IBM with RAG and LangChain (W7S171G-SPVC)


In this course, you learn how might help you to put AI to work in your business. You explore the foundation models supported in and improve your prompt engineering skills. You experiment with prompt tuning and seek to understand when to use it over prompt engineering. You explore the LangChain framework that helps you build AI applications based on foundation models. Lastly, you solve several use cases, such as RAG (Retrieval Augmented Generation) and summarization. The course has a large practical component with hands-on exercises on prompt engineering, prompt tuning, and the solving of several use cases with the tools and techniques described in this course.


This course is intended for Data Scientists, AI Specialists, watsonx Specialists, Solution Architects, or anyone interested in gaining basic knowledge of foundation models and generative AI with IBM watsonx.




After completing this course, you should be able to: 

  • Differentiate between the various foundation models available in the Prompt Lab. 
  • Demonstrate the benefits of prompt tuning over prompt engineering. 
  • Describe the Retrieval Augmented Generation (RAG) architecture and use case. 
  • Implement Jupyter Notebooks with Python code calling the Watson Machine Learning API to solve Generative AI problems, 
  • Experiment with the LangChain framework. 
  • Solve RAG, classification and text generation use cases.  
Show details

Course Outline

  • Introduction
  • Foundation Models
  • Prompt Engineering versus Prompt Tuning
  • Retrieval Augmented Generation (RAG)
  • The LangChain Framework
  • Review and Evaluation