Advance RAG : Vector to Graph RAG Neo4j Adaptive AutoGen AWS

Concept and Hands-on Vector RAG, Graph RAG, Self-Reflective RAG. RAG with Streamlit LangChain, Neo4J, Agent RAG, Bedrock

Created by: Soumen Kumar Mondal
Passionate about learning new open-source technologies.

What Will I Learn?

• Fundamentals of RAG (Retrieval-Augmented Generation) and NLP: Understand core concepts to build strong foundation of NLP and RAG.
• Understand process of NLP like tokenization, embedding, POS, TF-IDF, chunking etc.
• Understand evaluation of NLP models from Rule based to Transformer model.
• Understand transformer model with simple RAG example.
• Environment setup for hands on implementation of RAG application using Python and VS Code
• Learn to build vector based RAG application with Streamlit chatbot, langchain and vectordb.
• Learn advance RAG technique with Graph RAG , LLM and Streamlit chatbot. Learn how to setup Neo4j, create Graph RAG , show graph in your chatbot.
• Learn advance RAG with hybrid search technique using Graph RAG. Learn self reflective RAG with Langgraph. Practical use cases with python code of RAG.
• Re ranking RAG with cohere API to improve retrieval process of RAG.
• Practical use cases on RAG.
• Quizzes to check learning.
• Build Agent based RAG application with Autogen. Agentic RAG.

Requirements

• No prior RAG experience required.
• Very basic python knowledge will help.
• Don't worry without python knowledge also you will learn how to implement RAG chatbot.

Target audience

• Data Scientists
• Machine Learning Engineers
• AI and NLP Enthusiasts
• Developers and Software Engineers
• Researchers and Academics
• Product Managers and Technical Leads
• Students and Learners
• AI Practitioners and Consultants
• Quality Engineers