flopes - QnA instructions

README.md

@@ -9,14 +9,14 @@ Public repo with Solution Accelerators to support the Hackathon
 |--------------|-----------|------------|------------|------------|
 | [OpenAI chatGPT](https://github.com/Azure-Samples/cosmosdb-chatgpt) | This sample application combines Azure Cosmos DB with OpenAI ChatGPT with a Blazor Server front-end for an intelligent chat bot application that shows off how you can build a simple chat application with OpenAI ChatGPT and Azure Cosmos DB | [Alexandre Vieira](https://github.com/vieiraae) | Generative AI | [🔗](./docs/cosmosdb-chatgpt.md) |
 | [Customer Service Conversational Insights](https://github.com/microsoft/Customer-Service-Conversational-Insights-with-Azure-OpenAI-Services) | Solution accelerator built on top of Azure Cognitive Search, Bot Framework, Azure Speech Services and Azure OpenAI that allows to quickly deploy an integrated platform and immediately start extracting insights from customer conversations | [André Matos]() | Generative AI; New Ways of Working | [🔗]() |
-| [OpenAI Embeddings QnA](https://github.com/Azure-Samples/azure-open-ai-embeddings-qna) | Sample that uses Azure OpenAI Service for creating embeddings vectors from documents. For answering the question of a user, it retrieves the most relevant document and then uses GPT-3 to extract the matching answer for the question. | [Fábio Lopes]() | Knowledge Behind Data; Generative AI | [🔗]() |
+| [OpenAI Embeddings QnA](https://github.com/Azure-Samples/azure-open-ai-embeddings-qna) | Sample that uses Azure OpenAI Service for creating embeddings vectors from documents. For answering the question of a user, it retrieves the most relevant document and then uses GPT-3 to extract the matching answer for the question. | [Fábio Lopes]() | Knowledge Behind Data; Generative AI | [🔗](docs/openai-qna.md) |
 | [Retail Recommender](https://github.com/microsoft/Azure-Synapse-Retail-Recommender-Solution-Accelerator) | This accelerator was built to provide developers with all of the resources needed to quickly build an Retail Recommender Solution based on Azure. | [Alexandre Vieira](https://github.com/vieiraae) | Gamification; Knowledge Behind Data | [🔗]() |
 | [eShop on Containers](https://github.com/dotnet-architecture/eShopOnContainers) | Sample .NET Core reference application, powered by Microsoft, based on a simplified microservices architecture and Docker containers. | [André Matos]() | New online frontiers | [🔗]() |
-| [Business Process Automation](https://github.com/Azure/business-process-automation) | This accelerator provides a no code Studio for users to quickly build complex, multi-stage AI pipelines across multiple Azure AI and ML Services. | [Fábio Lopes]() | Future-Proof Supply Chains | [🔗]() |
 
 
-## Other solution accelerators
 
+## Other solution accelerators
+- [Business Process Automation](https://github.com/Azure/business-process-automation)
 - [Build a smart, frictionless checkout prototype using Azure Custom Vision](https://github.com/microsoft/solution-accelerator-containerized-store)
 - [Knowledge Mining Solution Accelerator](https://learn.microsoft.com/en-us/samples/azure-samples/azure-search-knowledge-mining/azure-search-knowledge-mining/)
 - [Non-fungible Token Solution Accelerator](https://github.com/microsoft/Azure-Non-Fungible-Token-Solution-Accelerator)

docs/openai-qna.md

@@ -0,0 +1,29 @@
+# Instructions to run the OpenAI Embeddings QnA Solution Accelerator
+
+## Prerequisites
+- Contributor access to the Azure resource group provided for the Hackathon
+- Reader access to the Azure OpenAI service provided for the Hackathon
+
+## Instructions to deploy the accelerator
+- From the solution accelerator main github page navigate to the "Deploy on Azure (WebApp + Redis Stack + Batch Processing)" section.
+- Click on the "Deploy to Azure" banner. This will open the Azure portal where you can configure the template for deployment.
+- Use the following configurations in the parameter selection:
+  - "Resource Group" field, select the Resource Group assigned to your workspace.
+  - "Region" field, select "West Europe".
+  - "Resource Prefix" field will be used to name the resources. Use any 2-13 string (without special characters).
+  - "Open AI Name" field, use the name of the resource provided to you. Eg, If assigned the endpoint https://bh-openai-1.openai.azure.com/, use "bh-openai-1".
+  - "Open AI Key" field, use the key provided to you.
+  - If no translation and/or Form Recognizer is used, you can use "NA" for the following fields: "Form Recognizer Endpoint", "Form Recognizer Key", "Translate Endpoint", "Translate Key", "Translate Region"
+ - Click "Review and Create".
+ - Your deployment will be validated. If it succeeds, click "Create". If not, reach out to one of the mentors for help.
+ - Once your deployment completes (should take a couple of minutes), navigate to your resource group in the Azure portal and identify the resource with suffix "-site".
+ - The URL for your application will be present in the essentials pane, in the "Default domain" field. 
+ - The first time you open the URL you can expect it to take a few seconds to load.
+
+## Notes
+
+Use the [Azure OpenAI Studio](https://oai.azure.com/) to access the [playground](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=programming-language-studio&tabs=command-line) to test the model and generate code for your use cases. Leverage the following guides for quick starts:
+- [C#](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=programming-language-csharp&tabs=command-line)
+- [Python](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=programming-language-python&tabs=command-line)
+- [Python samples](https://github.com/Azure-Samples/openai)
+- [REST](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=rest-api&tabs=command-line)