Building Retrieval-Augmented Systems & Knowledge Graphs

Overview

AI, Data Science & Cloud Certificates from Google, IBM & Meta — 40% Off

One plan covers every Professional Certificate on Coursera. 40% off your first 3 months — limited time.

This course teaches you how to enhance large language models (LLMs) by integrating retrieval-augmented generation (RAG) and structured knowledge through knowledge graphs. You'll learn how to design, optimize, and scale AI agents that combine external data sources with advanced reasoning capabilities. The practical applications of RAG and knowledge graphs are transforming the way intelligent agents operate, improving accuracy and reducing errors. Throughout this course, you will acquire valuable skills in building and refining AI systems. We focus on practical outcomes, where you will develop the expertise to create agents that leverage web data, RAG pipelines, and knowledge graphs. These techniques will allow you to tackle real-world challenges in AI development. What sets this course apart is its unique combination of theory and real-world application. You'll work through hands-on projects that use cutting-edge technology, ensuring that you gain practical experience while reinforcing theoretical concepts. The course emphasizes scalability, security, and the implementation of best practices. This course is ideal for AI developers, data scientists, and anyone interested in the field of intelligent agent development. It is particularly suited for individuals with a background in AI, machine learning, or software development who want to specialize in advanced AI systems. This course is part two of a three-course Specialization designed to provide a comprehensive learning pathway in this subject area. While it delivers standalone value and practical skills, learners seeking a more integrated and in-depth progression may benefit from completing the full Specialization.

Syllabus

Building a Web Scraping Agent with an LLM

This module explores how large language models (LLMs) can serve as the core of intelligent web scraping agents. Learners will examine the architecture of such agents, compare single-agent and multi-agent systems, and gain hands-on familiarity with key frameworks like Haystack and AutoGen. By the end, you'll understand how to leverage LLMs and supporting libraries to automate web-based information retrieval tasks.

Extending Your Agent with RAG to Prevent Hallucinations

This module explores how to enhance language model agents using Retrieval-Augmented Generation (RAG) to minimize hallucinations and improve reliability. Learners will examine RAG components, embedding strategies, vector databases, and evaluation metrics, and compare RAG with fine-tuning approaches. Practical application is demonstrated through building a movie recommendation agent.

Advanced RAG Techniques for Information Retrieval and Augmentation

This module explores advanced Retrieval-Augmented Generation (RAG) techniques designed to enhance information retrieval and augmentation in AI systems. Learners will examine improvements over naïve RAG, including query transformation, reranking, modular architectures, scalability, and security considerations. By the end, participants will understand how to implement and optimize sophisticated RAG pipelines for real-world applications.

Creating and Connecting a Knowledge Graph to an AI Agent

This module guides learners through the process of building, cleaning, and deploying knowledge graphs, and demonstrates how to connect them to AI agents using tools like Neo4j and LangChain. Learners will explore taxonomies, ontologies, and graph-based retrieval methods, as well as the challenges and applications of integrating knowledge graphs with large language models. The module also covers advanced topics such as graph reasoning, graph neural networks, and ongoing challenges in the field.