Experimentation is the key to unlocking innovation in any field. It's how we learn and grow, and it's what helps us continue to create features that help you do more.
So today, we're excited to announce that we're continuing to invest in experimentation with the release of Microsoft Garage ProjectExcel Labs. Excel Labs is an add-in that allows us to publish experimental ideas for you to try and provide us with feedback to help us improve Excel so that it's most useful to you.
Microsoft Garage is Microsoft’s official channel for conducting experimental projects across the company, so teams can receive early feedback from customers and better determine product market fit. With Excel Labs, aligned with the Garage's mission, expect to find very early-stage ideas that we are considering and want to evaluate with clients. While some of these ideas may never see the light of day in an Excel product, we believe that getting your feedback in this way is critical to creating more exciting features that change what's possible in Excel.
The first two experimental ideas released as part of Excel Labs are:
This one is for The advanced editor for complex formulas was previously released as a separate Garage project, the Advanced Formula Environment plugin. But out of a desire to experiment with various features, we're upgrading AFE and integrating all of its functionality into Excel Labs, so you don't need to install multiple add-ins.
As you saw in last month’s release of Microsoft 365 Copilot, we saw The huge potential of generative AI. So, with this experimental add-in, you can test the benefits of generative AI directly from your Excel grid using the LABS.GENERATIVEAI custom function. This feature allows you to send prompts from an Excel grid to a generative AI model, and then return the model's results to your worksheet. Note that this is not part of M365 Copilot, but is where you play and experiment with generated AI today within the Garage framework.
It's easy - just install the Excel Labs add-in through the Office Store. If you don't see the add-in when you type Excel Labs in the Office Store search box, your version of Office might not meet the minimum system requirements.
After installing or updating the add-in, select the Excel Lab button in the Home tab. This will open Excel Lab's Function Library page, where you can select the functions you want to use. To return to the library at any time, select the overflow menu in the navigation bar.
Excel Lab Function Library
AdvancedFormula Environment Function is a tool designed to help you create more easily , tools to edit and reuse complex formulas and LAMBDA functions. While the built-in Excel name manager allows you to name and create complex formulas, the advanced formula environment adds to this by providing features commonly found in modern code editors, such as IntelliSense, comments, inline errors, automatic formatting, and code folding. an experience.
For more information about this feature, please visit the previous blog post announcing the release of the standalone plugin. Remember, you don’t need to download this add-in separately as this functionality is now part of the Excel Labs add-in experience.
Advanced Formula Environment Features
Given the recent excitement around Generative AI, we are interested in hearing what types of Excel you have Scenarios can benefit from these AI models. So, to better help you experiment, we created the LABS.GENERATIVEAI custom function that enables you to prompt and display the responses of OpenAI's large language models directly into the grid.
LABS.GENERATIVEAI Custom Function
Generative AI models are large-scale language models that use machine learning to generate digital content such as human-like text, code, and even images. When given a prompt, a generative AI model returns a response generated by the model's algorithm.
The opportunities for using generative AI are endless, as it can generate responses in a variety of different formats. For the LABS.GENERATIVEAI custom function, we specifically connect to the OpenAI API for large language models. This includes models such as "gpt-3.5-turbo" (the model that supports ChatGPT) and "text-davinci-003". Some of the most common use cases for these models include text generation, text completion, summarization, classification, text transformation, and question answering. For example, you can prompt it to parse keywords in survey responses, or you can ask it to analyze the sentiment of a tweet table. In general, we encourage you to try different prompts to see how more general or specific prompts affect the responses you get. Instead of “write a poem about Excel,” try “write a poem about Excel that mentions pivot tables.” If you're interested, you can start with the examples in the add-on, or explore some common hint examples on OpenAI's website.
Given the nature of large language models, it is important to understand that these models may produce meaningless or even confident but erroneous responses due to their predictive nature. We are committed to building responsible AI, and LABS.GENERATIVEAI custom functions were created with our AI principles and responsible AI standards in mind. Additionally, the OpenAI Moderation endpoint is integrated into the functionality to automatically filter responses. However, it must be remembered that there are still some considerations to consider when using AI systems, such as validating results before making decisions.
Overall, the scope of generative AI capabilities is still being explored, and this is your chance to experiment with what it can do for you in an Excel environment.
When you select the LABS.GENERATIVEAI function in the function library, the first thing you need to do is add your OpenAI API key. If you don't have an API key yet, you'll need to sign up for an OpenAI account and then request one.
Once you have the key, add it to the task pane. You only need to perform this step once.
Configure your OpenAI API key
Now you can try the generative AI customization feature!
Enter =LABS.GENERATIVEAI to access the function in the grid and enter your prompt as input to the function.
Similar to OpenAI’s Playgound, in the Excel Labs task pane you can also generate AI Model Settings button to adjust the settings for model response. This reveals different settings that affect response formatting. Two key settings you may want to experiment with are temperature and maximum output length. Temperature determines the consistency of the response returned. For example, if you want to always get the same response from your model, you should set the temperature setting to 0. Another setting you might want to try is the maximum output length setting, which controls the maximum number of tokens returned in a response. Note that as you increase the number of tokens, you may turn on the AI's rate limit faster.
LABS.GENERATIVEAI Response Settings
While you can adjust settings in the task pane, you can also make adjustments directly in the grid using the optional parameters of this function. For example, the following function uses the "text-curie-001" model to generate a response with a temperature value of 1 and a maximum output length of 100.
=LABS.GENERATIVEAI("Write me a poem about Excel", 1, 100, "text-curie-001")
To learn more about the settings, Please visit Models - OpenAI API.
The above is the detailed content of Advanced Formula Environment is becoming Excel Labs, a Microsoft Garage Project!. For more information, please follow other related articles on the PHP Chinese website!
![[Web front-end] Node.js quick start](https://img.php.cn/upload/course/000/000/067/662b5d34ba7c0227.png)
