perf: password special chars;feat: llm paragraph;perf: chunk setting params;perf: text splitter worker (#4984)

* perf: password special chars

* feat: llm paragraph;perf: chunk setting params

* perf: text splitter worker

* perf: get rawtext buffer

* fix: test

* fix: test

* doc

* min chunk size
This commit is contained in:
Archer
2025-06-10 00:05:54 +08:00
committed by GitHub
parent 068918a9ee
commit 01ff56b42b
41 changed files with 546 additions and 448 deletions

View File

@@ -7,6 +7,7 @@ import { readDocsFile } from './extension/docx';
import { readPptxRawText } from './extension/pptx';
import { readXlsxRawText } from './extension/xlsx';
import { readCsvRawText } from './extension/csv';
import { workerResponse } from '../controller';
parentPort?.on('message', async (props: ReadRawTextProps<Uint8Array>) => {
const read = async (params: ReadRawTextByBuffer) => {
@@ -41,17 +42,16 @@ parentPort?.on('message', async (props: ReadRawTextProps<Uint8Array>) => {
};
try {
parentPort?.postMessage({
type: 'success',
workerResponse({
parentPort,
status: 'success',
data: await read(newProps)
});
} catch (error) {
console.log(error);
parentPort?.postMessage({
type: 'error',
workerResponse({
parentPort,
status: 'error',
data: error
});
}
process.exit();
});