[PR #20351] Improve CONVERSATION_TITLE_PROMPT to correctly handle Japanese and input #29371

Closed
opened 2026-02-21 20:45:25 -05:00 by yindo · 0 comments
Owner

Original Pull Request: https://github.com/langgenius/dify/pull/20351

State: closed
Merged: Yes


Summary

This PR improves the CONVERSATION_TITLE_PROMPT used for auto-generating conversation titles by enhancing support for Japanese input. Specifically, it addresses the issue where Japanese greetings such as "こんばんは!" were incorrectly producing Chinese output titles like "晚安问候😊".

Motivation

The existing prompt lacked clear Japanese examples, leading to incorrect language detection in multilingual models. This update:

  • Adds multiple examples for Japanese inputs, including casual greetings, questions, and context-rich messages
  • Balances the example set by reducing the number of Chinese cases
  • Strengthens the instruction to ensure output language matches the input, particularly for Japanese

These changes help ensure that users inputting Japanese receive natural, short, and correctly localized conversation titles.

Fixes #

Screenshots

Before After
"こんばんは!" → "晚安问候😊" "こんばんは!" → "こんばんはの挨拶😊"

Checklist

Important

Please review the checklist below before submitting your pull request.

  • This change requires a documentation update, included: Dify Document
  • I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
  • I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
  • I've updated the documentation accordingly.
  • I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods
**Original Pull Request:** https://github.com/langgenius/dify/pull/20351 **State:** closed **Merged:** Yes --- # Summary This PR improves the `CONVERSATION_TITLE_PROMPT` used for auto-generating conversation titles by enhancing support for Japanese input. Specifically, it addresses the issue where Japanese greetings such as "こんばんは!" were incorrectly producing Chinese output titles like "晚安问候😊". ### Motivation The existing prompt lacked clear Japanese examples, leading to incorrect language detection in multilingual models. This update: - Adds multiple examples for Japanese inputs, including casual greetings, questions, and context-rich messages - Balances the example set by reducing the number of Chinese cases - Strengthens the instruction to ensure output language matches the input, particularly for Japanese These changes help ensure that users inputting Japanese receive natural, short, and correctly localized conversation titles. Fixes #<issue number> # Screenshots | Before | After | |--------|-------| | "こんばんは!" → `"晚安问候😊"` | "こんばんは!" → `"こんばんはの挨拶😊"` | # Checklist > [!IMPORTANT] > Please review the checklist below before submitting your pull request. - [ ] This change requires a documentation update, included: [Dify Document](https://github.com/langgenius/dify-docs) - [x] I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!) - [x] I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change. - [x] I've updated the documentation accordingly. - [x] I ran `dev/reformat`(backend) and `cd web && npx lint-staged`(frontend) to appease the lint gods
yindo added the pull-request label 2026-02-21 20:45:25 -05:00
yindo closed this issue 2026-02-21 20:45:25 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#29371