You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/DeploymentGuide.md
+97-9Lines changed: 97 additions & 9 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -212,8 +212,7 @@ azd up
212
212
213
213
**⚠️ Deployment Issues:** If you encounter errors or timeouts, try a different region as there may be capacity constraints. For detailed error solutions, see our [Troubleshooting Guide](./TroubleShootingSteps.md).
214
214
215
-
## Step 5: Post-Deployment Script
216
-
215
+
## Step 5: Post Deployment Configuration
217
216
The post deployment process is very straightforward and simplified via a single [deployment script](../Deployment/resourcedeployment.ps1) that completes in approximately 20-30 minutes:
218
217
219
218
### Automated Deployment Steps:
@@ -223,28 +222,117 @@ The post deployment process is very straightforward and simplified via a single
223
222
- Docker build and push container images to Azure Container Registry.
224
223
- Display the deployment result and following instructions.
225
224
226
-
### 5.1 Script Execution
225
+
### 5.1 Execute the Script
226
+
227
+
#### 5.1.1 Open PowerShell, change directory where you code cloned, then run the deploy script:
228
+
229
+
```shell
230
+
cd .\Deployment\
231
+
```
232
+
233
+
#### 5.1.2 Choose the appropriate command based on your deployment method:
234
+
235
+
**If you deployed using `azd up` command:**
236
+
```shell
237
+
.\resourcedeployment.ps1
238
+
```
239
+
240
+
**If you deployed using custom templates, ARM/Bicep deployments, or `az deployment group` commands:**
2. Wait up to 20-30 minutes for completion of the script.
259
+
##### 5.1.3.1 **Email** - used for issuing certificates in Kubernetes clusters from the [Let's Encrypt](https://letsencrypt.org/) service. Email address should be valid.
> * Navigate to project in Azure OpenAI, then go to Azure AI Foundry, select Safety + security
279
+
> * Click on Create Content Filter and set the filters to a high threshold for the following categories:
280
+
```
281
+
Hate, Sexual, Self-harm, Violence
282
+
```
283
+
> * Please select the checkbox of profanity
284
+
> * Leave all other configurations at their default settings and click on create
285
+
286
+
### 5.3 Configure Azure OpenAI Rate Limits
287
+
288
+
> **Capacity Note:**
289
+
> * The deployment script creates models with a setting of 1 token per minute (TPM) rate limit.
290
+
> * Faster performance can be achieved by increasing the TPM limit with Azure AI Foundry.
291
+
> * Capacity varies for [regional quota limits](https://learn.microsoft.com/en-us/azure/ai-services/openai/quotas-limits#regional-quota-limits) as well as for [provisioned throughput](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/provisioned-throughput).
292
+
> * As a starting point, we recommend the following quota threshold be set up for this service run.
293
+
294
+
| Model Name | TPM Threshold |
295
+
|------------------------|---------------|
296
+
| GPT-4.1-mini | 100K TPM |
297
+
| text-embedding-3-large | 200K TPM |
298
+
299
+
> **⚠️ Warning:****Insufficient quota can cause failures during the upload process.** Please ensure you have the recommended capacity or request for additional capacity before start uploading the files.
300
+
301
+
#### 5.3.1 Browse to the project in Azure AI Foundry, and select **each of the 2 models** within the `Deployments` menu:
0 commit comments