## content package for DataRobot integration for SAP AI Core
## Objective
sap-ai-core-datarobot is a content package to deploy DataRobot workflows in AI Core. This package provides support for two distinct deployment workflows, provided that a trained model is already present in DataRobot.
- Export the model from DataRobot to an Object Store and then integrate the Object Store with AI Core for model deployment.
- Directly integrate AI Core with the model in DataRobot utilizing the DataRobot API.
### User Guide
#### 1. Workflow 1: Exporting Models from DataRobot to Object Store and Integrating with AI Core
*Pre-requisites*
1. Complete [AI Core Onboarding](https://help.sap.com/viewer/2d6c5984063c40a59eda62f4a9135bee/LATEST/en-US/8ce24833036d481cb3113a95e3a39a07.html)
- [Initial setup](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/initial-setup)
- Create a [Resource Group](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-resource-group)
2. Access to the [Git repository](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/register-your-git-repository-and-secrets), [Docker repository](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/register-your-docker-registry-secret) and [Object Store](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/register-your-object-store-secret) onboarded to AI Core
3. You have a registered DataRobot account, trained a model, downloaded the model from DataRobot and stored the model in Object Store configured with AI Core.
The interface for sap-ai-core-datarobot content package is part of the `ai-core-sdk`.ai-core-sdk provides a command-line utility as well as a python library to use AICore content packages.
Please note that this sap-ai-core-datarobot package documentation provides the instructions for using this specific content package. For a more comprehensive understanding of how to use a content package, refer to the [ai-core-sdk package documentation](https://pypi.org/project/ai-core-sdk/).
##### 1.1 CLI
*Steps*
1. Install AI Core SDK
```
pip install "ai-core-sdk[aicore_content]"
```
2. Install this content package
```
pip install sap-ai-core-datarobot
```
3. Explore the content package
List all content packages installed in the environment.
```
aicore-content list
```
List all available pipelines in the sap-ai-core-datarobot content package.
```
aicore-content list sap_datarobot
```
View the parameters available in the selected pipeline.
```
aicore-content show sap_datarobot model-jar-serving
```
Check all available commands by using the `--help` flag.
```
aicore-content --help
```
4. Create a config file with the name model_serving_config.yaml with the following content.
```
.contentPackage: sap_datarobot
.dockerType: default
.workflow: model-jar-serving
annotations:
executables.ai.sap.com/description: <YOUR EXECUTABLE DESCRIPTION>
executables.ai.sap.com/name: <YOUR EXECUTABLE NAME>
scenarios.ai.sap.com/description: <YOUR SCENARIO DESCRIPTION>
scenarios.ai.sap.com/name: <YOUR SCENARIO NAME>
image: <YOUR DOCKER IMAGE TAG>
imagePullSecret: <YOUR DOCKER REGISTRY SECRET NAME IN AI CORE>
labels:
ai.sap.com/version: <YOUR SCENARIO VERSION>
scenarios.ai.sap.com/id: <YOUR SCENARIO ID>
name: <YOUR SERVING TEMPLATE NAME>
```
5. Fill in the desired values in the config file. An example config file is shown below.
```
.contentPackage: sap_datarobot
.dockerType: default
.workflow: model-jar-serving
annotations:
executables.ai.sap.com/description: datarobot model serving
executables.ai.sap.com/name: datarobot-model-serving
scenarios.ai.sap.com/description: my datarobot scenario
scenarios.ai.sap.com/name: my-datarobot-scenario
image: docker.io/<YOUR_DOCKER_USERNAME>/model-serve:1.0
imagePullSecret: my-docker-secret
labels:
ai.sap.com/version: 0.0.1
scenarios.ai.sap.com/id: 00db4197-1538-4640-9ea9-44731041ed88
name: datarobot-model-serving
```
6. Generate a docker image.
This step involves building a docker image with the tag specified in the model_serving_config.yaml file. The command to perform this operation is as follows:
```
aicore-content create-image -p sap_datarobot -w model-jar-serving model_serving_config.yaml
```
7. Push the docker image to your docker repository
The image tag should correspond to the one provided in the 'model_serving_config.yaml' file.
```
docker push <YOUR DOCKER IMAGE TAG>
```
8. Generate a serving template
Clone the git repository that was registered with your SAP AI Core tenant during Onboarding.
```
aicore-content create-template -p sap_datarobot -w model-jar-serving model_serving_config.yaml -o '<TEMPLATES FOLDER PATH IN YOUR CLONED GIT REPO>/model-serving-template.yaml'
```
You can configure SAP AI Core to use different infrastructure resources for different tasks, based on demand. Within SAP AI Core, the resource plan is selected via the `ai.sap.com/resourcePlan` label in the serving template. By default, sap-ai-core-datarobot workflows use `starter` resource plan which entails the use of 1 CPU core and 3 Memeory GBs. For more information on how to select a different resource plan, you can refer to the documentation [choosing a resource plan](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/choose-resource-plan-c58d4e584a5b40a2992265beb9b6be3c?q=resource%20plan).
9. Push the serving template to your git repository
```
cd <PATH TO YOUR CLONED GIT REPO>
git add <TEMPLATES FOLDER PATH IN YOUR CLONED GIT REPO>/model-serving-template.yaml
git commit -m 'updated template model-serving-template.yaml'
git push
```
10. Obtain a client credentials token to AI Core
```
curl --location '<YOUR AI CORE AUTH ENDPOINT URL>/oauth/token' --header 'Authorization: Basic <YOUR AI CORE CREDENTIALS>'
```
11. Create an artifact to connect the DataRobot model, to make it available for use in SAP AI Core. Save the model artifact id from the response.
```
curl --location --request POST "<YOUR AI CORE URL>/v2/lm/artifacts" \
--header "Authorization: Bearer <CLIENT CREDENTAILS TOKEN>" \
--header "Content-Type: application/json" \
--header "AI-Resource-Group: <YOUR RESOURCE GROUP NAME>" \
--data-raw '{
"name": "my-datarobot-model",
"kind": "model",
"url": "ai://<YOUR OBJECTSTORE NAME>/<YOUR MODEL PATH>",
"description": "my datarobot model jar",
"scenarioId": "<YOUR SCENARIO ID>"
}'
```
12. Create a configuration and save the configuration id from the response.
```
curl --request POST "<YOUR AI CORE URL>/v2/lm/configurations" \
--header "Authorization: Bearer <CLIENT CREDENTAILS TOKEN>" \
--header "AI-Resource-Group: <YOUR RESOURCE GROUP NAME>" \
--header "Content-Type: application/json" \
--data '{
"name": "<CONFIGURATION NAME>",
"executableId": "<YOUR EXECUTABLE ID>",
"scenarioId": "<YOUR SCENARIO ID>",
"parameterBindings": [
{
"key": "modelName",
"value": "<YOUR MODEL JAR FILE NAME>"
}
],
"inputArtifactBindings": [
{
"key": "modeljar",
"artifactId": "<YOUR MODEL ARTIFACT ID>"
}
]
}'
```
13. Create a deployment and note down the deployment id from the response
```
curl --location --globoff --request POST '<YOUR AI CORE URL>/v2/lm/configurations/<YOUR CONFIGURATION ID>/deployments' \
--header 'AI-Resource-Group: <YOUR RESOURCE GROUP NAME>' \
--header 'Authorization: Bearer <CLIENT CREDENTAILS TOKEN>'
```
14. Check the status of the deployment. Note down the deployment URL after the status changes to RUNNING.
```
curl --location --globoff '<YOUR AI CORE URL>/v2/lm/deployments/<YOUR DEPLOYMENT ID>' \
--header 'AI-Resource-Group: <YOUR RESOURCE GROUP NAME>' \
--header 'Authorization: Bearer <CLIENT CREDENTAILS TOKEN>'
```
15. Use your deployment.
```
curl --location '<YOUR DEPLOYMENT URL>/v1/models/,<YOUR MODEL JAR FILE NAME>:predict' \
--header 'AI-Resource-Group: <YOUR RESOURCE GROUP NAME>' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer <CLIENT CREDENTAILS TOKEN>' \
--data '[
{
"<FEATURE_NAME>": <VALUE>,
...
}
]'
```
##### 1.2 Python
*Steps*
1. Install AI Core SDK
```
!python -m pip install "ai_core_sdk[aicore-content]"
```
2. Install this content package
```
!python -m pip install sap-ai-core-datarobot
```
3. Explore the content package
List all content packages installed in the environment.
```
from ai_core_sdk.content import get_content_packages
pkgs = get_content_packages()
for pkg in pkgs.values():
print(pkg)
```
List all available pipelines in the sap-ai-core-datarobot content package.
```
content_pkg = pkgs['sap_datarobot']
for workflow in content_pkg.workflows.values():
print(workflow)
```
4. Create a config file with the name model_serving_config.yaml with the following content.
```
!python -m pip install pyyaml
```
```
serving_workflow = content_pkg.workflows["model-jar-serving"]
serving_config = {
'.contentPackage': 'sap_datarobot',
'.workflow': 'model-jar-serving',
'.dockerType': 'default',
'name': '<YOUR SERVING TEMPLATE NAME>',
'labels': {
'scenarios.ai.sap.com/id': "<YOUR SCENARIO ID>",
'ai.sap.com/version': "<YOUR SCENARIO VERSION>"
},
"annotations": {
"scenarios.ai.sap.com/name": "<YOUR SCENARIO NAME>",
"scenarios.ai.sap.com/description": "<YOUR SCENARIO DESCRIPTION>",
"executables.ai.sap.com/name": "<YOUR EXECUTABLE NAME>",
"executables.ai.sap.com/description": "<YOUR EXECUTABLE DESCRIPTION>"
},
'image': '<YOUR DOCKER IMAGE TAG>',
"imagePullSecret": "<YOUR DOCKER REGISTRY SECRET NAME IN AI CORE>"
}
import yaml
serving_config_yaml_file = "model_serving_config.yaml"
ff = open(serving_config_yaml_file, 'w+')
yaml.dump(serving_config, ff , allow_unicode=True)
```
5. Fill in the desired values in the config file. An example config file is shown below.
```
serving_config = {
'.contentPackage': 'sap_datarobot',
'.workflow': 'model-jar-serving',
'.dockerType': 'default',
'name': 'datarobot-model-serving',
'labels': {
'scenarios.ai.sap.com/id': "00db4197-1538-4640-9ea9-44731041ed88",
'ai.sap.com/version': "0.0.1"
},
"annotations": {
"scenarios.ai.sap.com/name": "my-datarobot-scenario",
"executables.ai.sap.com/name": "datarobot-model-serving",
"executables.ai.sap.com/description": "datarobot model serving",
"scenarios.ai.sap.com/description": "my datarobot scenario"
},
'image': 'docker.io/<YOUR_DOCKER_USERNAME>/model-serve:1.0',
"imagePullSecret": "my-docker-secret"
}
import yaml
serving_config_yaml_file = "model_serving_config.yaml"
ff = open(serving_config_yaml_file, 'w+')
yaml.dump(serving_config, ff , allow_unicode=True)
```
6. Generate a docker image
This step involves building a docker image with the tag specified in the model_serving_config.yaml file.
```
# keep the docker up and running before executing this cell
# docker login
import os
docker_user = "[USER NAME]"
docker_pwd = "[PASSWORD]"
os.system(f'docker login <YOUR_DOCKER_REGISTRY_URL> -u {docker_user} -p {docker_pwd}')
with open(serving_config_yaml_file) as stream:
workflow_config = yaml.load(stream)
serving_workflow.create_image(workflow_config) # actually build the docker container
#When an error occurs, perform a dry run to debug any error occured while running the create_image() function.
docker_build_cmd = serving_workflow.create_image(workflow_config, return_cmd = True)
print(' '.join(docker_build_cmd))
```
7. Push the docker image to your docker repository
```
os.system(f'docker push {workflow_config["image"]}') # push the container
```
8. Generate a serving template
Clone the git repository that was registered with your SAP AI Core tenant during Onboarding.
```
import pathlib
output_file = '<TEMPLATES FOLDER PATH IN YOUR CLONED GIT REPO>/model-serving-template.yaml'
serving_workflow.create_template(serving_config_yaml_file, output_file)
```
You can configure SAP AI Core to use different infrastructure resources for different tasks, based on demand. Within SAP AI Core, the resource plan is selected via the `ai.sap.com/resourcePlan` label in the serving template. By default, sap-ai-core-datarobot workflows use `starter` resource plan which entails the use of 1 CPU core and 3 Memeory GBs. For more information on how to select a different resource plan, you can refer to the documentation [choosing a resource plan](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/choose-resource-plan-c58d4e584a5b40a2992265beb9b6be3c?q=resource%20plan).
9. Push the serving template to your git repository
```
import os
import subprocess
repo_path = "<PATH TO YOUR CLONED GIT REPO>"
current_dir = os.getcwd()
os.chdir(repo_path)
# add the file to the git repository
subprocess.run(["git", "add", f"{output_file}"])
# commit the changes
subprocess.run(["git", "commit", "-m", f'updated template {workflow_config["image"]}'])
# push the changes
subprocess.run(["git", "push"])
os.chdir(current_dir)
```
10. Obtain a client credentials token to AI Core
```
import json
from ai_api_client_sdk.ai_api_v2_client import AIAPIV2Client
from ai_api_client_sdk.models.artifact import Artifact
from ai_api_client_sdk.models.parameter_binding import ParameterBinding
from ai_api_client_sdk.models.input_artifact_binding import InputArtifactBinding
from ai_api_client_sdk.models.status import Status
from ai_api_client_sdk.models.target_status import TargetStatus
import time
from IPython.display import clear_output
import requests
import pprint
# Load AICore and Object Store credentials
credCF, credS3 = {}, {}
with open('aicore-creds.json') as cf:
credCF = json.load(cf)
with open('s3-creds.json') as s3:
credS3 = json.load(s3)
#Authentication
RESOURCE_GROUP="<YOUR RESOURCE GROUP NAME>"
ai_api_v2_client = AIAPIV2Client(
base_url=credCF["serviceurls"]["ML_API_URL"] + "/v2/lm",
auth_url=credCF["url"] + "/oauth/token",
client_id=credCF['clientid'],
client_secret=credCF['clientsecret'],
resource_group=RESOURCE_GROUP
)
```
11. Create an artifact to connect the DataRobot model, to make it available for use in SAP AI Core. Save the model artifact id from the response.
```
# GET scenario
response = ai_api_v2_client.scenario.query(RESOURCE_GROUP)
ai_scenario = next(scenario_obj for scenario_obj in response.resources if scenario_obj.id == workflow_config["labels"]["scenarios.ai.sap.com/id"] )
print("Scenario id: ", ai_scenario.id)
print("Scenario name: ", ai_scenario.name)
# GET List of scenario executables
response = ai_api_v2_client.executable.query(scenario_id=ai_scenario.id)
for executable in response.resources:
print(executable)
#Register the model from Object Store as an artifact
artifact = {
"name": "my-datarobot-model",
"kind": Artifact.Kind.MODEL,
"url": "ai://<YOUR OBJECTSTORE NAME>/<YOUR MODEL PATH>",
"description": "my datarobot model jar",
"scenario_id": ai_scenario.id
}
artifact_resp = ai_api_v2_client.artifact.create(**artifact)
assert artifact_resp.message == 'Artifact acknowledged'
print(artifact_resp.url)
```
12. Create a configuration and save the configuration id from the response.
```
#define deployment confgiuration
artifact_binding = {
"key": "modeljar",
"artifact_id": artifact_resp.id
}
parameter_binding = {
"key": "modelName",
"value": "<YOUR MODEL JAR FILE NAME>" #model file name in Object Store
}
deployment_configuration = {
"name": "<CONFIGURATION NAME>",
"scenario_id": workflow_config["labels"]["scenarios.ai.sap.com/id"],
"executable_id": workflow_config["name"],
"parameter_bindings": [ParameterBinding(**parameter_binding)],
"input_artifact_bindings": [ InputArtifactBinding(**artifact_binding) ]
}
deployment_config_resp = ai_api_v2_client.configuration.create(**deployment_configuration)
assert deployment_config_resp.message == 'Configuration created'
```
13. Create a deployment and note down the deployment id from the response
```
deployment_resp = ai_api_v2_client.deployment.create(deployment_config_resp.id)
```
14. Check the status of the deployment. Note down the deployment URL after the status changes to RUNNING.
```
# poll deployment status
status = None
while status != Status.RUNNING and status != Status.DEAD:
time.sleep(5)
clear_output(wait=True)
deployment = ai_api_v2_client.deployment.get(deployment_resp.id)
status = deployment.status
print('...... deployment status ......', flush=True)
print(deployment.status)
print(deployment.status_details)
time.sleep(10) # time for deployment url getting ready
print('endpoint: ', deployment.deployment_url)
```
15. Use your deployment.
```
with open('sample_payload.json') as cf:
sample_input = json.load(cf)
# inference
endpoint = "{deploy_url}/v1/models/{model_name}:predict".format(deploy_url=deployment.deployment_url, model_name = parameter_binding["value"])
headers = {"Authorization": ai_api_v2_client.rest_client.get_token(), 'ai-resource-group': RESOURCE_GROUP}
response = requests.post(endpoint, headers=headers, json=test_input)
pprint.pprint(['inference result:', response.json()])
time.sleep(10)
```
#### 2. Direct Integration of AI Core with DataRobot Models via DataRobot API
*Pre-requisites*
1. Complete [AI Core Onboarding](https://help.sap.com/viewer/2d6c5984063c40a59eda62f4a9135bee/LATEST/en-US/8ce24833036d481cb3113a95e3a39a07.html)
- [Initial setup](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/initial-setup)
- Create a [Resource Group](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-resource-group)
2. Access to the [Git repository](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/register-your-git-repository-and-secrets), [Docker repository](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/register-your-docker-registry-secret) and [Object Store](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/register-your-object-store-secret) onboarded to AI Core
3. You have a registered DataRobot account, trained a model in DataRobot.
The interface for sap-ai-core-datarobot content package is part of the `ai-core-sdk`.ai-core-sdk provides a command-line utility as well as a python library to use AICore content packages.
Please note that this sap-ai-core-datarobot package documentation provides the instructions for using this specific content package. For a more comprehensive understanding of how to use a content package, refer to the ai-core-sdk package documentation [here](https://pypi.org/project/ai-core-sdk/).
##### 2.1 CLI
*Steps*
1. Install AI Core SDK
```
pip install ai-core-sdk[aicore_content]
```
2. Install this content package
```
pip install sap-ai-core-datarobot
```
3. Explore the content package
List all content packages installed in the environment.
```
aicore-content list
```
List all available pipelines in the sap-ai-core-datarobot content package.
```
aicore-content list sap_datarobot
```
View the parameters available in the selected pipeline.
```
aicore-content show sap_datarobot model-id-serving
```
Check all available commands by using the `--help` flag.
```
aicore-content --help
```
4. Create a config file with the name model_serving_config.yaml with the following content.
```
.contentPackage: sap_datarobot
.dockerType: default
.workflow: model-id-serving
annotations:
executables.ai.sap.com/description: <YOUR EXECUTABLE DESCRIPTION>
executables.ai.sap.com/name: <YOUR EXECUTABLE NAME>
scenarios.ai.sap.com/description: <YOUR SCENARIO DESCRIPTION>
scenarios.ai.sap.com/name: <YOUR SCENARIO NAME>
image: <YOUR DOCKER IMAGE TAG>
imagePullSecret: <YOUR DOCKER REGISTRY SECRET NAME IN AI CORE>
datarobotToken: <DATAROBOT-API-TOKEN SECRET NAME IN AI CORE>
labels:
ai.sap.com/version: <YOUR SCENARIO VERSION>
scenarios.ai.sap.com/id: <YOUR SCENARIO ID>
name: <YOUR SERVING TEMPLATE NAME>
```
5. Fill in the desired values in the config file. An example config file is shown below.
```
.contentPackage: sap_datarobot
.dockerType: default
.workflow: model-id-serving
annotations:
executables.ai.sap.com/description: datarobot model serving
executables.ai.sap.com/name: datarobot-model-serving
scenarios.ai.sap.com/description: my datarobot scenario
scenarios.ai.sap.com/name: my-datarobot-scenario
image: docker.io/<YOUR_DOCKER_USERNAME>/model-serve:1.0
imagePullSecret: my-docker-secret
datarobotToken: my-datarobot-secret
labels:
ai.sap.com/version: 0.0.1
scenarios.ai.sap.com/id: 00db4197-1538-4640-9ea9-44731041ed88
name: datarobot-model-serving
```
6. Generate a docker image
This step involves building a docker image with the tag specified in the model_serving_config.yaml file. The command to perform this operation is as follows:
```
aicore-content create-image -p sap_datarobot -w model-id-serving model_serving_config.yaml
```
7. Push the docker image to your docker repository
The image tag should correspond to the one provided in the 'model_serving_config.yaml' file.
```
docker push <YOUR DOCKER IMAGE TAG>
```
8. Generate a serving template
Clone the git repository that was registered with your SAP AI Core tenant during Onboarding.
```
aicore-content create-template -p sap_datarobot -w model-id-serving model_serving_config.yaml -o '<TEMPLATES FOLDER PATH IN YOUR CLONED GIT REPO>/model-serving-template.yaml'
```
You can configure SAP AI Core to use different infrastructure resources for different tasks, based on demand. Within SAP AI Core, the resource plan is selected via the `ai.sap.com/resourcePlan` label in the serving template. By default, sap-ai-core-datarobot workflows use `starter` resource plan which entails the use of 1 CPU core and 3 Memeory GBs. For more information on how to select a different resource plan, you can refer to the documentation [choosing a resource plan](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/choose-resource-plan-c58d4e584a5b40a2992265beb9b6be3c?q=resource%20plan).
9. Fill in the datarobot secrets name in serving template
In the model-serving-template.yaml serving template file, substitute `<DATAROBOT-ENDPOINT-TOKEN>` with the name of your datarobot secrets.
10. Push the serving template to your git repository
```
cd <PATH TO YOUR CLONED GIT REPO>
git add <TEMPLATES FOLDER PATH IN YOUR CLONED GIT REPO>/model-serving-template.yaml
git commit -m 'updated template model-serving-template.yaml'
git push
```
11. Obtain a client credentials token to AI Core
```
curl --location '<YOUR AI CORE AUTH ENDPOINT URL>/oauth/token' --header 'Authorization: Basic <YOUR AI CORE CREDENTIALS>'
```
12. Create Generic Secrets in ResourceGroup
To authenticate with DataRobot's API, your code needs to have access to an endpoint and token. In AI Core, create a generic secret for the Endpoint and the token; these secrets are used to access the model from DataRobot. Refer AI Core documentation to [create a generic secret](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-generic-secret?q=generic%20secrets).
Note that the AI Core AI API expects sensitive data to be Base64-encoded. You can easily encode your data in Base64 format using the following command on Linux or MacOS:
```
echo -n 'my-sensitive-data' | base64
```
```
curl --location --request POST "<YOUR AI CORE URL>/v2/admin/secrets" \
--header "Authorization: Bearer <CLIENT CREDENTAILS TOKEN>" \
--header 'Content-Type: application/json' \
--header 'AI-Resource-Group: <YOUR RESOURCE GROUP NAME>' \
--data-raw '{
"name": "<DATAROBOT-API-TOKEN SECRET NAME IN AI CORE>",
"data": {
"endpoint": "<BASE64-ENCODED DATAROBOT API ENDPOINT>",
"token": "<BASE64-ENCODED DATAROBOT API TOKEN>"
}
}'
```
13. Create a configuration and save the configuration id from the response.
```
curl --request POST "<YOUR AI CORE URL>/v2/lm/configurations" \
--header "Authorization: Bearer <CLIENT CREDENTAILS TOKEN>" \
--header "AI-Resource-Group: <YOUR RESOURCE GROUP NAME>" \
--header "Content-Type: application/json" \
--data '{
"name": "<CONFIGURATION NAME>",
"executableId": "<YOUR EXECUTABLE ID>",
"scenarioId": "<YOUR SCENARIO ID>",
"parameterBindings": [
{
"key": "projectID",
"value": "<PROJECT ID OF YOUR MODEL IN DATAROBOT>"
},
{
"key": "modelID",
"value": "<YOUR MODEL ID FROM DATAROBOT>"
}
]
}'
```
14. Create a deployment and note down the deployment id from the response
```
curl --location --globoff --request POST '<YOUR AI CORE URL>/v2/lm/configurations/<YOUR CONFIGURATION ID>/deployments' \
--header 'AI-Resource-Group: <YOUR RESOURCE GROUP NAME>' \
--header 'Authorization: Bearer <CLIENT CREDENTAILS TOKEN>'
```
15. Check the status of the deployment. Note down the deployment URL after the status changes to RUNNING.
```
curl --location --globoff '<YOUR AI CORE URL>/v2/lm/deployments/<YOUR DEPLOYMENT ID>' \
--header 'AI-Resource-Group: <YOUR RESOURCE GROUP NAME>' \
--header 'Authorization: Bearer <CLIENT CREDENTAILS TOKEN>'
```
16. Use your deployment.
```
curl --location '<YOUR DEPLOYMENT URL>/v1/models/model:predict' \
--header 'AI-Resource-Group: <YOUR RESOURCE GROUP NAME>' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer <CLIENT CREDENTAILS TOKEN>' \
--data '[
{
"<FEATURE_NAME>": <FEATURE_VALUE>,
...
}
]'
```
##### 2.2 Python
*Steps*
1. Install AI Core SDK
```
!python -m pip install "ai_core_sdk[aicore-content]"
```
2. Install this content package
```
!python -m pip install sap-ai-core-datarobot
```
3. Explore the content package
List all content packages installed in the environment.
```
from ai_core_sdk.content import get_content_packages
pkgs = get_content_packages()
for pkg in pkgs.values():
print(pkg)
```
List all available pipelines in the sap-ai-core-datarobot content package.
```
content_pkg = pkgs['sap_datarobot']
for workflow in content_pkg.workflows.values():
print(workflow)
```
4. Create a config file with the name model_serving_config.yaml with the following content.
```
!python -m pip install pyyaml
```
```
serving_workflow = content_pkg.workflows["model-id-serving"]
serving_config = {
'.contentPackage': 'sap_datarobot',
'.workflow': 'model-id-serving',
'.dockerType': 'default',
'name': '<YOUR SERVING TEMPLATE NAME>',
'labels': {
'scenarios.ai.sap.com/id': "<YOUR SCENARIO ID>",
'ai.sap.com/version': "<YOUR SCENARIO VERSION>"
},
"annotations": {
"scenarios.ai.sap.com/name": "<YOUR SCENARIO NAME>",
"scenarios.ai.sap.com/description": "<YOUR SCENARIO DESCRIPTION>",
"executables.ai.sap.com/name": "<YOUR EXECUTABLE NAME>",
"executables.ai.sap.com/description": "<YOUR EXECUTABLE DESCRIPTION>"
},
'image': '<YOUR DOCKER IMAGE TAG>',
"imagePullSecret": "<YOUR DOCKER REGISTRY SECRET NAME IN AI CORE>",
"datarobotToken": "<DATAROBOT-API-TOKEN SECRET NAME IN AI CORE>"
}
import yaml
serving_config_yaml_file = "model_serving_config.yaml"
ff = open(serving_config_yaml_file, 'w+')
yaml.dump(serving_config, ff , allow_unicode=True)
```
5. Fill in the desired values in the config file. An example config file is shown below.
```
serving_config = {
'.contentPackage': 'sap_datarobot',
'.workflow': 'model-id-serving',
'.dockerType': 'default',
'name': 'datarobot-model-serving',
'labels': {
'scenarios.ai.sap.com/id': "00db4197-1538-4640-9ea9-44731041ed88",
'ai.sap.com/version': "0.0.1"
},
"annotations": {
"scenarios.ai.sap.com/name": "my-datarobot-scenario",
"executables.ai.sap.com/name": "datarobot-model-serving",
"executables.ai.sap.com/description": "datarobot model serving",
"scenarios.ai.sap.com/description": "my datarobot scenario"
},
'image': 'docker.io/<YOUR_DOCKER_USERNAME>/model-serve:1.0',
"imagePullSecret": "my-docker-secret",
"datarobotToken": "my-datarobot-secret"
}
import yaml
serving_config_yaml_file = "model_serving_config.yaml"
ff = open(serving_config_yaml_file, 'w+')
yaml.dump(serving_config, ff , allow_unicode=True)
```
6. Generate a docker image
This step involves building a docker image with the tag specified in the model_serving_config.yaml file.
```
# keep the docker up and running before executing this cell
# docker login
import os
docker_user = "[USER NAME]"
docker_pwd = "[PASSWORD]"
os.system(f'docker login <YOUR_DOCKER_REGISTRY_URL> -u {docker_user} -p {docker_pwd}')
with open(serving_config_yaml_file) as stream:
workflow_config = yaml.load(stream)
serving_workflow.create_image(workflow_config) # actually build the docker container
#When an error occurs, perform a dry run to debug any error occured while running the create_image() function.
docker_build_cmd = serving_workflow.create_image(workflow_config, return_cmd = True)
print(' '.join(docker_build_cmd))
```
7. Push the docker image to your docker repository
```
os.system(f'docker push {workflow_config["image"]}') # push the container
```
8. Generate a serving template
Clone the git repository that was registered with your SAP AI Core tenant during Onboarding.
```
import pathlib
output_file = '<TEMPLATES FOLDER PATH IN YOUR CLONED GIT REPO>/model-serving-template.yaml'
serving_workflow.create_template(serving_config_yaml_file, output_file)
```
You can configure SAP AI Core to use different infrastructure resources for different tasks, based on demand. Within SAP AI Core, the resource plan is selected via the `ai.sap.com/resourcePlan` label in the serving template. By default, sap-ai-core-datarobot workflows use `starter` resource plan which entails the use of 1 CPU core and 3 Memeory GBs. For more information on how to select a different resource plan, you can refer to the documentation [choosing a resource plan](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/choose-resource-plan-c58d4e584a5b40a2992265beb9b6be3c?q=resource%20plan).
9. Fill in the datarobot secrets name in serving template
In the model-serving-template.yaml serving template file, substitute `<DATAROBOT-ENDPOINT-TOKEN>` with the name of your datarobot secrets.
```
def modify_serving_template(workflow_config, template_file_path):
import yaml
import sys
from yaml.resolver import BaseResolver
with open(template_file_path, 'r') as f_read:
content = yaml.load(f_read, yaml.FullLoader)
predictor_spec = content["spec"]["template"]["spec"]
predictor_spec = predictor_spec.replace('<DATAROBOT-ENDPOINT-TOKEN>', serving_config['datarobotToken'] )
content["spec"]["template"]["spec"] = predictor_spec
yaml.SafeDumper.org_represent_str = yaml.SafeDumper.represent_str
def repr_str(dumper, data):
if '\n' in data:
return dumper.represent_scalar(u'tag:yaml.org,2002:str', data, style='|')
return dumper.org_represent_str(data)
yaml.add_representer(str, repr_str, Dumper=yaml.SafeDumper)
with open(template_file_path, 'w') as f_write:
f_write.write(yaml.safe_dump(content))
modify_serving_template(workflow_config, output_file)
```
10. Push the serving template to your git repository
```
import os
import subprocess
repo_path = "<PATH TO YOUR CLONED GIT REPO>"
current_dir = os.getcwd()
os.chdir(repo_path)
# add the file to the git repository
subprocess.run(["git", "add", f"{output_file}"])
# commit the changes
subprocess.run(["git", "commit", "-m", f'updated template {workflow_config["image"]}'])
# push the changes
subprocess.run(["git", "push"])
os.chdir(current_dir)
```
11. Obtain a client credentials token to AI Core
```
import json
from ai_api_client_sdk.ai_api_v2_client import AIAPIV2Client
from ai_api_client_sdk.models.artifact import Artifact
from ai_api_client_sdk.models.parameter_binding import ParameterBinding
from ai_api_client_sdk.models.input_artifact_binding import InputArtifactBinding
from ai_api_client_sdk.models.status import Status
from ai_api_client_sdk.models.target_status import TargetStatus
import time
from IPython.display import clear_output
import requests
import pprint
# Load AICore and Object Store credentials
credCF, credS3 = {}, {}
with open('aicore-creds.json') as cf:
credCF = json.load(cf)
with open('s3-creds.json') as s3:
credS3 = json.load(s3)
#Authentication
RESOURCE_GROUP="<YOUR RESOURCE GROUP NAME>"
ai_api_v2_client = AIAPIV2Client(
base_url=credCF["serviceurls"]["ML_API_URL"] + "/v2/lm",
auth_url=credCF["url"] + "/oauth/token",
client_id=credCF['clientid'],
client_secret=credCF['clientsecret'],
resource_group=RESOURCE_GROUP
)
```
12. Create Generic Secrets in ResourceGroup
To authenticate with DataRobot's API, your code needs to have access to an endpoint and token. In AI Core, create a generic secret for the Endpoint and the token; these secrets are used to access the model from DataRobot. Refer AI Core documentation to [create a generic secret](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-generic-secret?q=generic%20secrets).
Note that the AI Core AI API expects sensitive data to be Base64-encoded. You can easily encode your data in Base64 format using the following command on Linux or MacOS:
```
echo -n 'my-sensitive-data' | base64
```
```
import requests
ai_api_url = credCF["serviceurls"]["ML_API_URL"] + "/v2/admin/secrets"
token = ai_api_v2_client.rest_client.get_token()
headers = {
"Authorization": token,
"Content-Type": "application/json",
"AI-Resource-Group": RESOURCE_GROUP
}
data = {
"name": "<DATAROBOT-API-TOKEN SECRET NAME IN AI CORE>",
"data": {
"endpoint": "<BASE64-ENCODED DATAROBOT API ENDPOINT>",
"token": "<BASE64-ENCODED DATAROBOT API TOKEN>"
}
}
response = requests.post(ai_api_url, headers=headers, json=data)
if response.status_code == 201:
print("Secret created successfully!")
else:
print("Request failed with status code:", response.status_code)
print("Response text:", response.text)
```
13. Create a configuration and save the configuration id from the response.
```
#define deployment confgiuration
project_id = {
"key": "projectID",
"value": "<PROJECT ID OF YOUR MODEL IN DATAROBOT>"
}
model_id = {
"key": "modelID",
"value": "<YOUR MODEL ID FROM DATAROBOT>"
}
deployment_configuration = {
"name": "<CONFIGURATION NAME>",
"scenario_id": workflow_config["labels"]["scenarios.ai.sap.com/id"],
"executable_id": workflow_config["name"],
"parameter_bindings": [ParameterBinding(**project_id), ParameterBinding(**model_id)]
}
deployment_config_resp = ai_api_v2_client.configuration.create(**deployment_configuration)
assert deployment_config_resp.message == 'Configuration created'
```
14. Create a deployment and note down the deployment id from the response
```
deployment_resp = ai_api_v2_client.deployment.create(deployment_config_resp.id)
```
15. Check the status of the deployment. Note down the deployment URL after the status changes to RUNNING.
```
# poll deployment status
status = None
while status != Status.RUNNING and status != Status.DEAD:
time.sleep(5)
clear_output(wait=True)
deployment = ai_api_v2_client.deployment.get(deployment_resp.id)
status = deployment.status
print('...... deployment status ......', flush=True)
print(deployment.status)
print(deployment.status_details)
time.sleep(10) # time for deployment url getting ready
print('endpoint: ', deployment.deployment_url)
```
16. Use your deployment.
```
with open('sample_payload.json') as cf:
sample_input = json.load(cf)
# inference
endpoint = "{deploy_url}/v1/models/model:predict".format(deploy_url=deployment.deployment_url)
headers = {"Authorization": ai_api_v2_client.rest_client.get_token(), 'ai-resource-group': RESOURCE_GROUP}
response = requests.post(endpoint, headers=headers, json=test_input)
pprint.pprint(['inference result:', response.json()])
time.sleep(10)
```
### Security Guide
See [Security in SAP AI Core](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/security?locale=en-US) for general information about how SAP AI Core handles security.
Raw data
{
"_id": null,
"home_page": "https://www.sap.com/",
"name": "sap-ai-core-datarobot",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "SAP AI Core,DataRobot",
"author": "SAP SE",
"author_email": "",
"download_url": "https://pypi.python.org/pypi/sap-ai-core-datarobot",
"platform": null,
"description": "## content package for DataRobot integration for SAP AI Core\n\n## Objective\n\nsap-ai-core-datarobot is a content package to deploy DataRobot workflows in AI Core. This package provides support for two distinct deployment workflows, provided that a trained model is already present in DataRobot.\n- Export the model from DataRobot to an Object Store and then integrate the Object Store with AI Core for model deployment.\n- Directly integrate AI Core with the model in DataRobot utilizing the DataRobot API.\n\n### User Guide\n\n#### 1. Workflow 1: Exporting Models from DataRobot to Object Store and Integrating with AI Core\n\n*Pre-requisites*\n\n1. Complete [AI Core Onboarding](https://help.sap.com/viewer/2d6c5984063c40a59eda62f4a9135bee/LATEST/en-US/8ce24833036d481cb3113a95e3a39a07.html)\n - [Initial setup](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/initial-setup)\n - Create a [Resource Group](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-resource-group)\n2. Access to the [Git repository](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/register-your-git-repository-and-secrets), [Docker repository](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/register-your-docker-registry-secret) and [Object Store](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/register-your-object-store-secret) onboarded to AI Core\n3. You have a registered DataRobot account, trained a model, downloaded the model from DataRobot and stored the model in Object Store configured with AI Core.\n\nThe interface for sap-ai-core-datarobot content package is part of the `ai-core-sdk`.ai-core-sdk provides a command-line utility as well as a python library to use AICore content packages. \n\nPlease note that this sap-ai-core-datarobot package documentation provides the instructions for using this specific content package. For a more comprehensive understanding of how to use a content package, refer to the [ai-core-sdk package documentation](https://pypi.org/project/ai-core-sdk/).\n\n##### 1.1 CLI\n\n*Steps*\n\n1. Install AI Core SDK\n\n ```\n pip install \"ai-core-sdk[aicore_content]\"\n ```\n2. Install this content package\n\n ```\n pip install sap-ai-core-datarobot\n ```\n3. Explore the content package\n\n List all content packages installed in the environment.\n ```\n aicore-content list\n ```\n List all available pipelines in the sap-ai-core-datarobot content package.\n ```\n aicore-content list sap_datarobot\n ```\n View the parameters available in the selected pipeline.\n ```\n aicore-content show sap_datarobot model-jar-serving\n ```\n Check all available commands by using the `--help` flag.\n ```\n aicore-content --help\n ```\n4. Create a config file with the name model_serving_config.yaml with the following content.\n\n ```\n .contentPackage: sap_datarobot\n .dockerType: default\n .workflow: model-jar-serving\n annotations:\n executables.ai.sap.com/description: <YOUR EXECUTABLE DESCRIPTION>\n executables.ai.sap.com/name: <YOUR EXECUTABLE NAME>\n scenarios.ai.sap.com/description: <YOUR SCENARIO DESCRIPTION>\n scenarios.ai.sap.com/name: <YOUR SCENARIO NAME>\n image: <YOUR DOCKER IMAGE TAG>\n imagePullSecret: <YOUR DOCKER REGISTRY SECRET NAME IN AI CORE>\n labels:\n ai.sap.com/version: <YOUR SCENARIO VERSION>\n scenarios.ai.sap.com/id: <YOUR SCENARIO ID>\n name: <YOUR SERVING TEMPLATE NAME>\n ```\n5. Fill in the desired values in the config file. An example config file is shown below.\n\n ```\n .contentPackage: sap_datarobot\n .dockerType: default\n .workflow: model-jar-serving\n annotations:\n executables.ai.sap.com/description: datarobot model serving\n executables.ai.sap.com/name: datarobot-model-serving\n scenarios.ai.sap.com/description: my datarobot scenario\n scenarios.ai.sap.com/name: my-datarobot-scenario\n image: docker.io/<YOUR_DOCKER_USERNAME>/model-serve:1.0\n imagePullSecret: my-docker-secret\n labels:\n ai.sap.com/version: 0.0.1\n scenarios.ai.sap.com/id: 00db4197-1538-4640-9ea9-44731041ed88\n name: datarobot-model-serving\n ```\n6. Generate a docker image.\n\n This step involves building a docker image with the tag specified in the model_serving_config.yaml file. The command to perform this operation is as follows:\n ```\n aicore-content create-image -p sap_datarobot -w model-jar-serving model_serving_config.yaml\n ```\n7. Push the docker image to your docker repository\n\n The image tag should correspond to the one provided in the 'model_serving_config.yaml' file.\n ```\n docker push <YOUR DOCKER IMAGE TAG>\n ```\n8. Generate a serving template\n\n Clone the git repository that was registered with your SAP AI Core tenant during Onboarding.\n ```\n aicore-content create-template -p sap_datarobot -w model-jar-serving model_serving_config.yaml -o '<TEMPLATES FOLDER PATH IN YOUR CLONED GIT REPO>/model-serving-template.yaml'\n ```\n You can configure SAP AI Core to use different infrastructure resources for different tasks, based on demand. Within SAP AI Core, the resource plan is selected via the `ai.sap.com/resourcePlan` label in the serving template. By default, sap-ai-core-datarobot workflows use `starter` resource plan which entails the use of 1 CPU core and 3 Memeory GBs. For more information on how to select a different resource plan, you can refer to the documentation [choosing a resource plan](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/choose-resource-plan-c58d4e584a5b40a2992265beb9b6be3c?q=resource%20plan).\n9. Push the serving template to your git repository\n\n ```\n cd <PATH TO YOUR CLONED GIT REPO>\n git add <TEMPLATES FOLDER PATH IN YOUR CLONED GIT REPO>/model-serving-template.yaml\n git commit -m 'updated template model-serving-template.yaml'\n git push\n ```\n10. Obtain a client credentials token to AI Core\n\n ```\n curl --location '<YOUR AI CORE AUTH ENDPOINT URL>/oauth/token' --header 'Authorization: Basic <YOUR AI CORE CREDENTIALS>'\n ```\n11. Create an artifact to connect the DataRobot model, to make it available for use in SAP AI Core. Save the model artifact id from the response.\n\n ```\n curl --location --request POST \"<YOUR AI CORE URL>/v2/lm/artifacts\" \\\n --header \"Authorization: Bearer <CLIENT CREDENTAILS TOKEN>\" \\\n --header \"Content-Type: application/json\" \\\n --header \"AI-Resource-Group: <YOUR RESOURCE GROUP NAME>\" \\\n --data-raw '{\n \"name\": \"my-datarobot-model\",\n \"kind\": \"model\",\n \"url\": \"ai://<YOUR OBJECTSTORE NAME>/<YOUR MODEL PATH>\",\n \"description\": \"my datarobot model jar\",\n \"scenarioId\": \"<YOUR SCENARIO ID>\"\n }'\n ```\n12. Create a configuration and save the configuration id from the response.\n\n ```\n curl --request POST \"<YOUR AI CORE URL>/v2/lm/configurations\" \\\n --header \"Authorization: Bearer <CLIENT CREDENTAILS TOKEN>\" \\\n --header \"AI-Resource-Group: <YOUR RESOURCE GROUP NAME>\" \\\n --header \"Content-Type: application/json\" \\\n --data '{\n \"name\": \"<CONFIGURATION NAME>\",\n \"executableId\": \"<YOUR EXECUTABLE ID>\",\n \"scenarioId\": \"<YOUR SCENARIO ID>\",\n \"parameterBindings\": [\n {\n \"key\": \"modelName\",\n \"value\": \"<YOUR MODEL JAR FILE NAME>\"\n }\n ],\n \"inputArtifactBindings\": [\n {\n \"key\": \"modeljar\",\n \"artifactId\": \"<YOUR MODEL ARTIFACT ID>\"\n }\n ]\n }'\n ```\n13. Create a deployment and note down the deployment id from the response\n\n ```\n curl --location --globoff --request POST '<YOUR AI CORE URL>/v2/lm/configurations/<YOUR CONFIGURATION ID>/deployments' \\\n --header 'AI-Resource-Group: <YOUR RESOURCE GROUP NAME>' \\\n --header 'Authorization: Bearer <CLIENT CREDENTAILS TOKEN>'\n ```\n14. Check the status of the deployment. Note down the deployment URL after the status changes to RUNNING.\n\n ```\n curl --location --globoff '<YOUR AI CORE URL>/v2/lm/deployments/<YOUR DEPLOYMENT ID>' \\\n --header 'AI-Resource-Group: <YOUR RESOURCE GROUP NAME>' \\\n --header 'Authorization: Bearer <CLIENT CREDENTAILS TOKEN>'\n ```\n15. Use your deployment. \n\n ```\n curl --location '<YOUR DEPLOYMENT URL>/v1/models/,<YOUR MODEL JAR FILE NAME>:predict' \\\n --header 'AI-Resource-Group: <YOUR RESOURCE GROUP NAME>' \\\n --header 'Content-Type: application/json' \\\n --header 'Authorization: Bearer <CLIENT CREDENTAILS TOKEN>' \\\n --data '[\n {\n \"<FEATURE_NAME>\": <VALUE>,\n ...\n }\n ]'\n ```\n\n##### 1.2 Python\n\n*Steps*\n\n1. Install AI Core SDK\n\n ```\n !python -m pip install \"ai_core_sdk[aicore-content]\"\n ```\n2. Install this content package\n\n ```\n !python -m pip install sap-ai-core-datarobot\n ```\n3. Explore the content package\n\n List all content packages installed in the environment.\n ```\n from ai_core_sdk.content import get_content_packages\n pkgs = get_content_packages()\n for pkg in pkgs.values():\n print(pkg)\n ```\n List all available pipelines in the sap-ai-core-datarobot content package.\n ```\n content_pkg = pkgs['sap_datarobot']\n for workflow in content_pkg.workflows.values():\n print(workflow) \n ```\n4. Create a config file with the name model_serving_config.yaml with the following content.\n\n ```\n !python -m pip install pyyaml\n ```\n ```\n serving_workflow = content_pkg.workflows[\"model-jar-serving\"]\n\n serving_config = {\n '.contentPackage': 'sap_datarobot',\n '.workflow': 'model-jar-serving',\n '.dockerType': 'default',\n 'name': '<YOUR SERVING TEMPLATE NAME>',\n 'labels': {\n 'scenarios.ai.sap.com/id': \"<YOUR SCENARIO ID>\",\n 'ai.sap.com/version': \"<YOUR SCENARIO VERSION>\"\n },\n \"annotations\": {\n \"scenarios.ai.sap.com/name\": \"<YOUR SCENARIO NAME>\",\n \"scenarios.ai.sap.com/description\": \"<YOUR SCENARIO DESCRIPTION>\",\n \"executables.ai.sap.com/name\": \"<YOUR EXECUTABLE NAME>\",\n \"executables.ai.sap.com/description\": \"<YOUR EXECUTABLE DESCRIPTION>\"\n },\n 'image': '<YOUR DOCKER IMAGE TAG>',\n \"imagePullSecret\": \"<YOUR DOCKER REGISTRY SECRET NAME IN AI CORE>\"\n }\n\n import yaml\n serving_config_yaml_file = \"model_serving_config.yaml\"\n ff = open(serving_config_yaml_file, 'w+')\n yaml.dump(serving_config, ff , allow_unicode=True)\n ```\n5. Fill in the desired values in the config file. An example config file is shown below.\n\n ```\n serving_config = {\n '.contentPackage': 'sap_datarobot',\n '.workflow': 'model-jar-serving',\n '.dockerType': 'default',\n 'name': 'datarobot-model-serving',\n 'labels': {\n 'scenarios.ai.sap.com/id': \"00db4197-1538-4640-9ea9-44731041ed88\",\n 'ai.sap.com/version': \"0.0.1\"\n },\n \"annotations\": {\n \"scenarios.ai.sap.com/name\": \"my-datarobot-scenario\",\n \"executables.ai.sap.com/name\": \"datarobot-model-serving\",\n \"executables.ai.sap.com/description\": \"datarobot model serving\",\n \"scenarios.ai.sap.com/description\": \"my datarobot scenario\"\n },\n 'image': 'docker.io/<YOUR_DOCKER_USERNAME>/model-serve:1.0',\n \"imagePullSecret\": \"my-docker-secret\"\n }\n\n import yaml\n serving_config_yaml_file = \"model_serving_config.yaml\"\n ff = open(serving_config_yaml_file, 'w+')\n yaml.dump(serving_config, ff , allow_unicode=True)\n ```\n6. Generate a docker image\n\n This step involves building a docker image with the tag specified in the model_serving_config.yaml file.\n ```\n # keep the docker up and running before executing this cell\n # docker login\n import os\n docker_user = \"[USER NAME]\"\n docker_pwd = \"[PASSWORD]\"\n os.system(f'docker login <YOUR_DOCKER_REGISTRY_URL> -u {docker_user} -p {docker_pwd}')\n\n with open(serving_config_yaml_file) as stream:\n workflow_config = yaml.load(stream)\n serving_workflow.create_image(workflow_config) # actually build the docker container\n\n #When an error occurs, perform a dry run to debug any error occured while running the create_image() function.\n docker_build_cmd = serving_workflow.create_image(workflow_config, return_cmd = True)\n print(' '.join(docker_build_cmd))\n ```\n7. Push the docker image to your docker repository\n\n ```\n os.system(f'docker push {workflow_config[\"image\"]}') # push the container\n ```\n8. Generate a serving template\n\n Clone the git repository that was registered with your SAP AI Core tenant during Onboarding.\n ```\n import pathlib\n output_file = '<TEMPLATES FOLDER PATH IN YOUR CLONED GIT REPO>/model-serving-template.yaml'\n serving_workflow.create_template(serving_config_yaml_file, output_file)\n ```\n You can configure SAP AI Core to use different infrastructure resources for different tasks, based on demand. Within SAP AI Core, the resource plan is selected via the `ai.sap.com/resourcePlan` label in the serving template. By default, sap-ai-core-datarobot workflows use `starter` resource plan which entails the use of 1 CPU core and 3 Memeory GBs. For more information on how to select a different resource plan, you can refer to the documentation [choosing a resource plan](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/choose-resource-plan-c58d4e584a5b40a2992265beb9b6be3c?q=resource%20plan).\n9. Push the serving template to your git repository\n\n ```\n import os\n import subprocess\n repo_path = \"<PATH TO YOUR CLONED GIT REPO>\" \n current_dir = os.getcwd()\n os.chdir(repo_path)\n\n # add the file to the git repository\n subprocess.run([\"git\", \"add\", f\"{output_file}\"])\n\n # commit the changes\n subprocess.run([\"git\", \"commit\", \"-m\", f'updated template {workflow_config[\"image\"]}'])\n\n # push the changes\n subprocess.run([\"git\", \"push\"])\n\n os.chdir(current_dir)\n ```\n10. Obtain a client credentials token to AI Core\n\n ```\n import json\n from ai_api_client_sdk.ai_api_v2_client import AIAPIV2Client\n from ai_api_client_sdk.models.artifact import Artifact\n from ai_api_client_sdk.models.parameter_binding import ParameterBinding\n from ai_api_client_sdk.models.input_artifact_binding import InputArtifactBinding\n from ai_api_client_sdk.models.status import Status\n from ai_api_client_sdk.models.target_status import TargetStatus\n import time\n from IPython.display import clear_output\n import requests\n import pprint\n\n # Load AICore and Object Store credentials\n credCF, credS3 = {}, {}\n with open('aicore-creds.json') as cf:\n credCF = json.load(cf)\n with open('s3-creds.json') as s3:\n credS3 = json.load(s3)\n\n #Authentication\n RESOURCE_GROUP=\"<YOUR RESOURCE GROUP NAME>\"\n ai_api_v2_client = AIAPIV2Client(\n base_url=credCF[\"serviceurls\"][\"ML_API_URL\"] + \"/v2/lm\",\n auth_url=credCF[\"url\"] + \"/oauth/token\",\n client_id=credCF['clientid'],\n client_secret=credCF['clientsecret'],\n resource_group=RESOURCE_GROUP\n )\n ```\n11. Create an artifact to connect the DataRobot model, to make it available for use in SAP AI Core. Save the model artifact id from the response.\n\n ```\n # GET scenario\n response = ai_api_v2_client.scenario.query(RESOURCE_GROUP)\n ai_scenario = next(scenario_obj for scenario_obj in response.resources if scenario_obj.id == workflow_config[\"labels\"][\"scenarios.ai.sap.com/id\"] )\n print(\"Scenario id: \", ai_scenario.id)\n print(\"Scenario name: \", ai_scenario.name)\n\n # GET List of scenario executables\n response = ai_api_v2_client.executable.query(scenario_id=ai_scenario.id)\n for executable in response.resources:\n print(executable)\n\n #Register the model from Object Store as an artifact\n artifact = {\n \"name\": \"my-datarobot-model\",\n \"kind\": Artifact.Kind.MODEL,\n \"url\": \"ai://<YOUR OBJECTSTORE NAME>/<YOUR MODEL PATH>\",\n \"description\": \"my datarobot model jar\",\n \"scenario_id\": ai_scenario.id\n }\n artifact_resp = ai_api_v2_client.artifact.create(**artifact)\n assert artifact_resp.message == 'Artifact acknowledged'\n print(artifact_resp.url)\n ```\n12. Create a configuration and save the configuration id from the response.\n\n ```\n #define deployment confgiuration\n artifact_binding = {\n \"key\": \"modeljar\",\n \"artifact_id\": artifact_resp.id\n }\n\n parameter_binding = {\n \"key\": \"modelName\",\n \"value\": \"<YOUR MODEL JAR FILE NAME>\" #model file name in Object Store\n }\n\n deployment_configuration = {\n \"name\": \"<CONFIGURATION NAME>\",\n \"scenario_id\": workflow_config[\"labels\"][\"scenarios.ai.sap.com/id\"],\n \"executable_id\": workflow_config[\"name\"],\n \"parameter_bindings\": [ParameterBinding(**parameter_binding)],\n \"input_artifact_bindings\": [ InputArtifactBinding(**artifact_binding) ]\n }\n\n deployment_config_resp = ai_api_v2_client.configuration.create(**deployment_configuration)\n assert deployment_config_resp.message == 'Configuration created'\n ```\n13. Create a deployment and note down the deployment id from the response\n\n ```\n deployment_resp = ai_api_v2_client.deployment.create(deployment_config_resp.id)\n ```\n14. Check the status of the deployment. Note down the deployment URL after the status changes to RUNNING.\n\n ```\n # poll deployment status\n status = None\n while status != Status.RUNNING and status != Status.DEAD:\n time.sleep(5)\n clear_output(wait=True)\n deployment = ai_api_v2_client.deployment.get(deployment_resp.id)\n status = deployment.status\n print('...... deployment status ......', flush=True)\n print(deployment.status)\n print(deployment.status_details)\n\n time.sleep(10) # time for deployment url getting ready\n print('endpoint: ', deployment.deployment_url)\n ```\n15. Use your deployment.\n\n ```\n with open('sample_payload.json') as cf:\n sample_input = json.load(cf)\n\n # inference\n endpoint = \"{deploy_url}/v1/models/{model_name}:predict\".format(deploy_url=deployment.deployment_url, model_name = parameter_binding[\"value\"])\n headers = {\"Authorization\": ai_api_v2_client.rest_client.get_token(), 'ai-resource-group': RESOURCE_GROUP}\n\n response = requests.post(endpoint, headers=headers, json=test_input)\n pprint.pprint(['inference result:', response.json()])\n time.sleep(10) \n ```\n\n#### 2. Direct Integration of AI Core with DataRobot Models via DataRobot API\n\n*Pre-requisites*\n\n1. Complete [AI Core Onboarding](https://help.sap.com/viewer/2d6c5984063c40a59eda62f4a9135bee/LATEST/en-US/8ce24833036d481cb3113a95e3a39a07.html)\n - [Initial setup](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/initial-setup)\n - Create a [Resource Group](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-resource-group)\n2. Access to the [Git repository](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/register-your-git-repository-and-secrets), [Docker repository](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/register-your-docker-registry-secret) and [Object Store](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/register-your-object-store-secret) onboarded to AI Core\n3. You have a registered DataRobot account, trained a model in DataRobot.\n\nThe interface for sap-ai-core-datarobot content package is part of the `ai-core-sdk`.ai-core-sdk provides a command-line utility as well as a python library to use AICore content packages. \n\nPlease note that this sap-ai-core-datarobot package documentation provides the instructions for using this specific content package. For a more comprehensive understanding of how to use a content package, refer to the ai-core-sdk package documentation [here](https://pypi.org/project/ai-core-sdk/).\n\n##### 2.1 CLI\n\n*Steps*\n\n1. Install AI Core SDK\n\n ```\n pip install ai-core-sdk[aicore_content]\n ```\n2. Install this content package\n\n ```\n pip install sap-ai-core-datarobot\n ```\n3. Explore the content package\n\n List all content packages installed in the environment.\n ```\n aicore-content list\n ```\n List all available pipelines in the sap-ai-core-datarobot content package.\n ```\n aicore-content list sap_datarobot\n ```\n View the parameters available in the selected pipeline.\n ```\n aicore-content show sap_datarobot model-id-serving\n ```\n Check all available commands by using the `--help` flag.\n ```\n aicore-content --help\n ```\n4. Create a config file with the name model_serving_config.yaml with the following content.\n\n ```\n .contentPackage: sap_datarobot\n .dockerType: default\n .workflow: model-id-serving\n annotations:\n executables.ai.sap.com/description: <YOUR EXECUTABLE DESCRIPTION>\n executables.ai.sap.com/name: <YOUR EXECUTABLE NAME>\n scenarios.ai.sap.com/description: <YOUR SCENARIO DESCRIPTION>\n scenarios.ai.sap.com/name: <YOUR SCENARIO NAME>\n image: <YOUR DOCKER IMAGE TAG>\n imagePullSecret: <YOUR DOCKER REGISTRY SECRET NAME IN AI CORE>\n datarobotToken: <DATAROBOT-API-TOKEN SECRET NAME IN AI CORE>\n labels:\n ai.sap.com/version: <YOUR SCENARIO VERSION>\n scenarios.ai.sap.com/id: <YOUR SCENARIO ID>\n name: <YOUR SERVING TEMPLATE NAME>\n ```\n5. Fill in the desired values in the config file. An example config file is shown below.\n\n ```\n .contentPackage: sap_datarobot\n .dockerType: default\n .workflow: model-id-serving\n annotations:\n executables.ai.sap.com/description: datarobot model serving\n executables.ai.sap.com/name: datarobot-model-serving\n scenarios.ai.sap.com/description: my datarobot scenario\n scenarios.ai.sap.com/name: my-datarobot-scenario\n image: docker.io/<YOUR_DOCKER_USERNAME>/model-serve:1.0\n imagePullSecret: my-docker-secret\n datarobotToken: my-datarobot-secret\n labels:\n ai.sap.com/version: 0.0.1\n scenarios.ai.sap.com/id: 00db4197-1538-4640-9ea9-44731041ed88\n name: datarobot-model-serving\n ```\n6. Generate a docker image\n\n This step involves building a docker image with the tag specified in the model_serving_config.yaml file. The command to perform this operation is as follows:\n ```\n aicore-content create-image -p sap_datarobot -w model-id-serving model_serving_config.yaml\n ```\n7. Push the docker image to your docker repository\n\n The image tag should correspond to the one provided in the 'model_serving_config.yaml' file.\n ```\n docker push <YOUR DOCKER IMAGE TAG>\n ```\n8. Generate a serving template\n\n Clone the git repository that was registered with your SAP AI Core tenant during Onboarding.\n ```\n aicore-content create-template -p sap_datarobot -w model-id-serving model_serving_config.yaml -o '<TEMPLATES FOLDER PATH IN YOUR CLONED GIT REPO>/model-serving-template.yaml'\n ```\n You can configure SAP AI Core to use different infrastructure resources for different tasks, based on demand. Within SAP AI Core, the resource plan is selected via the `ai.sap.com/resourcePlan` label in the serving template. By default, sap-ai-core-datarobot workflows use `starter` resource plan which entails the use of 1 CPU core and 3 Memeory GBs. For more information on how to select a different resource plan, you can refer to the documentation [choosing a resource plan](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/choose-resource-plan-c58d4e584a5b40a2992265beb9b6be3c?q=resource%20plan).\n9. Fill in the datarobot secrets name in serving template\n\n In the model-serving-template.yaml serving template file, substitute `<DATAROBOT-ENDPOINT-TOKEN>` with the name of your datarobot secrets.\n10. Push the serving template to your git repository\n\n ```\n cd <PATH TO YOUR CLONED GIT REPO>\n git add <TEMPLATES FOLDER PATH IN YOUR CLONED GIT REPO>/model-serving-template.yaml\n git commit -m 'updated template model-serving-template.yaml'\n git push\n ```\n11. Obtain a client credentials token to AI Core\n\n ```\n curl --location '<YOUR AI CORE AUTH ENDPOINT URL>/oauth/token' --header 'Authorization: Basic <YOUR AI CORE CREDENTIALS>'\n ```\n12. Create Generic Secrets in ResourceGroup\n\n To authenticate with DataRobot's API, your code needs to have access to an endpoint and token. In AI Core, create a generic secret for the Endpoint and the token; these secrets are used to access the model from DataRobot. Refer AI Core documentation to [create a generic secret](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-generic-secret?q=generic%20secrets).\n\n Note that the AI Core AI API expects sensitive data to be Base64-encoded. You can easily encode your data in Base64 format using the following command on Linux or MacOS: \n ```\n echo -n 'my-sensitive-data' | base64\n ```\n ```\n curl --location --request POST \"<YOUR AI CORE URL>/v2/admin/secrets\" \\\n --header \"Authorization: Bearer <CLIENT CREDENTAILS TOKEN>\" \\\n --header 'Content-Type: application/json' \\\n --header 'AI-Resource-Group: <YOUR RESOURCE GROUP NAME>' \\\n --data-raw '{\n \"name\": \"<DATAROBOT-API-TOKEN SECRET NAME IN AI CORE>\",\n \"data\": {\n \"endpoint\": \"<BASE64-ENCODED DATAROBOT API ENDPOINT>\",\n \"token\": \"<BASE64-ENCODED DATAROBOT API TOKEN>\"\n }\n }'\t\t\t\t\n ```\n13. Create a configuration and save the configuration id from the response.\n\n ```\n curl --request POST \"<YOUR AI CORE URL>/v2/lm/configurations\" \\\n --header \"Authorization: Bearer <CLIENT CREDENTAILS TOKEN>\" \\\n --header \"AI-Resource-Group: <YOUR RESOURCE GROUP NAME>\" \\\n --header \"Content-Type: application/json\" \\\n --data '{\n \"name\": \"<CONFIGURATION NAME>\",\n \"executableId\": \"<YOUR EXECUTABLE ID>\",\n \"scenarioId\": \"<YOUR SCENARIO ID>\",\n \"parameterBindings\": [\n {\n \"key\": \"projectID\",\n \"value\": \"<PROJECT ID OF YOUR MODEL IN DATAROBOT>\"\n },\n {\n \"key\": \"modelID\",\n \"value\": \"<YOUR MODEL ID FROM DATAROBOT>\"\n }\n ]\n }'\n ```\n14. Create a deployment and note down the deployment id from the response\n\n ```\n curl --location --globoff --request POST '<YOUR AI CORE URL>/v2/lm/configurations/<YOUR CONFIGURATION ID>/deployments' \\\n --header 'AI-Resource-Group: <YOUR RESOURCE GROUP NAME>' \\\n --header 'Authorization: Bearer <CLIENT CREDENTAILS TOKEN>'\n ```\n15. Check the status of the deployment. Note down the deployment URL after the status changes to RUNNING.\n\n ```\n curl --location --globoff '<YOUR AI CORE URL>/v2/lm/deployments/<YOUR DEPLOYMENT ID>' \\\n --header 'AI-Resource-Group: <YOUR RESOURCE GROUP NAME>' \\\n --header 'Authorization: Bearer <CLIENT CREDENTAILS TOKEN>'\n ```\n16. Use your deployment.\n\n ```\n curl --location '<YOUR DEPLOYMENT URL>/v1/models/model:predict' \\\n --header 'AI-Resource-Group: <YOUR RESOURCE GROUP NAME>' \\\n --header 'Content-Type: application/json' \\\n --header 'Authorization: Bearer <CLIENT CREDENTAILS TOKEN>' \\\n --data '[\n {\n \"<FEATURE_NAME>\": <FEATURE_VALUE>,\n ...\n }\n ]'\n ```\n\n##### 2.2 Python\n\n*Steps*\n\n1. Install AI Core SDK\n\n ```\n !python -m pip install \"ai_core_sdk[aicore-content]\"\n ```\n2. Install this content package\n\n ```\n !python -m pip install sap-ai-core-datarobot\n ```\n3. Explore the content package\n\n List all content packages installed in the environment.\n ```\n from ai_core_sdk.content import get_content_packages\n pkgs = get_content_packages()\n for pkg in pkgs.values():\n print(pkg)\n ```\n List all available pipelines in the sap-ai-core-datarobot content package.\n ```\n content_pkg = pkgs['sap_datarobot']\n for workflow in content_pkg.workflows.values():\n print(workflow) \n ```\n4. Create a config file with the name model_serving_config.yaml with the following content.\n\n ```\n !python -m pip install pyyaml\n ```\n ```\n serving_workflow = content_pkg.workflows[\"model-id-serving\"]\n\n serving_config = {\n '.contentPackage': 'sap_datarobot',\n '.workflow': 'model-id-serving',\n '.dockerType': 'default',\n 'name': '<YOUR SERVING TEMPLATE NAME>',\n 'labels': {\n 'scenarios.ai.sap.com/id': \"<YOUR SCENARIO ID>\",\n 'ai.sap.com/version': \"<YOUR SCENARIO VERSION>\"\n },\n \"annotations\": {\n \"scenarios.ai.sap.com/name\": \"<YOUR SCENARIO NAME>\",\n \"scenarios.ai.sap.com/description\": \"<YOUR SCENARIO DESCRIPTION>\",\n \"executables.ai.sap.com/name\": \"<YOUR EXECUTABLE NAME>\",\n \"executables.ai.sap.com/description\": \"<YOUR EXECUTABLE DESCRIPTION>\"\n },\n 'image': '<YOUR DOCKER IMAGE TAG>',\n \"imagePullSecret\": \"<YOUR DOCKER REGISTRY SECRET NAME IN AI CORE>\",\n \"datarobotToken\": \"<DATAROBOT-API-TOKEN SECRET NAME IN AI CORE>\"\n }\n\n import yaml\n serving_config_yaml_file = \"model_serving_config.yaml\"\n ff = open(serving_config_yaml_file, 'w+')\n yaml.dump(serving_config, ff , allow_unicode=True)\n ```\n5. Fill in the desired values in the config file. An example config file is shown below.\n\n ```\n serving_config = {\n '.contentPackage': 'sap_datarobot',\n '.workflow': 'model-id-serving',\n '.dockerType': 'default',\n 'name': 'datarobot-model-serving',\n 'labels': {\n 'scenarios.ai.sap.com/id': \"00db4197-1538-4640-9ea9-44731041ed88\",\n 'ai.sap.com/version': \"0.0.1\"\n },\n \"annotations\": {\n \"scenarios.ai.sap.com/name\": \"my-datarobot-scenario\",\n \"executables.ai.sap.com/name\": \"datarobot-model-serving\",\n \"executables.ai.sap.com/description\": \"datarobot model serving\",\n \"scenarios.ai.sap.com/description\": \"my datarobot scenario\"\n },\n 'image': 'docker.io/<YOUR_DOCKER_USERNAME>/model-serve:1.0',\n \"imagePullSecret\": \"my-docker-secret\",\n \"datarobotToken\": \"my-datarobot-secret\"\n }\n\n import yaml\n serving_config_yaml_file = \"model_serving_config.yaml\"\n ff = open(serving_config_yaml_file, 'w+')\n yaml.dump(serving_config, ff , allow_unicode=True)\n ```\n6. Generate a docker image\n\n This step involves building a docker image with the tag specified in the model_serving_config.yaml file. \n ```\n # keep the docker up and running before executing this cell\n # docker login\n import os\n docker_user = \"[USER NAME]\"\n docker_pwd = \"[PASSWORD]\"\n os.system(f'docker login <YOUR_DOCKER_REGISTRY_URL> -u {docker_user} -p {docker_pwd}')\n\n with open(serving_config_yaml_file) as stream:\n workflow_config = yaml.load(stream)\n serving_workflow.create_image(workflow_config) # actually build the docker container\n\n #When an error occurs, perform a dry run to debug any error occured while running the create_image() function.\n docker_build_cmd = serving_workflow.create_image(workflow_config, return_cmd = True)\n print(' '.join(docker_build_cmd))\n ```\n7. Push the docker image to your docker repository\n\n ```\n os.system(f'docker push {workflow_config[\"image\"]}') # push the container\n ```\n8. Generate a serving template\n\n Clone the git repository that was registered with your SAP AI Core tenant during Onboarding.\n ```\n import pathlib\n output_file = '<TEMPLATES FOLDER PATH IN YOUR CLONED GIT REPO>/model-serving-template.yaml'\n serving_workflow.create_template(serving_config_yaml_file, output_file)\n ```\n You can configure SAP AI Core to use different infrastructure resources for different tasks, based on demand. Within SAP AI Core, the resource plan is selected via the `ai.sap.com/resourcePlan` label in the serving template. By default, sap-ai-core-datarobot workflows use `starter` resource plan which entails the use of 1 CPU core and 3 Memeory GBs. For more information on how to select a different resource plan, you can refer to the documentation [choosing a resource plan](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/choose-resource-plan-c58d4e584a5b40a2992265beb9b6be3c?q=resource%20plan).\n9. Fill in the datarobot secrets name in serving template\n\n In the model-serving-template.yaml serving template file, substitute `<DATAROBOT-ENDPOINT-TOKEN>` with the name of your datarobot secrets.\n ```\n def modify_serving_template(workflow_config, template_file_path):\n import yaml\n import sys\n from yaml.resolver import BaseResolver\n with open(template_file_path, 'r') as f_read:\n content = yaml.load(f_read, yaml.FullLoader) \n predictor_spec = content[\"spec\"][\"template\"][\"spec\"]\n predictor_spec = predictor_spec.replace('<DATAROBOT-ENDPOINT-TOKEN>', serving_config['datarobotToken'] )\n content[\"spec\"][\"template\"][\"spec\"] = predictor_spec\n yaml.SafeDumper.org_represent_str = yaml.SafeDumper.represent_str\n def repr_str(dumper, data):\n if '\\n' in data:\n return dumper.represent_scalar(u'tag:yaml.org,2002:str', data, style='|')\n return dumper.org_represent_str(data)\n yaml.add_representer(str, repr_str, Dumper=yaml.SafeDumper)\n with open(template_file_path, 'w') as f_write:\n f_write.write(yaml.safe_dump(content))\n\n\n modify_serving_template(workflow_config, output_file)\n ```\n10. Push the serving template to your git repository\n\n ```\n import os\n import subprocess\n repo_path = \"<PATH TO YOUR CLONED GIT REPO>\" \n current_dir = os.getcwd()\n os.chdir(repo_path)\n\n # add the file to the git repository\n subprocess.run([\"git\", \"add\", f\"{output_file}\"])\n\n # commit the changes\n subprocess.run([\"git\", \"commit\", \"-m\", f'updated template {workflow_config[\"image\"]}'])\n\n # push the changes\n subprocess.run([\"git\", \"push\"])\n\n os.chdir(current_dir)\n ```\n11. Obtain a client credentials token to AI Core\n\n ```\n import json\n from ai_api_client_sdk.ai_api_v2_client import AIAPIV2Client\n from ai_api_client_sdk.models.artifact import Artifact\n from ai_api_client_sdk.models.parameter_binding import ParameterBinding\n from ai_api_client_sdk.models.input_artifact_binding import InputArtifactBinding\n from ai_api_client_sdk.models.status import Status\n from ai_api_client_sdk.models.target_status import TargetStatus\n import time\n from IPython.display import clear_output\n import requests\n import pprint\n\n # Load AICore and Object Store credentials\n credCF, credS3 = {}, {}\n with open('aicore-creds.json') as cf:\n credCF = json.load(cf)\n with open('s3-creds.json') as s3:\n credS3 = json.load(s3)\n\n #Authentication\n RESOURCE_GROUP=\"<YOUR RESOURCE GROUP NAME>\"\n ai_api_v2_client = AIAPIV2Client(\n base_url=credCF[\"serviceurls\"][\"ML_API_URL\"] + \"/v2/lm\",\n auth_url=credCF[\"url\"] + \"/oauth/token\",\n client_id=credCF['clientid'],\n client_secret=credCF['clientsecret'],\n resource_group=RESOURCE_GROUP\n )\n ```\n12. Create Generic Secrets in ResourceGroup\n\n To authenticate with DataRobot's API, your code needs to have access to an endpoint and token. In AI Core, create a generic secret for the Endpoint and the token; these secrets are used to access the model from DataRobot. Refer AI Core documentation to [create a generic secret](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-generic-secret?q=generic%20secrets).\n\n Note that the AI Core AI API expects sensitive data to be Base64-encoded. You can easily encode your data in Base64 format using the following command on Linux or MacOS: \n ```\n echo -n 'my-sensitive-data' | base64\n ```\n ```\n import requests\n\n ai_api_url = credCF[\"serviceurls\"][\"ML_API_URL\"] + \"/v2/admin/secrets\"\n token = ai_api_v2_client.rest_client.get_token()\n\n headers = {\n \"Authorization\": token,\n \"Content-Type\": \"application/json\",\n \"AI-Resource-Group\": RESOURCE_GROUP\n }\n\n data = {\n \"name\": \"<DATAROBOT-API-TOKEN SECRET NAME IN AI CORE>\",\n \"data\": {\n \"endpoint\": \"<BASE64-ENCODED DATAROBOT API ENDPOINT>\",\n \"token\": \"<BASE64-ENCODED DATAROBOT API TOKEN>\"\n }\n }\n\n response = requests.post(ai_api_url, headers=headers, json=data)\n\n if response.status_code == 201:\n print(\"Secret created successfully!\")\n else:\n print(\"Request failed with status code:\", response.status_code)\n print(\"Response text:\", response.text)\n\n ```\n13. Create a configuration and save the configuration id from the response.\n\n ```\n #define deployment confgiuration\n project_id = {\n \"key\": \"projectID\",\n \"value\": \"<PROJECT ID OF YOUR MODEL IN DATAROBOT>\" \n }\n model_id = {\n \"key\": \"modelID\",\n \"value\": \"<YOUR MODEL ID FROM DATAROBOT>\" \n }\n\n deployment_configuration = {\n \"name\": \"<CONFIGURATION NAME>\",\n \"scenario_id\": workflow_config[\"labels\"][\"scenarios.ai.sap.com/id\"],\n \"executable_id\": workflow_config[\"name\"],\n \"parameter_bindings\": [ParameterBinding(**project_id), ParameterBinding(**model_id)]\n }\n\n deployment_config_resp = ai_api_v2_client.configuration.create(**deployment_configuration)\n assert deployment_config_resp.message == 'Configuration created'\n ```\n14. Create a deployment and note down the deployment id from the response\n\n ```\n deployment_resp = ai_api_v2_client.deployment.create(deployment_config_resp.id)\n ```\n15. Check the status of the deployment. Note down the deployment URL after the status changes to RUNNING.\n\n ```\n # poll deployment status\n status = None\n while status != Status.RUNNING and status != Status.DEAD:\n time.sleep(5)\n clear_output(wait=True)\n deployment = ai_api_v2_client.deployment.get(deployment_resp.id)\n status = deployment.status\n print('...... deployment status ......', flush=True)\n print(deployment.status)\n print(deployment.status_details)\n\n time.sleep(10) # time for deployment url getting ready\n print('endpoint: ', deployment.deployment_url)\n ```\n16. Use your deployment.\n\n ```\n with open('sample_payload.json') as cf:\n sample_input = json.load(cf)\n\n # inference\n endpoint = \"{deploy_url}/v1/models/model:predict\".format(deploy_url=deployment.deployment_url)\n headers = {\"Authorization\": ai_api_v2_client.rest_client.get_token(), 'ai-resource-group': RESOURCE_GROUP}\n\n response = requests.post(endpoint, headers=headers, json=test_input)\n pprint.pprint(['inference result:', response.json()])\n time.sleep(10) \n ```\n\n### Security Guide\n\nSee [Security in SAP AI Core](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/security?locale=en-US) for general information about how SAP AI Core handles security.\n\n",
"bugtrack_url": null,
"license": "SAP DEVELOPER LICENSE AGREEMENT",
"summary": "content package for DataRobot integration for SAP AI Core",
"version": "1.0.18",
"project_urls": {
"Download": "https://pypi.python.org/pypi/sap-ai-core-datarobot",
"Homepage": "https://www.sap.com/"
},
"split_keywords": [
"sap ai core",
"datarobot"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "0c0a966ec3c3e9f053966dbda332f1817d1b78d4d4a187331cd088ef05c2e536",
"md5": "a31edac577aa2cf415fa186323674606",
"sha256": "bd5f1c43a1954a8df12e037f519a04ea2e7618c9a10f8b2ca68879ee9fbd1f32"
},
"downloads": -1,
"filename": "sap_ai_core_datarobot-1.0.18-py3-none-any.whl",
"has_sig": false,
"md5_digest": "a31edac577aa2cf415fa186323674606",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 19583,
"upload_time": "2024-02-05T05:08:53",
"upload_time_iso_8601": "2024-02-05T05:08:53.162487Z",
"url": "https://files.pythonhosted.org/packages/0c/0a/966ec3c3e9f053966dbda332f1817d1b78d4d4a187331cd088ef05c2e536/sap_ai_core_datarobot-1.0.18-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-02-05 05:08:53",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "sap-ai-core-datarobot"
}
JSON