sij/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2024-11-23 23:48:56 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 16

Improve mode description given to LLM when determining how to respond.

Browse source 
Currently experiencing difficulty instruction following when an image is shared. It's more likely to try and output an image. Update to make a clearer distinction.
This commit is contained in:
sabaimran 2024-10-19 20:35:32 -07:00
parent 545259e308
commit cb6b3ec1e9
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
src/khoj/utils/helpers.py
View file

@ -350,9 +350,9 @@ tool_descriptions_for_llm = {
}
mode_descriptions_for_llm = {
ConversationCommand.Image: "Use this if the user is requesting you to generate a picture based on their description.",
ConversationCommand.Image: "Use this if the user is requesting you to create a new picture based on their description.",
ConversationCommand.Automation: "Use this if you are confident the user is requesting a response at a scheduled date, time and frequency",
ConversationCommand.Text: "Use this if the other response modes don't seem to fit the query.",
ConversationCommand.Text: "Use this if a normal text response would be sufficient for accurately responding to the query.",
}
mode_descriptions_for_agent = {