Multi Language Indexing & Retrieving Support?

Great work! I noticed that indexing and retrieving Chinese or Japanese documents shows low accuracy, is there any tricks to improve the performance without fine-tuning?

The issue names no files, tests, or entry points. Start by reproducing indexing and retrieval with Chinese and Japanese documents, then inspect the project’s retrieval configuration and documentation for non-fine-tuning options. Done should mean a documented, reproducible way to improve multilingual retrieval accuracy.

Written by the indexing model from the issue text.