Custom Components
In Langflow, a Custom Component is a special component type that allows users to extend the platform's functionality by creating their own reusable and configurable components.
A Custom Component is created from a user-defined Python script that uses the CustomComponent
class provided by the Langflow library. These components can be as simple as a basic function that takes and returns a string or as complex as a combination of multiple sub-components and API calls.
Let's take a look at the basic rules and features. Then we'll go over an example.
In Langflow, a Custom Component is a special component type that allows users to extend the platform's functionality by creating their own reusable and configurable components.
A Custom Component is created from a user-defined Python script that uses the CustomComponent
class provided by the Langflow library. These components can be as simple as a basic function that takes and returns a string or as complex as a combination of multiple sub-components and API calls.
Let's take a look at the basic rules and features. Then we'll go over an example.
TL;DR
Create a class that inherits from CustomComponent
and contains a build
method.
Use arguments with Type Annotations (or Type Hints) of the build
method to create component fields.
Use the build_config
method to customize how these fields look and behave.
Set up a folder with your components to load them up in Langflow's sidebar.
Create a class that inherits from CustomComponent
and contains a build
method.
Use arguments with Type Annotations (or Type Hints) of the build
method to create component fields.
Use the build_config
method to customize how these fields look and behave.
Set up a folder with your components to load them up in Langflow's sidebar.
from langflow import CustomComponent
from langchain.schema import Document
class DocumentProcessor(CustomComponent):
display_name = "Document Processor"
description = "This component processes a document"
def build_config(self) -> dict:
options = ["Uppercase", "Lowercase", "Titlecase"]
return {
"function": {"options": options,
"value": options[0]}}
def build(self, document: Document, function: str) -> Document:
if isinstance(document, list):
document = document[0]
page_content = document.page_content
if function == "Uppercase":
page_content = page_content.upper()
elif function == "Lowercase":
page_content = page_content.lower()
elif function == "Titlecase":
page_content = page_content.title()
self.repr_value = f"Result of {function} function: {page_content}"
return Document(page_content=page_content)
from langflow import CustomComponent
from langchain.schema import Document
class DocumentProcessor(CustomComponent):
display_name = "Document Processor"
description = "This component processes a document"
def build_config(self) -> dict:
options = ["Uppercase", "Lowercase", "Titlecase"]
return {
"function": {"options": options,
"value": options[0]}}
def build(self, document: Document, function: str) -> Document:
if isinstance(document, list):
document = document[0]
page_content = document.page_content
if function == "Uppercase":
page_content = page_content.upper()
elif function == "Lowercase":
page_content = page_content.lower()
elif function == "Titlecase":
page_content = page_content.title()
self.repr_value = f"Result of {function} function: {page_content}"
return Document(page_content=page_content)
from langflow import CustomComponent
from langchain.schema import Document
class DocumentProcessor(CustomComponent):
display_name = "Document Processor"
description = "This component processes a document"
def build_config(self) -> dict:
options = ["Uppercase", "Lowercase", "Titlecase"]
return {
"function": {"options": options,
"value": options[0]}}
def build(self, document: Document, function: str) -> Document:
if isinstance(document, list):
document = document[0]
page_content = document.page_content
if function == "Uppercase":
page_content = page_content.upper()
elif function == "Lowercase":
page_content = page_content.lower()
elif function == "Titlecase":
page_content = page_content.title()
self.repr_value = f"Result of {function} function: {page_content}"
return Document(page_content=page_content)
Check out FlowRunner Component for a more complex example.
Rules
Rule 1
The script must contain a single class that inherits from CustomComponent
.
The script must contain a single class that inherits from CustomComponent
.
from langflow import CustomComponent
from langchain.schema import Document
class MyComponent(CustomComponent):
display_name = "Custom Component"
description = "This is a custom component"
def build_config(self) -> dict:
...
def build(self, document: Document, function: str) -> Document:
...
Rule 2
This class requires a build
method used to run the component and define its fields.
The Return Type Annotation of the build
method defines the component type (e.g., Chain, BaseLLM, or basic Python types).
def build(self) -> Document:
...
Rule 3
The class can have a build_config
method, which defines configuration fields for the component. The build_config
method should always return a dictionary with specific keys representing the field names and their corresponding configurations. It must follow the format described below:
Top-level keys are field names.
Their values are also of type dict
. They specify the behavior of the generated fields.
from langflow import CustomComponent
from langchain.schema import Document
class MyComponent(CustomComponent):
display_name = "Custom Component"
description = "This is a custom component"
def build_config(self) -> dict:
...
def build(self, document: Document, function: str) -> Document:
...
Examples
Let's create a custom component that processes a document (langchain.schema.Document
) using a simple function.
Pick a display name
To start, let's choose a name for our component by adding a display_name
attribute. This name will appear on the canvas. The name of the class is not relevant, but let's call it DocumentProcessor
.
class DocumentProcessor(CustomComponent):
display_name = "Document Processor"
Write a description
We can also write a description for it using a description
attribute.
class DocumentProcessor(CustomComponent):
display_name = "Document Processor"
description = "This component processes a document"
Add the build method
Here, the build method takes two input parameters: document
, representing the input document to be processed, and function
, a string representing the selected text transformation to be applied (either "Uppercase," "Lowercase," or "Titlecase"). The method processes the text content of the input Document based on the selected function.
The attribute repr_value
is used to display the result of the component on the canvas. It is optional and can be used to display any string value.
The return type is Document
.
def build(self, document: Document, function: str) -> Document:
if isinstance(document, list):
document = document[0]
page_content = document.page_content
if function == "Uppercase":
page_content = page_content.upper()
elif function == "Lowercase":
page_content = page_content.lower()
elif function == "Titlecase":
page_content = page_content.title()
self.repr_value = f"Result of {function} function: {page_content}"
return Document(page_content=page_content)
Customize the component fields
The build_config
method is here defined to customize the component fields.
options
determines that the field will be a dropdown menu. The list values and field type must be str
.
value
is the default option of the dropdown menu.
display_name
is the name of the field to be displayed.
def build_config(self) -> dict:
options = ["Uppercase", "Lowercase", "Titlecase"]
return {
"function": {"options": options,
"value": options[0],
"display_name": "Function"
},
"document": {"display_name": "Document"}
}
All done! This is what our script and brand-new custom component look like:
Loading Custom Components
For advanced customization, Langflow offers the option to create and load custom components outside of the standard interface. This process involves creating the desired components using a text editor and loading them using the Langflow CLI.
Folder Structure
Create a folder that follows the same structural conventions as the config.yaml file. Inside this main directory, use a custom_components
subdirectory for your custom components.
Inside custom_components
, you can create a Python file for each component. Similarly, any custom agents should be housed in an agents
subdirectory.
If you use a subdirectory name that is not in our config.yaml file, your component will appear in an Other
category in the sidebar.
Your structure should look something like this:
Loading Custom Components
The recommended way to load custom components is to set the LANGFLOW_COMPONENTS_PATH
environment variable to the path of your custom components directory. Then, run the Langflow CLI as usual.
export LANGFLOW_COMPONENTS_PATH='["/path/to/components"]'
langflow
Alternatively, you can specify the path to your custom components using the --components-path
argument when running the Langflow CLI, as shown below:
langflow --components-path /path/to/components
Langflow will attempt to load all of the components found in the specified directory. If a component fails to load due to errors in the component's code, Langflow will print an error message to the console but will continue loading the rest of the components.
Interacting with Custom Components
Once your custom components have been loaded successfully, they will appear in Langflow's sidebar. From there, you can add them to your Langflow canvas for use. However, please note that components with errors will not be available for addition to the canvas. Always ensure your code is error-free before attempting to load components.
Remember, creating custom components allows you to extend the functionality of Langflow to better suit your unique needs. Happy coding!