dtamind-components
Version:
Apps integration for Dtamind. Contain Nodes and Credentials.
120 lines • 4.51 kB
JavaScript
;
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