05 Microsoft Azure AI Fundamentals: 02 Generative AI | 02 Fundamentals of Azure OpenAI Service
What does a response from a GPT model look like?
A key aspect of OpenAI's generative AI is that it takes an input, or prompt, to return a natural language, visual, or code response. GPT tries to infer, or guess, the context of the user's question based on the prompt.
How to use Azure OpenAI?
As of Dec 8, 2023, you need to apply for access to Azure OpenAI. Once granted access, you can use the service by creating an Azure OpenAI resource, like you would for other Azure services. Once the resource is created, you can use the service through REST APIs, Python SDK, or the web-based interface in the Azure OpenAI Studio.
What are Azure OpenAI capabilities?
Azure OpenAI's capabilities are made possible by specific generative AI models. Different models are optimized for different tasks; some models excel at summarization and providing general unstructured responses, and others are built to generate code or unique images from text input.
What is DALL-E?
DALL-E is an image generator model by using a prompt. The more detailed the prompt, the more likely the model will provide a desired result. With DALL-E, you can even request an image in a particular style, such as "a dog in the style of Vincent van Gogh". Styles can be used for edits and variations as well. See MS documentation for details.
Are there overlapping capabilities of Azure AI services?
Yes, there are several overlapping capabilities between Azure AI Language service and Azure OpenAI Service, such as translation, sentiment analysis, and keyword extraction.
What can you do in an Azure OpenAI Studio's "Completions" playground?
n the Completions playground, you can type in prompts, configure parameters, and see responses without having to code.
Which Azure AI service is used for use-cases that require highly customized generative models, or for exploratory research?
Azure OpenAI Service May be more beneficial for use-cases that require highly customized generative models, or for exploratory research.
Where did OpenAI come from?
Azure OpenAI Service is a result of the partnership between Microsoft and OpenAI. The service combines Azure's enterprise-grade capabilities with OpenAI's generative AI model capabilities.
Name four Azure OpenAI models.
Four Azure OpenAi models: - GPT-4 models (latest latest generative models for natural language and code. - GPT 3.5 models (generate natural language and code) - Embeddings models (text to numeric vectors for analysis) - DALL-E models (generate images)
How models are applied to new use cases?
Users interact on the front-end and the back-end includes the generative AI model. The combination of the front and back end can be described as a chatbot.
What can you do with OpenAI?
With Azure OpenAI, users can summarize text, get code suggestions, generate images for a web site, and much more. This module dives into these capabilities.
Can Azure OpenAI's AI models can all be trained and customized with fine-tuning?
Yes, Azure OpenAI's AI models can all be trained and customized with fine-tuning.
Can DALL-E edit generated art styles?
Yes, DALL-E can edit the image as requested by changing its style, adding or removing items, or generating new content to add. See MS documentation for detail and illustrations
Where can you experiment with OpenAI models?
You can experiment with OpenAI models in playgrounds.
What is Artificial Intelligence?
Artificial Intelligence Imitates human behavior by relying on machines to learn and execute tasks without explicit directions on what to output.
What Azure A service is widely known use-cases that require minimal tuning?
Azure AI Language service can be used for widely known use-cases that require minimal tuning (the process of optimizing a model's performance).
What are AI services used for?
Azure AI services are tools for solving AI workloads. The services you choose to use depend on what you need to accomplish.
How can customers gain access and use Azure Open AI?
Access to Azure OpenAI is currently limited. Customers that wish to use Azure OpenAI must submit a registration form for both initial experimentation access, and again for approval for use in production. See the Azure OpenAI limited access documentation.
What four components are Azure OpenAI
Azure OpenAI is available for Azure users and consists of four components: 1) Pre-trained generative AI models 2) Customization capabilities; the ability to fine-tune AI models with your own data 3) Built-in tools to detect and mitigate harmful use cases so users can implement AI responsibly 4) Enterprise-grade security with role-based access control (RBAC) and private networks
What are some of the Azure OpenAI workloads?
Common AI workloads include machine learning, computer vision, natural language processing, conversational AI, anomaly detection, and knowledge mining.
End of course
Course completed
What is Deep Learning and what can it do?
Deep learning models use layers of algorithms in the form of artificial neural networks to return results for more complex use cases. Many Azure AI services are built on deep learning models. You can check out this article to learn more about the difference between machine learning and deep learning.
How do you edit an image in DALL-E?
Edits are made by uploading the original image and specifying a transparent mask that indicates what area of the image to edit. Along with the image and mask, a prompt indicating what is to be edited instructs the model to then generate the appropriate content to fill the area.
What is GPT?
GPT - Generative pre-trained transformer (GPT) models are excellent at both understanding and creating natural language. If you've seen recent news around AI answering questions or writing a paragraph based on a prompt, it likely could have been generated by a GPT model such as GPT-35-Turbo or GPT-4.
Can OpenAI models do programming?
GPT models are able to take natural language or code snippets and translate them into code. The OpenAI GPT models are proficient in over a dozen languages, such as C#, JavaScript, Perl, PHP, and is most capable in Python.
How can GPT models help developers?
GPT models can help developers code faster, understand new coding languages, and focus on solving bigger problems in their application. Developers can break down their goals into simpler tasks and use GPT to help build out those tasks using known patterns. See MS documentation for details.
What type of natural language tasks can GPT models perform?
GPT models can perform: - Summarizing text - Classifying text - Generating names or phrases - Translation - Answering questions - Suggesting content See MS documentation for details.
Explain "Generating code"
Generating code Such as: translating code from one programming language into another, identifying and troubleshooting bugs in code, and much more
Explain "Generating images"
Generating images Such as: generating images for publications from text descriptions and much more
Explain "Generating natural language."
Generating natural language Such as: summarizing complex text for different reading levels, suggesting alternative wording for sentences, and much more
What is Generative AI and what can it do?
Generative AI models can produce new content based on what is described in the input. The OpenAI models are a collection of generative AI models that can produce language, code, and images.
Exercise - Explore Azure OpenAI Service (IMPORTANT - As of Dec 8, 2023, access to Azure OpenAI is limited, you need to "request" access by completing and submitting a request form t Microsoft.)
IMPORTANT - As of Dec 8, 2023, access to Azure OpenAI is limited, you need to "request" access by completing and submitting a request form t Microsoft.
What can an OpenAi Image genertion models do?
Image generation models can take a prompt, a base image, or both, and create something new. These generative AI models can create both realistic and artistic images, change the layout or style of an image, and create variations on a provided image.
How do you create image variations in DALL-E?
Image variations can be created by providing an image and specifying how many variations of the image you would like. The general content of the image will stay the same, but aspects will be adjusted such as where subjects are located or looking, background scene, and colors may change. See MS documentation for detail and illustrations
What do data scientist and developers use too build Azure OpenAI models?
In the Azure OpenAI Studio, you can build AI models and deploy them for public consumption in software applications.
What can you do in an Azure OpenAI Studio's "Chat" playground?
In the Chat playground, you can use the assistant setup to instruct the model about how it should behave. The assistant will try to mimic the responses you include in tone, rules, and format you've defined in your system message.
What is Machine Learning and what can it do?
Machine learning algorithms take in data like weather conditions and fit models to the data, to make predictions like how much money a store might make in a given day.
What is Microsoft's Transparency Notes on Azure OpenAI? Explain
Microsoft's Transparency Notes on Azure OpenAI Help you understand how Microsoft's AI technology works, the choices system owners can make that influence system performance and behavior, and the importance of thinking about the whole system, including the technology, the people, and the environment
How are Natural language learning models are trained?
Natural language learning models are trained on words or chunks of characters known as tokens. For example, the word "hamburger" gets broken up into the tokens ham, bur, and ger, while a short and common word like "pear" is a single token.
What is GitHub Copilot?
OpenAI partnered with GitHub to create GitHub Copilot, which they call an AI pair programmer. GitHub Copilot integrates the power of OpenAI Codex into a plugin for developer environments like Visual Studio Code.
What is OpenAI?
OpenAI, an AI research company, created a chatbot known as ChatGPT and an image generation application known as DALL-E. These technologies were built with AI models which can take natural language input from a user and return a machine-created human-like response.
Other AI workloads Azure OpenAI supports can be categorized by the following tasks they support
Other AI workloads Azure OpenAI supports can be categorized by tasks they support: * Generating Natural Language Text completion: generate and edit text Embeddings: search, classify, and compare text * Generating Code: generate, edit, and explain code * Generating Images: generate and edit images
IS the pricing the same for Azure OpenAI and Azure AI Language services?
Pricing is different for Azure OpenAI and Azure AI Language service. See: https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/
Azure OpenAI's relationship to Azure AI services
See: As of July 2023, Azure AI services encompass all of what were previously known as Cognitive Services and Azure Applied AI Services.
Explain the steps to setup and configure Azure OpenAI Service.
Setup and configure Azure OpenAI Service: 1) Prerequisite - An Azure subscription or free trail 2) Request access by submitting form - As of 12/08/2023 3) Provision an Azure OpenAI resource 4) Navigate to Azure OpenAI Studio 5) Connect you Azure OpenAI resource 6) Deploy a model for language generation (Left-side menu) 7) Use the Chat playground to work with the model 8) Use the DALL-E playground to generate images 9) Clean up
Summarize what you have learned in this flashcard deck as it pertains to MS Azure OpenAI.
Summary In this module, you also learned how to: Describe Azure OpenAI workloads and how to access the Azure OpenAI Service Understand generative AI models Understand Azure OpenAI's language, code, and image capabilities Understand Azure OpenAI's Responsible AI practices and Limited Access Policy
What are the capabilities of OpenAI? Name three.
There are several categories of capabilities found in OpenAI AI models, three of these include: 1) Generating natural language 2) Generating code 3) Generating images
What happens with the tokens, regarding machine learning?
These tokens are mapped into vectors for a machine learning model to use for training. When a trained natural language model takes in a user's input, it also breaks down the input into tokens.
Microsoft has partnered with OpenAI, to deliver what three goals?
Three main goals: 1) To utilize Azure's infrastructure, including security, compliance, and regional availability, to help users build enterprise-grade applications. 2) To deploy OpenAI AI model capabilities across Microsoft products, including and beyond Azure AI products. 3) To use Azure to power all of OpenAI's workloads.
After I gain access, what if I want to modify content filters or modify abuse monitoring settings in Azure OpenAi?
To apply for access and learn more about the limited access policy, see the Azure OpenAI limited access documentation.
Describe Azure OpenAI's access and responsible AI policies, there are six Microsoft AI principles, that are they?
six Microsoft AI principles: Fairness: AI systems shouldn't make decisions that discriminate against or support bias of a group or individual. Reliability and Safety: AI systems should respond safely to new situations and potential manipulation. Privacy and Security: AI systems should be secure and respect data privacy. Inclusiveness: AI systems should empower everyone and engage people. Accountability: People must be accountable for how AI systems operate. Transparency: AI systems should have explanations so users can understand how they're built and used.