Connect to OpenAI-compatible local servers from Microsoft Excel and Word

On Microsoft Excel and Word, GPT for Work can connect to any locally running LLM server that provides an OpenAI-compatible API. Once connected, all models available on the local server become available to use in GPT for Work.

note

Depending on the model you use, the spreadsheet settings defined in GPT for Work (temperature (creativity), top-p, frequency penalty, and presence penalty) may not work as expected. If you get bad results, try tweaking the settings.

Here are a few local server solutions that you can use with GPT for Work:

• LM Studio

• KoboldAI

• LocalAI

• Open WebUI

Connecting to a local server in GPT for Work means setting the URL for the server and selecting one of the models available on the server.

Prerequisites

• Local server that is running with one or more models and that supports the following OpenAI-compatible API endpoints:

  • /v1/chat/completions

  • /v1/models

  For instructions on how to set up LM Studio, see:

  • Set up LM Studio on macOS

  • Set up LM Studio on Windows

Set the local server URL

Excel

1. Open a Microsoft Excel workbook.

2. Click GPT for Excel Word in the Home tab.

   

   info

   You can also go to Home > Add-ins > My add-ins > GPT for Excel Word.

3. In the sidebar menu, select API keys.

   

4. In the Custom local server field, enter the URL for the local server, and click Save.

   
   tip

   If you get an error saying that the URL is invalid, make sure that the local server supports:

   • Cross-origin resource sharing (CORS). See the LM Studio setup instructions for macOS or Windows.

   • HTTPS (needed with Safari and with Microsoft Office for Mac). See the LM Studio setup instructions for macOS.

You have set the local server URL in GPT for Excel. You can now select local models.

Word

1. Open a Microsoft Word document.

2. Click GPT for Excel Word in the Home tab.

   

   info

   You can also go to Home > Add-ins > My add-ins > GPT for Excel Word.

3. In the sidebar menu, select Manage API keys.

   

4. In the Custom local server field, enter the URL for the local server, and click Save.

   
   tip

   If you get an error saying that the URL is invalid, make sure that the local server supports:

   • Cross-origin resource sharing (CORS). See the LM Studio setup instructions for macOS or Windows.

   • HTTPS (needed with Safari and with Microsoft Office for Mac). See the LM Studio setup instructions for macOS.

You have set the local server URL in GPT for Word. You can now select local models.

Select a model available on the local server

Excel

1. Expand the model switcher. You can find the available local models under Use your API key or endpoint.

   
   note

   The available models depend on the models installed on the local server.

2. Select a model.

GPT for Excel now uses the selected model to generate all responses.

Word

1. Expand the model switcher. You can find the available local models under Use your API key or endpoint.

   
   note

   The available models depend on the models installed on the local server.

2. Select a model.

GPT for Word now uses the selected model to generate all responses.