Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
db8ace4
Merge pull request #271 from microsoft/dev
Avijit-Microsoft Jun 29, 2026
7c9e9d8
chore: update CODEOWNERS handles
Rafi-Mohammad-69 Jun 29, 2026
1e3414b
chore: update CODEOWNERS handles
Avijit-Microsoft Jun 30, 2026
712798a
update GPT model; add container registry; add build scripts
HarshB-Microsoft Jul 1, 2026
f97eefa
fix: improve product parsing logic to handle leading product entries …
HarshB-Microsoft Jul 1, 2026
b89dd0d
remove unused image tag persistence for azd in build scripts
HarshB-Microsoft Jul 1, 2026
5a4e1c5
docs: update deployment guide to include container image build and pu…
HarshB-Microsoft Jul 1, 2026
6712e32
Fix ACR name resolution and azd_get error handling in build_push_imag…
Shubhangi-Microsoft Jul 3, 2026
f7e39fe
updating model in comments
Shubhangi-Microsoft Jul 3, 2026
782f15b
updating model version in comments
Shubhangi-Microsoft Jul 3, 2026
502ceb0
fixed copliot commetns
Shubhangi-Microsoft Jul 3, 2026
5e6bada
Merge pull request #280 from microsoft/psl-hb-acr-build
Roopan-Microsoft Jul 3, 2026
8c722ed
docs: update GPT model references from gpt-4.1-mini to gpt-5.4-mini
Shubhangi-Microsoft Jul 6, 2026
78b64cc
docs: address review feedback - clarify model name wording and align …
Shubhangi-Microsoft Jul 6, 2026
79fec0a
docs: align model references with actual code - keep 5.4-mini only wh…
Shubhangi-Microsoft Jul 6, 2026
53d8123
docs: make all doc model references uniformly gpt-5.4-mini (code upda…
Shubhangi-Microsoft Jul 7, 2026
b1b7f14
Merge pull request #281 from microsoft/psl-gptmodel-check
Roopan-Microsoft Jul 7, 2026
03e15e2
Update Owners ID for Vinay and Prajwal
NirajC3-Microsoft Jul 16, 2026
460e638
Merge pull request #292 from chaudhariniraj/main
Roopan-Microsoft Jul 16, 2026
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ For detailed technical information, see the component READMEs:
Foundry IQ provides fast, accurate product discovery and policy document retrieval using semantic and keyword search, enabling natural language queries across product catalogs and knowledge bases. Specialized agents access search indexes to retrieve relevant information from product catalogs and policy documents.

- **Natural language interaction**
Microsoft Foundry's Agent Framework orchestrates multi-agent workflows using GPT-4.1-mini to deliver conversational, context-aware responses that understand customer intent. The framework maintains conversation threads and context across sessions, enabling natural, flowing conversations with specialized agents.
Microsoft Foundry's Agent Framework orchestrates multi-agent workflows using GPT-5.4-mini to deliver conversational, context-aware responses that understand customer intent. The framework maintains conversation threads and context across sessions, enabling natural, flowing conversations with specialized agents.

- **Modern e-commerce experience**
React-based frontend with dual-panel layout featuring product browsing and integrated AI chat assistant for seamless shopping and support experiences
Expand Down Expand Up @@ -100,7 +100,7 @@ _Note: This is not meant to outline all costs as selected SKUs, scaled use, cust
| Product | Description | Tier / Expected Usage Notes | Cost |
|---|---|---|---|
| [Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry) | Used to orchestrate and build AI workflows with specialized agents for customer service. | Free Tier | [Pricing](https://azure.microsoft.com/pricing/details/ai-studio/) |
| [Azure AI Services (OpenAI)](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/overview) | Enables language understanding and chat capabilities using GPT models for conversational AI. | S0 Tier; pricing depends on token volume and model used (e.g., GPT-4.1-mini). | [Pricing](https://azure.microsoft.com/pricing/details/cognitive-services/) |
| [Azure AI Services (OpenAI)](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/overview) | Enables language understanding and chat capabilities using GPT models for conversational AI. | S0 Tier; pricing depends on token volume and model used (e.g., GPT-5.4-mini). | [Pricing](https://azure.microsoft.com/pricing/details/cognitive-services/) |
| [Foundry IQ](https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search) | Provides hybrid search capabilities for product catalogs and policy documents with semantic and keyword search. | Basic Tier; pricing based on search units and data storage. | [Pricing](https://azure.microsoft.com/pricing/details/search/) |
| [Azure App Service](https://learn.microsoft.com/en-us/azure/app-service/overview) | Hosts the frontend React application and backend FastAPI services. | Basic or Standard plan; includes a free tier for development. | [Pricing](https://azure.microsoft.com/pricing/details/app-service/windows/) |
| [Azure Container Registry](https://learn.microsoft.com/en-us/azure/container-registry/container-registry-intro) | Stores and serves container images used by Azure App Service. | Basic Tier; fixed daily cost per registry. | [Pricing](https://azure.microsoft.com/pricing/details/container-registry/) |
Expand Down
18 changes: 13 additions & 5 deletions azure.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ metadata:
template: customer-chatbot-solution-accelerator@1.0

requiredVersions:
azd: ">= 1.18.0 != 1.23.9"
azd: ">= 1.18.0 != 1.23.9"

hooks:
postprovision:
Expand All @@ -21,10 +21,13 @@ hooks:
Write-Host " Post-Deployment Steps" -ForegroundColor Yellow
Write-Host "----------------------------------------`n" -ForegroundColor Yellow

Write-Host "1. Run the data setup script to load sample product data:`n"
Write-Host "1. Build and push the backend/frontend container images to ACR, then point the web apps at them:`n"
Write-Host " infra\scripts\build_push_images.ps1`n" -ForegroundColor Cyan

Write-Host "2. Run the data setup script to load sample product data:`n"
Write-Host " infra\scripts\data_scripts\run_upload_data_scripts.ps1`n" -ForegroundColor Cyan

Write-Host "2. Run the agent setup script to create AI Foundry agents:`n"
Write-Host "3. Run the agent setup script to create AI Foundry agents:`n"
Write-Host " infra\scripts\agent_scripts\run_create_agents_scripts.ps1`n" -ForegroundColor Cyan
shell: pwsh
continueOnError: false
Expand All @@ -46,12 +49,17 @@ hooks:
echo "----------------------------------------"
echo ""

echo "1. Run the data setup script to load sample product data:"
echo "1. Build and push the backend/frontend container images to ACR, then point the web apps at them:"
echo ""
echo " bash ./infra/scripts/build_push_images.sh"
echo ""

echo "2. Run the data setup script to load sample product data:"
echo ""
echo " bash ./infra/scripts/data_scripts/run_upload_data_scripts.sh"
echo ""

echo "2. Run the agent setup script to create AI Foundry agents:"
echo "3. Run the agent setup script to create AI Foundry agents:"
echo ""
echo " bash ./infra/scripts/agent_scripts/run_create_agents_scripts.sh"
echo ""
Expand Down
2 changes: 1 addition & 1 deletion documents/AzureGPTQuotaSettings.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,6 @@
3. **Go to** the `Management Center` from the bottom-left navigation menu.
4. Select `Quota`
- Click on the `GlobalStandard` dropdown.
- Select the required **GPT model** (`GPT-4.1-mini`) or **Embeddings model** (`text-embedding-3-small`).
- Select the required **GPT model** (`gpt-5.4-mini`) or **Embeddings model** (`text-embedding-3-small`).
- Choose the **region** where the deployment is hosted.
5. Request More Quota or delete any unused model deployments as needed.
4 changes: 2 additions & 2 deletions documents/CustomizingAzdParameters.md
Original file line number Diff line number Diff line change
Expand Up @@ -13,8 +13,8 @@ By default this template will use the environment name as the prefix to prevent
| `AZURE_ENV_NAME` | string | `docgen` | Sets the environment name prefix for all Azure resources. | |
| `AZURE_ENV_AI_SERVICE_LOCATION` | string | `<User selects during deployment>` | Sets the Azure region for AI service resource deployment. |
| `AZURE_ENV_MODEL_DEPLOYMENT_TYPE` | string | `Standard` | Defines the model deployment type (allowed: `Standard`, `GlobalStandard`). |
| `AZURE_ENV_GPT_MODEL_NAME` | string | `gpt-4.1-mini` | Specifies the GPT model name (allowed: `gpt-4.1-mini`). |
| `AZURE_ENV_GPT_MODEL_VERSION` | string | `2025-04-14` | Set the Azure model version. |
| `AZURE_ENV_GPT_MODEL_NAME` | string | `gpt-5.4-mini` | Specifies the GPT model name (e.g., `gpt-5.4-mini`). |
| `AZURE_ENV_GPT_MODEL_VERSION` | string | `2026-03-17` | Set the Azure model version. |
| `AZURE_ENV_GPT_MODEL_CAPACITY` | integer | `10` | Sets the GPT model capacity (based on what's available in your subscription). |
| `AZURE_ENV_EMBEDDING_DEPLOYMENT_CAPACITY` | integer | `10` | Sets the embedding model deployment capacity (minimum: 10). |
| `AZURE_ENV_CONTAINER_REGISTRY_ENDPOINT` | string | `ccbcontainerreg.azurecr.io` | Sets the Azure Container Registry login server/endpoint (for example: `ccbcontainerreg.azurecr.io`). |
Comment thread
Harsh-Microsoft marked this conversation as resolved.
Expand Down
41 changes: 36 additions & 5 deletions documents/DeploymentGuide.md
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ Ensure you have access to an [Azure subscription](https://azure.microsoft.com/fr

**Required Azure Services:**
- [Azure AI Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/) - For Agent Framework orchestration and AI project management
- [Azure OpenAI Service](https://learn.microsoft.com/en-us/azure/ai-services/openai/) - For GPT-4.1-mini model deployments
- [Azure OpenAI Service](https://learn.microsoft.com/en-us/azure/ai-services/openai/) - For GPT-5.4-mini model deployments
- [Azure AI Search](https://learn.microsoft.com/en-us/azure/search/) - For hybrid search across product catalogs and policy documents
- [Azure Cosmos DB](https://learn.microsoft.com/en-us/azure/cosmos-db/) - For storing product catalogs, orders, and chat history
- [Azure App Service](https://learn.microsoft.com/en-us/azure/app-service/) - For hosting frontend and backend applications
Expand All @@ -62,10 +62,10 @@ Ensure you have access to an [Azure subscription](https://azure.microsoft.com/fr
📖 **Follow:** [Quota Check Instructions](./QuotaCheck.md) to ensure sufficient capacity.

**Default Quota Configuration:**
- **gpt-4.1-mini:** 50k tokens
- **gpt-5.4-mini:** 50k tokens

**Recommended Configuration:**
- **Minimum:** 50k tokens for Global Standard GPT-4.1-mini
- **Minimum:** 50k tokens for Global Standard GPT-5.4-mini
- **Optimal:** More than 50k tokens (for best performance)

> **Note:** When you run `azd up`, the deployment will automatically show you regions with available quota, so this pre-check is optional but helpful for planning purposes. You can customize these settings later in [Step 3.3: Advanced Configuration](#33-advanced-configuration-optional).
Expand Down Expand Up @@ -335,7 +335,38 @@ source .venv/bin/activate

### 5.2 Initialize Data and Agents

**Step 1: Populate Product Catalogs and Search Indexes**
**Step 1: Build and push container images**

The initial deployment configures the App Services with a placeholder container. Run the ACR build script to build the real backend/frontend images inside Azure Container Registry and point both web apps at them:

- **For PowerShell (Windows/Linux/macOS):**
```shell
infra\scripts\build_push_images.ps1
```
- **For Bash (Linux/macOS/WSL):**
```bash
bash ./infra/scripts/build_push_images.sh
```

**If you deployed using `AVM`:**

- **For PowerShell (Windows/Linux/macOS):**
```shell
infra\scripts\build_push_images.ps1 -ResourceGroup "<your-resource-group-name>"
```
- **For Bash (Linux/macOS/WSL):**
```bash
bash ./infra/scripts/build_push_images.sh --resource-group "<your-resource-group-name>"
```

This script will:
- Build the backend (`src/api`) and frontend (`src/App`) images remotely using `az acr build` (no local Docker required)
- Push them to your Azure Container Registry
- Update both App Services (`api-<suffix>` and `app-<suffix>`) to run the new image and restart them

> **Tip:** Pass `-ImageTag <tag>` (PowerShell) or `--image-tag <tag>` (bash) to publish a specific tag. Pass `-ShowLogs` / `--show-logs` to stream the full build output. Each run generates a fresh timestamp tag by default.

**Step 2: Populate Product Catalogs and Search Indexes**

Run the data setup script to load sample product data

Expand Down Expand Up @@ -364,7 +395,7 @@ This script will:
- Create and configure Azure AI Search indexes
- Populate search indexes with product and policy documents

**Step 2: Create AI Foundry Agents**
**Step 3: Create AI Foundry Agents**
Run the data setup script to load sample product data and create search indexes in Azure AI Search:

- **For PowerShell (Windows/Linux/macOS):**
Expand Down
4 changes: 2 additions & 2 deletions documents/LocalDevelopmentSetup.md
Original file line number Diff line number Diff line change
Expand Up @@ -221,12 +221,12 @@ ALLOWED_ORIGINS_STR="*"

# Azure AI Foundry
AZURE_AI_AGENT_ENDPOINT="https://your-ai-services.services.ai.azure.com/api/projects/your-project"
AZURE_AI_AGENT_MODEL_DEPLOYMENT_NAME="gpt-4.1-mini"
AZURE_AI_AGENT_MODEL_DEPLOYMENT_NAME="gpt-5.4-mini"
AZURE_FOUNDRY_ENDPOINT="https://your-ai-services.services.ai.azure.com/api/projects/your-project"

# Azure OpenAI
AZURE_OPENAI_ENDPOINT="https://your-openai.openai.azure.com/"
AZURE_OPENAI_DEPLOYMENT_NAME="gpt-4.1-mini"
AZURE_OPENAI_DEPLOYMENT_NAME="gpt-5.4-mini"
AZURE_OPENAI_API_VERSION="2025-01-01-preview"

# Azure AI Search
Expand Down
4 changes: 2 additions & 2 deletions documents/QuotaCheck.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ azd auth login

### 📌 Default Models & Capacities:
```
gpt-4.1-mini:50,text-embedding-3-small:10,gpt-realtime-mini:1
gpt-5.4-mini:50,text-embedding-3-small:10,gpt-realtime-mini:1
```
### 📌 Default Regions:
```
Expand Down Expand Up @@ -48,7 +48,7 @@ eastus, uksouth, eastus2, northcentralus, swedencentral, westus, westus2, southc
```
✔️ All parameters combined:
```
./quota_check_params.sh --models gpt-4:150,gpt-4.1-mini:150 --regions eastus,westus --verbose
./quota_check_params.sh --models gpt-4:150,gpt-5.4-mini:150 --regions eastus,westus --verbose
```

### **Sample Output**
Expand Down
2 changes: 1 addition & 1 deletion documents/TechnicalArchitecture.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ Orchestrates multi-agent workflows with an intelligent orchestrator agent that u
- **Policy/Knowledge Agent**: Retrieves information from policy documents and knowledge bases to answer customer support questions about warranties, returns, and company policies

### Azure OpenAI Service
Provides large language model (LLM) capabilities using GPT-4.1-mini to power natural language understanding and conversational responses across all AI agents.
Provides large language model (LLM) capabilities using GPT-5.4-mini to power natural language understanding and conversational responses across all AI agents.

### Azure AI Search
Provides hybrid search capabilities combining semantic and keyword search across product catalogs and policy documents. Enables fast, accurate retrieval of relevant information for specialized agents.
Expand Down
Loading
Loading