Do I need to know how to code to use Langflow?

Not to build and test flows. Python knowledge helps when you write custom components or call flows from an application, which later modules cover.

Why is the Docker command setting a password?

Official images ship with auto-login turned off, so you must set a superuser password, or explicitly enable auto-login for local-only experiments.

Langflow Module 1: Introduction and Installation

Introduction

Langflow is a visual builder for AI agents and workflows. You drag components onto a canvas, connect them, test the result in a built-in chat, and then serve the flow as an API. This first module of the ten-module Langflow course explains what it is, how to install it, and what you see when it starts.

Prerequisites

A computer with at least 2 GB of RAM (4 GB or more recommended)
An API key from an LLM provider, needed from Module 2 onward

Step-by-Step Guide

Step 1: Understand what Langflow does

A Langflow flow is a graph of components: inputs, prompts, language models, tools, vector stores, and outputs. Instead of writing the glue code, you connect components visually and configure their fields. You test in the Playground, and when it works you call it from your own application through a REST API or expose it as a tool through MCP.

Step 2: Choose how to run it

There are three common options. Langflow Desktop is the easiest and is the one the documentation recommends for getting started. The open-source Python package gives you the most control. Docker suits servers and teams. Note that Desktop does not include the Shareable Playground and Voice Mode features.

Step 3: Install the Python package with uv

Langflow needs Python 3.10 to 3.14 and the uv package manager. Create a virtual environment, install Langflow into it, and start the server. The first start can take a few minutes.

uv venv langflow-env

# macOS / Linux
source langflow-env/bin/activate
# Windows
# langflow-env\Scripts\activate

uv pip install langflow
uv run langflow run

Step 4: Open the interface

When the server is ready, open http://127.0.0.1:7860 in your browser. The host and port come from the LANGFLOW_HOST and LANGFLOW_PORT settings, which default to localhost and 7860. To use Docker instead, run the official image and open http://localhost:7860.

docker run -p 7860:7860 \
  -e LANGFLOW_AUTO_LOGIN=false \
  -e LANGFLOW_SUPERUSER_PASSWORD=choose-a-strong-password \
  langflowai/langflow:latest

Step 5: Take a tour

You land on the Projects page, which has a default Starter Project. Create flows inside a project with New Flow. Inside a flow, the workspace is the canvas where you place components, the Playground button opens the test chat, and the Share menu offers API access, Export, and MCP Server. Settings, under your profile icon, holds Model Providers, Global Variables, and Langflow API Keys.

FAQs

Do I need to know how to code to use Langflow?: Not to build and test flows. Python knowledge helps when you write custom components or call flows from an application, which later modules cover.
Why is the Docker command setting a password?: Official images ship with auto-login turned off, so you must set a superuser password, or explicitly enable auto-login for local-only experiments.

Summary

Langflow lets you build AI workflows visually. Install it with Desktop, uv, or Docker, open it on port 7860, and learn the layout: Projects, the canvas, the Playground, Share, and Settings. Next you will build your first flow.