RAG Explained: Giving a Model Access to Documents It Has Never Seen
A model cannot answer from documents it was never trained on. This post explains what RAG is, how its two paths work, and when fine-tuning is the wrong answer to it.
Tech Blog · Insights & Experiments
Exploring modern web & software engineering
Deep dives into code, design, and system architecture. From frontend to backend, from performance tricks to developer experience — practical notes for building better technology.
120+ articles
20+ technologies
weekly updates
Featured
View allLCEL Part 2: Chaining Chains, RunnableParallel, RunnableLambda and @chain
A straight line is the easy case. This post covers piping chains together, fanning out with RunnableParallel, wrapping your own functions, and drawing what you built.
LCEL Part 1: The Pipe Operator, Batching, Streaming and the Runnable Protocol
A single pipe operator turns three objects into a pipeline that batches, streams and runs async for free. Here is how, plus the step that silently breaks streaming.
Structured Output: with_structured_output and When You Still Need a Parser
Free text is unusable in a pipeline. This post covers getting validated objects back with Pydantic, and the narrower cases where an output parser is still the right tool.
Model Inputs in LangChain: Messages, Prompt Templates and Few-Shot Examples
LangChain's first real abstraction is the input side: typed messages, reusable prompt templates, and few-shot examples that teach a model by showing instead of telling.
The OpenAI API Before LangChain: Roles, Temperature, Max Tokens and Streaming
Before reaching for a framework, call the API directly. System, user and assistant roles, a sarcastic chatbot, and what temperature and streaming actually control.
Latest
View all
AI & Tools
9 min read
RAG Explained: Giving a Model Access to Documents It Has Never Seen
A model cannot answer from documents it was never trained on. This post explains what RAG is, how its two paths work, and when fine-tuning is the wrong answer to it.
AI & Tools
9 min read
LCEL Part 2: Chaining Chains, RunnableParallel, RunnableLambda and @chain
A straight line is the easy case. This post covers piping chains together, fanning out with RunnableParallel, wrapping your own functions, and drawing what you built.
AI & Tools
8 min read
LCEL Part 1: The Pipe Operator, Batching, Streaming and the Runnable Protocol
A single pipe operator turns three objects into a pipeline that batches, streams and runs async for free. Here is how, plus the step that silently breaks streaming.
AI & Tools
16 min read
Structured Output: with_structured_output and When You Still Need a Parser
Free text is unusable in a pipeline. This post covers getting validated objects back with Pydantic, and the narrower cases where an output parser is still the right tool.
AI & Tools
27 min read
Model Inputs in LangChain: Messages, Prompt Templates and Few-Shot Examples
LangChain's first real abstraction is the input side: typed messages, reusable prompt templates, and few-shot examples that teach a model by showing instead of telling.
AI & Tools
18 min read
The OpenAI API Before LangChain: Roles, Temperature, Max Tokens and Streaming
Before reaching for a framework, call the API directly. System, user and assistant roles, a sarcastic chatbot, and what temperature and streaming actually control.
Explore by topic
View allLearn by series
View all
Completed
9 posts
LangChain Fundamentals: From the OpenAI API to Your First RAG App
Eight posts taking LangChain from first principles to a working RAG pipeline — token costs, the raw OpenAI API, messages, prompt templates, structured output and LCEL.
Oct 2026 – Oct 2026
View series
Completed
6 posts
Algorithm Interview 2026: Data Structures — Know Your Tools
Master the 6 data structures that appear in 80% of technical interviews. Each post goes deep on one structure — how it works under the hood, every interview pattern it unlocks, and the exact templates that win offers.
Mar 2026 – Mar 2026
View series
Completed
6 posts
Part 7 — Routing, Hooks, and Build Optimizations (Vite/Webpack)
Learn how to structure routing, master custom hooks, and optimize React builds using Vite and Webpack for production-grade apps.
Jan 2026 – Feb 2026
View series
Completed
6 posts
Part 0 — Web Fundamentals for Modern Full-Stack
Build a rock-solid foundation in HTML, CSS, JavaScript, and modern tooling to prepare for a professional full-stack journey using React, NestJS, and PostgreSQL.
Nov 2025 – Nov 2025
View series