Introduction

Enterprises are increasingly adopting GPT-based solutions using Azure OpenAI and Copilot Studio to build secure, scalable, and context-aware AI assistants. A critical architectural decision in this journey is where enterprise documents should be storedso that the AI can search, index, and respond accurately.

Many organizations naturally consider SharePoint because it already houses documents and collaboration content. However, when building Enterprise GPT solutions with Azure OpenAI + Azure AI Search, Azure Blob Storageemerges as a more reliable and scalable choice.

This blog explains why Azure Blob Storage is preferred over SharePointfor Enterprise GPT implementations and provides a clear comparison to help architects and decision-makers choose the right approach

AI Grounding for Enterprise Documents

Let’s start with Step-by-step instructions how you can deploy a Open AI module using Azure Open AI.

Prerequisites

An Azure subscription.

• If you don’t already have one, you can sign up for an Azure free account.
• For students, you can use the free Azure for Students offerwhich doesn’t require a credit card only your school email.

Access to Azure OpenAI in the desired Azure subscription.

• Azure OpenAI requires registration and is currently only available to approved enterprise customers and partners. See Limited access to Azure OpenAI Servicefor more information.

Summary of the steps:

Step 1: Open Azure Portal and Create a new Resource group.

Step 2: Create an Azure Blob storage resource.

Step 3: Create an Azure AI Search resource.

Step 4: Create an Azure   OpenAI resource.

Step 5: Create a ChatGPT deployment.

Step 1: Open Azure Portal and Create a new Resource group

A resource group is a container that holds related resources for an Azure solution. The resource group can include all the resources for the solution or only those resources that you want to manage as a group. (Learn more: here)

1. Visit the Azure Portal https://portal.azure.comin your browser and sign in.

Now you are inside theAzure portal!

2. Type resource group in the search bar at the top of the portal page and select Resource groups from the options that appear.

3. Select Create from the toolbar to create a new resource group.

4. Perform the following tasks:

• Select your Subscription.
• Enter the Resource group name. It must be a unique value.
• Select the Region you’d like to use.
• Select Review + create followed by Create.

5. Wait for the resource group to be created then open it by selecting its name.

Step 2: Create an Azure Blob storage resource

Azure Blob Storage helps you create data lakes for your analytics needs and provides storage to build powerful cloud-native and mobile apps. Optimize costs with tiered storage for your long- term data and flexibly scale up for high-performance computing and machine learning workloads. (Learn more: here)

You will use it to store the uploaded documents.

1. Inside your newly created resource group, select Create resources.

2. Type storage account in the search bar of the Marketplace page and select Create Storage account from the options that appear.

3. Perform the following tasks:

• Select your Subscription.
• Select the Resource Group you previously created.
• Enter the Storage account name. It must be unique and only letters and numbers are allowed.
• Select the Region you’d like to use.
• Select the Performance tier you’d like to use. The Standard tier will work for you.
• Select the data Redundancy type you’d like to use. The GRS type will work for you.
• Check the Make read access to data available option.
• Select Review + create.

Now, you have successfully created a storage account that will contain all your Azure Storage data objects: blobs, files, queues, and tables.

Step 3: Create an Azure AI Search resource

Azure AI Search (formerly known as “Azure Cognitive Search”) is a cloud search service that gives developers infrastructure, APIs, and tools for building a rich search experience over private, heterogeneous content in web, mobile, and enterprise applications. (Learn more: here)

You will use it to search the uploaded documents’ content as it supports numerical filtering.

Azure OpenAI models only understand text and thus will not be able to provide us with the indexes.

1. Inside your resource group, select Create and type azure ai search in the search bar of the Marketplace page and select Create Azure AI Search from the options that appear.

2. Perform the following tasks:

• Select your Subscription.
• Select the Resource Group you previously created.
• Enter the Service name. It must be unique.
• Select the Location you’d like to use.
• Select the Pricing tier you’d like to use. The Basic or Standard tier will work for you.
• Select Review + create

Now, you have successfully created a Azur AI Search service that will add a full-text search experience to your custom app.

Step 4: Create an Azure OpenAI resource

Azure AI Search (formerly known as “Azure Cognitive Search”) is a cloud search service that gives developers infrastructure, APIs, and tools for building a rich search experience over private, heterogeneous content in web, mobile, and enterprise applications. (Learn more: here)

You will use it to search the uploaded documents’ content as it supports numerical filtering.

Azure OpenAI models only understand text and thus will not be able to provide us with the indexes.

1. Inside your resource group, select Create and type azure ai search in the search bar of the Marketplace page and select Create Azure AI Search from the options that appear.

2. Perform the following tasks:

• Select your Subscription.
• Select the Resource Group you previously created.
• Enter the Service name. It must be unique.
• Select the Location you’d like to use.
• Select the Pricing tier you’d like to use. The Basic or Standard tier will work for you.
• Select Review + create

Now, you have successfully created a Azur AI Search service that will add a full-text search experience to your custom app.

Step 5: Create a ChatGPT deployment

Deployments provide endpoints to the Azure OpenAI base models, or your fine-tuned models, configured with settings to meet your needs, including the content moderation model, version handling, and deployment size. (Learn more: here)

This is the large language model that will generate the chat.

1. Inside your resource group, select the Azure Open AI resource that you previously created.

2. Select Go to Azure AI Foundry portal to open the studio.

3. You have to login to your Azure AI Foundry portal and below page will be opened after login:

4. Select Deployments to go to the Model Deployments and create new deployment model

5. Select Deploy model and use gpt-4.1-mini to create a new ChatGPT deployment.

6. Perform the following tasks:

• Select a Model. gpt-4.1-mini is a large language model that can act as our ChatGPT.
• Select the Model version. 2015-04-14 (default)
• Enter a Deployment name. Any unique name shall work.
• Select Deploy.

Now, you have successfully created a model deployment that will enable you to have a conversation with your own data.

Step 6: Bring your own Data to Azure OpenAI

Now, you need to bring it all together to build our solution.

You are using the previously created resources to configure this feature.

1. Inside your Deployments, select the previously created deployment followed by selecting Open in playground. (The Playground is a place on Azure OpenAI where you can experiment with different generative models.)

2. Enter any text you want in the Chat session tab to test your deployed model.

Now, let’s add your own data to make the model more grounded and enable it to respond to specific questions related to the data.

3. Select Add your data

Inside the Data source tab, select Upload files as your data source followed by performing the following tasks:

• Select the Azure Blob storage resource that you have previously created.

• Select the Azure Cognitive Search resource that you have previously created.

• Select Turn on CORS to give Azure OpenAI access to your storage account.

• Enter the index name that will be used to index the uploaded files. Any name will work.

• Select the acknowledgment that informs you that you will be charged for using the Azure Cognitive Search service.

• Select Next.

5. Inside the Upload files tab, upload the document that you want to use as your data source followed by selecting Upload files, then selecting Next.

6. Inside the Data management tab, select the Search type followed by selecting Next. The Semantic type will work for you.

Note: Semantic search will give you better search results but it has limited availability.

7. Inside the Review and finish tab, review all the properties then, select Save and close.

Now we have grounded our large language model to overcome the hallucinations it might give whenever it doesn’t have a response for our prompt.

Conclusion:

While SharePoint remains excellent for collaboration and content management, it is not designed for high-performance AI retrieval and indexing scenarios. For Enterprise GPT solutions using Azure OpenAI and Copilot Studio, the combination of:

1. Azure Blob Storage(document storage)

1. Azure AI Search(indexing and semantic search)

1. Azure OpenAI(LLM reasoning)

provides a scalable, secure, and enterprise-ready architecture.

By using Azure Blob Storage, organizations gain better control over data ingestion, improved search accuracy, lower costs, and a future-proof foundation for AI-driven solutions. This is why Microsoft’s recommended approach for “Bring Your Own Data” scenarios relies on Blob Storage instead of SharePointfor Enterprise GPT implementations

About the author

Microsoft MVP | Business Central & Power Automate Expert | Helping SMBs Automate & Save 100+ Hours Monthly

S, Mishra (06/05/2026) Enterprise GPT using Azure Open AI and Copilot Studio – Model Deployment. (8) Enterprise GPT using Azure Open AI and Copilot Studio – Model Deployment | LinkedIn