feat: add PDFMathTranslate converter for PDF translation with mathematical content

- Introduced PDFMathTranslate converter to handle PDF translations while preserving mathematical formulas.
- Updated Dockerfile to include necessary dependencies and pre-download models during build.
- Enhanced README.md to document the new converter and its features.
- Added tests for PDFMathTranslate to ensure correct functionality and error handling.
This commit is contained in:
Your Name 2026-01-21 14:31:19 +08:00
parent 5322f85721
commit d943771f36
7 changed files with 864 additions and 40 deletions

View file

@ -26,6 +26,7 @@ import { convert as convertVcf, properties as propertiesVcf } from "./vcf";
import { convert as convertxelatex, properties as propertiesxelatex } from "./xelatex";
import { convert as convertMarkitdown, properties as propertiesMarkitdown } from "./markitdown";
import { convert as convertMineru, properties as propertiesMineru } from "./mineru";
import { convert as convertPDFMathTranslate, properties as propertiesPDFMathTranslate } from "./pdfmathtranslate";
// This should probably be reconstructed so that the functions are not imported instead the functions hook into this to make the converters more modular
@ -142,6 +143,10 @@ const properties: Record<
properties: propertiesMineru,
converter: convertMineru,
},
PDFMathTranslate: {
properties: propertiesPDFMathTranslate,
converter: convertPDFMathTranslate,
},
};
function chunks<T>(arr: T[], size: number): T[][] {