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

import { omit } from 'lodash'
import { ICommonObject, IDocument, INode, INodeData, INodeParams } from '../../../src/Interface'
import { TextSplitter } from 'langchain/text_splitter'
import { NotionAPILoader, NotionAPILoaderOptions } from '@langchain/community/document_loaders/web/notionapi'
import { getCredentialData, getCredentialParam, handleEscapeCharacters, INodeOutputsValue } from '../../../src'

class NotionPage_DocumentLoaders implements INode {
    label: string
    name: string
    version: number
    description: string
    type: string
    icon: string
    category: string
    baseClasses: string[]
    credential: INodeParams
    inputs: INodeParams[]
    outputs: INodeOutputsValue[]

    constructor() {
        this.label = 'Notion Page'
        this.name = 'notionPage'
        this.version = 2.0
        this.type = 'Document'
        this.icon = 'notion-page.svg'
        this.category = 'Document Loaders'
        this.description = 'Load data from Notion Page (including child pages all as separate documents)'
        this.baseClasses = [this.type]
        this.credential = {
            label: 'Connect Credential',
            name: 'credential',
            type: 'credential',
            credentialNames: ['notionApi']
        }
        this.inputs = [
            {
                label: 'Text Splitter',
                name: 'textSplitter',
                type: 'TextSplitter',
                optional: true
            },
            {
                label: 'Notion Page Id',
                name: 'pageId',
                type: 'string',
                description:
                    'The last The 32 char hex in the url path. For example: https://www.notion.so/skarard/LangChain-Notion-API-b34ca03f219c4420a6046fc4bdfdf7b4, b34ca03f219c4420a6046fc4bdfdf7b4 is the Page ID'
            },
            {
                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. Use * to omit all metadata keys execept the ones you specify in the Additional Metadata field',
                placeholder: 'key1, key2, key3.nestedKey1',
                optional: true,
                additionalParams: true
            }
        ]
        this.outputs = [
            {
                label: 'Document',
                name: 'document',
                description: 'Array of document objects containing metadata and pageContent',
                baseClasses: [...this.baseClasses, 'json']
            },
            {
                label: 'Text',
                name: 'text',
                description: 'Concatenated string from pageContent of documents',
                baseClasses: ['string', 'json']
            }
        ]
    }

    async init(nodeData: INodeData, _: string, options: ICommonObject): Promise<any> {
        const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
        const pageId = nodeData.inputs?.pageId as string
        const metadata = nodeData.inputs?.metadata
        const _omitMetadataKeys = nodeData.inputs?.omitMetadataKeys as string
        const output = nodeData.outputs?.output as string

        let omitMetadataKeys: string[] = []
        if (_omitMetadataKeys) {
            omitMetadataKeys = _omitMetadataKeys.split(',').map((key) => key.trim())
        }

        const credentialData = await getCredentialData(nodeData.credential ?? '', options)
        const notionIntegrationToken = getCredentialParam('notionIntegrationToken', credentialData, nodeData)

        const obj: NotionAPILoaderOptions = {
            clientOptions: {
                auth: notionIntegrationToken
            },
            id: pageId,
            type: 'page'
        }
        const loader = new NotionAPILoader(obj)

        let docs: IDocument[] = []
        if (textSplitter) {
            docs = await loader.load()
            docs = await textSplitter.splitDocuments(docs)
        } else {
            docs = await loader.load()
        }

        if (metadata) {
            const parsedMetadata = typeof metadata === 'object' ? metadata : JSON.parse(metadata)
            docs = docs.map((doc) => ({
                ...doc,
                metadata:
                    _omitMetadataKeys === '*'
                        ? {
                              ...parsedMetadata
                          }
                        : omit(
                              {
                                  ...doc.metadata,
                                  ...parsedMetadata
                              },
                              omitMetadataKeys
                          )
            }))
        } else {
            docs = docs.map((doc) => ({
                ...doc,
                metadata:
                    _omitMetadataKeys === '*'
                        ? {}
                        : omit(
                              {
                                  ...doc.metadata
                              },
                              omitMetadataKeys
                          )
            }))
        }

        if (output === 'document') {
            return docs
        } else {
            let finaltext = ''
            for (const doc of docs) {
                finaltext += `${doc.pageContent}\n`
            }
            return handleEscapeCharacters(finaltext, false)
        }
    }
}

module.exports = { nodeClass: NotionPage_DocumentLoaders }