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
The cache is working correctly for Python and languages which uses # as a character to start a comment. Languages that use // are not being registered in cache correctly. This is because the regex that we are using.
FIM Python request:
# Some context# my_path/my_file.py <-- Regex will match heredeffoo():
pass
FIM JS request
// Some context// my_path/my_file.js <-- Regex will not match here
...
The text was updated successfully, but these errors were encountered:
Closes: #405
The implemented cache was not working correctly because of the
way the context is added for FIM requests in other programming
languages which are not python. The context for the LLM is provided
as single line comments. In Python this means lines which start with
the character `#`. Other languages may have other starting sequence
for single line comments, e.g. Javascript uses `//`. This PR changes
the regex to detect the paths for other languages.
The cache is working correctly for Python and languages which uses
#
as a character to start a comment. Languages that use//
are not being registered in cache correctly. This is because the regex that we are using.FIM Python request:
FIM JS request
The text was updated successfully, but these errors were encountered: