GenAI Frequently Asked Questions (FAQ)

Artificial intelligence (AI) is transforming the software development landscape, offering innovative solutions to enhance efficiency, quality, and user experience. With OutSystems integrating advanced AI technologies like GenAI, businesses can harness the power of AI to streamline development processes, automate tasks, and create intelligent applications. This FAQ guide aims to answer common questions about AI, specifically focusing on its applications within the OutSystems platform.

What is GenAI?

Generative AI (GenAI) refers to a category of artificial intelligence systems capable of generating new content, such as text, images, music, or even code, that is similar to what a human might produce. These systems leverage machine learning models, particularly deep learning and neural networks, to understand patterns and structures within the data they have been trained on and use this understanding to create new, original outputs.

Key components and applications of Generative AI include:

1. Text Generation: Models like OpenAI’s GPT (Generative Pre-trained Transformer) can generate coherent and contextually relevant text based on a given prompt. These models are used in chatbots, content creation, and automated reporting.
2. Image Generation: Tools such as GANs (Generative Adversarial Networks) can create realistic images from scratch. These have applications in art, design, and even creating synthetic data for training other AI systems.
3. Music Generation: AI can compose music in various styles, providing musicians and producers with tools to generate new melodies or accompaniments.
4. Code Generation: AI systems can assist in writing code and suggesting snippets or even entire functions based on natural language descriptions or incomplete code.
5. Video Generation: AI can create new video content, including deepfakes, in which a person’s likeness is digitally manipulated to appear as if they are saying or doing something they did not.

Generative AI relies heavily on large datasets and substantial computational power for training. Key techniques include:

• Neural Networks: Particularly deep neural networks, which can model complex patterns in data.
• Transfer Learning: Where a pre-trained model on a large dataset is fine-tuned on a specific task.
• Adversarial Training: Used in GANs, where two networks (a generator and a discriminator) are trained together to improve the quality of generated outputs.

What are large language models (LLMs)?

LLMs are advanced AI systems designed to understand and generate human-like text. These models are trained on vast amounts of text data, learning patterns, and language structures to comprehend and produce written content effectively across a wide range of topics.

What are the requirements for using OutSystems AI Agent Builder?

• AI model: AI Agent Builder requires provisioning of a Large Language Model from Azure OpenAI or Amazon Bedrock.
• Data source (optional): We recommend Azure Blob storage or AWS Kendra for knowledge bases.
• OutSystems platform

What is Retrieval-Augmented Generation (RAG)?

An advanced AI technique that uses a retrieval mechanism to fetch relevant information from a large dataset, which it then incorporates into its generative process to produce high-quality and contextually relevant text outputs.

Where can I find Chat GPT Connector on OutSystems Forge?

You can find the Chat GPT Connector on OutSystems Forge by visiting the Azure OpenAI Connector. This connector facilitates the integration of ChatGPT capabilities within your OutSystems applications, allowing for enhanced AI-driven functionalities.