[Feature]: Multi-Language Support

[xjasonliu]

Feature Area

Ingestion (document processing, upload, Docling)

Problem Description

when trying to ingest a Chinese Document, got this error "'ascii' codec can't encode characters in position 0-10: ordinal not in range(128)", Any roadmap for multi-language support

Proposed Solution

Support UTF-8

Use Case

To handle multi language documents, and docling already can do that.

Alternatives Considered

No response

Priority

Critical for my use case

Additional Context

No response

Contribution

• I would be willing to help implement this feature.
• I can help test this feature once implemented.

Checklist

• I have searched existing issues and discussions to ensure this feature hasn't been requested before.