Building RAG Pipelines with LLMs

Bridge Knowledge and Language—Build Smarter AI with Retrieval-Augmented Generation

MODE
Mode(Online) TYPE
Mentor Based LEVEL
Moderate

Skills you will gain:

Building RAG Pipelines with LLMs is a specialized, project-based course that teaches how to combine the power of Large Language Models (like OpenAI GPT, Cohere, Claude, and Llama) with custom knowledge sources through Retrieval-Augmented Generation. RAG enhances AI responses by grounding them in factual, external data—making this a must-learn skill for developers, researchers, and innovators working in knowledge-intensive domains like legal tech, finance, healthcare, and education.

Aim:

To provide participants with practical skills and technical knowledge to design, build, and deploy Retrieval-Augmented Generation (RAG) pipelines using Large Language Models (LLMs) for accurate, context-aware AI applications.

Program Objectives:

To train participants in the practical construction of RAG architectures
To deepen understanding of how LLMs interact with external data
To empower learners to build scalable, accurate, and context-aware AI systems
To prepare professionals for high-demand GenAI engineering roles

What you will learn?

Week 1: Foundations of Retrieval-Augmented Generation

Module 1: Introduction to RAG Systems

Chapter 1.1: What is Retrieval-Augmented Generation?
Chapter 1.2: Components of a RAG Pipeline
Chapter 1.3: Benefits and Limitations of RAG

Module 2: Understanding Retrieval and Vector Databases

Chapter 2.1: Dense vs. Sparse Retrieval
Chapter 2.2: Vector Embeddings and Semantic Search
Chapter 2.3: Overview of Tools (FAISS, Weaviate, Pinecone, Qdrant)

Week 2: Building the Core RAG Stack

Module 3: Integrating LLMs with Search

Chapter 3.1: Embedding Generation (OpenAI, Hugging Face)
Chapter 3.2: Chunking and Preprocessing Strategies
Chapter 3.3: Prompt Templates for RAG
Chapter 3.4: Connecting LLMs to Vector DBs

Module 4: RAG System Implementation

Chapter 4.1: Document Ingestion and Indexing
Chapter 4.2: Query Handling and Retrieval Flow
Chapter 4.3: Response Synthesis using LLMs
Chapter 4.4: Evaluation Metrics for RAG Responses

Week 3: Optimization, Deployment, and Projects

Module 5: Advanced RAG Techniques

Chapter 5.1: Hybrid Search (BM25 + Embeddings)
Chapter 5.2: RAG with Structured and Unstructured Data
Chapter 5.3: Multi-turn and Conversational RAG

Module 6: Deployment and Capstone

Chapter 6.1: Deploying RAG Systems with LangChain or LlamaIndex
Chapter 6.2: Monitoring, Caching, and API Design
Chapter 6.3: Capstone Project – Build Your Own RAG Pipeline
Chapter 6.4: Industry Use Cases and Future Trends

Intended For :

Developers, data scientists, researchers, and AI engineers
Graduate students and working professionals in AI/ML or NLP
Prior experience with Python and APIs is recommended