We should be able to edit a models thoughts for the thinking models. Because lets say if we want a different response we can edit the response to modify that direction. With for example Deepseek-R1 we currently cannot edit its thoughts, the thoughts it currently has may cause issues when we want to guide its response a direction.
Originally created by @RealMrCactus on GitHub (Jan 28, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/9034
We should be able to edit a models thoughts for the thinking models. Because lets say if we want a different response we can edit the response to modify that direction. With for example Deepseek-R1 we currently cannot edit its thoughts, the thoughts it currently has may cause issues when we want to guide its response a direction.
If i understand correctly according to the documentation, this part of the model's response should not be sent to the server at all
<!-- gh-comment-id:2619826467 -->
@dpk-it commented on GitHub (Jan 28, 2025):
If i understand correctly according to the documentation, this part of the model's response should not be sent to the server at all
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @RealMrCactus on GitHub (Jan 28, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/9034
We should be able to edit a models thoughts for the thinking models. Because lets say if we want a different response we can edit the response to modify that direction. With for example Deepseek-R1 we currently cannot edit its thoughts, the thoughts it currently has may cause issues when we want to guide its response a direction.
@dpk-it commented on GitHub (Jan 28, 2025):
If i understand correctly according to the documentation, this part of the model's response should not be sent to the server at all