Retrieval Augmented Generation

Packt via Coursera Specialization

Go to class Write review

Details

Go to class

Provider

Coursera Specialization
Pricing

Paid Course
Languages

English
Certificate

Certificate Available
Duration & workload

4 weeks, 10 hours a week

Found in

Overview

Coursera Flash Sale

40% Off Coursera Plus for 3 Months!

Grab it

This specialization features Coursera Coach! A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the specialization. In this specialization, you’ll learn advanced techniques for building and deploying Retrieval-Augmented Generation (RAG) systems. You’ll explore methods like query expansion, re-ranking, and dense passage retrieval, while gaining hands-on experience with RAG's core components. The specialization also helps you navigate RAG deployment challenges and provides solutions for real-world applications. The specialization is divided into four parts. It begins with an introduction to RAG concepts, followed by developing RAG applications using LlamaIndex and integrating data with LLMs. Next, you'll explore using Knowledge Graphs to enhance AI systems, and finally, build multimodal systems by combining RAG with GPT for smarter solutions. This specialization is perfect for intermediate learners with a basic understanding of AI and programming. It’s suitable for those interested in AI, software development, and data science. Familiarity with Python is required. By the end of the specialization, you’ll be able to develop RAG applications, use Knowledge Graphs to improve AI systems, and create multimodal systems combining RAG with GPT.

Syllabus

Course 1: Master Retrieval-Augmented Generation (RAG) Systems
Course 2: Gen AI - RAG Application Development using LlamaIndex
Course 3: AI Enhancement with Knowledge Graphs - Mastering RAG Systems
Course 4: Multimodal RAG with GPT – Build Smarter Search & AI Systems

Courses

0 reviews
5 hours 50 minutes
View details

Updated in May 2025. This course now features Coursera Coach! A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course. Unleash the potential of AI systems by mastering Retrieval-Augmented Generation (RAG) techniques with Knowledge Graphs in this comprehensive course. You'll learn how to design, build, and query advanced Knowledge Graphs while integrating them with AI systems to boost contextual understanding and improve retrieval efficiency. The course begins with a solid introduction to Knowledge Graphs, including their structure, construction, and applications. You'll set up your development environment, dive into practical Neo4j implementations, and programmatically generate Knowledge Graphs. Through guided exercises, you'll extract real-world data, transform it into graph structures, and visually explore their interconnections. Moving further, you'll explore the synergy between Knowledge Graphs and RAG systems, creating vector indexes, embeddings, and integrating them into databases. Learn advanced querying methods, visualizations, and workflows for AI-powered use cases. By the end, you'll build a RAG-powered Knowledge Graph project, combining Neo4j and LangChain, to showcase the full flow of data transformation, retrieval, and application. This course is perfect for AI enthusiasts, data engineers, and developers eager to enhance their AI models with Knowledge Graphs. Prior experience with Python and basic AI concepts is recommended. Whether you’re at an intermediate or advanced level, you'll gain valuable, industry-relevant skills.
0 reviews
9 hours 37 minutes
View details

This course will equip you with the skills to develop RAG (retrieval-augmented generation) applications using LlamaIndex and Large Language Models (LLMs). You'll explore the integration of LlamaIndex with various data sources and how to fine-tune prompts for sophisticated AI-driven applications. The course starts with the fundamentals of LLMs and the key concepts around prompt engineering, before diving deep into the capabilities of LlamaIndex. You will first learn the essentials of LlamaIndex and its environment setup, followed by creating your first application. The course progressively takes you through different prompt types, including conversational prompts, and introduces semantic similarity evaluators. You’ll understand the significance of language embeddings, vector databases, and how to work with a Chroma DB or an SQL database to store and retrieve data efficiently. Further, the course will guide you in creating and optimizing query pipelines in LlamaIndex, such as sequential query pipelines and DAG (Directed Acyclic Graph) pipelines, and working with agents and tools. You will build real-world applications, including a calculator using a ReAct agent and a document agent with dynamic tools, demonstrating the versatility of LlamaIndex in various use cases. This course is designed for developers, data scientists, and AI enthusiasts who wish to delve deeper into LlamaIndex for advanced application development. A basic understanding of Python programming and AI concepts is recommended for this intermediate-level course. By the end of the course, you’ll be able to design, build, and deploy powerful RAG-based applications tailored to complex, real-world data needs.
0 reviews
4 hours 48 minutes
View details

Updated in May 2025. This course now features Coursera Coach! A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course. This course offers an in-depth exploration of Retrieval-Augmented Generation (RAG) systems, focusing on their practical application in real-world scenarios. By the end of the course, you'll gain expertise in advanced techniques like query expansion, re-ranking, and dense passage retrieval. You'll also understand the core components of RAG systems and learn how to address common challenges in their implementation. The course begins with an introduction to the basic concepts of RAG, providing an essential foundation for understanding both naive and advanced RAG approaches. You'll dive into the RAG triad and learn about the pitfalls associated with early-stage implementations of RAG, followed by an exploration of more sophisticated techniques. The practical sections will guide you step-by-step through hands-on exercises that involve splitting text, embedding chunks, and performing similarity searches. Advanced topics such as query expansion with generated answers, re-ranking using cross-encoders, and the Dense Passage Retrieval (DPR) technique will be explored thoroughly. You’ll also learn to visualize your results through graph projections and plot embeddings for better interpretation of your data. Throughout the course, you’ll get plenty of chances to apply your learning in hands-on sessions and practical challenges. This course is designed for learners with a foundational understanding of machine learning and natural language processing. It's suitable for professionals and developers looking to master advanced RAG systems for more efficient document retrieval and answer generation. Prior knowledge of Python and machine learning frameworks is recommended.
0 reviews
4 hours 16 minutes
View details

Updated in May 2025. This course now features Coursera Coach! A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course. This course equips you with the skills to build smarter AI-driven systems using Retrieval Augmented Generation (RAG) and multimodal technology. You'll dive into the principles behind RAG and how it powers systems like advanced search engines, chatbots, and recommendation systems. The course will provide hands-on experience, enabling you to create multimodal systems that utilize images, text, and other forms of data to provide more intelligent and context-aware solutions. Starting with foundational knowledge, you will explore RAG systems, their components, and benefits. The course delves into how search capabilities can be integrated into multimodal systems and why this approach enhances both search and recommendation functionalities. You'll build multimodal search systems, creating embeddings and setting up a robust workflow to integrate different data types. You will also gain expertise in constructing a multimodal recommender system that combines RAG with GPT. As you progress, you will experiment with embedding images and using them in a vector database, setting up end-to-end systems, and refining them using hands-on lessons. Furthermore, you'll add a user interface to your multimodal recommender system, creating a polished, interactive tool that can be deployed for real-world use. By the end, you will have built a comprehensive multimodal RAG system with a recommender engine, capable of delivering highly relevant results. This course is ideal for AI enthusiasts, software developers, or data scientists looking to deepen their understanding of advanced search systems, recommendation algorithms, and the application of RAG in multimodal environments. A basic understanding of programming and machine learning concepts is recommended, and the course is suitable for intermediate learners.