Sometimes I want to steer the AI in a specific direction. And specially in storytelling contexts, where you most likely dislike only one or two parts of the response, I feel that it would be easier to edit that part and let the model fill in from there. As in, If I edit the response "X Y Z" to "X Z" I should be able to send the edited response to the model to let it finish it as "X Z Y"
I think a nice solution would be to have a "Generate From Here" button next to the save button when editing a response.
Originally created by @Ufuk-a on GitHub (Feb 14, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/734
Originally assigned to: @tjbck on GitHub.
Sometimes I want to steer the AI in a specific direction. And specially in storytelling contexts, where you most likely dislike only one or two parts of the response, I feel that it would be easier to edit that part and let the model fill in from there. As in, If I edit the response "X Y Z" to "X Z" I should be able to send the edited response to the model to let it finish it as "X Z Y"
I think a nice solution would be to have a "Generate From Here" button next to the save button when editing a response.
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 @Ufuk-a on GitHub (Feb 14, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/734
Originally assigned to: @tjbck on GitHub.
Sometimes I want to steer the AI in a specific direction. And specially in storytelling contexts, where you most likely dislike only one or two parts of the response, I feel that it would be easier to edit that part and let the model fill in from there. As in, If I edit the response "X Y Z" to "X Z" I should be able to send the edited response to the model to let it finish it as "X Z Y"
I think a nice solution would be to have a "Generate From Here" button next to the save button when editing a response.