Advanced RAG : Vector to Graph RAG LangChain Neo4j AutoGen
- Description
- Curriculum
- FAQ
- Reviews
In this course, you will learn how to master Retrieval-Augmented Generation (RAG), a cutting-edge AI technique that combines retrieval-based methods with generative models. This course is designed for developers, data scientists, and AI enthusiasts, quality engineers, Students who want to build practical applications using RAG, ranging from simple vector RAG chatbot to advanced chatbot with Graph RAG and Self Reflective RAG. You’ll explore the theoretical foundations, practical implementations, and real-world use cases of RAG. By the end of this course, you will have the skills to create RAG-based AI applications.
After completing the course, you will be able to create chatbot with multiple RAG techniques using Streamlit, LangChain, LangGraph, Groq API and many more. Along with that you will also learn fundamentals and concepts.
Course Objectives
-
Understand the fundamental concepts of RAG and NLP.
-
Understand concepts of NLP with examples like tokenization, chunking, TF-IDF, embedding.
-
Understand evaluation of NLP models from rule based to transformer model.
-
Understand transformer model and components with examples.
-
Environment setup for hands on implementation.
-
Build first chatbot with Streamlit and Langchain.
-
Build a vector RAG with Streamlit chatbot with Groq API.
-
Understand Graph RAG and implement Graph RAG with Neo4j.
-
Understand Self Reflective or Adaptive RAG and implement with LangGraph.
-
Real world use cases of RAG.
-
Re-ranking RAG technique
-
Agentic RAG or Agent based RAG. AutoGen RAG.
-
Check your understanding with Quizzes.
Lets deep dive into world of RAG to understand it.
-
2
Generative AI without RAG. Why RAG?Lets build our foundation with fundamentals of RAG. Through Generative AI LLMs, we can get answers of all queries then why RAG is so important in AI field? We will look into the without RAG world and challenges and what is RAG.
-
3
What is RAG? RAG Process
Lets understand RAG process. The process will be converted into python code in hands on section.
-
4
What is NLP?
This is a short lecture on definition and applications of NLP.
-
5
POS , NER , Chunking, BoW, TF-IDF and Embedding
Lets deep dive into NLP processes like POS (Parts of Speech), NER, Chunking, BoW, TF-IDF and Embedding with examples.
-
6
Tokenization, Stemming and Lemmatization
Tokenization is important process to understand for RAG. In this lecture, we will understand tokenization with example.
-
7
Evaluation of NLP
Natural Language Processing, or NLP, has come a long way in helping machines understand and generate human language. But how do we evaluate the effectiveness of different NLP approaches? Let’s take a journey through the evolution of NLP models, from simple rule-based systems to advanced Transformer models
-
8
Transformer Model
We have seen Rule based and RNN model. In this module we will cover Transformer model.
-
9
Setup VS code , Python, Neo4j, Streamlit, PIP packages
This slide will guide you through the essential steps to set up your development environment. We'll cover everything from installing VS Code and Python to setting up necessary tools and API keys.
-
10
Create simple streamlit chatbot
Hands on coding to create a simple chatbot. Slowly in subsequent modules we will add RAG.
-
11
What is vector RAG ?
Let's dive into how Vector RAG works. We'll break down each step in the process, starting from the ingestion of knowledge data, all the way to how the system provides a response to a user query using similarity search
-
12
Develop vector RAG with Groq API and Langchain
Hands-on python coding to build a chatbot with Vector RAG.
-
13
What is Graph RAG
Now that we’ve explored the basics of Vector RAG, let’s take it a step further by diving into Graph RAG, an advanced approach that leverages the power of graph databases and graph-based data structures to enhance the retrieval-augmented generation process.
-
14
Implement Graph RAG chatbot to build and show graph with Neo4j
Hands-on implementation of RAG chatbot with Neo4j. Create graph and display graph in chatbot.
-
15
Implement hybrid search with Graph RAG and Neo4j
Lets implement hybrid search technique of Graph RAG.
-
16
Understand adaptive or self-reflective flow
Self-reflective RAG or Adaptive RAG is advance RAG technique to improve response of user query. With multiple level of checking into every layer will improve RAG response. Lets understand the flow of Adaptive RAG.
-
17
Implement Self-reflective RAG chatbot with Langgraph
Hands on of self reflective RAG. Will build a chatbot with the flow of adaptive RAG.
