Ready for an interactive learning experience to develop applications and chatbots for diverse use cases using generative AI? This course provides an opportunity to work on guided projects that provide step-by-step instructions to build generative AI-powered applications. You'll utilize Python, along with related libraries like Flask and Gradio, and frameworks such as Langchain.
Class Deals by MOOC List - Click here and see Coursera's Active Discounts, Deals, and Promo Codes.
In the course, you will work on hands-on projects to build chatbots and apps by utilizing popular large language models (LLMs) such as GPT-3 and Llama 2, hosted on platforms such as IBM watsonx and Hugging Face. Additionally, you'll explore retrieval-augmented generation (RAG) technology, enhancing LLMs by incorporating external information beyond their training data. This course also equips you to build voice-enabled chatbots and apps using IBM Watson® Speech Libraries for Embed.
To develop these projects, you'll be using Python, making it essential to have a basic understanding of the language. While knowing some HTML, CSS, and JavaScript can be beneficial, it's not a requirement. The course includes supporting videos and readings to build a foundational understanding of models, frameworks, and technologies used in the projects.
This course is part of the IBM AI Developer Professional Certificate.
What you'll learn
- Explain the core concepts of generative AI models, AI technologies, and AI platforms such as IBM watsonx and Hugging Face.
- Integrate and enhance large language models (LLMs) using RAG technology to infuse intelligence into apps and chatbots.
- Utilize Python libraries like Flask and Gradio to create web applications that interact with generative AI models.
- Build generative AI-powered applications and chatbots using generative AI models, Python, and related frameworks.
Syllabus
Image Captioning with Generative AI
In this module, you will learn the basics of generative AI models and explore the AI models and data sets using the Hugging Face platform. You will work on a guided project that involves image captioning using Python, the BLIP model, and Gradio. This project will let you build an automated image caption tool using generative AI and implement it for real-world scenarios.
Create Your Own ChatGPT-Like Website
In this module, you will learn to create a simple chatbot with open-source LLMs and integrate your chatbot into a web interface. You will explore the different components of the chatbot application and understand how a chatbot works. In addition, you will learn about selecting the right large language model or LLM for your chatbot. In this project, you will work with Facebook’s Blenderbot model and Hugging Face’s Python library, Transformers.
Create a Voice Assistant
In this module, you will learn the basics of chatbots and their applications. You will set up a development environment to build a chatbot. You will build a chatbot that can take voice input and generate a spoken response using IBM Watson speech-to-text functionality and integrate with OpenAI’s GPT 3 model to incorporate high intelligence within the chatbot. And finally, you will learn to deploy the chatbot to a public server.
Generative AI-Powered Meeting Assistant
In this module, you will work on creating an app that captures audio using OpenAI Whisper and summarize it using Llama 2 LLM. Then, you will learn to deploy the app in a serverless environment using the IBM cloud code engine. This module provides a solid foundation for using LLMs for text generation and summarization tasks.
Summarize Your Private Data with Generative AI and RAG
In this module, you will learn how large language models (LLMs) work and how to use them for data summarization and information extraction. You will work on a project to build your own chatbot that allows you to upload a PDF file and answer user queries based on the PDF. You will learn to use Llama 2 LLM supported by the Retrieval-augmented generation (RAG) technique. Finally, you will work with some of the popular frameworks like LangChain to make an intelligent chatbot.
Babel Fish (Universal Language Translator) with LLM and STT TTS
In this module, you will acquire the necessary skills to create a voice translator assistant leveraging generative AI models like flan-ul2 and AI technologies like IBM Watson® Speech Libraries for Embed. This translator application will convert speech input to text and then provide the output through speech in a specified language. You will implement your Python, Flask, HTML, CSS, and JavaScript proficiency to create the web-based voice assistant.
[Bonus] Module 7: Build an AI Career Coach
In this module, you will create an AI career coach to help bridge the gap between talent and opportunity. As part of this AI Career Coach, you will build three applications: a resume enhancement tool, a personalized cover letter generator, and a career advisor. You will leverage the Llama-2-70b-chat large language model (LLM) integrated into the IBM watsonx.ai platform to build these applications. You will also leverage Gradio to build the web interface for these applications.
