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
Hi there, I was going through some of the config options and ended up having to read the code to understand them enough. A few options that I was looking at were path, keyword, and hybrid. While I worked out more about all of these, I'd love to see things like:
What's the default value?
What do various settings imply?
eg, keyword = True implies that a defaults should not be used for the model (code)
eg, path = None in combination with keyword = True or defaults = False will disable semantic search (same code as above)
What does hybrid with different combinations of keyword and path?
Also, I don't know if this is a txtai or pytorch flag, but I found PYTORCH_MPS_DISABLE referenced in the txtai code and this was really important for my team in dealing with an mps memory issue. Particularly if this is a txtai flag, it'd be great to have it documented.
The text was updated successfully, but these errors were encountered:
Hi there, I was going through some of the config options and ended up having to read the code to understand them enough. A few options that I was looking at were
path
,keyword
, andhybrid
. While I worked out more about all of these, I'd love to see things like:keyword
=True
implies that a defaults should not be used for the model (code)path
=None
in combination withkeyword
=True
ordefaults
=False
will disable semantic search (same code as above)hybrid
with different combinations ofkeyword
andpath
?Also, I don't know if this is a txtai or pytorch flag, but I found
PYTORCH_MPS_DISABLE
referenced in the txtai code and this was really important for my team in dealing with an mps memory issue. Particularly if this is a txtai flag, it'd be great to have it documented.The text was updated successfully, but these errors were encountered: