Gen AI - RAG Application Development using LlamaIndex from Udemy

This course uses Open AI GPT and Google Gemini APIs, LlamaIndex LLM Framework and Vector Databases like ChromaDB and Pinecone, and is intended to help you learn how to build LLM RAG applications through solid conceptual and hands-on sessions. This course covers all the basic aspects to learn LLM RAG apps and Frameworks like Agents, Tools, QueryPipelines, Retrievers, Query Engines in a crisp and clear manner. It also takes a dive into concepts of Language Embeddings and Vector Databases to help you develop efficient semantic search and semantic similarity based RAG Applications. We will also cover multiple Prompt Engineering techniques that will help make your RAG Applications more efficient.

List of Projects/Hands-on included:

Basic RAG: Chat with multiple PDF documents using VectorStore, Retriever, Nodepostprocessor, ResponseSynthesizer and Query Engine.

ReAct Agent: Create a Calculator using a ReAct Agent and Tools.

Document Agent with Dynamic Tools : Create multiple QueryEngineTools dynamically and Orchestrate queries through Agent.

Semantic Similarity: Try Semantic Similarity operations and get Similarity Score.

Sequential Query Pipeline: Create Simple Sequential Query Pipeline.

DAG Pipeline: Develop complex DAG Pipelines.

Dataframe Pipeline: Develop complex Dataframe Analysis Pipelines with Pandas Output Parser and Response Synthesizer.

Working with SQL Databases: Develop SQL Database ingestion bots using multiple approaches.

For each project, you will learn:

- The Business Problem

- What LLM and LlamaIndex Components are used

- Analyze outcomes

- What are other similar use cases you can solve with a similar approach.

What's inside

Learning objectives

Fundamentals of llm rag application development
Using open ai gpt api to develop rag applications
Prompt engineering - write optimized prompts for your rag application
Using llamaindex query engines, retrievers and query pipelines
Building conversational memory
Using data connectors
Building smart agents and tools

Language embeddings and vector databases
Working with sql databases
Working with structured data and dataframes in rags
Convert your llamaindex rag as a fast api
Show more
Show less

Fundamentals of llm rag application development
Using open ai gpt api to develop rag applications
Prompt engineering - write optimized prompts for your rag application
Using llamaindex query engines, retrievers and query pipelines
Building conversational memory
Using data connectors
Building smart agents and tools
Language embeddings and vector databases
Working with sql databases
Working with structured data and dataframes in rags
Convert your llamaindex rag as a fast api
Show more
Show less

Syllabus

Introduction

Course Introduction

Introduction to LLMs

Introduction to LlamaIndex

Traffic lights

Read about what's good

what should give you pause

and possible dealbreakers

Provides a detailed overview of the core concepts and components of LLM RAG application development

Covers essential aspects such as agents, tools, query pipelines, retrievers, and query engines for building LLM RAG applications

Focuses on practical implementation with multiple hands-on projects, allowing learners to apply the concepts immediately

Emphasizes the importance of prompt engineering for optimizing LLM RAG applications

Demonstrates the integration of various data sources, including SQL databases and dataframes

Covers advanced concepts like language embeddings and vector databases for efficient semantic search

Reviews summary

Gen ai rag development with llamaindex

According to students, this course offers a highly practical and hands-on approach to Gen AI RAG application development using LlamaIndex. Learners consistently praise its comprehensive coverage of essential LlamaIndex components, including agents, tools, and various pipelines, along with vector databases and prompt engineering techniques. The clear explanations and digestible modules make complex topics accessible for those with some prior LLM knowledge. However, some find the pace challenging for absolute beginners, suggesting a need for foundational understanding. While the course provides a strong base for building real-world applications, a few wish for deeper dives into advanced scenarios or deployment strategies.

Complex topics explained clearly and concisely.

"The course explains concepts clearly, especially the parts on vector databases and embeddings."

"Excellent course... The instructor breaks down complex topics into digestible modules."

"The examples were clear, and I especially liked the sections on building various pipelines."

Covers a wide range of relevant topics.

"It's truly comprehensive for building real-world Gen AI apps."

"A very solid introduction to RAG with LlamaIndex. The course explains concepts clearly, especially the parts on vector databases and embeddings."

"The content is up-to-date and directly applicable. ...This course provided exactly what I needed to enhance my professional skills."

Focuses on hands-on application development.

"This course is a game-changer! The projects are incredibly practical and cover essential LlamaIndex components..."

"The hands-on projects, especially the document agent and DAG pipelines, were super helpful in understanding practical implementation."

"Great practical course! It delivered on its promise to teach RAG app development. The examples were clear..."

"Finally, a course that dives deep into LlamaIndex for RAG! ...The projects are well-structured, and I learned a lot about integrating different data sources."

Could benefit from more advanced details or troubleshooting.

"My only minor feedback is that some sections could have more advanced examples or troubleshooting for common issues."

"The course has good information, but I wish there was more depth on error handling and deployment strategies for these RAG applications."

"I think it would benefit from more explanation on the 'why' behind some design choices in a few places."

Requires prior LLM knowledge, challenging for beginners.

"The course covers a good range of topics but sometimes feels a bit rushed. I found myself needing to consult external documentation..."

"While the topics are relevant, I found the course prerequisites weren't clear enough. As someone new to LLMs, I struggled with the rapid introduction to advanced concepts."

"Not suitable for absolute beginners. The hands-on parts assumed more prior knowledge than I had."

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Gen AI - RAG Application Development using LlamaIndex with these activities:

Review basic Python syntax

Show steps

Recall the syntax for working with lists, strings, and dictionaries as these will be fundamental data structures used throughout the course.

Show steps

Review lecture notes from a previous Python course or workshop
Review Python documentation

Read "Natural Language Processing with Python" by Steven Bird, Ewan Klein, and Edward Loper

Show steps

Gain a theoretical understanding of natural language processing concepts, which will provide a foundation for understanding LLM RAG.

View Natural Language Processing with Python:... on Amazon

Show steps

Read through the chapters on text processing, machine learning, and natural language understanding
Work through the practice exercises to apply your knowledge

Complete the Hugging Face tutorial on Transformers and RAG

Show steps

Build a foundation for understanding how Transformers and RAG are applied with the support of Hugging Face libraries.

Browse courses on Hugging Face

Show steps

Set up your Python environment
Follow the Hugging Face tutorial
Experiment with different prompts and parameters

Three other activities

Expand to see all activities and additional details

Show all six activities

Solve coding challenges on LeetCode or HackerRank

Show steps

Strengthen your problem-solving skills and coding proficiency, which will be essential for building robust LLM RAG applications.

Show steps

Identify coding challenges that focus on data structures, algorithms, and problem-solving
Attempt to solve the challenges independently
Review solutions and discuss approaches with peers or mentors

Join a study group

Show steps

Connect with peers, discuss LLM applications, and share project ideas to enhance your understanding through collaboration.

Show steps

Reach out to classmates through online forums or social media
Identify students with shared interests and goals
Set up regular meetings to discuss course material, explore concepts, and collaborate on projects

Attend a workshop on LLM RAG applications

Show steps

Gain hands-on experience, learn from experts, and stay updated on industry trends by attending specialized workshops.

Browse courses on RAG

Show steps

Research and identify relevant workshops
Register for and attend the workshop
Engage with the instructors and participants
Apply the knowledge and skills gained to your own projects

Career center

Learners who complete Gen AI - RAG Application Development using LlamaIndex will develop knowledge and skills that may be useful to these careers:

Reading list

We haven't picked any books for this reading list yet.

Gen AI - RAG Application Development using LlamaIndex

What's inside

Learning objectives

Syllabus

Traffic lights

Save this course

Reviews summary

Gen ai rag development with llamaindex

Activities

Career center

Reading list

Share

Similar courses