How Azure OpenAI Is Used in Enterprises

Technical requirements

The following are the technical prerequisites of this section:

• An Azure subscription, which you can create for free here.

• Access to Azure OpenAI in the Azure subscription. Currently, access to this service is granted only by application. You can apply for access to Azure OpenAI by completing the form.

• An Azure OpenAI Service resource with a model deployed.

Use of Python and LLMs

All the code will be written using Python. To work with Azure OpenAI’s large language models (LLMs), we will use LangChain, a lightweight framework that makes it easier to wrap LLMs in applications. For the frontend, we will use Streamlit, an open source Python library that makes it easy to build and deploy web applications for data science and machine learning projects. It provides a simple and intuitive interface for creating interactive data-driven applications.

Note: For each scenario, while exporting the code and API from Azure OpenAI, we will also set some values to pre-set parameters such as temperature, max_tokens, and so on. For a comprehensive list of these parameters and their meaning, you can refer to the lesson, "What is OpenAI?" under the "An overview of OpenAI model families" heading.