Skip to content

feat: Move data source validation entrypoint to offline store #4197

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
jeremyary merged 2 commits into from
May 16, 2024
Merged

feat: Move data source validation entrypoint to offline store #4197

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3c1b255
move validate_data_source entrypoint to offline store
tokoko May 12, 2024
7488136
add validate_data_source to foo provider
tokoko May 12, 2024
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
14 changes: 14 additions & 0 deletions sdk/python/feast/infra/offline_stores/offline_store.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -351,3 +351,17 @@ def offline_write_batch(
to show progress.
"""
raise NotImplementedError

@staticmethod
def validate_data_source(
config: RepoConfig,
data_source: DataSource,
):
"""
Validates the underlying data source.

Args:
config: Configuration object used to configure a feature store.
data_source: DataSource object that needs to be validated
"""
data_source.validate(config=config)
8 changes: 8 additions & 0 deletions sdk/python/feast/infra/passthrough_provider.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@

from feast import importer
from feast.batch_feature_view import BatchFeatureView
from feast.data_source import DataSource
from feast.entity import Entity
from feast.feature_logging import FeatureServiceLoggingSource
from feast.feature_service import FeatureService
Expand Down Expand Up @@ -383,3 +384,10 @@ def retrieve_feature_service_logs(
start_date=make_tzaware(start_date),
end_date=make_tzaware(end_date),
)

def validate_data_source(
self,
config: RepoConfig,
data_source: DataSource,
):
self.offline_store.validate_data_source(config=config, data_source=data_source)
16 changes: 16 additions & 0 deletions sdk/python/feast/infra/provider.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
from tqdm import tqdm

from feast import FeatureService, errors
from feast.data_source import DataSource
from feast.entity import Entity
from feast.feature_view import FeatureView
from feast.importer import import_class
Expand Down Expand Up @@ -351,6 +352,21 @@ def retrieve_online_documents(
"""
pass

@abstractmethod
def validate_data_source(
self,
config: RepoConfig,
data_source: DataSource,
):
"""
Validates the underlying data source.

Args:
config: Configuration object used to configure a feature store.
data_source: DataSource object that needs to be validated
"""
pass


def get_provider(config: RepoConfig) -> Provider:
if "." not in config.provider:
Expand Down
6 changes: 4 additions & 2 deletions sdk/python/feast/repo_operations.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -205,10 +205,11 @@ def plan(repo_config: RepoConfig, repo_path: Path, skip_source_validation: bool)
project, registry, repo, store = _prepare_registry_and_repo(repo_config, repo_path)

if not skip_source_validation:
provider = store._get_provider()
data_sources = [t.batch_source for t in repo.feature_views]
# Make sure the data source used by this feature view is supported by Feast
for data_source in data_sources:
data_source.validate(store.config)
provider.validate_data_source(store.config, data_source)

registry_diff, infra_diff, _ = store.plan(repo)
click.echo(registry_diff.to_string())
Expand Down Expand Up @@ -282,10 +283,11 @@ def apply_total_with_repo_instance(
skip_source_validation: bool,
):
if not skip_source_validation:
provider = store._get_provider()
data_sources = [t.batch_source for t in repo.feature_views]
# Make sure the data source used by this feature view is supported by Feast
for data_source in data_sources:
data_source.validate(store.config)
provider.validate_data_source(store.config, data_source)

# For each object in the registry, determine whether it should be kept or deleted.
(
Expand Down
8 changes: 8 additions & 0 deletions sdk/python/tests/foo_provider.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@
from tqdm import tqdm

from feast import Entity, FeatureService, FeatureView, RepoConfig
from feast.data_source import DataSource
from feast.infra.offline_stores.offline_store import RetrievalJob
from feast.infra.provider import Provider
from feast.infra.registry.base_registry import BaseRegistry
Expand Down Expand Up @@ -130,3 +131,10 @@ def retrieve_online_documents(
]
]:
return []

def validate_data_source(
self,
config: RepoConfig,
data_source: DataSource,
):
pass