farcasclaudiu/Flowise
1
0
Fork 0
mirror of https://github.com/farcasclaudiu/Flowise.git synced 2026-06-28 23:01:09 +03:00
Code Issues Packages Projects Releases Wiki Activity

Feature/externalize files from chatflow - do not save as base64 (#1976)

Browse Source 
* initial commit. Externalizing the file base64 string from flowData

* csv - docloader - Externalizing the file base64 string from flowData

* csv - docloader - Externalizing the file base64 string from flowData

* DocX - docloader - Externalizing the file base64 string from flowData

* Json - docloader - Externalizing the file base64 string from flowData

* Jsonlines - docloader - Externalizing the file base64 string from flowData

* PDF - docloader - Externalizing the file base64 string from flowData

* Vectara - vector store - Externalizing the file base64 string from flowData

* OpenAPIToolkit - tools - Externalizing the file base64 string from flowData

* OpenAPIChain - chain - Externalizing the file base64 string from flowData

* lint fixes

* datasource enabled - initial commit

* CSVAgent - agents - Externalizing the file base64 string from flowData

* Externalizing the file base64 string from flowData

* Externalizing the file base64 string from flowData

* add pnpm-lock.yaml

* update filerepository to add try catch

* Rename FileRepository.ts to fileRepository.ts

---------

Co-authored-by: Henry <hzj94@hotmail.com>
Co-authored-by: Henry Heng <henryheng@flowiseai.com>
This commit is contained in:
Vinod Kiran
2024-04-04 21:41:06 +05:30
committed by GitHub
parent eed7de6df5
commit 658fa3984e
16 changed files with 593 additions and 194 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/components/nodes/documentloaders/Pdf/Pdf.ts
+64 -39
View File
@@ -1,6 +1,9 @@
import { INode, INodeData, INodeParams } from '../../../src/Interface'
import { ICommonObject, INode, INodeData, INodeParams } from '../../../src/Interface'
import { TextSplitter } from 'langchain/text_splitter'
import { PDFLoader } from 'langchain/document_loaders/fs/pdf'
import { getStoragePath } from '../../../src'
import fs from 'fs'
import path from 'path'
class Pdf_DocumentLoaders implements INode {
label: string
@@ -68,53 +71,44 @@ class Pdf_DocumentLoaders implements INode {
]
}
async init(nodeData: INodeData): Promise<any> {
async init(nodeData: INodeData, _: string, options: ICommonObject): 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 legacyBuild = nodeData.inputs?.legacyBuild as boolean
let alldocs = []
let alldocs: any[] = []
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,
pdfjs: () =>
// @ts-ignore
legacyBuild ? import('pdfjs-dist/legacy/build/pdf.js') : 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)
}
//FILE-STORAGE::["CONTRIBUTING.md","LICENSE.md","README.md"]
if (pdfFileBase64.startsWith('FILE-STORAGE::')) {
const fileName = pdfFileBase64.replace('FILE-STORAGE::', '')
if (fileName.startsWith('[') && fileName.endsWith(']')) {
files = JSON.parse(fileName)
} else {
const loader = new PDFLoader(new Blob([bf]), {
pdfjs: () =>
// @ts-ignore
legacyBuild ? import('pdfjs-dist/legacy/build/pdf.js') : 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)
}
files = [fileName]
}
const chatflowid = options.chatflowid
for (const file of files) {
const fileInStorage = path.join(getStoragePath(), chatflowid, file)
const fileData = fs.readFileSync(fileInStorage)
const bf = Buffer.from(fileData)
await this.extractDocs(usage, bf, legacyBuild, textSplitter, alldocs)
}
} else {
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')
await this.extractDocs(usage, bf, legacyBuild, textSplitter, alldocs)
}
}
@@ -136,6 +130,37 @@ class Pdf_DocumentLoaders implements INode {
return alldocs
}
private async extractDocs(usage: string, bf: Buffer, legacyBuild: boolean, textSplitter: TextSplitter, alldocs: any[]) {
if (usage === 'perFile') {
const loader = new PDFLoader(new Blob([bf]), {
splitPages: false,
pdfjs: () =>
// @ts-ignore
legacyBuild ? import('pdfjs-dist/legacy/build/pdf.js') : 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 {
const loader = new PDFLoader(new Blob([bf]), {
pdfjs: () =>
// @ts-ignore
legacyBuild ? import('pdfjs-dist/legacy/build/pdf.js') : 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)
}
}
}
}
module.exports = { nodeClass: Pdf_DocumentLoaders }