feat: Added "document parser" OCR strategy

[dlew]

Pull Request Template

Summary

The document parser uses libraries to parse the text out of known document types. This lets LibreChat handle some complex document types without having to use a secondary service (like Mistral or standing up a RAG API server).

To enable the document parser, set the ocr strategy to "document_parser" in librechat.yaml.

We now support:

• PDFs using pdfjs
• DOCX using mammoth
• XLS/XLSX using SheetJS

(The associated packages were also added to the project.)

Here's a documentation update PR as well.

Change Type

Please delete any irrelevant options.

• New feature (non-breaking change which adds functionality)
• This change requires a documentation update (here)

Testing

I have added automated tests for most cases (the exception being PDFs, as getting Jest to work with ECMAScript modules would be a big lift just for this one small PR).

I also manually tested uploading PDFs, Word documents, and Excel sheets to LibreChat as text, to make sure they are parsed out.

Test Configuration:

• Enable ocr agent capability in librechat.yaml:

  agents:
   capabilities:
     - "ocr"
  

• Set ocr strategy to document_parser:

  ocr:
    strategy: "document_parser"
  

Checklist

Please delete any irrelevant options.

• My code adheres to this project's style guidelines
• I have performed a self-review of my own code
• I have commented in any complex areas of my code
• I have made pertinent documentation changes
• My changes do not introduce new warnings
• I have written tests demonstrating that my changes are effective or that my feature works
• Local unit tests pass with my changes
• A pull request for updating the documentation has been submitted (here).