Skip to content

feat: Add missing pull_all_from_table_or_query to Clickhouse offline store #5667

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.

Sign up for GitHub

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

Merged
ntkathole merged 1 commit into from
Oct 15, 2025
+37 −1
Merged

feat: Add missing pull_all_from_table_or_query to Clickhouse offline store #5667

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 37 additions & 0 deletions sdk/python/feast/infra/offline_stores/contrib/clickhouse_offline_store/clickhouse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,6 +191,43 @@ def pull_latest_from_table_or_query(
on_demand_feature_views=None,
)

@staticmethod
def pull_all_from_table_or_query(
config: RepoConfig,
data_source: DataSource,
join_key_columns: List[str],
feature_name_columns: List[str],
timestamp_field: str,
created_timestamp_column: Optional[str] = None,
start_date: Optional[datetime] = None,
end_date: Optional[datetime] = None,
) -> RetrievalJob:
assert isinstance(config.offline_store, ClickhouseOfflineStoreConfig)
assert isinstance(data_source, ClickhouseSource)

from_expression = data_source.get_table_query_string()

timestamp_fields = [timestamp_field]

if created_timestamp_column:
timestamp_fields.append(created_timestamp_column)

field_string = ", ".join(
join_key_columns + feature_name_columns + timestamp_fields
)

query = f"""
SELECT {field_string}
FROM {from_expression}
WHERE {timestamp_field} BETWEEN parseDateTimeBestEffort('{start_date}') AND parseDateTimeBestEffort('{end_date}')
"""

return ClickhouseRetrievalJob(
query=query,
config=config,
full_feature_names=False,
)


class ClickhouseRetrievalJob(PostgreSQLRetrievalJob):
def _to_df_internal(self, timeout: Optional[int] = None) -> pd.DataFrame:
Expand Down
1 change: 0 additions & 1 deletion sdk/python/tests/integration/registration/test_universal_types.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -343,7 +343,6 @@ def offline_types_test_fixtures(request, environment):
if (
environment.data_source_creator.__class__.__name__
== "ClickhouseDataSourceCreator"
and config.feature_dtype in {"float", "datetime", "bool"}
and config.feature_is_list
and not config.has_empty_list
):
Expand Down
Loading