Does the code indexing feature support multiple languages?

[sfz009900]

What problem does this proposed feature solve?

For example, if I index the code, and then I ask a question in Chinese, such as "查找一下用户登陆的相关代码", will there be a different language problem in the vector search? This suggests that "登陆" is not found directly.

But I seem to be OK with asking questions in English.

Describe the proposed solution in detail

It's not a bug, I didn't even check if the language difference exists, just a question :)

Technical considerations or implementation details (optional)

No response

Describe alternatives considered (if any)

No response

Additional Context & Mockups

No response

Proposal Checklist

• I have searched existing Issues and Discussions to ensure this proposal is not a duplicate.
• This proposal is for a specific, actionable change intended for implementation (not a general idea).
• I understand that this proposal requires review and approval before any development work begins.

Are you interested in implementing this feature if approved?

• Yes, I would like to contribute to implementing this feature.

[hannesrudolph]

@daniel-lxs

[daniel-lxs]

To whoever takes this issue, The way to solve this is by modifying the tool description for codebase_search to always generate a query in English regardless of the user language.

Something like: Always generate the query in English regardless of the user's language

Since the code is in English it will only find semantic similarities when searching in English.