added gitBook integration

2026-06-29 01:01:11 +03:00 · 2023-06-30 22:33:11 +05:30
parent a5ccc991af
commit 894902ea83
2 changed files with 93 additions and 0 deletions
@@ -0,0 +1,82 @@
+import { INode, INodeData, INodeParams } from '../../../src/Interface'
+import { TextSplitter } from 'langchain/text_splitter'
+import { GitbookLoader } from 'langchain/document_loaders/web/gitbook'
+
+class Gitbook_DocumentLoaders implements INode {
+    label: string
+    name: string
+    description: string
+    type: string
+    icon: string
+    category: string
+    baseClasses: string[]
+    inputs?: INodeParams[]
+
+    constructor() {
+        this.label = 'GitBook'
+        this.name = 'gitbook'
+        this.type = 'Document'
+        this.icon = 'gitbook_logo.svg'
+        this.category = 'Document Loaders'
+        this.description = `Load data from GitBook`
+        this.baseClasses = [this.type]
+        this.inputs = [
+            {
+                label: 'Web Path',
+                name: 'webPath',
+                type: 'string',
+                placeholder: 'https://docs.gitbook.com/product-tour/navigation',
+                description: 'If want to load all paths from the GitBook provide only root path e.g.https://docs.gitbook.com/ '
+            },
+            {
+                label: 'Should Load All Paths',
+                name: 'shouldLoadAllPaths',
+                type: 'boolean',
+                description: 'Load from all paths in a given GitBook',
+                optional: true
+            },
+            {
+                label: 'Text Splitter',
+                name: 'textSplitter',
+                type: 'TextSplitter',
+                optional: true
+            },
+            {
+                label: 'Metadata',
+                name: 'metadata',
+                type: 'json',
+                optional: true,
+                additionalParams: true
+            }
+        ]
+    }
+    async init(nodeData: INodeData): Promise<any> {
+        const webPath = nodeData.inputs?.webPath as string
+        const shouldLoadAllPaths = nodeData.inputs?.shouldLoadAllPaths as boolean
+        const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
+        const metadata = nodeData.inputs?.metadata
+
+        const loader = shouldLoadAllPaths ? new GitbookLoader(webPath, { shouldLoadAllPaths }) : new GitbookLoader(webPath)
+
+        const docs = textSplitter ? await loader.loadAndSplit() : await loader.load()
+
+        if (metadata) {
+            const parsedMetadata = typeof metadata === 'object' ? metadata : JSON.parse(metadata)
+            return docs.map((doc) => {
+                return {
+                    ...doc,
+                    metadata: {
+                        ...doc.metadata,
+                        ...parsedMetadata
+                    }
+                }
+            })
+        }
+
+        return docs
+    }
+}
+
+module.exports = {
+    nodeClass: Gitbook_DocumentLoaders
+}