Skip to content

Commit e6fcc92

Browse files
docs: Merge pull request #257 from microsoft/psl-readme-draft-table
fix: resolved conflict and updated readme
2 parents 794e11b + 7c3afcf commit e6fcc92

File tree

1 file changed

+49
-37
lines changed

1 file changed

+49
-37
lines changed

README.md

Lines changed: 49 additions & 37 deletions
Original file line numberDiff line numberDiff line change
@@ -39,71 +39,83 @@ The sample data used in this repository is synthetic and generated using Azure O
3939
QUICK DEPLOY
4040
</h2>
4141

42-
[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/microsoft/Conversation-Knowledge-Mining-Solution-Accelerator)
43-
[![Open in Dev Containers](https://img.shields.io/static/v1?style=for-the-badge&label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/microsoft/Conversation-Knowledge-Mining-Solution-Accelerator)
44-
[![Deploy to Azure](https://aka.ms/deploytoazurebutton)](https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2Fmicrosoft%2FConversation-Knowledge-Mining-Solution-Accelerator%2Fmain%2Finfra%2Fmain.json)
42+
| [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/microsoft/Conversation-Knowledge-Mining-Solution-Accelerator) | **** | [![Open in Dev Containers](https://img.shields.io/static/v1?style=for-the-badge&label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/microsoft/Conversation-Knowledge-Mining-Solution-Accelerator) | **** | [![Deploy to Azure](https://aka.ms/deploytoazurebutton)](https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2Fmicrosoft/Conversation-Knowledge-Mining-Solution-Accelerator%2Fmain%2Finfra%2Fmain.json) |
43+
|---|---|---|---|---|
44+
4545

4646

4747
### **Prerequisites**
4848

49-
To deploy this solution accelerator, you will need access to an [Azure subscription](https://azure.microsoft.com/free/) with permission to create resource groups and resources.
49+
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**.
5050

51-
Please check the link [Azure Products by Region](https://azure.microsoft.com/en-us/explore/global-infrastructure/products-by-region/?products=all&regions=all) and choose a region where Azure AI Foundry, Azure OpenAI Services, Azure AI Search, Azure AI Content Understanding, Embedding Deployment Capacity and GPT Model Capacity are available. Recommended regions are eastus, eastus2.
51+
Check the [Azure Products by Region](https://azure.microsoft.com/en-us/explore/global-infrastructure/products-by-region/?products=all&regions=all) page and select a **region** where the following services are available:
5252

53-
> When you start the deployment using one of the options below, most parameters will have a default name set already. You can update the following settings:
53+
- **Azure AI Foundry**
54+
- **Azure OpenAI Services**
55+
- **Azure AI Search**
56+
- **Azure Semantic Search**
57+
- **Azure AI Content Understanding**
58+
- **Embedding Deployment Capacity**
59+
- **GPT Model Capacity**
5460

55-
- Azure region where the resources will be created in
61+
#### **Recommended Deployment Regions**
5662

57-
- Environment name, a 3-20 characters alphanumeric value that will be used to prefix resources
63+
> **eastus** (East US)
64+
> **eastus2** (East US 2)
5865
59-
- Content Understanding location from the drop-down list of values
66+
#### **Configurable Deployment Settings**
6067

61-
- Secondary location, a less busy location for Azure SQL and CosmoDB resources if you run into any availability constraints
68+
When you start the deployment, most parameters will have **default values**, but you can update the following:
6269

63-
- Deployment type from the drop-down list of values
70+
| **Setting** | **Description** |
71+
|------------|----------------|
72+
| **Azure Region** | The region where resources will be created. |
73+
| **Environment Name** | A **3-10 character alphanumeric value** used to prefix resources. |
74+
| **Content Understanding Location** | Select from a **drop-down list** of values. |
75+
| **Secondary Location** | A **less busy** region for **Azure SQL and CosmosDB**, useful in case of availability constraints. |
76+
| **Deployment Type** | Select from a **drop-down list**. |
77+
| **GPT Model** | Choose from **GPT-4, GPT-4o, GPT-4o Mini**. <br> **Default models:** GPT-4o Mini and text-embedding-ada-002. |
78+
| **GPT Model Deployment Capacity** | Configure capacity for **GPT models**. |
79+
| **Embedding Model** | Default: **text-embedding-ada-002**. |
80+
| **Embedding Model Capacity** | Set the capacity for **embedding models**. |
6481

65-
- GPT model from the drop-down list of values
66-
67-
- GPT model deployment capacity (GPT-4, GPT-4o, and GPT-4o Mini)
68-
69-
- Embedding model from the drop-down list of values (text-embedding-ada-002)
82+
---
7083

71-
- Embedding model capacity
84+
### **[Optional] Quota Recommendations**
7285

86+
By default, the **GPT model capacity** in deployment is set to **30k tokens**.
7387

74-
### Checking Resource Availability by Region
88+
#### **Recommended Quota for Optimal Performance**
7589

76-
Before deploying, ensure that the required Azure services are available in your region. Below are links to check service availability:
90+
| **Model Type** | **Default Capacity** | **Recommended Capacity** |
91+
|----------------------|--------------------|--------------------|
92+
| **GPT Model** | 30k tokens | 100k tokens |
7793

78-
- [Azure Products by Region](https://azure.microsoft.com/en-us/explore/global-infrastructure/products-by-region/)
79-
- [Semantic Search Availability](https://learn.microsoft.com/en-us/azure/search/search-region-support)
94+
To adjust quota settings, follow these steps:
8095

81-
## **Steps to Check Semantic Search Availability**
82-
1. Open the [Semantic Search Availability](https://learn.microsoft.com/en-us/azure/search/search-region-support) page.
83-
2. Scroll down to the **"Availability by Region"** section.
84-
3. Use the table to find supported regions for **Azure AI Search** and its **Semantic Search** feature.
85-
4. If your target region is not listed, choose a supported region for deployment.
96+
#### **How to Check & Update Quota**
8697

87-
📌 **Note:** Some features may only be available in specific regions, so ensure compatibility before proceeding.
98+
1. **Navigate** to the [Azure AI Foundry portal](https://portal.azure.com/).
99+
2. **Select** the AI Project associated with this accelerator.
100+
3. **Go to** the `Management Center` from the bottom-left navigation menu.
101+
4. Select `Quota`
102+
- Click on the `GlobalStandard` dropdown.
103+
- Select the required **GPT model** (`GPT-4, GPT-4o, GPT-4o Mini`) or **Embeddings model** (`text-embedding-ada-002`).
104+
- Choose the **region** where the deployment is hosted.
105+
5. Request More Quota or delete any unused model deployments as needed.
106+
<br>
88107

89-
### [Optional]: Quota Recommendations
90-
- The default for the GPT model capacity in deployment is **30k tokens**.
91-
- For optimal performance, it is recommended to increase to **100k tokens**.
92-
- Navigate to the [Azure AI Foundry portal](https://ai.azure.com/)
93-
- Select the AI Project you are using for this accelerator if you are not already in the project.
94-
- Select `Management center` from the bottom left navigation menu
95-
- Select `Quota`, click the `GlobalStandard` dropdown and select the GPT model (`GPT-4 / GPT-4o / GPT-4o mini`) or embeddings model (`text-embedding-ada-002`) and region you are using for this accelerator to see your available quota. Please note `GPT-4o mini` and `text-embedding-ada-002` are used as default.
108+
**⚠️ Warning:** **Insufficient quota can cause deployment issues.** Ensure you have the recommended capacity.
96109

97-
- Request more quota or delete any unused model deployments as needed.
98-
110+
---
99111

100112
### **Options**
101113
Pick from the options below to see step-by-step instructions for: GitHub Codespaces, VS Code Dev Containers, Local Environments, and Bicep deployments.
102114

103115
<details>
104116
<summary><b>Deploy in GitHub Codespaces</b></summary>
105117

106-
### GitHub Codpespaces
118+
### GitHub Codpespaces
107119

108120
You can run this solution accelerator virtually by using GitHub Codespaces. The button will open a web-based VS Code instance in your browser:
109121

0 commit comments

Comments
 (0)