HtmlToMarkdownTextSplitter

packages/components/nodes/textsplitters/HtmlToMarkdownTextSplitter/HtmlToMarkdownTextSplitter.ts

@@ -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 }

packages/components/nodes/textsplitters/HtmlToMarkdownTextSplitter/htmlToMarkdownTextSplitter.svg

@@ -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>

packages/components/package.json

@@ -42,6 +42,7 @@
         "mammoth": "^1.5.1",
         "moment": "^2.29.3",
         "node-fetch": "^2.6.11",
+        "node-html-markdown": "^1.3.0",
         "pdf-parse": "^1.1.1",
         "pdfjs-dist": "^3.7.107",
         "playwright": "^1.35.0",