Add more nodes for agents, loaders

2026-06-28 23:01:09 +03:00 · 2023-04-10 13:56:44 +01:00
parent 05c86ff9c5
commit 58e06718d1
57 changed files with 1584 additions and 89 deletions
@@ -0,0 +1,90 @@
+import { INode, INodeData, INodeParams } from '../../../src/Interface'
+
+class Pdf_DocumentLoaders implements INode {
+    label: string
+    name: string
+    description: string
+    type: string
+    icon: string
+    category: string
+    baseClasses: string[]
+    inputs: INodeParams[]
+
+    constructor() {
+        this.label = 'Pdf File'
+        this.name = 'pdfFile'
+        this.type = 'PDF'
+        this.icon = 'pdf.svg'
+        this.category = 'Document Loaders'
+        this.description = `Load data from PDF files`
+        this.inputs = [
+            {
+                label: 'Pdf File',
+                name: 'pdfFile',
+                type: 'file',
+                fileType: '.pdf'
+            },
+            {
+                label: 'Text Splitter',
+                name: 'textSplitter',
+                type: 'TextSplitter',
+                optional: true
+            },
+            {
+                label: 'Usage',
+                name: 'usage',
+                type: 'options',
+                options: [
+                    {
+                        label: 'One document per page',
+                        name: 'perPage'
+                    },
+                    {
+                        label: 'One document per file',
+                        name: 'perFile'
+                    }
+                ],
+                default: 'perPage'
+            }
+        ]
+    }
+
+    async getBaseClasses(): Promise<string[]> {
+        return ['Document']
+    }
+
+    async init(nodeData: INodeData): Promise<any> {
+        const { PDFLoader } = await import('langchain/document_loaders')
+
+        const textSplitter = nodeData.inputs?.textSplitter
+        const pdfFileBase64 = nodeData.inputs?.pdfFile as string
+        const usage = nodeData.inputs?.usage as string
+
+        const splitDataURI = pdfFileBase64.split(',')
+        splitDataURI.pop()
+        const bf = Buffer.from(splitDataURI.pop() || '', 'base64')
+        const blob = new Blob([bf])
+
+        if (usage === 'perFile') {
+            const loader = new PDFLoader(blob, { splitPages: false })
+            if (textSplitter) {
+                const docs = await loader.loadAndSplit(textSplitter)
+                return docs
+            } else {
+                const docs = await loader.load()
+                return docs
+            }
+        } else {
+            const loader = new PDFLoader(blob)
+            if (textSplitter) {
+                const docs = await loader.loadAndSplit(textSplitter)
+                return docs
+            } else {
+                const docs = await loader.load()
+                return docs
+            }
+        }
+    }
+}
+
+module.exports = { nodeClass: Pdf_DocumentLoaders }
@@ -0,0 +1,7 @@
+<svg xmlns="http://www.w3.org/2000/svg" class="icon icon-tabler icon-tabler-pdf" width="24" height="24" viewBox="0 0 24 24" stroke-width="2" stroke="currentColor" fill="none" stroke-linecap="round" stroke-linejoin="round">
+   <path stroke="none" d="M0 0h24v24H0z" fill="none"></path>
+   <path d="M10 8v8h2a2 2 0 0 0 2 -2v-4a2 2 0 0 0 -2 -2h-2z"></path>
+   <path d="M3 12h2a2 2 0 1 0 0 -4h-2v8"></path>
+   <path d="M17 12h3"></path>
+   <path d="M21 8h-4v8"></path>
+</svg>