{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Spacy Pre-Trained NER Deployment Example"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"[Container Structure](https://sagemaker-workshop.com/custom/containers.html)\n",
"- NER\n",
" - predictor.py: (Flask app for inference)\n",
" - wsgi.py: (Wrapper around predictor)\n",
" - nginx.conf: (Config for nginx front-end)\n",
" - serve: program for container hosting, launches gunicorn server\n",
" - Note that there is no train for pre-trained\n",
"- Dockerfile"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Push Docker Image to ECR"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%sh\n",
"\n",
"# Name of algo -> ECR\n",
"algorithm_name=sm-pretrained-spacy\n",
"\n",
"cd container\n",
"\n",
"#make serve executable\n",
"chmod +x NER/serve\n",
"\n",
"account=$(aws sts get-caller-identity --query Account --output text)\n",
"\n",
"# Region, defaults to us-west-2\n",
"region=$(aws configure get region)\n",
"region=${region:-us-east-1}\n",
"\n",
"fullname=\"${account}.dkr.ecr.${region}.amazonaws.com/${algorithm_name}:latest\"\n",
"\n",
"# If the repository doesn't exist in ECR, create it.\n",
"aws ecr describe-repositories --repository-names \"${algorithm_name}\" > /dev/null 2>&1\n",
"\n",
"if [ $? -ne 0 ]\n",
"then\n",
" aws ecr create-repository --repository-name \"${algorithm_name}\" > /dev/null\n",
"fi\n",
"\n",
"# Get the login command from ECR and execute it directly\n",
"aws ecr get-login-password --region ${region}|docker login --username AWS --password-stdin ${fullname}\n",
"\n",
"# Build the docker image locally with the image name and then push it to ECR\n",
"# with the full name.\n",
"\n",
"docker build -t ${algorithm_name} .\n",
"docker tag ${algorithm_name} ${fullname}\n",
"\n",
"docker push ${fullname}"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# SageMaker Client Setup\n",
"\n",
"- [SageMaker Client](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sagemaker.html#SageMaker.Client.create_model): Model, Endpoint Config, and Endpoint Creation\n",
"- [SageMaker RunTime Client](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sagemaker-runtime.html#SageMakerRuntime.Client.invoke_endpoint): Endpoint Invocation/Testing"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import boto3\n",
"from sagemaker import get_execution_role\n",
"\n",
"sm_client = boto3.client(service_name='sagemaker')\n",
"runtime_sm_client = boto3.client(service_name='sagemaker-runtime')\n",
"\n",
"account_id = boto3.client('sts').get_caller_identity()['Account']\n",
"region = boto3.Session().region_name\n",
"\n",
"#not really used in this use case, use when need to store model artifacts (Ex: MME)\n",
"s3_bucket = 'spacy-sagemaker-us-east-1-bucket'\n",
"\n",
"role = get_execution_role()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Model Creation\n",
"[Documentation](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sagemaker.html#SageMaker.Client.create_model)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from time import gmtime, strftime\n",
"\n",
"model_name = 'spacy-nermodel-' + strftime(\"%Y-%m-%d-%H-%M-%S\", gmtime())\n",
"model_url = 's3://{}/spacy/'.format(s3_bucket) ## MODEL S3 URL\n",
"container = '{}.dkr.ecr.{}.amazonaws.com/sm-pretrained-spacy:latest'.format(account_id, region)\n",
"instance_type = 'ml.c5d.18xlarge'\n",
"\n",
"print('Model name: ' + model_name)\n",
"print('Model data Url: ' + model_url)\n",
"print('Container image: ' + container)\n",
"\n",
"container = {\n",
" 'Image': container\n",
"}\n",
"\n",
"create_model_response = sm_client.create_model(\n",
" ModelName = model_name,\n",
" ExecutionRoleArn = role,\n",
" Containers = [container])\n",
"\n",
"print(\"Model Arn: \" + create_model_response['ModelArn'])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Endpoint Config Creation\n",
"\n",
"[Documentation](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sagemaker.html#SageMaker.Client.create_endpoint_config)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"endpoint_config_name = 'spacy-ner-config' + strftime(\"%Y-%m-%d-%H-%M-%S\", gmtime())\n",
"print('Endpoint config name: ' + endpoint_config_name)\n",
"\n",
"create_endpoint_config_response = sm_client.create_endpoint_config(\n",
" EndpointConfigName = endpoint_config_name,\n",
" ProductionVariants=[{\n",
" 'InstanceType': instance_type,\n",
" 'InitialInstanceCount': 1,\n",
" 'InitialVariantWeight': 1,\n",
" 'ModelName': model_name,\n",
" 'VariantName': 'AllTraffic'}])\n",
"\n",
"print(\"Endpoint config Arn: \" + create_endpoint_config_response['EndpointConfigArn'])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Endpoint Creation\n",
"[Documentation](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sagemaker.html#SageMaker.Client.create_endpoint)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%time\n",
"\n",
"import time\n",
"\n",
"endpoint_name = 'spacy-ner-endpoint' + strftime(\"%Y-%m-%d-%H-%M-%S\", gmtime())\n",
"print('Endpoint name: ' + endpoint_name)\n",
"\n",
"create_endpoint_response = sm_client.create_endpoint(\n",
" EndpointName=endpoint_name,\n",
" EndpointConfigName=endpoint_config_name)\n",
"print('Endpoint Arn: ' + create_endpoint_response['EndpointArn'])\n",
"\n",
"resp = sm_client.describe_endpoint(EndpointName=endpoint_name)\n",
"status = resp['EndpointStatus']\n",
"print(\"Endpoint Status: \" + status)\n",
"\n",
"print('Waiting for {} endpoint to be in service...'.format(endpoint_name))\n",
"waiter = sm_client.get_waiter('endpoint_in_service')\n",
"waiter.wait(EndpointName=endpoint_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Endpoint Invocation\n",
"\n",
"[Documentation](https://boto3.amazonaws.com/v1/documentation/api/1.9.42/reference/services/sagemaker-runtime.html#SageMakerRuntime.Client.invoke_endpoint)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"content_type = \"application/json\"\n",
"request_body = {\"input\": \"This is a test with NER in America with Amazon and Microsoft in Seattle, writing random stuff.\"}\n",
"\n",
"#Serialize data for endpoint\n",
"data = json.loads(json.dumps(request_body))\n",
"payload = json.dumps(data)\n",
"\n",
"#Endpoint invocation\n",
"response = runtime_sm_client.invoke_endpoint(\n",
" EndpointName=endpoint_name,\n",
" ContentType=content_type,\n",
" Body=payload)\n",
"\n",
"#Parse results\n",
"result = json.loads(response['Body'].read().decode())['output']\n",
"result"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Delete Endpoint"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Before leaving this exercise, it is a good practice to delete the resources created."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# sm_client.delete_endpoint(EndpointName=endpoint_name)\n",
"# sm_client.delete_endpoint_config(EndpointConfigName=EndpointConfigName)\n",
"# sm_client.delete_model(ModelName=ModelName)"
]
}
],
"metadata": {
"instance_type": "ml.t3.medium",
"kernelspec": {
"display_name": "Python 3 (Data Science)",
"language": "python",
"name": "python3__SAGEMAKER_INTERNAL__arn:aws:sagemaker:us-west-2:236514542706: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": 5
}