Langflow Embedded Chat ⛓️

Welcome to the Langflow Embedded Chat repository! 🎉

The Langflow Embedded Chat is a powerful web component that enables seamless communication with the Langflow ⛓️. This widget provides a chat interface, allowing you to integrate Langflow ⛓️ into your web applications effortlessly.

What is Langflow?

Langflow is a no-code open-source project that empowers developers to build cutting-edge applications using Language Model technologies. With Langflow, you can leverage the power of LLMs (Large Language Models) to enhance user interactions, generate human-like text, and gain valuable insights from natural language data.

Features

🌟 Seamless Integration: Easily integrate the Langflow Widget into your website or web application with just a few lines of JavaScript.

🚀 Interactive Chat Interface: Engage your users with a user-friendly chat interface, powered by Langflow's advanced language understanding capabilities.

🎛️ Customizable Styling: Customize the appearance of the chat widget to match your application's design and branding.

🌐 Multilingual Support: Communicate with users in multiple languages, opening up your application to a global audience.

Installation

Option 1: CDN Link

Use the Langflow Widget directly from the CDN by including the following script tag in your HTML:

<script src="https://cdn.jsdelivr.net/gh/logspace-ai/langflow-embedded-chat@v1.0.6/dist/build/static/js/bundle.min.js"></script>

Option 2: Local Build

Clone this repository to your local machine:

git clone https://github.com/logspace-ai/langflow-embedded-chat.git

Navigate to the project directory:

cd langflow-embedded-chat

Build the project to generate the bundle:

npm run build

After the build process completes, you'll find the bundle in the dist/build/static/js folder. You can include this JavaScript file in your HTML:

<script src="https://github.com/langflow-ai/langflow-embedded-chat/raw/main/path/to/your/langflow-widget.js"></script>

Usage

on simple HTML

<html lang="en">
<head>
<script src="https://cdn.jsdelivr.net/gh/logspace-ai/langflow-embedded-chat@v1.0.6/dist/build/static/js/bundle.min.js"></script>
</head>
<body>
<langflow-chat
    host_url="langflow url"
    flow_id="your_flow_id"
  ></langflow-chat>
</body>
</html>

on React

Import the js bundle in the index.html of your react project

<script src="https://cdn.jsdelivr.net/gh/logspace-ai/langflow-embedded-chat@v1.0.6/dist/build/static/js/bundle.min.js"></script>

Encapsulate your custom element in a react component

export default function ChatWidget() {
  return (
    <div>
<langflow-chat
    host_url="langflow url"
    flow_id="your_flow_id"></langflow-chat>
    </div>
  );
}

Configuration

Use the widget API to customize your widget:

Prop	Type	Required
bot_message_style	json	No
chat_position	string	No
chat_trigger_style	json	No
chat_window_style	json	No
output_type	string	No
input_type	string	No
output_component	string	No
error_message_style	json	No
flow_id	string	Yes
height	number	No
host_url	string	Yes
input_container_style	json	No
input_style	json	No
online	boolean	No
start_open	boolean	No
online_message	string	No
placeholder	string	No
placeholder_sending	string	No
send_button_style	json	No
send_icon_style	json	No
tweaks	json	No
user_message_style	json	No
width	number	No
window_title	string	No
session_id	string	No
additional_headers	json	No

bot_message_style:
- Type: JSON
- Required: No
- Description: Styling options for formatting bot messages in the chat window.
input_type:
- Type: String
- Required: No
- Description: Specifies the input type for chat messages.
output_type:
- Type: String
- Required: No
- Description: Specifies the output type for chat messages.
output_component:
- Type: String
- Required: No
- Description: Specify the output ID for chat messages; this is necessary when multiple outputs are present.
chat_position:
- Type: String
- Required: No
- Description: Determines the position of the chat window (top-left, top-center, top-right, center-left, center-right, bottom-right, bottom-center, bottom-left).
chat_trigger_style:
- Type: JSON
- Required: No
- Description: Styling options for the chat trigger.
chat_window_style:
- Type: JSON
- Required: No
- Description: Styling options for the overall chat window.
error_message_style:
- Type: JSON
- Required: No
- Description: Styling options for error messages in the chat window.
flow_id:
- Type: String
- Required: Yes
- Description: Identifier for the flow associated with the component.
height:
- Type: Number
- Required: No
- Description: Specifies the height of the chat window in pixels.
host_url:
- Type: String
- Required: Yes
- Description: The URL of the host for communication with the chat component.
input_container_style:
- Type: JSON
- Required: No
- Description: Styling options for the input container where chat messages are typed.
input_style:
- Type: JSON
- Required: No
- Description: Styling options for the chat input field.
Online:
- Type: Boolean
- Required: No
- Description: Indicates if the chat component is online or offline.
start_open:
- Type: Boolean
- Required: No
- Description: Indicates if the chat window should be open by default.
online_message:
- Type: String
- Required: No
- Description: Custom message to display when the chat component is online.
placeholder:
- Type: String
- Required: No
- Description: Placeholder text for the chat input field.
placeholder_sending:
- Type: String
- Required: No
- Description: Placeholder text to display while a message is being sent.
send_button_style:
- Type: JSON
- Required: No
- Description: Styling options for the send button in the chat window.
send_icon_style:
- Type: JSON
- Required: No
- Description: Styling options for the send icon in the chat window.
tweaks:
- Type: JSON
- Required: No
- Description: Additional custom tweaks for the associated flow.
user_message_style:
- Type: JSON
- Required: No
- Description: Styling options for formatting user messages in the chat window.
width:
- Type: Number
- Required: No
- Description: Specifies the width of the chat window in pixels.
window_title:
- Type: String
- Required: No
- Description: Title for the chat window, displayed in the header or title bar.
session_id:
- Type: String
- Required: No
- Description: Custom session id to override the random session id used as default.
additional_headers:
- Type: JSON
- Required: No
- Description: Additional headers to be sent to Langflow server

Live example:

Try out or live example to see how the Langflow Embedded Chat ⛓️ works.

first create a Flow and save it using Langflow ⛓️.
Get the hosted URL to use in the live example.
If you are using a public host (like Hugging Face Spaces) use tweaks to keep your API keys safe.

License

This project is licensed under the MIT License - see the LICENSE file for details.

langflow-ai / langflow-embedded-chat

readme