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
| Contact Center Customer Support | Analyst | Difficulty in extracting actionable insights from large, complex datasets due to limited context or practical considerations. Limited ability to engage with data interactively, making it challenging to find the right questions to dig deeper.| Contextualized insights from mined data that enables employees to solve problems and take action. Interactive data that allow employees to ask questions and receive timely responses, providing better understanding and problem-solving.|
164
+
IT Helpdesk | IT Helpdesk Analyst | Manually reviewing IT Helpdesk calls to identify recurring issues is time-consuming and inefficient. Creating graphs, analyzing performance problems, and drafting FAQs is often a slow process, leaving gaps in self-service support. | Address these challenges by leveraging AI to gain insights from call data, generating visual summaries, uncovering common issues, and producing FAQ content, transforming a labor-intensive review process into a fast, accurate, and actionable workflow. |
Write-Host "`nRun the following command in your Bash terminal. It will grant the necessary permissions between resources and your user account, and also process and load the sample data into the application."
echo "Run the following command in your Bash terminal. It will grant the necessary permissions between resources and your user account, and also process and load the sample data into the application."
Copy file name to clipboardExpand all lines: documents/CustomizeData.md
+17-8Lines changed: 17 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -14,15 +14,24 @@ If you would like to update the solution to leverage your own data please follow
14
14
> **Note for WAF-aligned deployments:** If your deployment uses private networking, you'll need to log into a VM within the virtual network to upload files. See [VM login instructions](#how-to-login-to-vm-using-azure-bastion) below.
15
15
16
16
3. If you have audio files, upload them to `custom_audiodata` folder. If you have call transcript files, upload them to `custom_transcripts` folder.
17
-
4. Navigate to the terminal and run the `run_process_data_scripts.sh` to process the new data into the solution with the following commands.
4. Navigate to the terminal and run the `process_custom_data.sh` script to process the new data into the solution with the following commands:
18
+
19
+
```bash
20
+
bash ./infra/scripts/process_custom_data.sh
21
+
```
22
+
23
+
If you don't have `azd env` then you need to pass parameters along with the command. Parameters are grouped by service for clarity. The command will look like the following:
Copy file name to clipboardExpand all lines: documents/DeploymentGuide.md
+60-6Lines changed: 60 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,11 +6,11 @@ To deploy this solution, ensure you have access to an [Azure subscription](https
6
6
7
7
Check the [Azure Products by Region](https://azure.microsoft.com/en-us/explore/global-infrastructure/products-by-region/?products=all®ions=all) page and select a **region** where the following services are available:
8
8
9
-
-[Azure AI Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry)
10
-
-[Azure AI Content Understanding Service](https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/)
- [Microsoft ODBC Driver 18](https://learn.microsoft.com/en-us/sql/connect/odbc/download-odbc-driver-for-sql-server?view=sql-server-ver16) for SQL Server.
153
154
154
155
2. Clone the repository or download the project code via command-line:
155
156
@@ -176,6 +177,7 @@ When you start the deployment, most parameters will have **default values**, but
176
177
|**Azure Region**| The region where resources will be created. |*(empty)*|
177
178
|**Environment Name**| A **3–20 character alphanumeric value** used to generate a unique ID to prefix the resources. | env\_name |
178
179
|**Azure AI Content Understanding Location**| Region for content understanding resources. | swedencentral |
180
+
|**Use Case**| Industry use case: **Contact-center** or **IT_helpdesk**. | (empty) |
179
181
|**Secondary Location**| A **less busy** region for**Azure SQL and Azure Cosmos DB**, usefulincase of availability constraints. | eastus2 |
180
182
|**Deployment Type**| Select from a drop-down list (allowed: `Standard`, `GlobalStandard`). | GlobalStandard |
181
183
|**GPT Model**| Choose from **gpt-4, gpt-4o, gpt-4o-mini**. | gpt-4o-mini |
@@ -244,12 +246,64 @@ Once you've opened the project in [Codespaces](#github-codespaces), [Dev Contain
244
246
245
247
3. Provide an `azd` environment name (e.g., "ckmapp").
246
248
4. Select a subscription from your Azure account and choose a location that has quota for all the resources.
247
-
-- This deployment will take *7-10 minutes* to provision the resources in your account and set up the solution with sample data.
249
+
5. Choose the use case:
250
+
- **Contact-center**
251
+
- **IT_helpdesk**
252
+
253
+
- This deployment generally takes **7-10 minutes** to provision the resources in your account and set up the solution.
248
254
- If you encounter an error or timeout during deployment, changing the location may help, as there could be availability constraints for the resources.
249
255
250
-
5. Once the deployment has completed successfully, open the [Azure Portal](https://portal.azure.com/), go to the deployed resource group, find the App Service, and get the app URL from `Default domain`.
256
+
5. Once the deployment has completed successfully, copy the bash command from terminal: (ex: `bash ./infra/scripts/process_sample_data.sh`) for later use.
257
+
258
+
6. Create and activate a virtual environment in bash terminal:
259
+
260
+
```shell
261
+
python -m venv .venv
262
+
```
263
+
264
+
**For Windows (Bash):**
265
+
```shell
266
+
source .venv/Scripts/activate
267
+
```
268
+
269
+
**For Linux/VS Code Web (Bash):**
270
+
```shell
271
+
source .venv/bin/activate
272
+
```
273
+
274
+
7. Login to Azure:
275
+
276
+
```shell
277
+
az login
278
+
```
279
+
280
+
Alternatively, login to Azure using a device code (recommended when using VS Code Web):
281
+
282
+
```shell
283
+
az login --use-device-code
284
+
```
285
+
8. Run the bash script from the output of the azd deployment. The script will look like the following:
286
+
287
+
```bash
288
+
bash ./infra/scripts/process_sample_data.sh
289
+
```
290
+
291
+
If you don't have `azd env`then you need to pass parameters along with the command. Parameters are grouped by service for clarity. The command will look like the following:
9. Once the deployment has completed successfully, open the [Azure Portal](https://portal.azure.com/), go to the deployed resource group, find the App Service, and get the app URL from `Default domain`.
251
305
252
-
6. If you are done trying out the application, you can delete the resources by running `azd down`.
306
+
10. You can now delete the resources by running `azd down`, if you are done trying out the application.
253
307
>**Note:** If you deployed with `enableRedundancy=true` and Log Analytics workspace replication is enabled, you must first disable replication before running `azd down`else resource group delete will fail. Follow the steps in [Handling Log Analytics Workspace Deletion with Replication Enabled](./LogAnalyticsReplicationDisable.md), waituntil replication returns `false`, then run `azd down`.
Copy file name to clipboardExpand all lines: documents/SampleQuestions.md
+8Lines changed: 8 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -5,6 +5,7 @@ To help you get started, here are some **Sample Prompts** you can ask in the app
5
5
> Note: To avoid rate limit errors, pause for 2–3 seconds after a response before submitting the next question. <br>
6
6
Average response time is 8–14 seconds.
7
7
8
+
For Contact Center (telecom) use case:
8
9
1. Ask the following questions:
9
10
- Total number of calls by date for last 7 days.
10
11
- To view the response data as a graph, just prompt "Generate Chart".
@@ -16,5 +17,12 @@ Average response time is 8–14 seconds.
16
17
17
18
18
19
20
+
For IT Helpdesk use case:
21
+
1. Ask the following questions:
22
+
- Please provide the total number of calls by date for last 7 days
23
+
- Generate a bar chart showing the number of helpdesk calls per day for the last week.
24
+
- Provide a summary of performance issues users reported this week.
25
+
- Turn these key topics into a structured FAQ.
26
+
19
27
20
28
This structured approach helps users quickly extract actionable insights from client conversations to help users understand priorities, trends, and opportunities for better engagement.
0 commit comments