Get started with OpenAI in .NET

Introduction

Welcome to this blog series on OpenAI and .NET!

Artificial intelligence (AI) is changing the ways we live and work. Some early examples of how AI is being embedded into the applications you use today include search in Bing, office productivity in Microsoft 365, and developer productivity in GitHub.

As a developer, you might be thinking, “I want to use these same AI features in my own applications”. Although the technology used to train the underlying AI models can be complex, using these models in your applications doesn’t have to be.

Over the next few months, we plan on publishing a series of blog posts showcasing samples and discussing a series of AI-related building blocks to help you add OpenAI-powered AI capabilities to your .NET applications.

But first, an introduction.

What is OpenAI

OpenAI is a research and deployment company. They are the creators of the models powering experiences like ChatGPT and Bing Image Creator. These models include:

• Generative Pretrained Transformers (GPT) – A model that can understand and generate text or code.
• DALL-E – A model that can generate and edit images given a text description.
• Whisper – A model that can convert audio into text.

What can I do with models like GPT

While there are countless applications OpenAI models like GPT can be used for, the following are just a few examples:

• Create a chatbot to answer questions about your business
• Categorize the sentiment of a product review
• Extract keywords and entities from a document
• Translate text from one language to another
• Generate images for blog posts

How can I access OpenAI models

Access to models like GPT is available via REST APIs and libraries.

Additionally, Azure OpenAI Service provides Azure customers with access to OpenAI’s advanced language AI models such as OpenAI GPT-4 with the security and enterprise promise of Microsoft Azure.

The APIs are co-developed with OpenAI to ensure compatibility and a smooth transition between the two. Customers also benefit from private networking, regional availability, and responsible AI content filtering.

For more details, see the documentation on comparing Azure OpenAI Service and OpenAI.

How do I get started with OpenAI models and .NET

There’s a few options to get started using OpenAI models in .NET:

• REST API
• Azure OpenAI .NET SDK

NOTE: The Azure OpenAI .NET SDK is currently in preview.

We recommend using the Azure OpenAI .NET SDK which supports both OpenAI and Azure OpenAI Service.

To get started using OpenAI models with the Azure OpenAI .NET SDK:

1. Sign up or request access with OpenAI or Azure OpenAI Service.
2. Use your credentials to start experimenting with the OpenAI .NET samples.

What’s next

In the next post, we’ll go into more detail on the topic of completions, which are the text and code generated by OpenAI models. Stay tuned!

We want to hear from you

Help us learn more about how you’re looking to use AI in your applications. Take a few minutes to complete this survey.

The post Get started with OpenAI in .NET appeared first on .NET Blog.

source https://devblogs.microsoft.com/dotnet/getting-started-azure-openai-dotnet/