Updated README to refer to signalr branch (#392)

## Purpose
Updated the "Guidance" section to include a link to `signalr` branch. It
provides readers guidance on how to scale token streaming in production.

## Does this introduce a breaking change?
```
[ ] Yes
[X] No
```

## Pull Request Type
```
[ ] Bugfix
[ ] Feature
[ ] Code style update (formatting, local variables)
[ ] Refactoring (no functional changes, no api changes)
[X] Documentation content changes
[ ] Other... Please describe:
```

## What to Check
- Verify if the description is coherent with the rest of the "Guidance"
section.
- Verify if the links to Azure SignalR service and to `signalr` branch
work.

Author: kevinguo-ed

README.md

@@ -371,6 +371,8 @@ to production. Here are some things to consider:
 
 - **Loadtesting**: We recommend running a loadtest for your expected number of users.
 
+- **Stream tokens to web clients**: Consider using SignalR library which allows bi-directional communication between clients and server. You can easily reuse the single persistent connection for streaming down tokens to clients and receiving signals from them. SignalR simplifies implementing common features in AI chatbot, such as token cancellation. When leveraging [Azure SignalR service](https://learn.microsoft.com/azure/azure-signalr/signalr-overview), you can easily scale to 1M connections. Additionally, Azure SignalR fits nicely in a serverless deployment, providing a cost-efficient solution without worrying about server management. Refer to the [signalr branch](https://github.com/Azure-Samples/azure-search-openai-demo-csharp/tree/signalr) for code sample.
+
 ### Resources
 
 - [Revolutionize your Enterprise Data with ChatGPT: Next-gen Apps w/ Azure OpenAI and Azure AI Search](https://aka.ms/entgptsearchblog)