fix: removal of dall-e-3 model

Author: Avijit-Microsoft

.github/workflows/deploy-ci.yml

@@ -109,7 +109,6 @@ on:
         options:
           - 'gpt-image-1'
           - 'gpt-image-1.5'
-          - 'dall-e-3'
           - 'none'
 
   schedule:
@@ -311,7 +310,7 @@ jobs:
           
           # Validate and output image_model_choice
           IMAGE_MODEL="${INPUT_IMAGE_MODEL_CHOICE:-gpt-image-1}"
-          ALLOWED_MODELS=("gpt-image-1" "gpt-image-1.5" "dall-e-3" "none")
+          ALLOWED_MODELS=("gpt-image-1" "gpt-image-1.5" "none")
           if [[ ! " ${ALLOWED_MODELS[@]} " =~ " ${IMAGE_MODEL} " ]]; then
             echo "❌ ERROR: image_model_choice '$IMAGE_MODEL' is invalid. Allowed: ${ALLOWED_MODELS[*]}"
             exit 1

.github/workflows/deploy-orchestrator.yml

@@ -62,7 +62,7 @@ on:
         required: true
         type: string
       image_model_choice:
-        description: 'Image model to deploy (gpt-image-1, gpt-image-1.5, dall-e-3, none)'
+        description: 'Image model to deploy (gpt-image-1, gpt-image-1.5, none)'
         required: false
         default: 'gpt-image-1'
         type: string

.github/workflows/job-deploy.yml

@@ -67,7 +67,7 @@ on:
         default: ''
         type: string
       image_model_choice:
-        description: 'Image model to deploy (gpt-image-1, gpt-image-1.5, dall-e-3, none)'
+        description: 'Image model to deploy (gpt-image-1, gpt-image-1.5, none)'
         required: false
         default: 'gpt-image-1'
         type: string

README.md

@@ -49,7 +49,7 @@ The sample data includes synthetic product catalogs and brand guidelines. The da
   Parse free-text creative briefs into structured fields (overview, objectives, target audience, key message, tone/style, deliverable, timelines, visual guidelines, CTA).
 
   - **Multimodal Content Generation** <br/>
-  Generate marketing copy and images using GPT models and DALL-E 3 grounded in enterprise product data.
+  Generate marketing copy and images using GPT models grounded in enterprise product data.
 
   - **Brand Compliance Validation** <br/>
   Validate all generated content against brand guidelines with severity-categorized feedback (Error, Warning, Info).
@@ -102,7 +102,7 @@ _Note: This is not meant to outline all costs as selected SKUs, scaled use, cust
 |---|---|---|
 | [Azure AI Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/) | Free tier. Build generative AI applications on an enterprise-grade platform. | [Pricing](https://azure.microsoft.com/pricing/details/ai-studio/) |
 | [Azure Storage Account](https://learn.microsoft.com/en-us/azure/storage/blobs/) | Standard tier, LRS. Pricing is based on storage and operations. Blob storage for product images and generated content. | [Pricing](https://azure.microsoft.com/pricing/details/storage/blobs/) |
-| [Azure AI Services](https://learn.microsoft.com/en-us/azure/ai-services/) | S0 tier, defaults to gpt-5.1 (GPT) and gpt-image-1 (DALL-E 3) models. Pricing is based on token count. | [Pricing](https://azure.microsoft.com/pricing/details/cognitive-services/) |
+| [Azure AI Services](https://learn.microsoft.com/en-us/azure/ai-services/) | S0 tier, defaults to gpt-5.1 (GPT) and gpt-image-1 models. Pricing is based on token count. | [Pricing](https://azure.microsoft.com/pricing/details/cognitive-services/) |
 | [Azure Container Instance](https://learn.microsoft.com/en-us/azure/container-instances/) | Backend API hosting with private VNet integration. Pricing is based on resource allocation. | [Pricing](https://azure.microsoft.com/pricing/details/container-instances/) |
 | [Azure App Service](https://learn.microsoft.com/en-us/azure/app-service/) | B1 tier. Frontend hosting with Node.js proxy server. | [Pricing](https://azure.microsoft.com/pricing/details/app-service/) |
 | [Azure Container Registry](https://learn.microsoft.com/en-us/azure/container-registry/) | Basic tier. Build, store, and manage container images and artifacts in a private registry for all types of container deployments | [Pricing](https://azure.microsoft.com/pricing/details/container-registry/) |
@@ -140,7 +140,7 @@ Accelerate your marketing content creation by leveraging AI to interpret creativ
   Parse unstructured creative briefs into structured fields automatically, ensuring all campaign requirements are captured.
 
   - **Generate multimodal content** <br/>
-  Create marketing copy and images that align with your brand voice and product catalog using GPT and DALL-E 3.
+  Create marketing copy and images that align with your brand voice and product catalog using GPT models (text and image generation models).
 
   - **Ensure brand compliance** <br/>
   Validate all generated content against brand guidelines with severity-categorized feedback before publication.

content-gen/.env.sample

@@ -31,15 +31,14 @@ AZURE_OPENAI_ENDPOINT=https://your-openai.openai.azure.com/
 AZURE_OPENAI_GPT_MODEL=gpt-5.1
 
 # Image Generation Model Configuration
-# Supported models: dall-e-3 or gpt-image-1
+# Supported models: gpt-image-1 or gpt-image-1.5
 AZURE_OPENAI_IMAGE_MODEL=gpt-image-1
 
-# For gpt-image-1 (if using a different endpoint than DALL-E)
+# For gpt-image-1 or gpt-image-1.5, the endpoint is the same as the main OpenAI endpoint, but you can specify a different one if needed
 AZURE_OPENAI_GPT_IMAGE_ENDPOINT=https://your-openai.openai.azure.com
 
 # Image generation settings
-# For dall-e-3: sizes are 1024x1024, 1024x1792, 1792x1024; quality is standard or hd
-# For gpt-image-1: sizes are 1024x1024, 1536x1024, 1024x1536, auto; quality is low, medium, high, auto
+# For gpt-image-1/1.5: sizes are 1024x1024, 1536x1024, 1024x1536, auto; quality is low, medium, high, auto
 AZURE_OPENAI_IMAGE_SIZE=1024x1024
 AZURE_OPENAI_IMAGE_QUALITY=medium
 

content-gen/README.md

@@ -7,7 +7,7 @@ A multimodal content generation solution for retail marketing campaigns using Mi
 This accelerator provides an internal chatbot that can:
 
 - **Interpret Creative Briefs**: Parse free-text creative briefs into structured fields (overview, objectives, target audience, key message, tone/style, deliverable, timelines, visual guidelines, CTA)
-- **Generate Multimodal Content**: Create marketing copy and images using GPT models and DALL-E 3
+- **Generate Multimodal Content**: Create marketing copy and images using GPT models (text and image generation models)
 - **Ensure Brand Compliance**: Validate all content against brand guidelines with severity-categorized warnings
 - **Ground in Enterprise Data**: Leverage product information, product images, and brand guidelines stored in Azure services
 
@@ -33,7 +33,7 @@ The solution uses **HandoffBuilder** orchestration with 6 specialized agents:
 | **PlanningAgent** | Parses creative briefs, develops content strategy, returns for user confirmation |
 | **ResearchAgent** | Retrieves products from CosmosDB, fetches brand guidelines, assembles grounding data |
 | **TextContentAgent** | Generates marketing copy (headlines, body, CTAs) using GPT |
-| **ImageContentAgent** | Creates marketing images via DALL-E 3 with product context |
+| **ImageContentAgent** | Creates marketing images via GPT image models with product context |
 | **ComplianceAgent** | Validates content against brand guidelines, categorizes violations |
 
 ### Compliance Severity Levels
@@ -49,7 +49,7 @@ The solution uses **HandoffBuilder** orchestration with 6 specialized agents:
 | Service | Purpose |
 |---------|---------|
 | Azure OpenAI (GPT) | Text generation and content creation |
-| Azure OpenAI (DALL-E 3) | Image generation (can be separate resource) |
+| Azure OpenAI (GPT Image) | Image generation (can be separate resource) |
 | Azure Cosmos DB | Products catalog, chat conversations |
 | Azure Blob Storage | Product images, generated images |
 | Azure Container Instance | Backend API hosting |
@@ -92,7 +92,7 @@ The system extracts the following fields from free-text creative briefs:
 
 - Azure subscription with access to:
   - Azure OpenAI (GPT model - GPT-4 or higher recommended)
-  - Azure OpenAI (DALL-E 3 - can be same or different resource)
+  - Azure OpenAI (GPT Image model - can be same or different resource)
   - Azure Cosmos DB
   - Azure Blob Storage
   - Azure Container Instance
@@ -156,9 +156,9 @@ See `src/backend/settings.py` for all configuration options. Key settings:
 | Variable | Description |
 |----------|-------------|
 | `AZURE_OPENAI_ENDPOINT` | Azure OpenAI endpoint for GPT model |
-| `AZURE_OPENAI_DEPLOYMENT_NAME` | GPT model deployment name |
-| `AZURE_OPENAI_DALLE_ENDPOINT` | Azure OpenAI endpoint for DALL-E (if separate) |
-| `AZURE_OPENAI_DALLE_DEPLOYMENT` | DALL-E deployment name (dall-e-3) |
+| `AZURE_OPENAI_GPT_MODEL` | GPT model deployment name |
+| `AZURE_OPENAI_GPT_IMAGE_ENDPOINT` | Azure OpenAI endpoint for GPT image model (if separate) |
+| `AZURE_OPENAI_IMAGE_MODEL` | GPT image model deployment name (gpt-image-1) |
 | `COSMOS_ENDPOINT` | Azure Cosmos DB endpoint |
 | `COSMOS_DATABASE` | Cosmos DB database name |
 | `AZURE_STORAGE_ACCOUNT_NAME` | Storage account name |
@@ -182,7 +182,7 @@ BRAND_SECONDARY_COLOR=#107C10
 - [Local Development Guide](docs/LOCAL_DEPLOYMENT.md) - Run locally for development
 - [AZD Deployment Guide](docs/AZD_DEPLOYMENT.md) - Deploy with Azure Developer CLI
 - [Manual Deployment Guide](docs/DEPLOYMENT.md) - Step-by-step manual deployment
-- [Image Generation Configuration](docs/IMAGE_GENERATION.md) - DALL-E 3 and GPT-Image-1 setup
+- [Image Generation Configuration](docs/IMAGE_GENERATION.md) - GPT image model setup
 
 ## License
 

content-gen/docs/AZD_DEPLOYMENT.md

@@ -38,15 +38,14 @@ This guide covers deploying the Content Generation Solution Accelerator using Az
 
 - An Azure subscription with the following permissions:
   - Create Resource Groups
-  - Deploy Azure AI Services (GPT-4o, DALL-E 3 or GPT-Image-1, Text Embeddings)
+  - Deploy Azure AI Services (GPT-5.1, GPT-Image-1)
   - Create Container Registry, Container Instances, App Service
   - Create Cosmos DB, Storage Account, AI Search
   - Assign RBAC roles
 
 - **Quota**: Ensure you have sufficient quota for:
-  - GPT-4o (or your chosen model)
-  - DALL-E 3 or GPT-Image-1 (for image generation)
-  - Text-embedding-3-large
+  - GPT-5.1 (or your chosen model)
+  - GPT-Image-1 (or GPT-Image-1.5 - for image generation)
 
 ## Quick Start
 
@@ -301,7 +300,7 @@ When `enablePrivateNetworking` is enabled:
 │          │                                                      │
 │  ┌───────▼──────────┐      ┌───────────────────────────────┐   │
 │  │  Storage Account │      │      Azure AI Services        │   │
-│  └──────────────────┘      │  (GPT-4o, DALL-E, Embeddings) │   │
+│  └──────────────────┘      │  (GPT-5.1, GPT-Image-1) │   │
 │                            └───────────────────────────────┘   │
 └─────────────────────────────────────────────────────────────────┘
 ```

content-gen/docs/CustomizingAzdParameters.md

@@ -15,8 +15,8 @@ By default this template will use the environment name as the prefix to prevent
 | `gptModelVersion`                      | string  | `2025-11-13`               | Sets the GPT model version.                                                   |
 | `gptModelDeploymentType`               | string  | `GlobalStandard`           | Defines the model deployment type (allowed: `Standard`, `GlobalStandard`).    |
 | `gptModelCapacity`                     | integer | `150`                      | Sets the GPT model token capacity (minimum: `10`).                            |
-| `imageModelChoice`                     | string  | `gpt-image-1`             | Image model to deploy (allowed: `gpt-image-1`, `gpt-image-1.5`, `dall-e-3`, `none`). |
-| `dalleModelCapacity`                   | integer | `1`                        | Sets the image model deployment capacity in RPM (minimum: `1`).               |
+| `imageModelChoice`                     | string  | `gpt-image-1`             | Image model to deploy (allowed: `gpt-image-1`, `gpt-image-1.5`, `none`). |
+| `imageModelCapacity`                   | integer | `1`                        | Sets the image model deployment capacity in RPM (minimum: `1`).               |
 | `azureOpenaiAPIVersion`                | string  | `2025-01-01-preview`       | Specifies the API version for Azure OpenAI service.                           |
 | `AZURE_ENV_OPENAI_LOCATION`           | string  | `<User selects during deployment>` | Sets the Azure region for OpenAI resource deployment.                         |
 | `AZURE_ENV_LOG_ANALYTICS_WORKSPACE_ID` | string  | `""`                       | Reuses an existing Log Analytics Workspace instead of creating a new one.     |
@@ -38,6 +38,6 @@ azd env set <PARAMETER_NAME> <VALUE>
 azd env set AZURE_LOCATION westus2
 azd env set gptModelName gpt-5.1
 azd env set gptModelDeploymentType Standard
-azd env set imageModelChoice dall-e-3
+azd env set imageModelChoice gpt-image-1
 azd env set ACR_NAME contentgencontainerreg
 ```

content-gen/docs/DEPLOYMENT.md

@@ -8,7 +8,6 @@ Check the [Azure Products by Region](https://azure.microsoft.com/en-us/explore/g
 
 - [Azure AI Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry)
 - [GPT Model Capacity](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models)
-- [DALL-E 3 Model Capacity](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#dall-e-models)
 - [Azure App Service](https://learn.microsoft.com/en-us/azure/app-service/)
 - [Azure Container Registry](https://learn.microsoft.com/en-us/azure/container-registry/)
 - [Azure Container Instance](https://learn.microsoft.com/en-us/azure/container-instances/)
@@ -138,7 +137,7 @@ When you start the deployment, most parameters will have **default values**, but
 | **GPT Model Version**                       | The version of the selected GPT model.                                                                    | 2025-11-13            |
 | **OpenAI API Version**                      | The Azure OpenAI API version to use.                                                                      | 2025-01-01-preview     |
 | **GPT Model Deployment Capacity**           | Configure capacity for **GPT models** (in thousands).                                                     | 150k                    |
-| **Image Model**                            | Choose from **dall-e-3, gpt-image-1, gpt-image-1.5**                                                                          | gpt-image-1             |
+| **Image Model**                            | Choose from **gpt-image-1, gpt-image-1.5**                                                                          | gpt-image-1             |
 | **Image Tag**                               | Docker image tag to deploy. Common values: `latest`, `dev`, `hotfix`.                                     | latest                 |
 | **Existing Log Analytics Workspace**        | To reuse an existing Log Analytics Workspace ID.                                                          | *(empty)*              |
 | **Existing Azure AI Foundry Project**       | To reuse an existing Azure AI Foundry Project ID instead of creating a new one.                           | *(empty)*              |
@@ -148,11 +147,11 @@ When you start the deployment, most parameters will have **default values**, but
 <details>
   <summary><b>[Optional] Quota Recommendations</b></summary>
 
-By default, the **GPT-4o-mini model capacity** in deployment is set to **30k tokens**, so we recommend updating the following:
+By default, the **GPT-5.1 model capacity** in deployment is set to **150k tokens**, so we recommend updating the following:
 
-> **For GPT-4o-mini - increase the capacity to at least 150k tokens post-deployment for optimal performance.**
+> **For GPT-5.1 - increase the capacity post-deployment for optimal performance if required.**
 
-> **For DALL-E 3 - ensure you have sufficient capacity for image generation requests.**
+> **For GPT-Image-1 - ensure you have sufficient capacity for image generation requests.**
 
 Depending on your subscription quota and capacity, you can adjust quota settings to better meet your specific needs.
 
@@ -213,13 +212,13 @@ az webapp config set -g $RESOURCE_GROUP -n <app-name> --http20-enabled false
 
 ### Image Generation Not Working
 
-**Symptom**: DALL-E/GPT-Image requests fail
+**Symptom**: GPT-Image requests fail
 
-**Cause**: Missing DALL-E/GPT-Image model deployment or incorrect endpoint
+**Cause**: Missing GPT-Image model deployment or incorrect endpoint
 
 **Solution**: 
-1. Verify DALL-E 3 or GPT-Image-1 or GPT-Image-1.5 deployment exists in Azure OpenAI resource
-2. Check `AZURE_OPENAI_IMAGE_MODEL` environment variable
+1. Verify GPT-Image-1 or GPT-Image-1.5 deployment exists in Azure OpenAI resource
+2. Check `AZURE_OPENAI_IMAGE_MODEL` and `AZURE_OPENAI_GPT_IMAGE_ENDPOINT` environment variables
 
 </details>
 
@@ -245,7 +244,7 @@ The solution consists of:
 - **Frontend**: React + Vite + TypeScript + Fluent UI running on Azure App Service with Node.js proxy
 - **AI Services**: 
   - Azure OpenAI (GPT model for text generation)
-  - Azure OpenAI (DALL-E 3 for image generation)
+  - Azure OpenAI (GPT Image model for image generation)
 - **Data Services**:
   - Azure Cosmos DB (products catalog, conversations)
   - Azure Blob Storage (product images, generated images)