Custom Components

Used to create a custom component, a special type of Langflow component that allows users to extend the functionality of the platform by creating their own reusable and configurable components from a Python script.

To use a custom component, follow these steps:

• Create a class that inherits from langflow.CustomComponent and contains a build method.
• Use arguments with Type Annotations (or Type Hints) of the build method to create component fields.
• If applicable, use the build_config method to customize how these fields look and behave.

info

For an in-depth explanation of custom components, their rules, and applications, make sure to read Custom Component guidelines.

Params

• Code: The Python code to define the component.

The CustomComponent Class

The CustomComponent class serves as the foundation for creating custom components. By inheriting this class, users can create new, configurable components, tailored to their specific requirements.

Methods

• build: This method is required within a Custom Component class. It defines the component's functionality and specifies how it processes input data to produce output data. This method is called when the component is built (i.e., when you click the Build ⚡ button in the canvas).

  The type annotations of the build instance method are used to create the fields of the component.

  Supported Types
  str, int, float, bool, list, dict
  langflow.field_typing.NestedDict
  langflow.field_typing.Prompt
  langchain.chains.base.Chain
  langchain.PromptTemplate
  langchain.llms.base.BaseLLM
  langchain.Tool
  langchain.document_loaders.base.BaseLoader
  langchain.schema.Document
  langchain.text_splitters.TextSplitter
  langchain.vectorstores.base.VectorStore
  langchain.embeddings.base.Embeddings
  langchain.schema.BaseRetriever

  The difference between dict and langflow.field_typing.NestedDict is that one adds a simple key-value pair field, while the other opens a more robust dictionary editor.

  info

  To use the Prompt type, you must also add **kwargs to the build method. This is because the Prompt type passes new arbitrary keyword arguments to it.

  If you want to add the values of the variables to the template you defined, you must format the PromptTemplate inside the CustomComponent class.

  info

  Unlike Langchain types, base Python types do not add a handle to the field by default. To add handles, use the input_types key in the build_config method.

• build_config: Used to define the configuration fields of the component (if applicable). It should always return a dictionary with specific keys representing the field names and corresponding configurations. This method is called when the code is processed (i.e., when you click Check and Save in the code editor). It must follow the format described below:

  • Top-level keys are field names.
  • Their values are can be of type langflow.field_typing.TemplateField or dict. They specify the behavior of the generated fields.

  Below are the available keys used to configure component fields:

  Key	Description
  field_type: str	The type of the field (can be any of the types supported by the build method).
  is_list: bool	If the field can be a list of values, meaning that the user can manually add more inputs to the same field.
  options: List[str]	When defined, the field becomes a dropdown menu where a list of strings defines the options to be displayed. If the value attribute is set to one of the options, that option becomes default. For this parameter to work, field_type should invariably be str.
  multiline: bool	Defines if a string field opens a text editor. Useful for longer texts.
  input_types: List[str]	Used when you want a str field to have connectable handles.
  display_name: str	Defines the name of the field.
  advanced: bool	Hide the field in the canvas view (displayed component settings only). Useful when a field is for advanced users.
  password: bool	To mask the input text. Useful to hide sensitive text (e.g. API keys).
  required: bool	Makes the field required.
  info: str	Adds a tooltip to the field.
  file_types: List[str]	This is a requirement if the field_type is file. Defines which file types will be accepted. For example, json, yaml or yml.
  range_spec: langflow.field_typing.RangeSpec	This is a requirement if the field_type is float. Defines the range of values accepted and the step size. If none is defined, the default is [-1, 1, 0.1].
  title_case: bool	Formats the name of the field when display_name is not defined. Set it to False to keep the name as you set it in the build method.

  info

  Keys options and value can receive a method or function that returns a list of strings or a string, respectively. This is useful when you want to dynamically generate the options or the default value of a field. A refresh button will appear next to the field in the component, allowing the user to update the options or the default value.

• The CustomComponent class also provides helpful methods for specific tasks (e.g., to load and use other flows from the Langflow platform):

  Method Name	Description
  list_flows	Returns a list of Flow objects with an id and a name.
  get_flow	Returns a Flow object. Parameters are flow_name or flow_id.
  load_flow	Loads a flow from a given id.

• Useful attributes:

  Attribute Name	Description
  status	Displays the value it receives in the build method. Useful for debugging.
  field_order	Defines the order the fields will be displayed in the canvas.
  icon	Defines the emoji (for example, :rocket:) that will be displayed in the canvas.

  info

  Check out the FlowRunner example to understand how to call a flow from a custom component.