/RAG_Workshop_DHS2024

A beginner to advanced journey in building GenAI applications using RAG

Primary LanguageJupyter Notebook

RAG

Collection of notebooks to understand world of Retrieval Augmented Generation (RAG), one of the most popular applications of LLMs

00_Quick_Start_Guide.ipynb: Warm up notebook to help you set up your env file and to test LLM calls

01_Tokenization.ipynb: let's understand the world of tokens in LLMs

02_Let's_talk_Embeddings.ipynb: Full fledged notebook to appreciate the power of embeddings from scratch

03_Basic_RAG.ipynb: Build a RAG pipeline using LangChain, Key steps in building a RAG application, Document loaders, Strategies for Data Chunking, Building Vector Stores, Retrieval Techniques and their Importance

04_Advanced_RAG_Retriever.ipynb: Advanced Retrival Strategies for better retrieval

05_Advanced_RAG_MVR.ipynb: Parent Document Retriver or Multi Vector Retriver

06_Advanced_RAG_Cross_encoder.ipynb: Cross encoder based reranking of retieved documents

07_Advanced_RAG_Query_Expansion.ipynb: Query expansion technique to increase the chance of getting user question answered

08_RAG_using_OpenSource_LLMs.ipynb: Building RAG pipelines using open source LLMs [WIP]

09_RAG_Evaluation.ipynb: Let's understand how to evaluate the RAG pipeline using various cool metrics

10_Agentic_RAG.ipynb : Empowering your your RAG pipeline using Autonomous AI Agents [WIP]