Skip to content

Commit 4203b4b

Browse files
Roopan-MicrosoftRoopan-Microsoft
authored
Merge pull request #716 from microsoft/dev
chore: dev to main
2 parents 8631dcc + 0f56338 commit 4203b4b

File tree

1 file changed

+149
-17
lines changed

1 file changed

+149
-17
lines changed

‎documents/AVMPostDeploymentGuide.md‎

Lines changed: 149 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -4,40 +4,172 @@
44
55
---
66

7+
## Overview
8+
79
This document provides guidance on post-deployment steps after deploying the Conversation Knowledge Mining solution accelerator from the [AVM (Azure Verified Modules) repository](https://github.com/Azure/bicep-registry-modules/tree/main/avm/ptn/sa/conversation-knowledge-mining).
810

11+
---
12+
913
## Prerequisites
1014

11-
- **Deployed Infrastructure** - A successful Conversation Knowledge Mining solution accelerator deployment from the [AVM repository](https://github.com/Azure/bicep-registry-modules/tree/main/avm/ptn/sa/conversation-knowledge-mining)
15+
Before proceeding, ensure you have the following:
16+
17+
### 1. Azure Subscription & Permissions
18+
19+
You need access to an [Azure subscription](https://azure.microsoft.com/free/) with permissions to:
20+
- Create resource groups and resources
21+
- Create app registrations
22+
- Assign roles at the resource group level (Contributor + RBAC)
23+
24+
📖 Follow the steps in [Azure Account Set Up](./AzureAccountSetUp.md) for detailed instructions.
25+
26+
### 2. Deployed Infrastructure
27+
28+
A successful Conversation Knowledge Mining solution accelerator deployment from the [AVM repository](https://github.com/Azure/bicep-registry-modules/tree/main/avm/ptn/sa/conversation-knowledge-mining).
29+
30+
### 3. Required Tools
31+
32+
Ensure the following tools are installed on your machine:
33+
34+
| Tool | Version | Download Link |
35+
|------|---------|---------------|
36+
| PowerShell | v7.0+ | [Install PowerShell](https://learn.microsoft.com/en-us/powershell/scripting/install/installing-powershell?view=powershell-7.5) |
37+
| Azure Developer CLI (azd) | v1.18.0+ | [Install azd](https://aka.ms/install-azd) |
38+
| Python | 3.9+ | [Download Python](https://www.python.org/downloads/) |
39+
| Docker Desktop | Latest | [Download Docker](https://www.docker.com/products/docker-desktop/) |
40+
| Git | Latest | [Download Git](https://git-scm.com/downloads) |
41+
| Microsoft ODBC Driver | 18 | [Download ODBC Driver](https://learn.microsoft.com/en-us/sql/connect/odbc/download-odbc-driver-for-sql-server?view=sql-server-ver16) |
42+
43+
---
44+
45+
## Post-Deployment Steps
1246

13-
## Post Deployment Steps
47+
### Step 1: Clone the Repository
1448

15-
### 1. Access the Application
49+
Clone this repository to access the post-deployment scripts and sample data:
50+
51+
```powershell
52+
git clone https://github.com/microsoft/Conversation-Knowledge-Mining-Solution-Accelerator.git
53+
```
54+
55+
```powershell
56+
cd Conversation-Knowledge-Mining-Solution-Accelerator
57+
```
58+
59+
---
60+
61+
### Step 2: Run the Data Processing Script
62+
63+
#### 2.1 Login to Azure
64+
65+
```shell
66+
az login
67+
```
68+
69+
> 💡 **Tip**: If using VS Code Web, use device code authentication:
70+
> ```shell
71+
> az login --use-device-code
72+
> ```
73+
74+
#### 2.2 Execute the Script
75+
76+
Run the bash script from the output of the AVM deployment:
77+
78+
```bash
79+
bash ./infra/scripts/process_sample_data.sh <Resource-Group-Name>
80+
```
81+
82+
> ⚠️ **Important**: Replace `<Resource-Group-Name>` with your actual resource group name from the deployment.
83+
84+
---
85+
86+
### Step 3: Access the Application
1687

1788
1. Navigate to the [Azure Portal](https://portal.azure.com)
18-
2. Open the resource group created during deployment
19-
3. Locate the App Service with name starting with `app-`
89+
2. Open the **resource group** created during deployment
90+
3. Locate the **App Service** with name starting with `app-`
2091
4. Copy the **URL** from the Overview page
2192
5. Open the URL in your browser to access the application
2293

23-
### 2. Configure Authentication (Optional)
94+
---
95+
96+
### Step 4: Configure Authentication (Optional)
97+
98+
If you want to enable authentication for your application, follow the [App Authentication Guide](./AppAuthentication.md).
99+
100+
---
101+
102+
### Step 5: Verify Data Processing
103+
104+
Confirm your deployment is working correctly:
105+
106+
| Check | Location |
107+
|-------|----------|
108+
| ✅ Sample data uploaded | Storage Account |
109+
| ✅ AI Search index created and populated | Azure AI Search |
110+
| ✅ Application loads without errors | App Service URL |
111+
112+
---
113+
114+
### 6. Customize with Your Own Data (Optional)
24115

25-
If you want to enable authentication, configure it by following the [App Authentication Guide](./AppAuthentication.md).
116+
To replace the sample data with your own conversational data, follow these steps:
26117

27-
### 3. Verify Data Processing
118+
#### Prerequisites
119+
- Your data must be in **JSON** (transcripts) or **WAV** (audio) format
120+
- File names should be prefixed with "convo" followed by a GUID and timestamp
121+
- Example: `convo_32e38683-bbf7-407e-a541-09b37b77921d_2024-12-07 04%3A00%3A00`
122+
- For examples, see the sample data in the `infra/data/` folder
28123

29-
- Check that sample data has been uploaded to the storage account
30-
- Verify that the AI Search index has been created and populated
31-
- Confirm that the application loads without errors
124+
#### Upload Your Data
125+
126+
1. Navigate to your **Storage Account** in the Azure Portal
127+
2. Open the `data` container
128+
3. Upload your files to the appropriate folder:
129+
- **Audio files** → `custom_audiodata` folder
130+
- **Transcript files** → `custom_transcripts` folder
131+
132+
> **📝 Note for WAF-aligned deployments**: If your deployment uses private networking, you'll need to upload files from a VM within the virtual network. See the [VM login instructions](#vm-access-for-waf-deployments) below.
133+
134+
#### Process Your Custom Data
135+
136+
Run the processing script to integrate your data into the solution:
137+
138+
```bash
139+
bash ./infra/scripts/process_custom_data.sh
140+
```
141+
142+
If you don't have `azd env` configured, pass the required parameters:
143+
144+
```bash
145+
bash ./infra/scripts/process_custom_data.sh \
146+
<Resource-Group-Name> <Azure-Subscription-ID> \
147+
<Storage-Account-Name> <Storage-Container-Name> \
148+
<SQL-Server-Name> <SQL-Database-Name> <Backend-User-MID-Client-ID> <Backend-User-MID-Display-Name> \
149+
<AI-Search-Name> <Search-Endpoint> \
150+
<AI-Foundry-Resource-ID> <CU-Foundry-Resource-ID> \
151+
<OpenAI-Endpoint> <Embedding-Model> <Deployment-Model> \
152+
<CU-Endpoint> <AI-Agent-Endpoint> <CU-API-Version>
153+
```
154+
155+
#### VM Access for WAF Deployments
156+
157+
For deployments with private networking:
158+
159+
1. Navigate to your VM in the Azure portal
160+
2. Click **Connect** → **Bastion**
161+
3. Enter your VM credentials and click **Connect**
162+
4. Wait for the Bastion connection to establish
163+
5. Upload files through the connected VM interface
32164

33165
## Getting Started
34166

35167
### Sample Questions
36168

37-
Try these questions in the application to explore the solution capabilities:
169+
To help you get started, here are some [Sample Questions](./SampleQuestions.md) you can follow to try it out.
170+
171+
---
172+
173+
## Troubleshooting
38174

39-
- "Total number of calls by date for the last 7 days"
40-
- "Show average handling time by topics in minutes"
41-
- "What are the top 7 challenges users reported?"
42-
- "Give a summary of billing issues"
43-
- "When customers call in about unexpected charges, what types of charges are they seeing?"
175+
If you encounter issues, refer to the [Troubleshooting Guide](./TroubleShootingSteps.md).

0 commit comments

Comments
 (0)