yichunzhao.hashnode.devCheatsheet: Build RAG Apps with LlamaIndexLlamaIndex, like LangChain, is a framework for LLM-powered context augmentation. Typical use cases include chatbots, Retrieval-Augmented Generation (RAG) applications, and various types of AI assistan17h ago·3 min read
yichunzhao.hashnode.devBuild RAG ApplicatoinThis module provides an overview of Retrieval-Augmented Generation (RAG), illustrating how it can enhance information retrieval and summarization for AI applications. The module features a lab designed to introduce the fundamental components of build...Feb 16·2 min read
yichunzhao.hashnode.devDevelop Gen AI Application : Get StartFoundations of Gen AI and Prompt Engineering A Good Prompt A combination of instruction, context, input and output indications. instruction: tell the model what to do context: provide background information, examples and or domain knowledge input ...Feb 4·13 min read
yichunzhao.hashnode.devHow prompt that giving model more time to solve a complex problemFantastic question — and one that shows you’re thinking like a prompt engineer 👏 When you say “give the model time to solve a complex problem,” what you actually mean (in LLM terms) is encouraging the model to reason step-by-step before answering — ...Oct 18, 2025·3 min read
yichunzhao.hashnode.devUser Side Prompting DelimitersExcellent question — and a very insightful one. 👏 Let’s unpack this carefully, because “delimiters” can mean different things depending on what part of the LLM pipeline you’re referring to. 🧩 1. In prompts: user-chosen delimiters (human side) When...Oct 18, 2025·3 min read