Module 3: Text Generation

Meor Amer and Jay Alammar

Meor Amer and Jay Alammar

Hello, and welcome to Module 3, from your instructors Meor and Jay!

In this module, you’ll learn about text generation. Large language models (LLMs) are powerful AI systems trained on vast amounts of text data, enabling them to generate text with impressive accuracy and creativity. LLMs have revolutionized text generation, allowing for the creation of diverse and engaging content, from stories and articles to chatbots and customer support, enhancing human-computer interactions and driving innovation across industries.

What Is Generative AI?

Generative AI is a type of artificial intelligence that focuses on creating or generating new content or data. This can be in the form of text, images, videos, and more.

Its market potential is significant as it has the power to revolutionize many industries and drive innovation in a wide range of fields. For example, in creative arts, generative AI can be used to generate unique and engaging content. In the business world, generative AI can be used to generate reports, presentations, and other business documents, reducing the need for manual data analysis and enhancing productivity.

In this module, the focus is on text. We want to enable developers to add generative text to their technology stack and build impactful applications with it.

Module Overview

Here are the chapters and topics that we’ll cover in this module:

  1. Introduction to Text Generation: Learn about Cohere’s Command model and how an LLM chatbot works, and get an introduction to Cohere’s Chat endpoint.
  2. Building a Chatbot: Learn how to build a chatbot from scratch using the Chat endpoint, and explore features like defining preambles, streaming, and state management.
  3. Parameters for Controlling Outputs: Learn about the parameters that you can leverage to ​​control the Chat endpoint's output.
  4. Prompt Engineering Basics: Learn the basics of prompt engineering and how to craft creative and effective prompts to obtain desirable outputs for various tasks.
  5. Fine-Tuning for Chat: Learn how to fine-tune the Chat endpoint model on custom datasets, enhancing its performance on specific tasks.
  6. Introduction to RAG: Learn how to connect LLMs to external knowledge sources, enhancing the accuracy and relevance of chatbot responses.
  7. Conclusion - Text Generation: Recap what you have learned and explore suggested topics to continue your learning.

What’s Next

Let's get started with text generation!