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: content-gen/docs/AZD_DEPLOYMENT.md
+9-104Lines changed: 9 additions & 104 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -58,6 +58,11 @@ azd auth login
58
58
59
59
# Login to Azure CLI (required for some post-deployment scripts)
60
60
az login
61
+
```
62
+
Alternatively, login to Azure using a device code (recommended when using VS Code Web):
63
+
64
+
```
65
+
az login --use-device-code
61
66
```
62
67
63
68
### 2. Initialize Environment
@@ -72,36 +77,7 @@ azd env new <environment-name>
72
77
azd env new content-gen-dev
73
78
```
74
79
75
-
### 3. Configure Parameters (Optional)
76
-
77
-
The deployment has sensible defaults, but you can customize:
78
-
79
-
```bash
80
-
# Set the Azure region (default: eastus)
81
-
azd env set AZURE_LOCATION swedencentral
82
-
83
-
# Set AI Services region (must support your models)
84
-
azd env set AZURE_ENV_OPENAI_LOCATION swedencentral
85
-
86
-
# GPT Model configuration
87
-
azd env set gptModelName gpt-4o
88
-
azd env set gptModelVersion 2024-11-20
89
-
azd env set gptModelDeploymentType GlobalStandard
90
-
azd env set gptModelCapacity 50
91
-
92
-
# Image generation model (dalle-3 or gpt-image-1)
93
-
azd env set imageModelChoice gpt-image-1
94
-
azd env set dalleModelCapacity 1
95
-
96
-
# Embedding model
97
-
azd env set embeddingModel text-embedding-3-large
98
-
azd env set embeddingDeploymentCapacity 50
99
-
100
-
# Azure OpenAI API version
101
-
azd env set azureOpenaiAPIVersion 2024-12-01-preview
102
-
```
103
-
104
-
### 4. Choose Deployment Configuration
80
+
### 3. Choose Deployment Configuration
105
81
106
82
The [`infra`](../infra) folder contains the [`main.bicep`](../infra/main.bicep) Bicep script, which defines all Azure infrastructure components for this solution.
107
83
@@ -124,7 +100,7 @@ Before running `azd up`, copy the contents from the production configuration fil
124
100
5. Select all existing content (Ctrl+A) and paste the copied content (Ctrl+V).
125
101
6. Save the file (Ctrl+S).
126
102
127
-
### 5. Deploy
103
+
### 4. Deploy
128
104
129
105
```bash
130
106
azd up
@@ -139,25 +115,6 @@ This single command will:
139
115
6.**Configure** RBAC and Cosmos DB roles
140
116
7.**Upload** sample data and create the search index
141
117
142
-
## Deployment Parameters Reference
143
-
144
-
| Parameter | Default | Description |
145
-
|-----------|---------|-------------|
146
-
|`AZURE_LOCATION`| eastus | Primary Azure region |
147
-
|`azureAiServiceLocation`| eastus | Region for AI Services (must support chosen models) |
148
-
|`gptModelName`| gpt-4o | GPT model for content generation |
149
-
|`gptModelVersion`| 2024-11-20 | Model version |
150
-
|`gptModelDeploymentType`| GlobalStandard | Deployment type |
151
-
|`gptModelCapacity`| 50 | TPM capacity (in thousands) |
152
-
|`imageModelChoice`| dalle-3 | Image model: `dalle-3` or `gpt-image-1`|
153
-
|`dalleModelCapacity`| 1 | Image model capacity |
154
-
|`embeddingModel`| text-embedding-3-large | Embedding model |
@@ -174,13 +131,6 @@ azd env set AZURE_EXISTING_AI_PROJECT_RESOURCE_ID "/subscriptions/<sub-id>/resou
174
131
azd env set AZURE_ENV_LOG_ANALYTICS_WORKSPACE_ID "/subscriptions/<sub-id>/resourceGroups/<rg>/providers/Microsoft.OperationalInsights/workspaces/<workspace-name>"
|**Azure Region**| The region where resources will be created. |*(empty)*|
136
136
|**Environment Name**| A **3–20 character alphanumeric value** used to generate a unique ID to prefix the resources. | env\_name |
137
-
|**GPT Model**| Choose from **gpt-4, gpt-4o, gpt-4o-mini**. | gpt-4o-mini |
138
-
|**GPT Model Version**| The version of the selected GPT model. |2024-07-18 |
137
+
|**GPT Model**| Choose from **gpt-4, gpt-4o, gpt-4o-mini, gpt-5.1**. | gpt-5.1|
138
+
|**GPT Model Version**| The version of the selected GPT model. |2025-11-13|
139
139
|**OpenAI API Version**| The Azure OpenAI API version to use. | 2025-01-01-preview |
140
-
|**GPT Model Deployment Capacity**| Configure capacity for**GPT models** (in thousands). |30k|
141
-
|**DALL-E Model**|DALL-E model forimage generation.| dall-e-3 |
140
+
|**GPT Model Deployment Capacity**| Configure capacity for**GPT models** (in thousands). |150k|
141
+
|**Image Model**|Choose from **dall-e-3, gpt-image-1, gpt-image-1.5**| gpt-image-1|
142
142
|**Image Tag**| Docker image tag to deploy. Common values: `latest`, `dev`, `hotfix`. | latest |
143
-
|**Use Local Build**| Boolean flag to determine iflocal container builds should be used. |false|
144
143
|**Existing Log Analytics Workspace**| To reuse an existing Log Analytics Workspace ID. |*(empty)*|
145
144
|**Existing Azure AI Foundry Project**| To reuse an existing Azure AI Foundry Project ID instead of creating a new one. |*(empty)*|
146
145
@@ -171,30 +170,14 @@ Once you've opened the project in [Codespaces](#github-codespaces), [Dev Contain
171
170
172
171
Follow steps in [App Authentication](./AppAuthentication.md) to configure authentication in app service. Note: Authentication changes can take up to 10 minutes.
173
172
174
-
2. **Assign RBAC Roles (if needed)**
175
-
176
-
If you encounter 401/403 errors, run the RBAC assignment script and wait 5-10 minutes for propagation:
177
-
178
-
```shell
179
-
bash ./scripts/assign_rbac_roles.sh
180
-
```
181
-
182
-
3. **Deleting Resources After a Failed Deployment**
173
+
2. **Deleting Resources After a Failed Deployment**
183
174
- Follow steps in [Delete Resource Group](./DeleteResourceGroup.md) if your deployment fails and/or you need to clean up the resources.
184
175
185
176
## Troubleshooting
186
177
187
178
<details>
188
179
<summary><b>Common Issues and Solutions</b></summary>
189
180
190
-
### 401 Unauthorized Errors
191
-
192
-
**Symptom**: API calls return 401 errors
193
-
194
-
**Cause**: Missing RBAC role assignments
195
-
196
-
**Solution**: Run `assign_rbac_roles.sh` and wait 5-10 minutes for propagation
197
-
198
181
### 403 Forbidden from Cosmos DB
199
182
200
183
**Symptom**: Cosmos DB operations fail with 403
@@ -230,56 +213,29 @@ az webapp config set -g $RESOURCE_GROUP -n <app-name> --http20-enabled false
230
213
231
214
### Image Generation Not Working
232
215
233
-
**Symptom**: DALL-E requests fail
216
+
**Symptom**: DALL-E/GPT-Image requests fail
234
217
235
-
**Cause**: Missing DALL-E model deployment or incorrect endpoint
218
+
**Cause**: Missing DALL-E/GPT-Image model deployment or incorrect endpoint
236
219
237
220
**Solution**:
238
-
1. Verify DALL-E 3 deployment exists in Azure OpenAI resource
239
-
2. Check `AZURE_OPENAI_DALLE_ENDPOINT` and `AZURE_OPENAI_DALLE_DEPLOYMENT` environment variables
221
+
1. Verify DALL-E 3 or GPT-Image-1 or GPT-Image-1.5 deployment exists in Azure OpenAI resource
| BACKEND_URL | Backend API URL | http://backend.contentgen.internal:8000 |
268
-
| WEBSITES_PORT | App Service port | 3000 |
269
-
270
-
</details>
226
+
## Sample Workflow
271
227
272
-
## Sample Prompts
228
+
To get started with the Content Generation solution, follow these steps:
273
229
274
-
To help you get started, here are some **sample prompts** you can use with the Content Generation Solution:
230
+
1. **Task:** From the welcome screen, select one of the suggested prompts. Sample prompts include:
231
+
- *"I need to create a social media post about paint products for home remodels. The campaign is titled 'Brighten Your Springtime' and the audience is new homeowners. I need marketing copy plus an image."*
232
+
- *"Generate a social media campaign with ad copy and an image. This is for 'Back to School' and the audience is parents of school age children. Tone is playful and humorous."*
275
233
276
-
- "Create a product description for a new eco-friendly water bottle"
277
-
- "Generate marketing copy for a summer sale campaign"
278
-
- "Write social media posts promoting our latest product launch"
279
-
- "Create an image for a blog post about sustainable living"
280
-
- "Generate a product image showing a modern office setup"
234
+
2. **Task:** Click the **"Confirm Brief"** button.
235
+
> **Observe:** The system analyzes the creative brief to provide suggestions later.
281
236
282
-
These prompts serve as a great starting point to explore the solution's capabilities with text generation, image generation, and content management.
237
+
3. **Task:** Select a product from the product list, then click **"Generate Content"**.
238
+
> **Observe:** Enters "Thinking Process" with a "Generating Content.." spinner. Once complete, the detailed output is displayed.
0 commit comments