Latest articles, tutorials, and deep dives from ndlab tech blog.
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.
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.
Before reaching for a framework, call the API directly. System, user and assistant roles, a sarcastic chatbot, and what temperature and streaming actually control.
Tokens are the unit you are billed in, and they are not words. This post covers tokenization, counting before you send, model tiers, and how the costs really add up.
Most LangChain tutorials online were written before v1 and no longer run. Here is what moved, what landed in langchain-classic, and how to read old code safely.
LangChain is widely used and widely misunderstood. This post explains the problems it actually solves, where it earns its complexity, and what this series will build.
Results