-
Notifications
You must be signed in to change notification settings - Fork 509
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Configuration documentation update request #705
Milestone
Comments
I'll work to clarify as best I can and update when that's complete. |
davidmezzetti
added a commit
that referenced
this issue
Jun 4, 2024
Just made clarifications that I believe address the questions raised. |
Assuming these clarifications did the job. |
Yes thank you! Sorry for the delay; I was traveling and am just catching up on email. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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: