Search SharePoint and OneDrive files in natural language with OpenAI function calling and Microsoft Graph Search API

By now, we have seen "Chat with your documents" functionality being introduced in many Microsoft 365 applications. It is typically built by combining Large Language Models (LLMs) and vector databases. 

To make the documents "chat ready", they have to be converted to embeddings and stored in vector databases like Azure AI Search. However, indexing the documents and keeping the index in sync are not trivial tasks. There are many moving pieces involved. Also, many times there is no need for "similarity search" or "vector search" where the search is made based on meaning of the query. 

In such cases, a simple "keyword" search can do the trick. The advantage of using keyword search in Microsoft 365 applications is that the Microsoft Search indexes are already available as part of the service. APIs like the Microsoft Graph Search API and the SharePoint Search REST API give us "ready to consume" endpoints which can be used to query documents across SharePoint and OneDrive. Keeping these search indexes in sync with the changes in the documents is also handled by the Microsoft 365 service itself.

So in this post, let's have a look at how we can combine OpenAI's gpt-4o Large Language Model with Microsoft Graph Search API to query SharePoint and OneDrive documents in natural language. 

On a high level we will be using OpenAI function calling to achieve this. Our steps are going to be:

1. Define an OpenAI function and make it available to the LLM.  

2. During the course of the chat, if the LLM thinks that to respond to the user, it needs to call our function, it will respond with the function name along with the parameters.

3. Call the Microsoft Graph Search API based on the parameters provided by the LLM.

4. Send the results returned from the Microsoft Graph back to the LLM to generate a response in natural language.

So let's see how to achieve this. In this code I have used the following nuget packages:

https://www.nuget.org/packages/Azure.AI.OpenAI/2.1.0

https://www.nuget.org/packages/Microsoft.Graph/5.64.0

The first thing we will look at is our OpenAI function definition:

In this function we are informing the LLM that if needs to search any files as part of providing the responses, it can call this function. The function name will be returned in the response and the relevant parameter will be provided as well. Now let's see how our orchestrator function looks:

There is a lot to unpack here as this function is the one which does the heavy lifting. This code is responsible for handling the chat with OpenAI, calling the MS Graph and also responding back to the user based on the response from the Graph. 

Next, let's have a look at the code which calls the Microsoft Graph based on the parameters provided by the LLM. 

Before executing this code, you will need to have created an App registration. Here is how to do that: https://learn.microsoft.com/en-us/azure/active-directory/develop/quickstart-register-app 

Since we are calling the Microsoft Graph /search endpoint with delegated permissions, the app registration will need a minimum of the User.Read and Files.Read.All permissions granted. https://learn.microsoft.com/en-us/graph/api/search-query?view=graph-rest-1.0&tabs=http

This code get the parameters sent from the LLM and uses the Microsoft Graph .NET SDK to call the /search endpoint and fetch the files based on the searchQuery properties. Once the files are returned, their summary value is concatenated into a string and returned to the orchestrator function so that it can be sent again to the LLM. 

Finally, lets have a look at our CallOpenAI function which is responsible for talking to the Open AI chat api.

 

This code defines the Open AI function which will be included in our Chat API calls. Also, the user's search query is sent to the API to determine if the function needs to be called. This function is also called again after the response from the Microsoft Graph is fetched. At that time, this function contains the details fetched from the Graph to generate an output in natural language. This way, we can use Open AI function calling together with Microsoft Graph API to search files in SharePoint and OneDrive.

Hope this helps!

Add a Site Collection administrator to all Site Collections in a Tenant (including OneDrive for Business sites)

I have come across this scenario many times where even if I am the tenant admin in my SharePoint Online tenant, it is not necessary that I will be the site collection admin of every site collection by default. This is by design and makes perfect sense as there might be some site collections where sensitive data might be stored and I might not have rights to see that data despite being the tenant admin. However, in some scenarios you might feel the need to give a user site collection admin rights for all the site collections in the tenant.

Also for OneDrive for Business site collections in the tenant, the user who is owner of the site collection is the only person who has site collection admin rights on it by default. This can be a problem for compliance and e-discovery reasons. You might be in a situation where you need to give site collection admin rights to a compliance manager or a global administrator on all the OneDrive for Business sites in a tenant.

In this post, lets have a look at how you can make a user a site collection admin on all the site collections in a tenant as well as on all the OneDrive for Business site collections in the tenant.

Some notes:

1) For now, this only works with SharePoint Online/Office 365.
2) You will need the SharePoint Online Client Side Object Model Nuget package
3) By changing a parameter in the SetSiteAdmin function, you can also remove a user from the site collection admins of all site collections.
4) The user who runs this code will need Tenant Administrator rights on the Tenant.

1) Add a site collection admin to all site collections in a tenant:

This is the easy part, all you need to do it get the urls of the site collections in the tenant and add the desired user as a site collection admin to it using the Tenant.SetSiteAdmin function.

2) Add a site collection admin to all the OneDrive for Business site collections in a tenant:

This takes a bit more work. Here are all the things we need to do:

1) Get the account names of the users in a tenant using People Search. Now bear in mind that search has a limitation of returning a maximum of 500 rows on SharePoint Online. That will be 500 users in our case. So if your tenant as more than 500 users, you will need to call search in batches of 500 to get the account names of all the users.

2) Once we have the account names of the users, we need to get the url of their OneDrive for Business sites. We can do this by querying the CSOM UserProfile API

3) After getting the OneDrive for Business site urls, all we need to do is use the same Tenant.SetSiteAdmin function as above.

Here is the complete code for that:


There is also another way to do the same thing where you get the OneDrive for Business site urls from the UserProfileService.asmx and then use the Set-SPOUser SharePoint Online PowerShell cmdlet to set the user as the site collection admin. Here are the details for that https://technet.microsoft.com/en-us/library/dn765092.aspx

Hope you found this article useful!