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
Copy file name to clipboardExpand all lines: README.md
+84-13Lines changed: 84 additions & 13 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -15,7 +15,9 @@ This solution accelerator is a powerful tool that helps you create your own copi
15
15
16
16
It leverages Azure OpenAI Service, Azure AI Search and Microsoft Fabric, to streamline daily tasks and customer meeting preparation for customer-facing roles. As a result, this helps to improve client retention and customer satisfaction. By increasing employee productivity and improving customer conversations, our solution enables organizations to serve more customers and drive increased revenue for the entire company.
17
17
18
-
18
+
> Note: Some features contained in this repository are in private preview. Certain features might not be supported or might have constrained capabilities. For more information, see [Supplemental Terms of Use for Microsoft Azure Previews](https://azure.microsoft.com/en-us/support/legal/preview-supplemental-terms).
19
+
20
+
19
21
**Scenario**
20
22
21
23
A Woodgrove Bank Client Advisor is preparing for upcoming client meetings. He wants insight into his scheduled client meetings, access to portfolio information, a comprehensive understanding of previous meetings, and the ability to ask questions about client’s financial details and interests.
@@ -36,31 +38,100 @@ The sample data used in this repository is synthetic and generated using Azure O
To use this solution accelerator, you will need access to an [Azure subscription](https://azure.microsoft.com/free/) with permission to create resource groups and resources. While not required, a prior understanding of Azure OpenAI, Azure AI Search and Microsoft Fabric will be helpful.
51
+
To deploy this solution accelerator, ensure you have access to an [Azure subscription](https://azure.microsoft.com/free/) with the necessary permissions to create **resource groups and resources**. Follow the steps in [Azure Account Set Up](./docs/AzureAccountSetUp.md)
48
52
49
-
For additional training and support, please see:
53
+
Check the [Azure Products by Region](https://azure.microsoft.com/en-us/explore/global-infrastructure/products-by-region/table) page and select a **region** where the following services are available:
➡️ To ensure sufficient quota is available in your subscription, please follow **[Quota check instructions guide](./docs/quota_check.md)** before you deploy the solution.
68
+
69
+
<!-- Here are some example regions where the services are available: East US, East US2, Australia East, UK South, France Central. -->
70
+
<!--
71
+
| [](https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2Fmicrosoft%2Fdocument-generation-solution-accelerator%2Fmain%2Finfra%2Fmain.json) |
72
+
|---|
73
+
-->
74
+
<<<<< Placeholder for Codespace | Placeholder for Dev Container >>>>>
75
+
76
+
### Configurable Deployment Settings
77
+
78
+
When you start the deployment, most parameters will have **default values**, but you can update the below settings by following the steps [here](./docs/CustomizingAzdParameters.md):
79
+
80
+
|**Setting**|**Description**|**Default value**|
81
+
|------------|----------------| ------------|
82
+
|**Azure Region**| The region where resources will be created. | eastus |
83
+
|**Environment Name**| A **3-20 character alphanumeric value** used to generate a unique ID to prefix the resources. | byocatemplate |
84
+
|**Secondary Location**| A **less busy** region for **CosmosDB**, useful in case of availability constraints. | eastus2 |
85
+
|**Deployment Type**| Select from a drop-down list. | Global Standard |
86
+
|**GPT Model**| OpenAI GPT model | gpt-4o-mini |
87
+
|**GPT Model Deployment Capacity**| Configure capacity for **GPT models**. | 30k |
88
+
|**Embedding Model**| OpenAI embedding model | text-embedding-ada-002 |
89
+
|**Embedding Model Capacity**| Set the capacity for **embedding models**. | 80k |
90
+
91
+
92
+
### [Optional] Quota Recommendations
93
+
By default, the **Gpt-4o-mini model capacity** in deployment is set to **30k tokens**, so we recommend
94
+
95
+
<!-- **For Global Standard | GPT-4o-mini - the capacity to at least 150k tokens post-deployment for optimal performance.** -->
96
+
97
+
To adjust quota settings, follow these [steps](./docs/AzureGPTQuotaSettings.md)
98
+
99
+
### Deploying
100
+
101
+
To change the azd parameters from the default values, follow the steps [here](./docs/CustomizingAzdParameters.md).
102
+
103
+
104
+
1. Login to Azure:
105
+
106
+
```shell
107
+
azd auth login
108
+
```
109
+
110
+
#### To authenticate with Azure Developer CLI (`azd`), use the following command with your **Tenant ID**:
111
+
112
+
```sh
113
+
azd auth login --tenant-id <tenant-id>
114
+
```
115
+
116
+
2. Provision and deploy all the resources:
117
+
118
+
```shell
119
+
azd up
120
+
```
121
+
122
+
3. Provide an `azd` environment name (like "byocaapp")
123
+
4. Select a subscription from your Azure account, and selecta location which has quota for all the resources.
124
+
* This deployment will take *7-10 minutes* to provision the resources in your account and set up the solution with sample data.
125
+
* If you get an error or timeout with deployment, changing the location can help, as there may be availability constraints for the resources.
60
126
127
+
5. Once the deployment has completed successfully and you would like to use the sample data, run the bash command printed in the terminal. The bash command will look like the following:
128
+
```shell
129
+
bash ./infra/scripts/process_sample_data.sh
130
+
```
61
131
62
-
> Note: Some features contained in this repository are in private preview. Certain features might not be supported or might have constrained capabilities. For more information, see [Supplemental Terms of Use for Microsoft Azure Previews](https://azure.microsoft.com/en-us/support/legal/preview-supplemental-terms).
132
+
6. 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`.
63
133
134
+
6. You can now delete the resources by running `azd down`, if you are done trying out the application.
By default this template will use the environment name as the prefix to prevent naming collisions within Azure. The parameters below show the default values. You only need to run the statements below if you need to change the values.
4
+
5
+
6
+
> To override any of the parameters, run `azd env set <key> <value>` before running `azd up`. On the first azd command, it will prompt you for the environment name. Be sure to choose 3-20 charaters alphanumeric unique name.
7
+
8
+
9
+
Change the Secondary Location (example: eastus2, westus2, etc.)
10
+
11
+
```shell
12
+
azd env set AZURE_ENV_SECONDARY_LOCATION eastus2
13
+
```
14
+
15
+
Change the Model Deployment Type (allowed values: Standard, GlobalStandard)
16
+
17
+
```shell
18
+
azd env set AZURE_ENV_MODEL_DEPLOYMENT_TYPE Standard
19
+
```
20
+
21
+
Set the Model Name (allowed values: gpt-4, gpt-4o)
22
+
23
+
```shell
24
+
azd env set AZURE_ENV_MODEL_NAME gpt-4o
25
+
```
26
+
27
+
Change the Model Capacity (choose a number based on available GPT model capacity in your subscription)
28
+
29
+
```shell
30
+
azd env set AZURE_ENV_MODEL_CAPACITY 30
31
+
```
32
+
33
+
Change the Embedding Model
34
+
35
+
```shell
36
+
azd env set AZURE_ENV_EMBEDDING_MODEL_NAME text-embedding-ada-002
37
+
```
38
+
39
+
Change the Embedding Deployment Capacity (choose a number based on available embedding model capacity in your subscription)
0 commit comments