farcasclaudiu/Flowise
1
0
Fork 0
mirror of https://github.com/farcasclaudiu/Flowise.git synced 2026-06-28 13:00:56 +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/Text/Text.ts
+49 -21
View File
@@ -1,8 +1,10 @@
import { INode, INodeData, INodeOutputsValue, INodeParams } from '../../../src/Interface'
import { ICommonObject, INode, INodeData, INodeOutputsValue, INodeParams } from '../../../src/Interface'
import { TextSplitter } from 'langchain/text_splitter'
import { TextLoader } from 'langchain/document_loaders/fs/text'
import { Document } from '@langchain/core/documents'
import { handleEscapeCharacters } from '../../../src'
import { getStoragePath, handleEscapeCharacters } from '../../../src'
import fs from 'fs'
import path from 'path'
class Text_DocumentLoaders implements INode {
label: string
@@ -63,7 +65,7 @@ class Text_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 txtFileBase64 = nodeData.inputs?.txtFile as string
const metadata = nodeData.inputs?.metadata
@@ -72,25 +74,51 @@ class Text_DocumentLoaders implements INode {
let alldocs = []
let files: string[] = []
if (txtFileBase64.startsWith('[') && txtFileBase64.endsWith(']')) {
files = JSON.parse(txtFileBase64)
} else {
files = [txtFileBase64]
}
for (const file of files) {
const splitDataURI = file.split(',')
splitDataURI.pop()
const bf = Buffer.from(splitDataURI.pop() || '', 'base64')
const blob = new Blob([bf])
const loader = new TextLoader(blob)
if (textSplitter) {
const docs = await loader.loadAndSplit(textSplitter)
alldocs.push(...docs)
//FILE-STORAGE::["CONTRIBUTING.md","LICENSE.md","README.md"]
if (txtFileBase64.startsWith('FILE-STORAGE::')) {
const fileName = txtFileBase64.replace('FILE-STORAGE::', '')
if (fileName.startsWith('[') && fileName.endsWith(']')) {
files = JSON.parse(fileName)
} 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 blob = new Blob([fileData])
const loader = new TextLoader(blob)
if (textSplitter) {
const docs = await loader.loadAndSplit(textSplitter)
alldocs.push(...docs)
} else {
const docs = await loader.load()
alldocs.push(...docs)
}
}
} else {
if (txtFileBase64.startsWith('[') && txtFileBase64.endsWith(']')) {
files = JSON.parse(txtFileBase64)
} else {
files = [txtFileBase64]
}
for (const file of files) {
const splitDataURI = file.split(',')
splitDataURI.pop()
const bf = Buffer.from(splitDataURI.pop() || '', 'base64')
const blob = new Blob([bf])
const loader = new TextLoader(blob)
if (textSplitter) {
const docs = await loader.loadAndSplit(textSplitter)
alldocs.push(...docs)
} else {
const docs = await loader.load()
alldocs.push(...docs)
}
}
}