Sandeep Sharma·Aug 9Chunking and Metadata : Backbone of RAG — Part 2When we talk about RAG, most of the discussion usually goes towards the Large Language Models, embeddings, vector databases or retrieval.
Sandeep Sharma·Jul 10Everything About RAG — Part 1 - Basics of RAGSee how a RAG chatbot uses trusted knowledge to deliver more accurate, grounded and source-based answers.
Sandeep Sharma·Jun 26Fine Tuning LLMs for Domain Specific Gen-AI projectsGenerative AI has made it very easy to write emails, summarize documents, generate code, and explain complex topics.A response icon1A response icon1
Sandeep Sharma·Jun 14Context Window in LLMs: Working Memory Behind AIIn simple words, a context window is the amount of information an AI model can read and use at one time before giving an answer.A response icon1A response icon1
Sandeep Sharma·May 19Transformer Architecture: Starting of Modern AITransformer Architecture is one of the most important ideas behind modern AI. Today, many Large Language Models, chatbots, translation…
Sandeep Sharma·May 15Attention Mechanism II: Core Attention Types Behind LLMsIn my previous article, “Attention Mechanism: Idea Behind LLMs,” I explained the basic idea of attention and why it became so important in…
Sandeep Sharma·May 10Attention Mechanism : Idea Behind LLMsWhen we read a sentence, we do not give equal importance to every word.A response icon1A response icon1
Sandeep Sharma·May 3Large Language Models: The Brain Behind Modern Generative AILarge Language Models (LLMs) are a breakthrough in modern AI, enabling machines to write, code, summarize, and act as thinking assistants.A response icon1A response icon1
Sandeep Sharma·Apr 27Foundation Models: The Engine Behind Generative AI and LLMsFoundation Models Explained: The Engine Behind Generative AI and LLMs