Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add
broker
andewallet
schema (and data):broker
has camelCased table/column names and a standard prefix for all column names from the same table.broker
also avoids the user of FOREIGN KEY/REFERENCESewallet
contains a transactional tech/e-commerce company's schema.ewallet
has a schema nameconsumer_div.
prepended to each table's name, and uses REFERENCESTogether with the earlier 2 schema:
car_dealership
has a sales-ish inventory schema that mimic a sales function in a companyderm_treatment
mimics a pharmaceutical company tracking clinical trials and various experimental treatments. It contains cohort-style data in a wide-formatWe also sparsified the descriptions for the
car_dealership
schema to avoid excessively long contexts with redundant information.Added tests to check for the number of columns for each schema.
Did a test on the number of tokens (using codellama's tokenizer) required to tokenize the sql (without the insert statements, and not using the json):
And here are the number of tokens required to tokenize the glossary: