Flowise/packages/components/nodes/documentloaders/Notion/NotionFolder.ts

111 lines
3.6 KiB
TypeScript

import { omit } from 'lodash'
import { IDocument, INode, INodeData, INodeParams } from '../../../src/Interface'
import { TextSplitter } from 'langchain/text_splitter'
import { NotionLoader } from 'langchain/document_loaders/fs/notion'
class NotionFolder_DocumentLoaders implements INode {
label: string
name: string
version: number
description: string
type: string
icon: string
category: string
baseClasses: string[]
inputs: INodeParams[]
constructor() {
this.label = 'Notion Folder'
this.name = 'notionFolder'
this.version = 1.0
this.type = 'Document'
this.icon = 'notion-folder.svg'
this.category = 'Document Loaders'
this.description = 'Load data from the exported and unzipped Notion folder'
this.baseClasses = [this.type]
this.inputs = [
{
label: 'Notion Folder',
name: 'notionFolder',
type: 'string',
description: 'Get folder path',
placeholder: 'Paste folder path'
},
{
label: 'Text Splitter',
name: 'textSplitter',
type: 'TextSplitter',
optional: true
},
{
label: 'Additional Metadata',
name: 'metadata',
type: 'json',
description: 'Additional metadata to be added to the extracted documents',
optional: true,
additionalParams: true
},
{
label: 'Omit Metadata Keys',
name: 'omitMetadataKeys',
type: 'string',
rows: 4,
description:
'Each document loader comes with a default set of metadata keys that are extracted from the document. You can use this field to omit some of the default metadata keys. The value should be a list of keys, seperated by comma',
placeholder: 'key1, key2, key3.nestedKey1',
optional: true,
additionalParams: true
}
]
}
async init(nodeData: INodeData): Promise<any> {
const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
const notionFolder = nodeData.inputs?.notionFolder as string
const metadata = nodeData.inputs?.metadata
const _omitMetadataKeys = nodeData.inputs?.omitMetadataKeys as string
let omitMetadataKeys: string[] = []
if (_omitMetadataKeys) {
omitMetadataKeys = _omitMetadataKeys.split(',').map((key) => key.trim())
}
const loader = new NotionLoader(notionFolder)
let docs: IDocument[] = []
if (textSplitter) {
docs = await loader.loadAndSplit(textSplitter)
} else {
docs = await loader.load()
}
if (metadata) {
const parsedMetadata = typeof metadata === 'object' ? metadata : JSON.parse(metadata)
docs = docs.map((doc) => ({
...doc,
metadata: omit(
{
...doc.metadata,
...parsedMetadata
},
omitMetadataKeys
)
}))
} else {
docs = docs.map((doc) => ({
...doc,
metadata: omit(
{
...doc.metadata
},
omitMetadataKeys
)
}))
}
return docs
}
}
module.exports = { nodeClass: NotionFolder_DocumentLoaders }