added confluence document loader and html-to-text dependency

This commit is contained in:
Neeraj Bansal
2023-05-30 23:12:45 +05:30
parent b6308e2a5d
commit ac75215218
3 changed files with 122 additions and 1 deletions
@@ -0,0 +1,120 @@
import { INode, INodeData, INodeParams } from '../../../src/Interface'
import { TextSplitter } from 'langchain/text_splitter'
// import { GithubRepoLoader, GithubRepoLoaderParams } from 'langchain/document_loaders/web/github'
import { ConfluencePagesLoader, ConfluencePagesLoaderParams } from "langchain/document_loaders/web/confluence";
class Confluence_DocumentLoaders implements INode {
label: string
name: string
description: string
type: string
icon: string
category: string
baseClasses: string[]
inputs: INodeParams[]
constructor() {
this.label = 'Confluence'
this.name = 'confluence'
this.type = 'Document'
this.icon = 'confluence.png'
this.category = 'Document Loaders'
this.description = `Load data from a Confluence Document`
this.baseClasses = [this.type]
this.inputs = [
{
label: 'Text Splitter',
name: 'textSplitter',
type: 'TextSplitter',
optional: true
},
{
label: 'Username',
name: 'username',
type: 'string',
placeholder: '<CONFLUENCE_USERNAME>',
},
{
label: 'Access Token',
name: 'accessToken',
type: 'password',
placeholder: '<CONFLUENCE_ACCESS_TOKEN>',
},
{
label: 'Base URL',
name: 'baseUrl',
type: 'string',
placeholder: "https://example.atlassian.net/wiki"
},
{
label: 'Space Key',
name: 'spaceKey',
type: 'string',
placeholder: '~EXAMPLE362906de5d343d49dcdbae5dEXAMPLE'
},
{
label: 'Limit',
name: 'limit',
type: 'number',
default: 0,
optional: true
},
{
label: 'Metadata',
name: 'metadata',
type: 'json',
optional: true,
additionalParams: true
}
]
}
async init(nodeData: INodeData): Promise<any> {
const username = nodeData.inputs?.username as string
const accessToken = nodeData.inputs?.accessToken as string
const spaceKey = nodeData.inputs?.spaceKey as string
const baseUrl = nodeData.inputs?.baseUrl as string
const limit = nodeData.inputs?.limit as number
const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
const metadata = nodeData.inputs?.metadata
const options: ConfluencePagesLoaderParams = {
username,
accessToken,
baseUrl,
spaceKey,
limit
}
const loader = new ConfluencePagesLoader(options)
console.log('loader')
let docs = []
if (textSplitter) {
docs = await loader.loadAndSplit(textSplitter)
} else {
docs = await loader.load()
}
if (metadata) {
const parsedMetadata = typeof metadata === 'object' ? metadata : JSON.parse(metadata)
let finaldocs = []
for (const doc of docs) {
const newdoc = {
...doc,
metadata: {
...doc.metadata,
...parsedMetadata
}
}
finaldocs.push(newdoc)
}
return finaldocs
}
return docs
}
}
module.exports = { nodeClass: Confluence_DocumentLoaders }
Binary file not shown.

After

Width:  |  Height:  |  Size: 14 KiB

+2 -1
View File
@@ -38,7 +38,8 @@
"node-fetch": "^2.6.11", "node-fetch": "^2.6.11",
"pdf-parse": "^1.1.1", "pdf-parse": "^1.1.1",
"weaviate-ts-client": "^1.1.0", "weaviate-ts-client": "^1.1.0",
"ws": "^8.9.0" "ws": "^8.9.0",
"html-to-text": "^9.0.5"
}, },
"devDependencies": { "devDependencies": {
"@types/gulp": "4.0.9", "@types/gulp": "4.0.9",