mirror of
https://github.com/farcasclaudiu/Flowise.git
synced 2026-06-24 19:00:50 +03:00
658fa3984e
* 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>
136 lines
4.5 KiB
TypeScript
136 lines
4.5 KiB
TypeScript
import { ICommonObject, INode, INodeData, INodeParams } from '../../../src/Interface'
|
|
import { TextSplitter } from 'langchain/text_splitter'
|
|
import { CSVLoader } from 'langchain/document_loaders/fs/csv'
|
|
import path from 'path'
|
|
import { getStoragePath } from '../../../src'
|
|
import fs from 'fs'
|
|
|
|
class Csv_DocumentLoaders implements INode {
|
|
label: string
|
|
name: string
|
|
version: number
|
|
description: string
|
|
type: string
|
|
icon: string
|
|
category: string
|
|
baseClasses: string[]
|
|
inputs: INodeParams[]
|
|
|
|
constructor() {
|
|
this.label = 'Csv File'
|
|
this.name = 'csvFile'
|
|
this.version = 1.0
|
|
this.type = 'Document'
|
|
this.icon = 'csv.svg'
|
|
this.category = 'Document Loaders'
|
|
this.description = `Load data from CSV files`
|
|
this.baseClasses = [this.type]
|
|
this.inputs = [
|
|
{
|
|
label: 'Csv File',
|
|
name: 'csvFile',
|
|
type: 'file',
|
|
fileType: '.csv'
|
|
},
|
|
{
|
|
label: 'Text Splitter',
|
|
name: 'textSplitter',
|
|
type: 'TextSplitter',
|
|
optional: true
|
|
},
|
|
{
|
|
label: 'Single Column Extraction',
|
|
name: 'columnName',
|
|
type: 'string',
|
|
description: 'Extracting a single column',
|
|
placeholder: 'Enter column name',
|
|
optional: true
|
|
},
|
|
{
|
|
label: 'Metadata',
|
|
name: 'metadata',
|
|
type: 'json',
|
|
optional: true,
|
|
additionalParams: true
|
|
}
|
|
]
|
|
}
|
|
|
|
async init(nodeData: INodeData, _: string, options: ICommonObject): Promise<any> {
|
|
const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
|
|
const csvFileBase64 = nodeData.inputs?.csvFile as string
|
|
const columnName = nodeData.inputs?.columnName as string
|
|
const metadata = nodeData.inputs?.metadata
|
|
|
|
let alldocs = []
|
|
let files: string[] = []
|
|
|
|
if (csvFileBase64.startsWith('FILE-STORAGE::')) {
|
|
const fileName = csvFileBase64.replace('FILE-STORAGE::', '')
|
|
if (fileName.startsWith('[') && fileName.endsWith(']')) {
|
|
files = JSON.parse(fileName)
|
|
} else {
|
|
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 CSVLoader(blob, columnName.trim().length === 0 ? undefined : columnName.trim())
|
|
|
|
if (textSplitter) {
|
|
const docs = await loader.loadAndSplit(textSplitter)
|
|
alldocs.push(...docs)
|
|
} else {
|
|
const docs = await loader.load()
|
|
alldocs.push(...docs)
|
|
}
|
|
}
|
|
} else {
|
|
if (csvFileBase64.startsWith('[') && csvFileBase64.endsWith(']')) {
|
|
files = JSON.parse(csvFileBase64)
|
|
} else {
|
|
files = [csvFileBase64]
|
|
}
|
|
|
|
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 CSVLoader(blob, columnName.trim().length === 0 ? undefined : columnName.trim())
|
|
|
|
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: Csv_DocumentLoaders }
|