UNPKG

dtamind-components

Version:

Apps integration for Dtamind. Contain Nodes and Credentials.

120 lines 4.51 kB
"use strict"; Object.defineProperty(exports, "__esModule", { value: true }); const lodash_1 = require("lodash"); const documents_1 = require("@langchain/core/documents"); const src_1 = require("../../../src"); class PlainText_DocumentLoaders { constructor() { this.label = 'Plain Text'; this.name = 'plainText'; this.version = 2.0; this.type = 'Document'; this.icon = 'plaintext.svg'; this.category = 'Document Loaders'; this.description = `Load data from plain text`; this.baseClasses = [this.type]; this.inputs = [ { label: 'Text', name: 'text', type: 'string', rows: 4, placeholder: 'Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua...' }, { label: 'Text Splitter', name: 'textSplitter', type: 'TextSplitter', optional: true }, { label: 'Additional Metadata', name: 'metadata', type: 'json', description: 'Additional metadata to be added to the extracted documents', optional: true, additionalParams: true }, { label: 'Omit Metadata Keys', name: 'omitMetadataKeys', type: 'string', rows: 4, description: 'Each document loader comes with a default set of metadata keys that are extracted from the document. You can use this field to omit some of the default metadata keys. The value should be a list of keys, seperated by comma. Use * to omit all metadata keys execept the ones you specify in the Additional Metadata field', placeholder: 'key1, key2, key3.nestedKey1', optional: true, additionalParams: true } ]; this.outputs = [ { label: 'Document', name: 'document', description: 'Array of document objects containing metadata and pageContent', baseClasses: [...this.baseClasses, 'json'] }, { label: 'Text', name: 'text', description: 'Concatenated string from pageContent of documents', baseClasses: ['string', 'json'] } ]; } async init(nodeData) { const textSplitter = nodeData.inputs?.textSplitter; const text = nodeData.inputs?.text; const metadata = nodeData.inputs?.metadata; const output = nodeData.outputs?.output; const _omitMetadataKeys = nodeData.inputs?.omitMetadataKeys; let omitMetadataKeys = []; if (_omitMetadataKeys) { omitMetadataKeys = _omitMetadataKeys.split(',').map((key) => key.trim()); } let docs = []; if (textSplitter) { docs.push(...(await textSplitter.createDocuments([text]))); } else { docs.push(new documents_1.Document({ pageContent: text })); } if (metadata) { const parsedMetadata = typeof metadata === 'object' ? metadata : JSON.parse(metadata); docs = docs.map((doc) => ({ ...doc, metadata: _omitMetadataKeys === '*' ? { ...parsedMetadata } : (0, lodash_1.omit)({ ...doc.metadata, ...parsedMetadata }, omitMetadataKeys) })); } else { docs = docs.map((doc) => ({ ...doc, metadata: _omitMetadataKeys === '*' ? {} : (0, lodash_1.omit)({ ...doc.metadata }, omitMetadataKeys) })); } if (output === 'document') { return docs; } else { let finaltext = ''; for (const doc of docs) { finaltext += `${doc.pageContent}\n`; } return (0, src_1.handleEscapeCharacters)(finaltext, false); } } } module.exports = { nodeClass: PlainText_DocumentLoaders }; //# sourceMappingURL=PlainText.js.map