add markdown text splitter

This commit is contained in:
chungyau97 2023-05-06 09:54:35 +07:00
parent aa0795c4ed
commit 9682f62b2c
2 changed files with 61 additions and 0 deletions

View File

@ -0,0 +1,55 @@
import { INode, INodeData, INodeParams } from '../../../src/Interface'
import { getBaseClasses } from '../../../src/utils'
import { MarkdownTextSplitter, MarkdownTextSplitterParams } from 'langchain/text_splitter'
class MarkdownTextSplitter_TextSplitters implements INode {
label: string
name: string
description: string
type: string
icon: string
category: string
baseClasses: string[]
inputs: INodeParams[]
constructor() {
this.label = 'Markdown Text Splitter'
this.name = 'markdownTextSplitter'
this.type = 'MarkdownTextSplitter'
this.icon = 'markdownTextSplitter.svg'
this.category = 'Text Splitters'
this.description = `Split your content into documents based on the Markdown headers`
this.baseClasses = [this.type, ...getBaseClasses(MarkdownTextSplitter)]
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 MarkdownTextSplitterParams
if (chunkSize) obj.chunkSize = parseInt(chunkSize, 10)
if (chunkOverlap) obj.chunkOverlap = parseInt(chunkOverlap, 10)
const splitter = new MarkdownTextSplitter(obj)
return splitter
}
}
module.exports = { nodeClass: MarkdownTextSplitter_TextSplitters }

View File

@ -0,0 +1,6 @@
<svg xmlns="http://www.w3.org/2000/svg" class="icon icon-tabler icon-tabler-markdown" width="24" height="24" viewBox="0 0 24 24" stroke-width="2" stroke="currentColor" fill="none" stroke-linecap="round" stroke-linejoin="round">
<path stroke="none" d="M0 0h24v24H0z" fill="none"></path>
<path d="M3 5m0 2a2 2 0 0 1 2 -2h14a2 2 0 0 1 2 2v10a2 2 0 0 1 -2 2h-14a2 2 0 0 1 -2 -2z"></path>
<path d="M7 15v-6l2 2l2 -2v6"></path>
<path d="M14 13l2 2l2 -2m-2 2v-6"></path>
</svg>

After

Width:  |  Height:  |  Size: 482 B