You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
inputs=conversation.inputs
if conversation
else self._prepare_user_inputs(
user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
),
I have a workflow, and update it add some inputs passed to the workflow nodes.
It's works for the new conversation, but for the old conversations it always uses the conversation's inputs not app_config.variables.
It's designed for that?
In the chat-messages API, we can modify inputs to adapter the workflow. For example:
We can pass width=1024, height=768 for one chat and width = 1024 , height = 1024 for another chat.
But as the code now , if the conversation created we can not change it.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Self Checks
Content
https://github.com/langgenius/dify/blob/634b382a3d14e27a17e727d5a0311c8a87caafdc/api/core/app/apps/advanced_chat/app_generator.py#L143C13-L147C15
I have a workflow, and update it add some inputs passed to the workflow nodes.
It's works for the new conversation, but for the old conversations it always uses the conversation's inputs not app_config.variables.
It's designed for that?
In the chat-messages API, we can modify inputs to adapter the workflow. For example:
We can pass width=1024, height=768 for one chat and width = 1024 , height = 1024 for another chat.
But as the code now , if the conversation created we can not change it.
Beta Was this translation helpful? Give feedback.
All reactions