53 lines
1.8 KiB
TypeScript
53 lines
1.8 KiB
TypeScript
import { INode, INodeData, INodeParams } from '../../../src/Interface'
|
|
import { getBaseClasses } from '../../../src/utils'
|
|
import { RecursiveCharacterTextSplitter, RecursiveCharacterTextSplitterParams } from 'langchain/text_splitter'
|
|
|
|
class LatexTextSplitter_TextSplitters implements INode {
|
|
label: string
|
|
name: string
|
|
description: string
|
|
type: string
|
|
icon: string
|
|
category: string
|
|
baseClasses: string[]
|
|
inputs: INodeParams[]
|
|
constructor() {
|
|
this.label = 'Latex Text Splitter'
|
|
this.name = 'latexTextSplitter'
|
|
this.type = 'LatexTextSplitter'
|
|
this.icon = 'latexTextSplitter.svg'
|
|
this.category = 'Text Splitters'
|
|
this.description = `Split documents along Latex headings, headlines, enumerations and more.`
|
|
this.baseClasses = [this.type, ...getBaseClasses(RecursiveCharacterTextSplitter)]
|
|
this.inputs = [
|
|
{
|
|
label: 'Chunk Size',
|
|
name: 'chunkSize',
|
|
type: 'number',
|
|
default: 1000,
|
|
optional: true
|
|
},
|
|
{
|
|
label: 'Chunk Overlap',
|
|
name: 'chunkOverlap',
|
|
type: 'number',
|
|
optional: true
|
|
}
|
|
]
|
|
}
|
|
async init(nodeData: INodeData): Promise<any> {
|
|
const chunkSize = nodeData.inputs?.chunkSize as string
|
|
const chunkOverlap = nodeData.inputs?.chunkOverlap as string
|
|
|
|
const obj = {} as RecursiveCharacterTextSplitterParams
|
|
|
|
if (chunkSize) obj.chunkSize = parseInt(chunkSize, 10)
|
|
if (chunkOverlap) obj.chunkOverlap = parseInt(chunkOverlap, 10)
|
|
|
|
const splitter = RecursiveCharacterTextSplitter.fromLanguage('latex', obj)
|
|
|
|
return splitter
|
|
}
|
|
}
|
|
module.exports = { nodeClass: LatexTextSplitter_TextSplitters }
|