-
Notifications
You must be signed in to change notification settings - Fork 48
docs: deprecate default model in TextEmbedddingGenerator
, GeminiTextGenerator
, and other bigframes.ml.llm
classes
#1570
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
Conversation
f6c59f4
to
1e9fd7a
Compare
1e9fd7a
to
c72346a
Compare
c72346a
to
3c77d3c
Compare
3c77d3c
to
81cb659
Compare
failing notebook is not relevant to this change, please help me with the review @tswast @shobsi @GarrettWu |
TextEmbedddingGenerator
, GeminiTextGenerator
, and other bigframes.ml.llm
classes
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.
FYI: I updated the PR title to reflect what we're doing in a way the user would understand.
81cb659
to
b58fa9c
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.
Looks good, thank you!
Let's make sure these code paths are covered by tests, such as by adding unit tests that check that the warning is issued at construction time.
For example:
python-bigquery-dataframes/tests/unit/ml/test_matrix_factorization.py
Lines 49 to 65 in b03e44f
def test_decomposition_mf_invalid_feedback_type_raises(): | |
feedback_type = "explimp" | |
with pytest.raises( | |
ValueError, | |
match="Expected feedback_type to be `explicit` or `implicit`.", | |
): | |
decomposition.MatrixFactorization( | |
# Intentionally pass in the wrong type. This will fail if the user is using | |
# a type checker, but we can't assume that everyone is doing so, especially | |
# not in notebook environments. | |
num_factors=16, | |
feedback_type=feedback_type, # type: ignore | |
user_col="user_id", | |
item_col="item_col", | |
rating_col="rating_col", | |
l2_reg=9.83, | |
) |
but in this case, use pytest.warns
instead.
b58fa9c
to
cb1b0c4
Compare
May I suggest the title: chore: warn if default llm is used in |
@shobsi We don't want to use |
Ack, |
docs: add remove default model warning, default LLM model will be removed for Bigframes 3.0