Building Generative AI-Powered Applications with Python

IBM via Coursera

Go to class Write review

Details

Go to class

Provider

Coursera
Pricing

Paid Course
Languages

English
Certificate

Paid Certificate Available
Duration & workload

14 hours 49 minutes
Sessions

On-Demand
Subtitles

English

Found in

Part of

IBM Generative AI Engineering

Overview

Coursera Flash Sale

40% Off Coursera Plus for 3 Months!

Grab it

Ready for an interactive learning experience to build real-world generative AI applications and chatbots? In this hands-on course, you’ll develop a series of guided projects using Python, Flask, Gradio, and LangChain to create AI-powered applications for practical scenarios, including a voice assistant, a meeting summarizer, a language translator, and a personalized career coach. You’ll work with popular large language models (LLMs) such as GPT-3, Llama 2, and Flan-UL2, hosted on platforms like IBM watsonx and Hugging Face. You’ll also explore advanced concepts, such as retrieval-augmented generation (RAG), to enhance LLM responses with external knowledge, and integrate speech-to-text (STT) and text-to-speech (TTS) using IBM Watson® Speech Libraries and OpenAI Whisper to enable voice interactions. While a basic understanding of Python is essential, knowledge of HTML, CSS, or JavaScript is helpful but not required. The course includes supporting readings and videos to build foundational knowledge of the models and frameworks used. In addition, a comprehensive course glossary will help reinforce your learning.

Syllabus

Image Captioning with Generative AI

In this module, you will explore the fundamentals of generative AI and foundation models, understanding how they drive modern AI applications. You will gain hands-on experience with image captioning using the bootstrapping language image pretraining (BLIP) model and build interactive UIs with Gradio. The module guides you through using Hugging Face for accessing pretrained models and datasets. You’ll also learn to deploy your AI app using IBM Code Engine for scalable access.

Create Your Own ChatGPT-Like Website

In this module, you will learn how to build your own ChatGPT-like application using generative AI tools. As part of the project, you will work with Facebook’s BlenderBot model using Hugging Face’s Transformers library in Python. You’ll explore key components such as large language models (LLMs), prompt engineering, and user interface design. Practical readings and labs will guide you through integrating models through APIs and deploying your app. You’ll also gain hands-on experience with frameworks like Gradio and Hugging Face. By the end, you’ll be equipped to create and customize your own conversational AI web app.

Create a Voice Assistant

In this module, you will explore how to build a generative AI-powered voice assistant by combining OpenAI’s GPT-3 with IBM Watson’s speech-to-text and text-to-speech services. You will learn how to structure the application, apply containerization using Docker for consistent deployment, and implement a basic voice assistant that can understand spoken input and respond naturally through synthesized speech. Finally, you will learn to deploy the chatbot to a public server.

Generative AI-Powered Meeting Assistant

In this module, you will learn how to build a generative AI-powered meeting assistant that can transcribe, summarize, and answer questions based on meeting content. You will explore key technologies such as IBM watsonx.ai, Meta Llama 2, and OpenAI Whisper, and understand their roles in creating enterprise-ready AI solutions. Through hands-on labs, you will implement a functional meeting assistant that showcases real-world business applications of generative AI.

Summarize Your Private Data with Generative AI and RAG

In this module, you will learn how to build generative AI applications that summarize and answer questions using your own data. You will explore the concept of retrieval-augmented generation (RAG), understand how tools like LangChain and Llama 2 support this process, and apply these technologies to create a functional chatbot that retrieves and summarizes private documents. This hands-on experience will prepare you to implement secure, domain-specific AI assistants in enterprise settings.

Babel Fish (Universal Language Translator) with LLM and STT TTS

In this module, you will acquire the skills to build a real-time voice translator assistant using generative AI technologies. You will learn how to integrate large language models, such as Flan-UL2, with IBM Watson® Speech Libraries for Embed to convert spoken input into translated speech output. The application workflow includes converting speech-to-text (STT), translating the text using an LLM, and converting it back to speech (TTS) in a target language. You will also apply your knowledge of Python, Flask, HTML, CSS, and JavaScript to create a functional and user-friendly web-based voice assistant that supports multilingual communication in real time. To support your learning, this module also includes a course glossary to reinforce key generative AI terms and technologies. You will conclude with a course wrap-up that summarizes major concepts and prepares you to apply your new skills to real-world AI applications.

[Bonus] Module 7: Build an AI Career Coach

In this module, you will learn to build a personalized AI-powered career coach using large language models (LLMs). You will explore how generative AI can assist job seekers by providing resume feedback, job matching insights, and interview preparation guidance. Through hands-on practice, you will implement a job application assistant that uses user inputs and prompt engineering to generate tailored career advice. This module will also help you understand how to apply LLMs in practical, user-centric scenarios that support professional development and career advancement.