Skip to content

Commit 1856d21

Browse files
brown9804brown9804
authored
Merge pull request #8 from MicrosoftCloudEssentials-LearningHub/refs-AI-SA
Update README with detailed project information
2 parents 70850fc + 6656e02 commit 1856d21

File tree

2 files changed

+29
-20
lines changed

2 files changed

+29
-20
lines changed

‎README.md‎

Lines changed: 27 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ Costa Rica
88
[![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/)
99
[brown9804](https://github.com/brown9804)
1010

11-
Last updated: 2025-09-17
11+
Last updated: 2025-10-29
1212

1313
-----------------------------
1414

@@ -40,21 +40,30 @@ Last updated: 2025-09-17
4040

4141
- [Solution Accelerator for AI Document Processor (ADP)](https://github.com/azure/ai-document-processor) - AI Factory
4242

43-
| **Category** | **Details** |
44-
|------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
45-
| **Purpose** | Automate document processing using Azure services and LLMs. Extracts data from files (PDF, Word, MP3), processes via Azure OpenAI, and outputs structured insights (JSON/CSV) to blob storage. |
46-
| **Infrastructure Provisioning** | Uses Bicep templates to deploy all required Azure resources. Automates setup of networking, identity, and access controls using RBAC and managed identities to ensure secure and scalable deployment. |
47-
| **Main Azure Resources** | - **Azure Function App**: Hosts the orchestrator and activity functions using Durable Functions to manage the document processing workflow.<br>- **Azure Storage Account**: Stores input documents (bronze container) and output results (gold container). Also holds prompt configurations if UI is not deployed.<br>- **Azure Static Web App**: Provides a user-friendly interface for uploading files, editing prompts, and triggering workflows.<br>- **Azure OpenAI**: Processes extracted text using LLMs to generate structured summaries or insights.<br>- **Azure Cognitive Services**: Specifically uses Document Intelligence for OCR and text extraction from uploaded files.<br>- **Cosmos DB**: Stores prompt configurations when the frontend UI is enabled, allowing dynamic updates from the web interface.<br>- **Key Vault**: Securely stores secrets, keys, and credentials used by the Function App and other services.<br>- **Application Insights**: Enables monitoring, logging, and diagnostics for the Function App and other components.<br>- **App Service Plan**: Provides the compute resources for running the Function App. |
48-
| **Pipeline Components** | - `function_app.py`: Main orchestrator using Durable Functions chaining pattern.<br>- `activities/runDocIntel.py`: Extracts text from documents using Azure Document Intelligence.<br>- `activities/callAoai.py`: Sends extracted text and prompt to Azure OpenAI and receives structured JSON.<br>- `activities/writeToBlob.py`: Writes the final output to the gold container in blob storage. |
49-
| **Data Flow** | 1. Upload document to bronze container<br>2. OCR via Document Intelligence<br>3. Send extracted text + prompt to Azure OpenAI<br>4. Receive structured JSON<br>5. Write output to gold container |
50-
| **Frontend UI (Optional)** | - Allows business users to upload files and edit prompts<br>- Prompts are stored in Cosmos DB<br>- Users can trigger workflows and view job status directly from the interface |
51-
| **Prompt Configuration** | - Without UI: Prompts are stored in `prompts.yaml` file in blob storage<br>- With UI: Prompts are stored and managed in Cosmos DB via the web interface |
52-
| **Deployment Steps** | 1. Fork and clone the GitHub repo<br>2. Run `az login`, `azd auth login`, `azd up`<br>3. Provide User Principal ID for RBAC setup<br>4. Choose whether to deploy frontend UI |
53-
| **Execution (Without UI)** | - Update `prompts.yaml` with desired instructions<br>- Send POST request to `http_start` endpoint with blob metadata<br>- Monitor pipeline execution via Log Stream |
54-
| **Execution (With UI)** | - Upload files via web interface<br>- Edit system and user prompts<br>- Click "Start Workflow" to trigger pipeline<br>- View success/failure messages and job status |
55-
| **Monitoring & Troubleshooting** | - Use Log Stream for real-time logs<br>- Use Log Analytics Workspace to query exceptions and performance metrics<br>- Use SSH console in Development Tools to inspect deployment logs and file system |
56-
| **Pre-Requisites** | - Azure CLI<br>- Azure Developer CLI (azd)<br>- Node.js 18.x.x<br>- npm 9.x.x<br>- Python 3.11 |
57-
| **License** | MIT License – Free to use, modify, and distribute with attribution. No warranty provided. |
43+
| **Category** | **Details** |
44+
|------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
45+
| **Purpose** | Automate document processing using Azure services and LLMs. Extracts data from files (PDF, Word, MP3), processes via Azure OpenAI, and outputs structured insights (JSON/CSV) to blob storage. |
46+
| **Infrastructure Provisioning** | Uses Bicep templates to deploy all required Azure resources. Automates setup of networking, identity, and access controls using RBAC and managed identities to ensure secure and scalable deployment. |
47+
| **Main Azure Resources** | - **Azure Function App**: Hosts the orchestrator and activity functions using Durable Functions to manage the document processing workflow.<br>- **Azure Storage Account**: Stores input documents (bronze container) and output results (gold container). Also holds prompt configurations if UI is not deployed.<br>- **Azure Static Web App**: Provides a user-friendly interface for uploading files, editing prompts, and triggering workflows.<br>- **Azure OpenAI**: Processes extracted text using LLMs to generate structured summaries or insights.<br>- **Azure Cognitive Services**: Specifically uses Document Intelligence for OCR and text extraction from uploaded files.<br>- **Cosmos DB**: Stores prompt configurations when the frontend UI is enabled, allowing dynamic updates from the web interface.<br>- **Key Vault**: Securely stores secrets, keys, and credentials used by the Function App and other services.<br>- **Application Insights**: Enables monitoring, logging, and diagnostics for the Function App and other components.<br>- **App Service Plan**: Provides the compute resources for running the Function App. |
48+
| **Pipeline Components** | - `function_app.py`: Main orchestrator using Durable Functions chaining pattern.<br>- `activities/runDocIntel.py`: Extracts text from documents using Azure Document Intelligence.<br>- `activities/callAoai.py`: Sends extracted text and prompt to Azure OpenAI and receives structured JSON.<br>- `activities/writeToBlob.py`: Writes the final output to the gold container in blob storage. |
49+
| **Data Flow** | 1. Upload document to bronze container<br>2. OCR via Document Intelligence<br>3. Send extracted text + prompt to Azure OpenAI<br>4. Receive structured JSON<br>5. Write output to gold container |
50+
| **Frontend UI (Optional)** | - Allows business users to upload files and edit prompts<br>- Prompts are stored in Cosmos DB<br>- Users can trigger workflows and view job status directly from the interface |
51+
| **Prompt Configuration** | - Without UI: Prompts are stored in `prompts.yaml` file in blob storage<br>- With UI: Prompts are stored and managed in Cosmos DB via the web interface |
52+
| **Deployment Steps** | 1. Fork and clone the GitHub repo<br>2. Run `az login`, `azd auth login`, `azd up`<br>3. Provide User Principal ID for RBAC setup<br>4. Choose whether to deploy frontend UI |
53+
| **Execution (Without UI)** | - Update `prompts.yaml` with desired instructions<br>- Send POST request to `http_start` endpoint with blob metadata<br>- Monitor pipeline execution via Log Stream |
54+
| **Execution (With UI)** | - Upload files via web interface<br>- Edit system and user prompts<br>- Click "Start Workflow" to trigger pipeline<br>- View success/failure messages and job status |
55+
| **Monitoring & Troubleshooting** | - Use Log Stream for real-time logs<br>- Use Log Analytics Workspace to query exceptions and performance metrics<br>- Use SSH console in Development Tools to inspect deployment logs and file system |
56+
| **Pre-Requisites** | - Azure CLI<br>- Azure Developer CLI (azd)<br>- Node.js 18.x.x<br>- npm 9.x.x<br>- Python 3.11 |
57+
| **License** | MIT License – Free to use, modify, and distribute with attribution. No warranty provided. |
58+
59+
<img width="835" height="535" alt="image" src="https://github.com/user-attachments/assets/61dbac57-f635-4dd6-9292-50e51823a8c4" />
60+
61+
> Data flow:
62+
63+
<img width="930" height="620" alt="image" src="https://github.com/user-attachments/assets/2f01a07b-71cd-4ee9-b316-c0a2273d01b2" />
64+
65+
> ZTA:
66+
<img width="1840" height="935" alt="image" src="https://github.com/user-attachments/assets/947ddf0d-daf3-4df3-949c-1271a3fef7bb" />
5867
5968
- [Use Azure AI services with SynapseML in Microsoft Fabric](https://learn.microsoft.com/en-us/fabric/data-science/how-to-use-ai-services-with-synapseml)
6069
- [Plan and manage costs for Azure AI Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/costs-plan-manage)
@@ -528,7 +537,7 @@ Last updated: 2025-09-17
528537

529538
<!-- START BADGE -->
530539
<div align="center">
531-
<img src="https://img.shields.io/badge/Total%20views-1292-limegreen" alt="Total views">
532-
<p>Refresh Date: 2025-09-17</p>
540+
<img src="https://img.shields.io/badge/Total%20views-1297-limegreen" alt="Total views">
541+
<p>Refresh Date: 2025-10-29</p>
533542
</div>
534543
<!-- END BADGE -->

‎terraform-infrastructure/README.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -109,7 +109,7 @@ graph TD;
109109

110110
<!-- START BADGE -->
111111
<div align="center">
112-
<img src="https://img.shields.io/badge/Total%20views-1292-limegreen" alt="Total views">
113-
<p>Refresh Date: 2025-09-17</p>
112+
<img src="https://img.shields.io/badge/Total%20views-1297-limegreen" alt="Total views">
113+
<p>Refresh Date: 2025-10-29</p>
114114
</div>
115115
<!-- END BADGE -->

0 commit comments

Comments
 (0)