jyapayne/langflow
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions

Merge branch 'python_custom_node_component' of github.com:logspace-ai/langflow into python_custom_node_component

Browse source
This commit is contained in:
Lucas Oliveira 2023-07-28 15:01:08 -03:00
commit 22faf54737
2 changed files with 64 additions and 63 deletions
Download patch file Download diff file Expand all files Collapse all files

112
docs/docs/components/custom.mdx
View file

@ -2,78 +2,80 @@ import Admonition from "@theme/Admonition";
# Custom Component
Used to create a custom component. The code is the class that will be converted to a Custom Component with the fields and formatting you define.
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 user-defined 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)](https://docs.python.org/3/library/typing.html) of the _`build`_ method to create component fields.
- If applicable, use the _`build_config`_ method to customize how these fields look and behave.
<Admonition type="info" label="Tip">
For an in depth explanation of custom components, their rules and applications, make sure to read [Custom Component guidelines](../guidelines/custom-component).
</Admonition>
**Params**
- **Code:** The Python code to define the component.
The code must be a class that inherits from the _`langflow.CustomComponent`_ class.
The type annotations of the _`build`_ instance method will be used to create the fields of the component.
## The CustomComponent Class
| Supported types |
| --------------------------------------------------------- |
| _`str`_, _`int`_, _`float`_, _`bool`_, _`list`_, _`dict`_ |
| _`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 class can have a [_`build_config`_](focus://8) instance method, which is used to define configuration fields for the component.
The [_`build_config`_](focus://8) method should always return a dictionary with specific keys representing the field names and their corresponding configurations.
It must follow the format described below:
**Methods**
The top-level keys are the field names.
- **build**: This is a required method within a Custom Component class. It defines the functionality of the component and specifies how it processes input data to produce output data. The type annotations of the _`build`_ instance method are used to create the fields of the component.
Their values are of type _`dict`_ with any of the following keys (all of them are **optional**):
| Supported types |
| --------------------------------------------------------- |
| _`str`_, _`int`_, _`float`_, _`bool`_, _`list`_, _`dict`_ |
| _`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`_ |
| Key | Description |
| -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| _`field_type: str`_ | The type of the field (can be any of the types supported by the _`build`_ method, passed as a string). |
| _`is_list: bool`_ | If the field is a list. |
| _`options: List[str]`_ | This defines the options to be displayed. The _`field_type`_ should invariably be _`str`_. If you set the _`value`_ attribute to one of the options, it will be selected by default. Having _`options`_ will display a dropdown menu. |
| _`multiline: bool`_ | When the field is a string, this would allow the user to open a text editor. |
| _`input_types: List[str]`_ | To be used when you want a _`str`_ field to have connectable handles. |
| _`display_name: str`_ | To define the name of the field. |
| _`advanced: bool`_ | To hide the field in default view. This is useful when a field is for advanced users or you simply want to remove it from view. |
| _`password: bool`_ | To mask the input text. This is used to allow the user to hide the values of the text (e.g. API keys). |
| _`required: bool`_ | To make the field required. |
| _`info: str`_ | To add 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. |
The CustomComponent class provides the following methods:
- **build_config**: Used to define the configuration fields of the component. Should always return a dictionary with specific keys representing the field names and their corresponding configurations. It must follow the format described below:
| Method name | Description |
| -------------- | ------------------------------------------------------------- |
| _`list_flows`_ | Returns a list of Flow objects with an _`id`_ and a _`name`_. |
| _`load_flow`_ | Loads a flow from the given _`id`_. |
- Top-level keys are field names.
- Their values are also of type _`dict`_. They specify the behavior of the generated fields.
### Usage
Following are the available keys used to customize component fields:
```python
# In the CustomComponent class
def build(self, flow_name: str)
# This is a list of Flow objects with an id and a name
flows = self.list_flows()
found_flow = next((f for f in flows if f.name == flow_name), None)
if not found_flow:
raise ValueError(f"Flow {flow_name} not found")
| 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 contains a list of values. When paired with _`options`_, becomes a dropdown menu. |
| _`options: List[str]`_ | Defines the options to be displayed in a dropdown menu. If the _`value`_ attribute is set to one of the options, that option becomes the default. For this parameter to work, _`field_type`_ should invariably be _`str`_. |
| _`multiline: bool`_ | When the field is a string, if it should be multiline. Useful for longer texts when a text modal is helpful. |
| _`input_types: List[str]`_ | To be used when you want a _`str`_ field to have connectable handles. |
| _`display_name: str`_ | Defines the field name. |
| _`advanced: bool`_ | To hide the field in canvas view (shown only in the component's settings). |
| _`password: bool`_ | To mask the input text. |
| _`required: bool`_ | To make the field required. |
| _`info: str`_ | To add a tooltip with information 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*. |
flow = self.load_flow(found_flow.id)
result = flow() # Run the flow
return result
```
<Admonition type="info" label="Tip">
- The CustomComponent class also provides methods to load and use other flows from the Langflow platform:
[Learn more about Custom Components](../guidelines/custom-component)
| Method name | Description |
| -------------- | ------------------------------------------------------------- |
| _`list_flows`_ | Returns a list of Flow objects with an _`id`_ and a _`name`_. |
| _`load_flow`_ | Loads a flow from a given _`id`_. |
</Admonition>
<Admonition type="info" label="Tip">
Check out the [FlowRunner](../guidelines/custom-component) example to understand how to call a flow from a custom component.
</Admonition>

15
docs/docs/guidelines/custom-component.mdx
View file

@ -8,17 +8,17 @@ import Admonition from "@theme/Admonition";
# Custom Components
In Langflow, a Custom Component is a special component type that allows users to extend the functionality of the platform by creating their own reusable and configurable 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.
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)](https://docs.python.org/3/library/typing.html) of the _`build`_ method to create component fields.
- Use the _`build_config`_ method to customize these fields look and behave.
- Use the _`build_config`_ method to customize how these fields look and behave.
Here is an example:
@ -87,7 +87,7 @@ class MyComponent(CustomComponent):
### Rule 2
This class requires a _`build`_ method, which is used to run the component and defines its fields.
This class requires a _`build`_ method used to run the component and define its fields.
```python
from langflow import CustomComponent
@ -108,7 +108,7 @@ class MyComponent(CustomComponent):
---
The [Return Type Annotation](https://docs.python.org/3/library/typing.html) of the _`build`_ method defines the component type (e.g., Chain, BaseLLM or basic Python types). Check out all supported types in the [component reference](../components/custom).
The [Return Type Annotation](https://docs.python.org/3/library/typing.html) of the _`build`_ method defines the component type (e.g., Chain, BaseLLM, or basic Python types). Check out all supported types in the [component reference](../components/custom).
```python
from langflow import CustomComponent
@ -146,7 +146,7 @@ class MyComponent(CustomComponent):
### Rule 3
The class can have a [_`build_config`_](focus://8) method, which is used to define configuration fields for the component. The [_`build_config`_](focus://8) method should always return a dictionary with specific keys representing the field names and their corresponding configurations. It must follow the format described below:
The class can have a [_`build_config`_](focus://8) method, which defines configuration fields for the component. The [_`build_config`_](focus://8) 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.
@ -184,8 +184,7 @@ If you were to do this using Langflow's native components, you would create a To
### Pick a display name
First, let's choose a name for our component by adding a _`display_name`_ attribute. This is the component name to be displayed in the canvas.
The name of the class is not important, but let's call it _`DocumentProcessor`_.
First, let's choose a name for our component by adding a _`display_name`_ attribute. This is the component name to be displayed in the canvas. The name of the class is not important, but let's call it _`DocumentProcessor`_.
```python
from langflow import CustomComponent