Guidelines

Features

Features

When you click for New Project, you will see on the top left corner of the screen, some options such as Import, Export, Code and Save, as displayed in the image below:

Further down, we will explain each of these options.

Import and Export

Flows can be exported and imported as JSON files.

CAUTION

Watch out for API keys being stored in local files.

Code

The Code button shows snippets to use your flow as a Python object or an API.

Python Code

Through the Langflow package, you can load a flow from a JSON file and use it as a LangChain object.

from langflow import load_flow_from_json

flow = load_flow_from_json("path/to/flow.json")
# Now you can use it like any chain
flow("Hey, have you heard of Langflow?")

API

Once you save a flow, the API endpoint is created with your latest changes. Click the "code" button to use that flow as an API. You can post-adjust component parameters using the global variable TWEAKS.

The example below shows a Python script making a POST request to a local API endpoint, which gets a prediction based on the message input.

Getting Started

👋 Welcome to Langflow
📦 How to install?
🤗 HuggingFace Spaces
🎨 Creating Flows

Guidelines

Sign up and Sign in
API Keys
Assynchronous Processing
Component
Features
Collection
Prompt Customization
Chat Interface
Chat Widget
Custom Components

Step-by-Step Guides

Async API
Integrating documents with prompt variables
Building chatbots with System Message
Integrating Langfuse with Langflow

Examples

FlowRunner Component
Conversation Chain
Buffer Memory
MidJourney Prompt Chain
CSV Loader
Serp API Tool
Multiple Vector Stores
Python Function
📚 How to Upload Examples?

Deployment

Deploy on Google Cloud Platform

Contributing

How to contribute?
GitHub Issues
Community

Search Docs…

Search Docs…