File size: 4,128 Bytes
4114d85 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 |
import { INode, INodeData, INodeParams } from '../../../src/Interface'
import { TextSplitter } from 'langchain/text_splitter'
import { PDFLoader } from 'langchain/document_loaders/fs/pdf'
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
let alldocs = []
let files: string[] = []
if (pdfFileBase64.startsWith('[') && pdfFileBase64.endsWith(']')) {
files = JSON.parse(pdfFileBase64)
} else {
files = [pdfFileBase64]
}
for (const file of files) {
const splitDataURI = file.split(',')
splitDataURI.pop()
const bf = Buffer.from(splitDataURI.pop() || '', 'base64')
if (usage === 'perFile') {
const loader = new PDFLoader(new Blob([bf]), {
splitPages: false,
// @ts-ignore
pdfjs: () => import('pdf-parse/lib/pdf.js/v1.10.100/build/pdf.js')
})
if (textSplitter) {
const docs = await loader.loadAndSplit(textSplitter)
alldocs.push(...docs)
} else {
const docs = await loader.load()
alldocs.push(...docs)
}
} else {
// @ts-ignore
const loader = new PDFLoader(new Blob([bf]), { pdfjs: () => import('pdf-parse/lib/pdf.js/v1.10.100/build/pdf.js') })
if (textSplitter) {
const docs = await loader.loadAndSplit(textSplitter)
alldocs.push(...docs)
} else {
const docs = await loader.load()
alldocs.push(...docs)
}
}
}
if (metadata) {
const parsedMetadata = typeof metadata === 'object' ? metadata : JSON.parse(metadata)
let finaldocs = []
for (const doc of alldocs) {
const newdoc = {
...doc,
metadata: {
...doc.metadata,
...parsedMetadata
}
}
finaldocs.push(newdoc)
}
return finaldocs
}
return alldocs
}
}
module.exports = { nodeClass: Pdf_DocumentLoaders }
|