HtmlToMarkdownTextSplitter

2026-06-28 07:00:49 +03:00 · 2023-07-15 18:53:57 -03:00
parent 7d985dbfce
commit 1f8fcb3983
3 changed files with 82 additions and 0 deletions
@@ -0,0 +1,75 @@
+import { INode, INodeData, INodeParams } from '../../../src/Interface'
+import { getBaseClasses } from '../../../src/utils'
+import { MarkdownTextSplitter, MarkdownTextSplitterParams } from 'langchain/text_splitter'
+import { NodeHtmlMarkdown } from 'node-html-markdown'
+
+class HtmlToMarkdownTextSplitter_TextSplitters implements INode {
+    label: string
+    name: string
+    description: string
+    type: string
+    icon: string
+    category: string
+    baseClasses: string[]
+    inputs: INodeParams[]
+
+    constructor() {
+        this.label = 'HtmlToMarkdown Text Splitter'
+        this.name = 'htmlToMarkdownTextSplitter'
+        this.type = 'HtmlToMarkdownTextSplitter'
+        this.icon = 'htmlToMarkdownTextSplitter.svg'
+        this.category = 'Text Splitters'
+        this.description = `Converts Html to Markdown and then split your content into documents based on the Markdown headers`
+        this.baseClasses = [this.type, ...getBaseClasses(HtmlToMarkdownTextSplitter)]
+        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 HtmlToMarkdownTextSplitter(obj)
+
+        return splitter
+    }
+}
+class HtmlToMarkdownTextSplitter extends MarkdownTextSplitter implements MarkdownTextSplitterParams {
+    constructor(fields?: Partial<MarkdownTextSplitterParams>) {
+        {
+            super(fields)
+        }
+    }
+    splitText(text: string): Promise<string[]> {
+        return new Promise((resolve, reject) => {
+            const markdown = NodeHtmlMarkdown.translate(
+                /* html */ text,
+                /* options (optional) */ {},
+                /* customTranslators (optional) */ undefined,
+                /* customCodeBlockTranslators (optional) */ undefined
+            )
+            super.splitText(markdown).then((result) => {
+                resolve(result)
+            })
+        })
+    }
+}
+module.exports = { nodeClass: HtmlToMarkdownTextSplitter_TextSplitters }