AKApurva kanthinapurvak3.hashnode.dev·Apr 16 · 4 min read Agentic AI: A Complete End-to-End Guide (Agents, Tools, LangChain & Real-World Flow)Artificial Intelligence is no longer just about generating text or images. We are now entering the era of Agentic AI — systems that can think, decide, and act. If you're preparing for top tech roles (10
AKApurva kanthinapurvak3.hashnode.dev·Apr 7 · 5 min read Understanding Pretraining, Fine-Tuning & PEFT (LoRA, QLoRA Explained) Training large AI models from scratch is extremely expensive and resource-intensive. That’s why modern AI development relies heavily on pretrained models and efficient ways to adapt them to specific t10
AKApurva kanthinapurvak3.hashnode.dev·Apr 1 · 4 min read📊 How to Evaluate RAG (Retrieval-Augmented Generation) Systems — Complete GuideBuilding a RAG system is only half the job. The real challenge is evaluating whether your system is actually working correctly. Unlike traditional ML systems, RAG has two critical components: Retriev10
AKApurva kanthinapurvak3.hashnode.dev·Apr 1 · 4 min read🚀 How RAG (Retrieval-Augmented Generation) Works — Step-by-Step GuideRetrieval-Augmented Generation (RAG) is one of the most powerful techniques used in modern AI systems to make Large Language Models (LLMs) more accurate, up-to-date, and context-aware. Instead of rely10
AKApurva kanthinapurvak3.hashnode.dev·Dec 26, 2025 · 5 min readFlashAttention: Making Transformers Faster and More Memory-EfficientLarge Language Models (LLMs) like GPT, BERT, and modern Transformers rely heavily on the self-attention mechanism. While powerful, self-attention is also the biggest performance bottleneck when working with long sequences. In 2022, Tri Dao and collab...10