#2 of 3 Masterclasses: RAG Pipeline Engineering with LlamaIndex & Pinecone

This is the second masterclass in our 3-part AI Accelerator Bootcamp series, focused on helping participants move from AI concepts to practical AI application building.

In this session, we will go deeper into RAG Pipeline Engineering and understand how modern AI applications retrieve, process, and generate responses using company or domain-specific data.

You will learn how to structure a practical RAG workflow using LlamaIndex for orchestration and Pinecone as a vector database for storing and retrieving embeddings.

Session Details

Topic: RAG Pipeline Engineering with LlamaIndex & Pinecone
Part: Masterclass 2 of 3
Date: Saturday, 25th July
Time: 11:00 AM. GST
Program: AI Accelerator Bootcamp
Certification: CPD UK Certified Bootcamp
CPD Hours: Part of the 10 CPD hours bootcamp certification

What we will cover

• How a RAG pipeline works from documents to final LLM response
• How to prepare and structure data sources
• Chunking and indexing strategies for real-world applications
• Using LlamaIndex to orchestrate retrieval logic
• Using Pinecone as a vector database for semantic search
• How retrieval connects with LLM responses
• Practical design principles for building scalable RAG applications

This masterclass is ideal for learners, developers, data professionals, and AI enthusiasts who want to understand how to build AI applications that can work with real documents, business knowledge, and private datasets.

By the end of the session, participants will have a clearer understanding of how RAG systems are engineered and how tools like LlamaIndex and Pinecone fit into the AI application development workflow.