71 lines
2.4 KiB
TypeScript
71 lines
2.4 KiB
TypeScript
import { INode, INodeData, INodeParams } from '../../../src/Interface'
|
|
import { getBaseClasses } from '../../../src/utils'
|
|
import { CharacterTextSplitter, CharacterTextSplitterParams } from 'langchain/text_splitter'
|
|
|
|
class CharacterTextSplitter_TextSplitters implements INode {
|
|
label: string
|
|
name: string
|
|
version: number
|
|
description: string
|
|
type: string
|
|
icon: string
|
|
category: string
|
|
baseClasses: string[]
|
|
inputs: INodeParams[]
|
|
|
|
constructor() {
|
|
this.label = 'Character Text Splitter'
|
|
this.name = 'characterTextSplitter'
|
|
this.version = 1.0
|
|
this.type = 'CharacterTextSplitter'
|
|
this.icon = 'textsplitter.svg'
|
|
this.category = 'Text Splitters'
|
|
this.description = `splits only on one type of character (defaults to "\\n\\n").`
|
|
this.baseClasses = [this.type, ...getBaseClasses(CharacterTextSplitter)]
|
|
this.inputs = [
|
|
{
|
|
label: 'Chunk Size',
|
|
name: 'chunkSize',
|
|
type: 'number',
|
|
description: 'Number of characters in each chunk. Default is 1000.',
|
|
default: 1000,
|
|
optional: true
|
|
},
|
|
{
|
|
label: 'Chunk Overlap',
|
|
name: 'chunkOverlap',
|
|
type: 'number',
|
|
description: 'Number of characters to overlap between chunks. Default is 200.',
|
|
default: 200,
|
|
optional: true
|
|
},
|
|
{
|
|
label: 'Custom Separator',
|
|
name: 'separator',
|
|
type: 'string',
|
|
placeholder: `" "`,
|
|
description: 'Separator to determine when to split the text, will override the default separator',
|
|
optional: true
|
|
}
|
|
]
|
|
}
|
|
|
|
async init(nodeData: INodeData): Promise<any> {
|
|
const separator = nodeData.inputs?.separator as string
|
|
const chunkSize = nodeData.inputs?.chunkSize as string
|
|
const chunkOverlap = nodeData.inputs?.chunkOverlap as string
|
|
|
|
const obj = {} as CharacterTextSplitterParams
|
|
|
|
if (separator) obj.separator = separator
|
|
if (chunkSize) obj.chunkSize = parseInt(chunkSize, 10)
|
|
if (chunkOverlap) obj.chunkOverlap = parseInt(chunkOverlap, 10)
|
|
|
|
const splitter = new CharacterTextSplitter(obj)
|
|
|
|
return splitter
|
|
}
|
|
}
|
|
|
|
module.exports = { nodeClass: CharacterTextSplitter_TextSplitters }
|