add multiple loaders and documents

2026-06-28 17:01:00 +03:00 · 2023-04-30 22:57:12 +01:00
parent e333db8245
commit 40b655e66b
7 changed files with 96 additions and 15 deletions
@@ -0,0 +1,67 @@
+import { INode, INodeData, INodeParams } from '../../../src/Interface'
+import { TextSplitter } from 'langchain/text_splitter'
+import { TextLoader } from 'langchain/document_loaders/fs/text'
+import { DirectoryLoader } from 'langchain/document_loaders/fs/directory'
+import { JSONLoader } from 'langchain/document_loaders/fs/json'
+import { CSVLoader } from 'langchain/document_loaders/fs/csv'
+import { PDFLoader } from 'langchain/document_loaders/fs/pdf'
+import { DocxLoader } from 'langchain/document_loaders/fs/docx'
+
+class Folder_DocumentLoaders implements INode {
+    label: string
+    name: string
+    description: string
+    type: string
+    icon: string
+    category: string
+    baseClasses: string[]
+    inputs: INodeParams[]
+
+    constructor() {
+        this.label = 'Folder with Files'
+        this.name = 'folderFiles'
+        this.type = 'Document'
+        this.icon = 'folder.svg'
+        this.category = 'Document Loaders'
+        this.description = `Load data from folder with multiple files`
+        this.baseClasses = [this.type]
+        this.inputs = [
+            {
+                label: 'Folder Path',
+                name: 'folderPath',
+                type: 'string',
+                placeholder: ''
+            },
+            {
+                label: 'Text Splitter',
+                name: 'textSplitter',
+                type: 'TextSplitter',
+                optional: true
+            }
+        ]
+    }
+
+    async init(nodeData: INodeData): Promise<any> {
+        const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
+        const folderPath = nodeData.inputs?.folderPath as string
+
+        const loader = new DirectoryLoader(folderPath, {
+            '.json': (path) => new JSONLoader(path),
+            '.txt': (path) => new TextLoader(path),
+            '.csv': (path) => new CSVLoader(path),
+            '.docx': (path) => new DocxLoader(path),
+            // @ts-ignore
+            '.pdf': (path) => new PDFLoader(path, { pdfjs: () => import('pdf-parse/lib/pdf.js/v1.10.100/build/pdf.js') })
+        })
+
+        if (textSplitter) {
+            const docs = await loader.loadAndSplit(textSplitter)
+            return docs
+        } else {
+            const docs = await loader.load()
+            return docs
+        }
+    }
+}
+
+module.exports = { nodeClass: Folder_DocumentLoaders }