add unstructured

This commit is contained in:
Henry 2023-10-12 15:31:19 +01:00
parent c419274c06
commit 21b2ef7f1d
4 changed files with 212 additions and 0 deletions

View File

@ -0,0 +1,26 @@
import { INodeParams, INodeCredential } from '../src/Interface'
class UnstructuredApi implements INodeCredential {
label: string
name: string
version: number
description: string
inputs: INodeParams[]
constructor() {
this.label = 'Unstructured API'
this.name = 'unstructuredApi'
this.version = 1.0
this.description =
'Refer to <a target="_blank" href="https://unstructured.io/#get-api-key">official guide</a> on how to get api key on Unstructured'
this.inputs = [
{
label: 'API Key',
name: 'unstructuredAPIKey',
type: 'password'
}
]
}
}
module.exports = { credClass: UnstructuredApi }

View File

@ -0,0 +1,93 @@
import { ICommonObject, INode, INodeData, INodeParams } from '../../../src/Interface'
import { UnstructuredLoader, UnstructuredLoaderOptions } from 'langchain/document_loaders/fs/unstructured'
import { getCredentialData, getCredentialParam } from '../../../src/utils'
class UnstructuredFile_DocumentLoaders implements INode {
label: string
name: string
version: number
description: string
type: string
icon: string
category: string
baseClasses: string[]
credential: INodeParams
inputs: INodeParams[]
constructor() {
this.label = 'Unstructured File Loader'
this.name = 'unstructuredFileLoader'
this.version = 1.0
this.type = 'Document'
this.icon = 'unstructured.png'
this.category = 'Document Loaders'
this.description = 'Use Unstructured.io to load data from a file path'
this.baseClasses = [this.type]
this.credential = {
label: 'Connect Credential',
name: 'credential',
type: 'credential',
credentialNames: ['unstructuredApi'],
optional: true
}
this.inputs = [
{
label: 'File Path',
name: 'filePath',
type: 'string',
placeholder: ''
},
{
label: 'Unstructured API URL',
name: 'unstructuredAPIUrl',
description:
'Unstructured API URL. Read <a target="_blank" href="https://unstructured-io.github.io/unstructured/introduction.html#getting-started">more</a> on how to get started',
type: 'string',
default: 'http://localhost:8000/general/v0/general'
},
{
label: 'Metadata',
name: 'metadata',
type: 'json',
optional: true,
additionalParams: true
}
/*TODO Add Filter Options*/
]
}
async init(nodeData: INodeData, _: string, options: ICommonObject): Promise<any> {
const filePath = nodeData.inputs?.filePath as string
const unstructuredAPIUrl = nodeData.inputs?.unstructuredAPIUrl as string
const metadata = nodeData.inputs?.metadata
const obj: UnstructuredLoaderOptions = { apiUrl: unstructuredAPIUrl }
const credentialData = await getCredentialData(nodeData.credential ?? '', options)
const unstructuredAPIKey = getCredentialParam('unstructuredAPIKey', credentialData, nodeData)
if (unstructuredAPIKey) obj.apiKey = unstructuredAPIKey
const loader = new UnstructuredLoader(filePath, obj)
const 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: UnstructuredFile_DocumentLoaders }

View File

@ -0,0 +1,93 @@
import { ICommonObject, INode, INodeData, INodeParams } from '../../../src/Interface'
import { UnstructuredDirectoryLoader, UnstructuredLoaderOptions } from 'langchain/document_loaders/fs/unstructured'
import { getCredentialData, getCredentialParam } from '../../../src/utils'
class UnstructuredFolder_DocumentLoaders implements INode {
label: string
name: string
version: number
description: string
type: string
icon: string
category: string
baseClasses: string[]
credential: INodeParams
inputs: INodeParams[]
constructor() {
this.label = 'Unstructured Folder Loader'
this.name = 'unstructuredFolderLoader'
this.version = 1.0
this.type = 'Document'
this.icon = 'unstructured.png'
this.category = 'Document Loaders'
this.description = 'Use Unstructured.io to load data from a folder'
this.baseClasses = [this.type]
this.credential = {
label: 'Connect Credential',
name: 'credential',
type: 'credential',
credentialNames: ['unstructuredApi'],
optional: true
}
this.inputs = [
{
label: 'Folder Path',
name: 'folderPath',
type: 'string',
placeholder: ''
},
{
label: 'Unstructured API URL',
name: 'unstructuredAPIUrl',
description:
'Unstructured API URL. Read <a target="_blank" href="https://unstructured-io.github.io/unstructured/introduction.html#getting-started">more</a> on how to get started',
type: 'string',
default: 'http://localhost:8000/general/v0/general'
},
{
label: 'Metadata',
name: 'metadata',
type: 'json',
optional: true,
additionalParams: true
}
/*TODO Add Filter Options*/
]
}
async init(nodeData: INodeData, _: string, options: ICommonObject): Promise<any> {
const folderPath = nodeData.inputs?.folderPath as string
const unstructuredAPIUrl = nodeData.inputs?.unstructuredAPIUrl as string
const metadata = nodeData.inputs?.metadata
const obj: UnstructuredLoaderOptions = { apiUrl: unstructuredAPIUrl }
const credentialData = await getCredentialData(nodeData.credential ?? '', options)
const unstructuredAPIKey = getCredentialParam('unstructuredAPIKey', credentialData, nodeData)
if (unstructuredAPIKey) obj.apiKey = unstructuredAPIKey
const loader = new UnstructuredDirectoryLoader(folderPath, obj)
const 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: UnstructuredFolder_DocumentLoaders }

Binary file not shown.

After

Width:  |  Height:  |  Size: 16 KiB