The AI Concepts Podcast
by Sheetal ’Shay’ Dhar
Module 7: Building an LLM Application End to End
About this podcast
The AI Concepts Podcast is my attempt to turn the complex world of artificial intelligence into bite-sized, easy-to-digest episodes. Imagine a space where you can pick any AI topic and immediately grasp it, like flipping through an Audio Lexicon - but even better! Using vivid analogies and storytelling, I guide you through intricate ideas, helping you create mental images that stick. Whether you’re a tech enthusiast, business leader, technologist or just curious, my episodes bridge the gap between cutting-edge AI and everyday understanding. Dive in and let your imagination bring these concepts to life!
Episodes
The newest 20 of 81 episodes
- Module 7: Building an LLM Application End to End · 13 min · Episode 81In this episode, we bring everything together by following one LLM application from the user's first request to the final response. We see retrieval, context, tools, model calls…
- Module 7: Building LLM Applications | LangChain, LangGraph, LlamaIndex and the LLM Application Stack · 8 min · Episode 80In this episode, we map the modern LLM application stack and explore where frameworks, SDKs, runtimes and protocols actually fit. We look at how tools like LangChain, LangGraph…
- Module 7: Building LLM Applications | State and Memory: How Does an LLM Application Remember? · 13 min · Episode 79This episode separates two concepts that are often confused: state, which keeps track of what is happening now, and memory, which allows information from the past to become…
- Module 7: Building LLM Applications | What Does Orchestration Actually Mean? · 12 min · Episode 78This episode breaks down what orchestration actually means, from sequencing and routing to retries, parallel execution and human approvals, and explores the different ways those…
- Module 7: The LLM Application Loop · 10 min · Episode 77Who actually decides what happens next inside an LLM application? This episode explores the difference between decisions made by code and decisions made by the model, and why…
- Module 7: Why Do We Need LLM Frameworks? · 10 min · Episode 76If LLM applications can be built with regular code and APIs, why do frameworks exist at all? This episode explores what happens as a simple application grows and starts needing…
- Module 7: Building LLM Applications | What Is an LLM Application, Really? · 11 min · Episode 75What actually sits behind an LLM application? This episode takes one simple request and follows it beneath the surface, revealing how the model, application code, APIs, external…
- Module 6: RAG | Long Context vs RAG - Do You Still Need Retrieval at All · 9 min · Episode 74This episode closes out Module 6 by tackling the question that has been getting louder since large context windows arrived. If a model can hold hundreds of thousands or even…
- Module 6: RAG | GraphRAG - When Relationships Matter More Than Text · 8 min · Episode 73This episode addresses the category of questions that vector search fundamentally cannot answer, questions about relationships between things. We explore what a knowledge graph…
- Module 6: RAG | Query Transformation - When the Question Is the Bottleneck · 7 min · Episode 72This episode addresses a retrieval failure that has nothing to do with your index and everything to do with the query itself. We explore the vocabulary gap between how people ask…
- Module 6: RAG | Parent-Child Indexing - Search Small, Retrieve Big · 7 min · Episode 71This episode addresses the fundamental tension between retrieval precision and generation context. We explore why small chunks produce tight embeddings that retrieve well but…
- Module 6: RAG | Reranking - The Second Stage That Gets Retrieval Right · 10 min · Episode 70This episode addresses the gap between finding candidate chunks and finding the right ones. We explore the bi-encoder bottleneck, why compressing text into a single vector for…
- Module 6: RAG | Dense and Sparse Search - Why Vector Search Alone Is Not Enough · 11 min · Episode 69This episode addresses one of the most common gaps in RAG pipelines, relying solely on semantic search. We explore how dense retrieval works and where it excels, then introduce…
- Module 6: RAG | Chunking - Where You Cut Decides What Gets Found · 11 min · Episode 68This episode is about chunking, the quiet step in a RAG pipeline that decides whether your system retrieves the right answer or a confidently wrong one. It covers why the chunk…
- Module 6: RAG | Data Ingestion - Before Your Documents Can Be Found · 12 min · Episode 67This episode is about the step that every RAG system depends on. Before meaning can be stored or retrieved, your raw documents have to become clean text. What goes wrong here…
- Module 6: RAG | Vector Databases - Where That Meaning Gets Stored · 10 min · Episode 66This episode is about the infrastructure underneath every RAG system. It covers the purpose-built engine that stores all that meaning and searches millions of vectors in…
- Module 6: RAG | Embeddings - Teaching Machines to Understand Meaning · 8 min · Episode 65This episode is about the layer of RAG that makes semantic search possible. It covers how machines turn language into math that clusters similar ideas together, so a question and…
- Module 6: The RAG Pipeline - End to End · 13 min · Episode 64This episode maps out the full RAG pipeline end to end using one concrete scenario, a defense contractor building an AI assistant for fighter jet maintenance crews. It walks…
- Module 6: What is RAG and Why it Exists · 9 min · Episode 63This episode kicks off Module 6 with RAG (Retrieval Augmented Generation), the #1 architecture every serious enterprise actually uses. Discover why regular LLMs hallucinate on…
- Module 5: Reasoning Models · 8 min · Episode 62This episode covers reasoning models, the shift from manually guiding a model's thinking to letting the model reason through complex problems on its own before responding. It…







