Merge pull request #19 from FlowiseAI/feature/CSVLoader

Feature/csv loader

packages/components/nodes/documentloaders/Csv/Csv.ts

@@ -0,0 +1,68 @@
+import { INode, INodeData, INodeParams } from '../../../src/Interface'
+import { TextSplitter } from 'langchain/text_splitter'
+import { CSVLoader } from 'langchain/document_loaders/fs/csv'
+
+class Csv_DocumentLoaders implements INode {
+    label: string
+    name: string
+    description: string
+    type: string
+    icon: string
+    category: string
+    baseClasses: string[]
+    inputs: INodeParams[]
+
+    constructor() {
+        this.label = 'Csv File'
+        this.name = 'csvFile'
+        this.type = 'Document'
+        this.icon = 'Csv.png'
+        this.category = 'Document Loaders'
+        this.description = `Load data from CSV files`
+        this.baseClasses = [this.type]
+        this.inputs = [
+            {
+                label: 'Csv File',
+                name: 'csvFile',
+                type: 'file',
+                fileType: '.csv'
+            },
+            {
+                label: 'Text Splitter',
+                name: 'textSplitter',
+                type: 'TextSplitter',
+                optional: true
+            },
+            {
+                label: 'Single Column Extraction',
+                name: 'columnName',
+                type: 'string',
+                description: 'Extracting a single column',
+                placeholder: 'Enter column name',
+                optional: true
+            }
+        ]
+    }
+
+    async init(nodeData: INodeData): Promise<any> {
+        const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
+        const csvFileBase64 = nodeData.inputs?.csvFile as string
+        const columnName = nodeData.inputs?.columnName as string
+        const splitDataURI = csvFileBase64.split(',')
+        splitDataURI.pop()
+        const bf = Buffer.from(splitDataURI.pop() || '', 'base64')
+
+        const blob = new Blob([bf])
+        const loader = new CSVLoader(blob, columnName.trim().length === 0 ? undefined : columnName.trim())
+
+        if (textSplitter) {
+            const docs = await loader.loadAndSplit(textSplitter)
+            return docs
+        } else {
+            const docs = await loader.load()
+            return docs
+        }
+    }
+}
+
+module.exports = { nodeClass: Csv_DocumentLoaders }

packages/components/package.json

@@ -21,6 +21,7 @@
         "@pinecone-database/pinecone": "^0.0.12",
         "axios": "^0.27.2",
         "chromadb": "^1.3.1",
+        "d3-dsv": "2",
         "dotenv": "^16.0.0",
         "express": "^4.17.3",
         "form-data": "^4.0.0",