mirror of
https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git
synced 2025-08-01 04:01:59 +08:00
5038552ed9
What problem does this PR solve? When creating or updating datasets with custom embedding models (e.g., Ollama), the validation logic was too restrictive and prevented valid models from being used. The previous implementation would reject valid custom models if they weren't in the predefined list, even when they existed in TenantLLMService. Changes: - Simplify and improve the embedding model validation flow in create/update endpoints - Check TenantLLMService for custom models before rejecting - Make validation logic more consistent between create and update operations ### What problem does this PR solve? This fix allows users to successfully create and update datasets with custom embedding models while maintaining proper validation checks. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) --------- Co-authored-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com> Co-authored-by: liuhua <10215101452@stu.ecnu.edu.cn>