Skip to main content

API pane

The API pane presents code templates for integrating your flow into external applications.

cURL​

The cURL tab displays sample code for posting a query to your flow. Modify the input_value to change your input message. Copy the code and run it to post a query to your flow and get the result.

Python API​

The Python API tab displays code to interact with your flow using the Python HTTP requests library.

To use the requests library:

  1. Copy and paste the code into a Python script.
  2. Run the script and pass your message with it.

_10
python3 python-api-script.py --message="tell me about something interesting"

Python code​

The Python Code tab displays code to interact with your flow's .json file using the Langflow runtime.

To use your code in a Python application using the Langflow runtime, you have to first download your flow’s JSON file.

  1. In your Workspace, click Settings, and then select Export.

  2. Download the flow to your local machine. Make sure the flow path in the script matches the flow’s location on your machine.

  3. Copy and paste the code from the API tab into a Python script file. It will look like this:


_14
from langflow.load import run_flow_from_json
_14
TWEAKS = {
_14
"ChatInput-kKhri": {},
_14
"Prompt-KDSi5": {},
_14
"ChatOutput-Vr3Q7": {},
_14
"OpenAIModel-4xYtx": {}
_14
}
_14
_14
result = run_flow_from_json(flow="./basic-prompting-local.json",
_14
input_value="tell me about something interesting",
_14
fallback_to_env_vars=True, # False by default
_14
tweaks=TWEAKS)
_14
_14
print(result)

  1. Run the script:

_10
python3 python-api-script.py

Tweaks​

The Tweaks tab displays the available parameters for your flow. Modifying the parameters changes the code parameters across all windows. For example, changing the Chat Input component's input_value will change that value across all API calls.

Send image files to your flow with the API​

For information on sending files to the Langflow API, see API examples.

Chat Widget​

The Chat Widget HTML tab displays code that can be inserted in the <body> of your HTML to interact with your flow.

The Langflow Chat Widget is a powerful web component that enables communication with a Langflow project. This widget allows for a chat interface embedding, allowing the integration of Langflow into web applications effortlessly.

You can get the HTML code embedded with the chat by clicking the Code button at the Sidebar after building a flow.

Clicking the Chat Widget HTML tab, you'll get the code to be inserted. Read below to learn how to use it with HTML, React and Angular.

Embed the chat widget into HTML​

To embed the chat widget into any HTML page, insert the code snippet. inside a <body> tag.


_10
<script src="https://cdn.jsdelivr.net/gh/logspace-ai/langflow-embedded-chat@v1.0.6/dist/build/static/js/bundle.min.js""></script>
_10
_10
<langflow-chat
_10
window_title="Basic Prompting"
_10
flow_id="801abb1e-19b9-4278-9632-179b6d84f126"
_10
host_url="http://localhost:7860"
_10
_10
></langflow-chat>

Embed the chat widget with React​

To embed the Chat Widget using React, insert this <script> tag into the React index.html file, inside the <body>tag:


_10
<script src="https://cdn.jsdelivr.net/gh/langflow-ai/langflow-embedded-chat@main/dist/build/static/js/bundle.min.js"></script>

Declare your Web Component and encapsulate it in a React component.


_20
declare global {
_20
namespace JSX {
_20
interface IntrinsicElements {
_20
"langflow-chat": any;
_20
}
_20
}
_20
}
_20
_20
export default function ChatWidget({ className }) {
_20
return (
_20
<div className={className}>
_20
<langflow-chat
_20
chat_inputs='{"your_key":"value"}'
_20
chat_input_field="your_chat_key"
_20
flow_id="your_flow_id"
_20
host_url="langflow_url"
_20
></langflow-chat>
_20
</div>
_20
);
_20
}

Place the component anywhere in your code to display the Chat Widget.

Embed the chat widget with Angular​

To use the chat widget in Angular, first add this <script> tag into the Angular index.html file, inside the <body> tag.


_10
<script src="https://cdn.jsdelivr.net/gh/langflow-ai/langflow-embedded-chat@main/dist/build/static/js/bundle.min.js"></script>

When you use a custom web component in an Angular template, the Angular compiler might show a warning when it doesn't recognize the custom elements by default. To suppress this warning, add CUSTOM_ELEMENTS_SCHEMA to the module's @NgModule.schemas.

  • Open the module file (it typically ends with .module.ts) where you'd add the langflow-chat web component.
  • Import CUSTOM_ELEMENTS_SCHEMA at the top of the file:

import { NgModule, CUSTOM_ELEMENTS_SCHEMA } from '@angular/core';

  • Add CUSTOM_ELEMENTS_SCHEMA to the 'schemas' array inside the '@NgModule' decorator:

_12
@NgModule({
_12
declarations: [
_12
// ... Other components and directives ...
_12
],
_12
imports: [
_12
// ... Other imported modules ...
_12
],
_12
schemas: [
_12
CUSTOM_ELEMENTS_SCHEMA // Add the CUSTOM_ELEMENTS_SCHEMA here
_12
]
_12
})
_12
export class YourModule { }

In your Angular project, find the component belonging to the module where CUSTOM_ELEMENTS_SCHEMA was added. Inside the template, add the langflow-chat tag to include the Chat Widget in your component's view:


_10
<langflow-chat chat_inputs='{"your_key":"value"}' chat_input_field="your_chat_key" flow_id="your_flow_id" host_url="langflow_url"></langflow-chat>

tip

CUSTOM_ELEMENTS_SCHEMA is a built-in schema that allows Angular to recognize custom elements. Adding CUSTOM_ELEMENTS_SCHEMA tells Angular to allow custom elements in your templates, and it will suppress the warning related to unknown elements like langflow-chat. Notice that you can only use the Chat Widget in components that are part of the module where you added CUSTOM_ELEMENTS_SCHEMA.

Chat widget configuration​

Use the widget API to customize your Chat Widget:

caution

Props with the type JSON need to be passed as stringified JSONs, with the format {"key":"value"}.

PropTypeRequiredDescription
bot_message_styleJSONNoApplies custom formatting to bot messages.
chat_input_fieldStringYesDefines the type of the input field for chat messages.
chat_inputsJSONYesDetermines the chat input elements and their respective values.
chat_output_keyStringNoSpecifies which output to display if multiple outputs are available.
chat_positionStringNoPositions the chat window on the screen (options include: top-left, top-center, top-right, center-left, center-right, bottom-right, bottom-center, bottom-left).
chat_trigger_styleJSONNoStyles the chat trigger button.
chat_window_styleJSONNoCustomizes the overall appearance of the chat window.
error_message_styleJSONNoSets the format for error messages within the chat window.
flow_idStringYesIdentifies the flow that the component is associated with.
heightNumberNoSets the height of the chat window in pixels.
host_urlStringYesSpecifies the URL of the host for chat component communication.
input_container_styleJSONNoApplies styling to the container where chat messages are entered.
input_styleJSONNoSets the style for the chat input field.
onlineBooleanNoToggles the online status of the chat component.
online_messageStringNoSets a custom message to display when the chat component is online.
placeholderStringNoSets the placeholder text for the chat input field.
placeholder_sendingStringNoSets the placeholder text to display while a message is being sent.
send_button_styleJSONNoSets the style for the send button in the chat window.
send_icon_styleJSONNoSets the style for the send icon in the chat window.
tweaksJSONNoApplies additional custom adjustments for the associated flow.
user_message_styleJSONNoDetermines the formatting for user messages in the chat window.
widthNumberNoSets the width of the chat window in pixels.
window_titleStringNoSets the title displayed in the chat window's header or title bar.

Hi, how can I help you?