Skip to content

Commit b5bdd7a

Browse files
qmacroqmacro
committed
2 parents e5bbca9 + 547e879 commit b5bdd7a

472 files changed

Lines changed: 29395 additions & 7865 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎tutorials/ai-core-deploy/ai-core-deploy.md‎

Lines changed: 31 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -183,8 +183,36 @@ docker push docker.io/<YOUR_DOCKER_USERNAME>/house-server:01
183183

184184

185185

186-
### Create a serving executable
186+
### Set Compute Resources for Serving - Pre Read
187+
188+
SAP AI Core allows you to configure compute resources for serving workloads using either an instance type or a resource plan. You must specify at least one of these options.
189+
190+
- If you specify an **instance type**, a resource plan is not required.
191+
192+
- If you specify a **resource plan**, an instance type is not required.
193+
194+
```YAML
195+
labels:
196+
ai.sap.com/resourcePlan: <yourChoiceOfResourcePlace>
197+
(or)
198+
ai.sap.com/instanceType: <yourChoiceOfInstanceType>
199+
```
200+
201+
**Note:**
187202
203+
- Resource plans are suitable for most standard serving workloads.
204+
205+
- Instance types are recommended for GPU-based or performance-critical serving scenarios.
206+
207+
**Reference:**
208+
209+
- [SAP Help Portal – Choose an Instance (SAP AI Core)](https://help.sap.com/docs/sap-ai-core/predictive-ai-db13d59d17204c01b3b79c24fb82a19a/choose-instance)
210+
211+
- [SAP Note 3660109 – Available Instance Types](https://me.sap.com/notes/3660109)
212+
213+
214+
215+
### Create a serving executable
188216
189217
Create an executable (YAML file) named `house-price-server.yaml` in your GitHub repository. You may use the existing GitHub path which is already tracked synced to your application of SAP AI Core.
190218

@@ -219,7 +247,7 @@ spec:
219247
autoscaling.knative.dev/target: 1
220248
autoscaling.knative.dev/targetBurstCapacity: 0
221249
labels: |
222-
ai.sap.com/resourcePlan: starter # computing power
250+
ai.sap.com/resourcePlan: starter # or ai.sap.com/instanceType: <yourChoiceOfInstanceType>
223251
spec: |
224252
predictor:
225253
imagePullSecrets:
@@ -247,7 +275,7 @@ spec:
247275
248276
1. You use an input artifacts placeholder `housepricemodel` for your model.
249277
2. You use an input parameters placeholder `greetmessage` to pass any value in a string.
250-
3. You use the `starter` computing resource plan with `ai.sap.com/resourcePlan`. To start, using a non-GPU based resource plan for serving (like `starter`) is cost effective. Find out more about available resource plans in [the help portal](https://help.sap.com/docs/AI_CORE/2d6c5984063c40a59eda62f4a9135bee/57f4f19d9b3b46208ee1d72017d0eab6.html?locale=en-US).
278+
3. You configure compute resources using the **ai.sap.com/resourcePlan** label. In this tutorial, the starter resource plan is used for serving, as it is cost-effective for non-GPU workloads. Alternatively, you can use **ai.sap.com/instanceType** for advanced or GPU-enabled serving scenarios. Learn more in the [SAP Help Portal – Choose an Instance](https://help.sap.com/docs/AI_CORE/2d6c5984063c40a59eda62f4a9135bee/57f4f19d9b3b46208ee1d72017d0eab6.html?locale=en-US).
251279
4. You set the auto scaling of the server with the parameters: `minReplicas` and `maxReplicas`.
252280
5. You set the serving code to use through a Docker `image`, and the credentials to access it via `imagePullSecrets`. You must ensure that if you are using a public docker registry that has the file type `docker.io`, your secret points to the URL `https://index.docker.io`. You may delete and recreate the docker registry secret. This will not affect training templates running in parallel.
253281
6. You use the placeholder `env` to pass your `inputs` values as environment variables in your Docker image.

tutorials/ai-core-genaihub-evaluation/PUT_YOUR_DATASET_HERE/medicalqna_dataset.csv renamed to tutorials/ai-core-genaihub-evaluation-comprehensive/DATASET/medicalqna_dataset.csv

File renamed without changes.

‎tutorials/ai-core-genaihub-evaluation-comprehensive/README.md‎

Lines changed: 548 additions & 0 deletions
Large diffs are not rendered by default.

0 commit comments

Comments
 (0)