I'd like to suggest the addition of an option that allows users to disable all time-related cutoffs (not just autosuggest) for slow local Large Language Models. This feature would greatly benefit users who work with intricate or resource-intensive tasks (locally).
By turning off the timeouts, users can ensure that their queries are not cut off prematurely due to timing constraints, resulting in more accurate and complete responses from the query. This would enhance the overall user experience for those who need to rely on longer or more complex interactions with the system.
I believe this enhancement would be valuable for Butterfish users and would appreciate your consideration of its implementation. Thank you for your continued work on improving the AI integration in our command-line environments.
tldr: Please add an argument to disable all time constraints, I don't understand much of the repo yet to do the change myself.
I'd like to suggest the addition of an option that allows users to disable all time-related cutoffs (not just autosuggest) for slow local Large Language Models. This feature would greatly benefit users who work with intricate or resource-intensive tasks (locally).
By turning off the timeouts, users can ensure that their queries are not cut off prematurely due to timing constraints, resulting in more accurate and complete responses from the query. This would enhance the overall user experience for those who need to rely on longer or more complex interactions with the system.
I believe this enhancement would be valuable for Butterfish users and would appreciate your consideration of its implementation. Thank you for your continued work on improving the AI integration in our command-line environments.
tldr: Please add an argument to disable all time constraints, I don't understand much of the repo yet to do the change myself.