← All Series
Ongoing
Generative AI using LangChain
Building real generative AI applications with LangChain, from models, prompts, and chains to RAG pipelines, tool calling, and AI agents.
LangChain Fundamentals
Post 1•Ch.1: Introduction to LangChain: What It Is and Why You Need It
Where LangChain sits in generative AI, and why it exists: building a chat-with-your-PDF app from scratch, how semantic search and embeddings find the right pages, the three hard problems in an LLM application, and how LangChain's chains, model-agnostic design, integrations, and memory solve the orchestration one.
- Post 2•
Ch.2: LangChain Components: The Six Building Blocks
A map of LangChain before writing real code: models, prompts, chains, indexes, memory, and agents. What problem each component solves, what breaks without it, and what each one looks like in current LangChain 1.x.