Sitemap
Data Science Collective

Advice, insights, and ideas from the Medium data science community

Member-only story

LangChain vs Langflow: Build a Simple LLM-App with Code or Drag & Drop

A hands-on guide of the popular framework LangChain and the visual Drag-&Drop-Builder Langflow with Ollama & FAISS

11 min readJun 12, 2025

--

Over the past 5 years as a Salesforce consultant, I’ve collected hundreds of notes from client projects.

Now that I’m about to start a Master’s in Data Science, I wanted to see if I could build a simple LLM chatbot that answers questions based on my own notes.

I’ve worked with LangChain before — but lately, I kept hearing about Langflow.

Thats why I wanted to built the same use case twice: Once with code (LangChain) and once with the visual drag-and-drop builder (Langflow).

Let’s dive in!

Press enter or click to view image in full size
With Langflow we have the possibility to build AI Agents in a visual Drag- & Drop-Builder.
Screenshot taken by the author

LangWHAT?

Terms like LangChain, LangGraph, Langflow or LangSmith are popping up everywhere — but what’s really behind them?

In this article, I’ll show you the differences between the four tools and how you can build a simple chatbot with LangChain and Langflow.

The theory follows along the way.

Table of Content
Simple AI chatbot with LangChain vs. Langflow
So, what is LangChain?
And if we don’t want to write any code —

--

--

Data Science Collective
Data Science Collective

Published in Data Science Collective

Advice, insights, and ideas from the Medium data science community

Sarah Lea
Sarah Lea

Written by Sarah Lea

Simplifying tech for curious minds - Follow for insights 🚀 | Writing on Data, AI, ML & Python | MSc Data Science | Ex-Salesforce-Consultant, now at Big Tech