{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Deploy/Update endpoint\n",
    "\n",
    "In this section we will be deploying the latest approved model to an endpoint\n",
    "\n",
    "<b>Note: Make sure you have already approved a model in the model registry</b>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import boto3\n",
    "import json\n",
    "import sagemaker\n",
    "\n",
    "sess = boto3.Session()\n",
    "role = sagemaker.get_execution_role()\n",
    "sagemaker_session = sagemaker.Session(boto_session=sess)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_package_group_name = f\"HuggingFaceSentimentPackageGroupName\"\n",
    "endpoint_name = \"DEMO-endpoint-sentiment-analysis\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from scripts.utils import get_approved_package\n",
    "\n",
    "sm_client = boto3.client(\"sagemaker\")\n",
    "\n",
    "pck = get_approved_package(\n",
    "    model_package_group_name\n",
    ")  \n",
    "model_description = sm_client.describe_model_package(ModelPackageName=pck[\"ModelPackageArn\"])\n",
    "\n",
    "model_description"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from scripts.utils import deploy_or_update_endpoint\n",
    "\n",
    "model_package_arn = model_description[\"ModelPackageArn\"]\n",
    "\n",
    "deploy_or_update_endpoint(endpoint_name, model_package_arn, role, sagemaker_session)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Test the model\n",
    "Run the below to test that your model was deployed successfully and can ge"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%time\n",
    "\n",
    "\n",
    "runtime = boto3.client(service_name=\"sagemaker-runtime\")\n",
    "\n",
    "sentiment_input = {\"inputs\": \"I love using SageMaker endpoints to serve my real-time models.\"}\n",
    "\n",
    "response = runtime.invoke_endpoint(\n",
    "    EndpointName=endpoint_name,\n",
    "    Body=json.dumps(sentiment_input),\n",
    "    ContentType=\"application/json\",\n",
    ")\n",
    "\n",
    "print(response[\"Body\"].read())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%time \n",
    "for i in range(100):\n",
    "    response = runtime.invoke_endpoint(\n",
    "        EndpointName=endpoint_name,\n",
    "        Body=json.dumps(sentiment_input),\n",
    "        ContentType=\"application/json\",\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# # Delete the endpoint when no longer needed\n",
    "# sm_client.delete_endpoint(\n",
    "#     EndpointName=endpoint_name\n",
    "# )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "instance_type": "ml.t3.medium",
  "kernelspec": {
   "display_name": "Python 3 (Data Science)",
   "language": "python",
   "name": "python3__SAGEMAKER_INTERNAL__arn:aws:sagemaker:eu-west-1:470317259841:image/datascience-1.0"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}