110 lines
3.4 KiB
TypeScript
110 lines
3.4 KiB
TypeScript
import { INode, INodeData, INodeParams } from '../../../src/Interface'
|
|
import { TextSplitter } from 'langchain/text_splitter'
|
|
import { PDFLoader } from 'langchain/document_loaders/fs/pdf'
|
|
import { getBlob } from '../../../src/utils'
|
|
|
|
class Pdf_DocumentLoaders implements INode {
|
|
label: string
|
|
name: string
|
|
description: string
|
|
type: string
|
|
icon: string
|
|
category: string
|
|
baseClasses: string[]
|
|
inputs: INodeParams[]
|
|
|
|
constructor() {
|
|
this.label = 'Pdf File'
|
|
this.name = 'pdfFile'
|
|
this.type = 'Document'
|
|
this.icon = 'pdf.svg'
|
|
this.category = 'Document Loaders'
|
|
this.description = `Load data from PDF files`
|
|
this.baseClasses = [this.type]
|
|
this.inputs = [
|
|
{
|
|
label: 'Pdf File',
|
|
name: 'pdfFile',
|
|
type: 'file',
|
|
fileType: '.pdf'
|
|
},
|
|
{
|
|
label: 'Text Splitter',
|
|
name: 'textSplitter',
|
|
type: 'TextSplitter',
|
|
optional: true
|
|
},
|
|
{
|
|
label: 'Usage',
|
|
name: 'usage',
|
|
type: 'options',
|
|
options: [
|
|
{
|
|
label: 'One document per page',
|
|
name: 'perPage'
|
|
},
|
|
{
|
|
label: 'One document per file',
|
|
name: 'perFile'
|
|
}
|
|
],
|
|
default: 'perPage'
|
|
},
|
|
{
|
|
label: 'Metadata',
|
|
name: 'metadata',
|
|
type: 'json',
|
|
optional: true,
|
|
additionalParams: true
|
|
}
|
|
]
|
|
}
|
|
|
|
async init(nodeData: INodeData): Promise<any> {
|
|
const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
|
|
const pdfFileBase64 = nodeData.inputs?.pdfFile as string
|
|
const usage = nodeData.inputs?.usage as string
|
|
const metadata = nodeData.inputs?.metadata
|
|
|
|
const blob = new Blob(getBlob(pdfFileBase64))
|
|
let docs = []
|
|
if (usage === 'perFile') {
|
|
// @ts-ignore
|
|
const loader = new PDFLoader(blob, { splitPages: false, pdfjs: () => import('pdf-parse/lib/pdf.js/v1.10.100/build/pdf.js') })
|
|
if (textSplitter) {
|
|
docs = await loader.loadAndSplit(textSplitter)
|
|
} else {
|
|
docs = await loader.load()
|
|
}
|
|
} else {
|
|
// @ts-ignore
|
|
const loader = new PDFLoader(blob, { pdfjs: () => import('pdf-parse/lib/pdf.js/v1.10.100/build/pdf.js') })
|
|
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: Pdf_DocumentLoaders }
|