0;32mIn[16], line 3\u001b[0m\n\u001b[1;32m 1\u001b[0m deployment_client\u001b[38;5;241m.\u001b[39mdelete_deployment(name\u001b[38;5;241m=\u001b[39mdeployment_name)\n\u001b[0;32m----> 3\u001b[0m validation_info \u001b[38;5;241m=\u001b[39m \u001b[43mdeployment_client\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_deployment\u001b[49m\u001b[43m(\u001b[49m\u001b[43mname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdeployment_name\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 4\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMLflow SageMaker Deployment status is: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mvalidation_info[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mEndpointStatus\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n", "File \u001b[0;32m~/anaconda3/envs/python3/lib/python3.10/site-packages/mlflow/sagemaker/__init__.py:2659\u001b[0m, in \u001b[0;36mSageMakerDeploymentClient.get_deployment\u001b[0;34m(self, name, endpoint)\u001b[0m\n\u001b[1;32m 2657\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m sage_client\u001b[38;5;241m.\u001b[39mdescribe_endpoint(EndpointName\u001b[38;5;241m=\u001b[39mname)\n\u001b[1;32m 2658\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m exc:\n\u001b[0;32m-> 2659\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m MlflowException(\n\u001b[1;32m 2660\u001b[0m message\u001b[38;5;241m=\u001b[39m\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThere was an error while retrieving the deployment: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mexc\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 2661\u001b[0m )\n", "\u001b[0;31mMlflowException\u001b[0m: There was an error while retrieving the deployment: An error occurred (ValidationException) when calling the DescribeEndpoint operation: Could not find endpoint \"arn:aws:sagemaker:us-east-1:103233932089:endpoint/sagemaker-sk-randforest-94\".\n" ] } ], "source": [ "deployment_client.delete_deployment(name=deployment_name)\n", "\n", "validation_info = deployment_client.get_deployment(name=deployment_name)\n", "print(f\"MLflow SageMaker Deployment status is: {validation_info['EndpointStatus']}\")" ] } ], "metadata": { "kernelspec": { "display_name": "conda_python3", "language": "python", "name": "conda_python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.10.12" } }, "nbformat": 4, "nbformat_minor": 5 }