Developing Gen AI – RAG Applications using LlamaIndex

Learn development of Large Language Model (LLM) Retrieval-Augmented Generation (RAG) applications, leveraging cutting-edge technologies like OpenAI GPT, Google Gemini APIs, LlamaIndex LLM Framework, and Vector Databases such as ChromaDB and Pinecone.

Designed to equip learners with the necessary skills to build powerful LLM RAG applications, this course combines conceptual foundations with hands-on sessions.

Covering the fundamental aspects of LLM RAG applications and frameworks, the course offers a crisp and clear exploration of Agents, Tools, QueryPipelines, Retrievers, and Query Engines. Participants will gain insights into language embeddings and vector databases, enabling them to develop efficient semantic search and semantic similarity-based RAG applications. Additionally, the course delves into multiple prompt engineering techniques, empowering learners to enhance the efficiency of their RAG applications.

The hands-on projects and exercises included in the course are:

Fundamental RAG: Engage in interactive conversations with multiple PDF documents using VectorStore, Retriever, Nodepostprocessor, ResponseSynthesizer, and Query Engine.

ReAct Agent: Construct a Calculator application utilizing a ReAct Agent and Tools.

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

Semantic Similarity: Explore semantic similarity operations and obtain similarity scores.

Sequential Query Pipeline: Develop a simple Sequential Query Pipeline.

DAG Pipeline: Build complex DAG Pipelines.

Dataframe Pipeline: Construct intricate 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, learners will gain insights into:

• The Business Problem
• The LLM and LlamaIndex Components utilized
• Outcome Analysis
• Potential similar use cases that can be solved using a similar approach.