import { INode, INodeData, INodeParams } from '../../../src/Interface' import { TextSplitter } from 'langchain/text_splitter' import { DocxLoader } from 'langchain/document_loaders/fs/docx' import { getBlob } from '../../../src/utils' class Docx_DocumentLoaders implements INode { label: string name: string description: string type: string icon: string category: string baseClasses: string[] inputs: INodeParams[] constructor() { this.label = 'Docx File' this.name = 'docxFile' this.type = 'Document' this.icon = 'Docx.png' this.category = 'Document Loaders' this.description = `Load data from DOCX files` this.baseClasses = [this.type] this.inputs = [ { label: 'Docx File', name: 'docxFile', type: 'file', fileType: '.docx' }, { label: 'Text Splitter', name: 'textSplitter', type: 'TextSplitter', optional: true }, { label: 'Metadata', name: 'metadata', type: 'json', optional: true, additionalParams: true } ] } async init(nodeData: INodeData): Promise { const textSplitter = nodeData.inputs?.textSplitter as TextSplitter const docxFileBase64 = nodeData.inputs?.docxFile as string const metadata = nodeData.inputs?.metadata const blob = new Blob(getBlob(docxFileBase64)) const loader = new DocxLoader(blob) let docs = [] if (textSplitter) { docs = await loader.loadAndSplit(textSplitter) } else { docs = await loader.load() } if (metadata) { const parsedMetadata = typeof metadata === 'object' ? metadata : JSON.parse(metadata) let finaldocs = [] for (const doc of docs) { const newdoc = { ...doc, metadata: { ...doc.metadata, ...parsedMetadata } } finaldocs.push(newdoc) } return finaldocs } return docs } } module.exports = { nodeClass: Docx_DocumentLoaders }