Sultan
/
Flowise
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

use pdf-parser

This commit is contained in:
Henry 2023-04-13 19:56:48 +01:00
parent 02d8284f58
commit 930449f956
2 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
packages/components/nodes/documentloaders/Pdf/Pdf.ts
View File

@ -66,7 +66,8 @@ class Pdf_DocumentLoaders implements INode {
const blob = new Blob([bf])
if (usage === 'perFile') {
const loader = new PDFLoader(blob, { splitPages: false })
// @ts-ignore
const loader = new PDFLoader(blob, { splitPages: false, pdfjs: () => import('pdf-parse/lib/pdf.js/v1.10.100/build/pdf.js') })
if (textSplitter) {
const docs = await loader.loadAndSplit(textSplitter)
return docs
@ -75,7 +76,8 @@ class Pdf_DocumentLoaders implements INode {
return docs
}
} else {
const loader = new PDFLoader(blob)
// @ts-ignore
const loader = new PDFLoader(blob, { pdfjs: () => import('pdf-parse/lib/pdf.js/v1.10.100/build/pdf.js') })
if (textSplitter) {
const docs = await loader.loadAndSplit(textSplitter)
return docs

2
packages/components/package.json
View File

@ -27,7 +27,7 @@
"langchain": "^0.0.44",
"moment": "^2.29.3",
"node-fetch": "2",
"pdfjs-dist": "^3.5.141",
"pdf-parse": "^1.1.1",
"ws": "^8.9.0"
},
"devDependencies": {