-
-
Notifications
You must be signed in to change notification settings - Fork 19
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
literal workaround #777
literal workaround #777
Conversation
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #777 +/- ##
==========================================
- Coverage 60.92% 60.87% -0.06%
==========================================
Files 103 103
Lines 12556 12573 +17
==========================================
+ Hits 7650 7654 +4
- Misses 4906 4919 +13 ☔ View full report in Codecov by Sentry. |
7139864
to
53076d4
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Honestly, I believe you this works but it seems pretty hacky.
Superseded by #799 |
Since quotations
'"table"."name"'
is unconventional, the LLMs would hallucinate table names, i.e. drop quotations, and it would crash the Pydantic model, raising an invalid error. So, to workaround that, replaces everything except alphanumeric with_
which the LLM understands/copies well, then remaps it back to the original table name with all the special characters after the LLM chooses the table.