[FEATURE]: Please add an independent vision model config line #31117

Activity

1. github-actions

   assigned

   nexxeln

   on Jun 6, 2026
2. github-actions commented on Jun 6, 2026

   

   github-actionsBot

   on Jun 6, 2026 – with GitHub Actions

   Contributor

   More actions

   This issue might be a duplicate of an existing issue. Please check:

   • [FEATURE]: Auto image-to-text transcription via multimodal model for non-multimodal providers #22828: [FEATURE]: Auto image-to-text transcription via multimodal model for non-multimodal providers — this request covers essentially the same use-case: configuring a separate vision-capable model to handle images when the primary model does not support vision input.

   If your request is different in a meaningful way, please clarify the distinction in a comment.

   👍React with 👍1Reacted by Zhengyuan Huang
3. Neclyon

   closed this as a duplicateof [FEATURE]: Auto image-to-text transcription via multimodal model for non-multimodal providers #22828 on Jun 6, 2026