[MS] Bring your custom engine copilot from Azure OpenAI Studio to Microsoft Teams: now in public preview - devamazonaws.blogspot.com

Azure OpenAI announced many new capabilities for connecting to your data with Azure OpenAI at Microsoft Build 2024. Today, we are excited to announce that Azure OpenAI now offers a Deploy to a Teams app option in public preview, providing a new way to help developers connect their enterprise data with their custom engine copilots on Microsoft Teams. If you've been crafting your chat experience using Azure OpenAI Studio, you can now seamlessly bring your chat apps to Microsoft Teams. If you're eager to extend your chat experience from Azure OpenAI Studio to Teams, this option is perfect for you! This feature helps developers create a project source code with an integration of their configuration and data from Azure OpenAI Studio. You can connect your enterprise data from Azure AI Search, Azure Blob Storage, URL/web address, Azure Cosmos DB, Elasticsearch and ground your Azure OpenAI models on your data. This source code is powered by Teams AI library, which helps developers build conversational bots designed to harness the powerful capabilities of Large Language Models (LLMs) for seamless user interaction. Ready to bring your chat app with your data from Azure OpenAI Studio to Teams? Let's get started with just a few simple steps!

Start from Azure OpenAI Studio, chat on Teams

Here are the quick steps to craft your chat experience in Azure OpenAI Studio and seamlessly integrate it into Teams.

Pre-requisites

Configure your data in the chat playground

Before proceeding with the "Deploy to a Teams app" option, ensure that you have designed your chat experience on Azure OpenAI Studio.
  1. In Azure OpenAI Studio, navigate to Chat and Add your data, then Add a data source.
  2. Select Upload files (preview), and set up "Azure Blob storage" and "Azure AI Search" resources. Enter the index name of your choice, then select Next.
A screenshot of a computer Description automatically generated
  1. Drag and drop the files you prefer to use as your data in the chat app. Select Upload files, then Next.
  2. Keep the "Data management" configuration as default, select Next.
  3. Select the Azure resource authentication type of your choice in the "Data connection" step, select Next. Then, Save and close.
Once your data ingestion process is complete, test your setup in the playground by asking questions relevant to your data.

Bring your chat experience to Teams

  1. When ready, select Deploy to in the Chat playground and select A new Teams app (preview) option.
A screenshot of a computer Description automatically generated 2. Enter a name for your Teams app. Then, select Download. A screenshot of a computer Description automatically generated This will download a source code of your Teams app with integrated data.

Test your app on Teams

1. Unzip your downloaded project and open it in Visual Studio Code. 2. Explore the project source code, then select Teams Toolkit from the left side menu. A screenshot of a computer Description automatically generated 3. If you select API Key in data connection, navigate to src\prompts\chat\config.json in your project folder and place the API inside the authentication. 4. Sign in with your Microsoft 365 account in Teams Toolkit, select local environment, then choose Debug (Edge) or Debug (Chrome). A screenshot of a computer Description automatically generated 5. Once your Teams app is provisioned and deployed, Microsoft Teams will open in your browser with your app. Select Add to add your app to a Teams personal chat. 6. Enjoy chatting with your data on Teams by asking questions related to your data! 🎉 A screenshot of a computer Description automatically generated

Next Steps

If you are interested in diving deeper into the source code powered by Teams AI library and Teams Toolkit, check out the tutorial on building your custom copilot for Teams with your data from scratch: Tutorial - Build Custom Copilot - Teams | Microsoft Learn We value your feedback! Please reach out to us if you have any questions or suggestions, we'd love to hear about your experience. Happy coding! 🚀 Follow us on X (Twitter) / @Microsoft365Dev, LinkedIn, and subscribe to our YouTube channel to stay up to date on the latest developer news and announcements.
Post Updated on July 25, 2024 at 04:36PM
Thanks for reading
from devamazonaws.blogspot.com

Comments

Post a Comment

Popular posts from this blog

[MS] Pulling a single item from a C++ parameter pack by its index, remarks - devamazonaws.blogspot.com

In my earlier discussion of pulling a single item from a C++ parameter pack by its index , I noted that with the Pack Indexing proposal, you would be able to write this to pull an item from a parameter pack while preserving its reference category. template<int index, typename...Args> void example(Args&&... args) { auto&& arg = (Args...[index]&&)args...[index]; using Arg = Args...[index]&&; } Why did I need to apply the (Args...[index]&&) cast ? Why can't I just write this: auto&& arg = args...[index]; or possibly decltype(auto) arg = args...[index]; Well, when you write the name of a variable, the result is an lvalue reference, even if the variable is an rvalue reference . Watch: struct S { S(S&); // construct from lvalue S(S&&); // construct from rvalue }; void whathappens(S&& s) { S t = s; // which will it use? } Try it out in your favorite compiler. This code construc...
Read more

[MS] Boosting Azure DevOps Security with GHAS Code Scanning - devamazonaws.blogspot.com

Image
Debjyoti Ganguly shares insights on the security benefits and configuration of GHAS Code Scanning with Azure DevOps. Boosting Azure DevOps Security with GHAS Code Scanning Code scanning, a pipeline-based tool available in GitHub Advanced Security, is designed to detect code vulnerabilities and bugs within the source code of ADO (Azure DevOps) repositories. Utilizing CodeQL as a static analysis tool, it performs query analysis and variant analysis. When vulnerabilities are found, it generates security alerts. CodeQL CodeQL is a powerful static analysis tool used for showing vulnerabilities and bugs in source code. It enables developers to write custom queries that analyze codebases, searching for specific patterns and potential security issues. By converting code into a database format, CodeQL allows for sophisticated, database-like queries to detect flaws. CodeQL in Action 1. Preparing the Code Create a CodeQL Database : Extract and structure the code into a database for analy...
Read more

[MS] Going beyond the empty set: Embracing the power of other empty things - devamazonaws.blogspot.com

The empty set contains nothing. This sounds really silly, but it's actually really nice. The Windows Runtime has a policy that if a method returns a collection (such as an IVector ), and the method produces no results, then it should return an empty collection, rather than a null reference . That way, consumers can just iterate over the collection without having to deal with a null test. For example, suppose you have a method Widget:: Get­Associated­Doodads which returns an IVectorView<Doodad> representing the Doodad objects that have been associated with a Widget object. If no Doodad s have been associated with the Widget , then it should return an empty vector, not a null pointer. That allows developers to write the natural-looking code: // C# foreach (var doodad in widget.GetAssociatedDoodads()) { ⟦ process each doodad ⟧ } // C++/WinRT for (auto&& doodad : widget.GetAssociatedDoodads()) { ⟦ process each doodad ⟧ } // JavaScript widget.GetAssociated...
Read more