def get_online_features(
self,
feature_refs: List[str],
entity_rows: List[Dict[str, Any]],
project: Optional[str] = None,
) -> OnlineResponse:
"""
Retrieves the latest online feature data from Feast Serving.
Args:
feature_refs: List of feature references that will be returned for each entity.
Each feature reference should have the following format:
"feature_table:feature" where "feature_table" & "feature" refer to
the feature and feature table names respectively.
Only the feature name is required.
entity_rows: A list of dictionaries where each key-value is an entity-name, entity-value pair.
project: Optionally specify the the project override. If specified, uses given project for retrieval.
Overrides the projects specified in Feature References if also are specified.
Returns:
GetOnlineFeaturesResponse containing the feature data in records.
Each EntityRow provided will yield one record, which contains
data fields with data value and field status metadata (if included).
Examples:
>>> from feast import Client
>>>
>>> feast_client = Client(core_url="localhost:6565", serving_url="localhost:6566")
>>> feature_refs = ["sales:daily_transactions"]
>>> entity_rows = [{"customer_id": 0},{"customer_id": 1}]
>>>
>>> online_response = feast_client.get_online_features(
>>> feature_refs, entity_rows, project="my_project")
>>> online_response_dict = online_response.to_dict()
>>> print(online_response_dict)
{'sales:daily_transactions': [1.1,1.2], 'sales:customer_id': [0,1]}
"""
if self._telemetry_enabled:
if self._telemetry_counter["get_online_features"] % 1000 == 0:
log_usage(
"get_online_features",
self._telemetry_id,
datetime.utcnow(),
self.version(sdk_only=True),
)
self._telemetry_counter["get_online_features"] += 1
try:
response = self._serving_service.GetOnlineFeaturesV2(
GetOnlineFeaturesRequestV2(
features=_build_feature_references(
feature_ref_strs=feature_refs),
entity_rows=_infer_online_entity_rows(entity_rows),
project=project if project is not None else self.project,
),
timeout=self._config.getint(opt.GRPC_CONNECTION_TIMEOUT),
metadata=self._get_grpc_metadata(),
)
except grpc.RpcError as e:
raise grpc.RpcError(e.details())
response = OnlineResponse(response)
return response
def get_online_features(
self, feature_refs: List[str], entity_rows: List[Dict[str, Any]],
) -> OnlineResponse:
"""
Retrieves the latest online feature data.
Args:
feature_refs: List of feature references that will be returned for each entity.
Each feature reference should have the following format:
"feature_table:feature" where "feature_table" & "feature" refer to
the feature and feature table names respectively.
Only the feature name is required.
entity_rows: A list of dictionaries where each key-value is an entity-name, entity-value pair.
Returns:
OnlineResponse containing the feature data in records.
Examples:
>>> from feast import FeatureStore
>>>
>>> store = FeatureStore(repo_path="...")
>>> feature_refs = ["sales:daily_transactions"]
>>> entity_rows = [{"customer_id": 0},{"customer_id": 1}]
>>>
>>> online_response = store.get_online_features(
>>> feature_refs, entity_rows, project="my_project")
>>> online_response_dict = online_response.to_dict()
>>> print(online_response_dict)
{'sales:daily_transactions': [1.1,1.2], 'sales:customer_id': [0,1]}
"""
response = self._get_online_features(
feature_refs=feature_refs,
entity_rows=_infer_online_entity_rows(entity_rows),
project=self.config.project,
)
return OnlineResponse(response)
def get_online_features(
self,
feature_refs: List[str],
entity_rows: List[Dict[str, Any]],
) -> OnlineResponse:
"""
Retrieves the latest online feature data.
Note: This method will download the full feature registry the first time it is run. If you are using a
remote registry like GCS or S3 then that may take a few seconds. The registry remains cached up to a TTL
duration (which can be set to infinitey). If the cached registry is stale (more time than the TTL has
passed), then a new registry will be downloaded synchronously by this method. This download may
introduce latency to online feature retrieval. In order to avoid synchronous downloads, please call
refresh_registry() prior to the TTL being reached. Remember it is possible to set the cache TTL to
infinity (cache forever).
Args:
feature_refs: List of feature references that will be returned for each entity.
Each feature reference should have the following format:
"feature_table:feature" where "feature_table" & "feature" refer to
the feature and feature table names respectively.
Only the feature name is required.
entity_rows: A list of dictionaries where each key-value is an entity-name, entity-value pair.
Returns:
OnlineResponse containing the feature data in records.
Examples:
>>> from feast import FeatureStore
>>>
>>> store = FeatureStore(repo_path="...")
>>> feature_refs = ["sales:daily_transactions"]
>>> entity_rows = [{"customer_id": 0},{"customer_id": 1}]
>>>
>>> online_response = store.get_online_features(
>>> feature_refs, entity_rows, project="my_project")
>>> online_response_dict = online_response.to_dict()
>>> print(online_response_dict)
{'sales:daily_transactions': [1.1,1.2], 'sales:customer_id': [0,1]}
"""
response = self._get_online_features(
feature_refs=feature_refs,
entity_rows=_infer_online_entity_rows(entity_rows),
project=self.config.project,
)
return OnlineResponse(response)
def get_online_features(
self,
feature_refs: List[str],
entity_rows: List[Dict[str, Any]],
) -> OnlineResponse:
"""
Retrieves the latest online feature data.
Note: This method will download the full feature registry the first time it is run. If you are using a
remote registry like GCS or S3 then that may take a few seconds. The registry remains cached up to a TTL
duration (which can be set to infinitey). If the cached registry is stale (more time than the TTL has
passed), then a new registry will be downloaded synchronously by this method. This download may
introduce latency to online feature retrieval. In order to avoid synchronous downloads, please call
refresh_registry() prior to the TTL being reached. Remember it is possible to set the cache TTL to
infinity (cache forever).
Args:
feature_refs: List of feature references that will be returned for each entity.
Each feature reference should have the following format:
"feature_table:feature" where "feature_table" & "feature" refer to
the feature and feature table names respectively.
Only the feature name is required.
entity_rows: A list of dictionaries where each key-value is an entity-name, entity-value pair.
Returns:
OnlineResponse containing the feature data in records.
Examples:
>>> from feast import FeatureStore
>>>
>>> store = FeatureStore(repo_path="...")
>>> feature_refs = ["sales:daily_transactions"]
>>> entity_rows = [{"customer_id": 0},{"customer_id": 1}]
>>>
>>> online_response = store.get_online_features(
>>> feature_refs, entity_rows)
>>> online_response_dict = online_response.to_dict()
>>> print(online_response_dict)
{'sales:daily_transactions': [1.1,1.2], 'sales:customer_id': [0,1]}
"""
provider = self._get_provider()
entities = self.list_entities(allow_cache=True)
entity_name_to_join_key_map = {}
for entity in entities:
entity_name_to_join_key_map[entity.name] = entity.join_key
join_key_rows = []
for row in entity_rows:
join_key_row = {}
for entity_name, entity_value in row.items():
try:
join_key = entity_name_to_join_key_map[entity_name]
except KeyError:
raise Exception(
f"Entity {entity_name} does not exist in project {self.project}"
)
join_key_row[join_key] = entity_value
join_key_rows.append(join_key_row)
entity_row_proto_list = _infer_online_entity_rows(join_key_rows)
union_of_entity_keys = []
result_rows: List[GetOnlineFeaturesResponse.FieldValues] = []
for entity_row_proto in entity_row_proto_list:
union_of_entity_keys.append(_entity_row_to_key(entity_row_proto))
result_rows.append(_entity_row_to_field_values(entity_row_proto))
all_feature_views = self._registry.list_feature_views(
project=self.project, allow_cache=True)
grouped_refs = _group_refs(feature_refs, all_feature_views)
for table, requested_features in grouped_refs:
entity_keys = _get_table_entity_keys(table, union_of_entity_keys,
entity_name_to_join_key_map)
read_rows = provider.online_read(
project=self.project,
table=table,
entity_keys=entity_keys,
)
for row_idx, read_row in enumerate(read_rows):
row_ts, feature_data = read_row
result_row = result_rows[row_idx]
if feature_data is None:
for feature_name in requested_features:
feature_ref = f"{table.name}__{feature_name}"
result_row.statuses[
feature_ref] = GetOnlineFeaturesResponse.FieldStatus.NOT_FOUND
else:
for feature_name in feature_data:
feature_ref = f"{table.name}__{feature_name}"
if feature_name in requested_features:
result_row.fields[feature_ref].CopyFrom(
feature_data[feature_name])
result_row.statuses[
feature_ref] = GetOnlineFeaturesResponse.FieldStatus.PRESENT
return OnlineResponse(
GetOnlineFeaturesResponse(field_values=result_rows))
def get_online_features(
self,
features: Union[List[str], FeatureService],
entity_rows: List[Dict[str, Any]],
feature_refs: Optional[List[str]] = None,
full_feature_names: bool = False,
) -> OnlineResponse:
"""
Retrieves the latest online feature data.
Note: This method will download the full feature registry the first time it is run. If you are using a
remote registry like GCS or S3 then that may take a few seconds. The registry remains cached up to a TTL
duration (which can be set to infinity). If the cached registry is stale (more time than the TTL has
passed), then a new registry will be downloaded synchronously by this method. This download may
introduce latency to online feature retrieval. In order to avoid synchronous downloads, please call
refresh_registry() prior to the TTL being reached. Remember it is possible to set the cache TTL to
infinity (cache forever).
Args:
features: List of feature references that will be returned for each entity.
Each feature reference should have the following format:
"feature_table:feature" where "feature_table" & "feature" refer to
the feature and feature table names respectively.
Only the feature name is required.
entity_rows: A list of dictionaries where each key-value is an entity-name, entity-value pair.
Returns:
OnlineResponse containing the feature data in records.
Raises:
Exception: No entity with the specified name exists.
Examples:
Materialize all features into the online store over the interval
from 3 hours ago to 10 minutes ago, and then retrieve these online features.
>>> from feast import FeatureStore, RepoConfig
>>> fs = FeatureStore(repo_path="feature_repo")
>>> online_response = fs.get_online_features(
... features=[
... "driver_hourly_stats:conv_rate",
... "driver_hourly_stats:acc_rate",
... "driver_hourly_stats:avg_daily_trips",
... ],
... entity_rows=[{"driver_id": 1001}, {"driver_id": 1002}, {"driver_id": 1003}, {"driver_id": 1004}],
... )
>>> online_response_dict = online_response.to_dict()
"""
_feature_refs = self._get_features(features, feature_refs)
provider = self._get_provider()
entities = self.list_entities(allow_cache=True)
entity_name_to_join_key_map = {}
for entity in entities:
entity_name_to_join_key_map[entity.name] = entity.join_key
join_key_rows = []
for row in entity_rows:
join_key_row = {}
for entity_name, entity_value in row.items():
try:
join_key = entity_name_to_join_key_map[entity_name]
except KeyError:
raise EntityNotFoundException(entity_name, self.project)
join_key_row[join_key] = entity_value
join_key_rows.append(join_key_row)
entity_row_proto_list = _infer_online_entity_rows(join_key_rows)
union_of_entity_keys = []
result_rows: List[GetOnlineFeaturesResponse.FieldValues] = []
for entity_row_proto in entity_row_proto_list:
union_of_entity_keys.append(_entity_row_to_key(entity_row_proto))
result_rows.append(_entity_row_to_field_values(entity_row_proto))
all_feature_views = self._registry.list_feature_views(
project=self.project, allow_cache=True)
_validate_feature_refs(_feature_refs, full_feature_names)
grouped_refs = _group_feature_refs(_feature_refs, all_feature_views)
for table, requested_features in grouped_refs:
entity_keys = _get_table_entity_keys(table, union_of_entity_keys,
entity_name_to_join_key_map)
read_rows = provider.online_read(
config=self.config,
table=table,
entity_keys=entity_keys,
requested_features=requested_features,
)
for row_idx, read_row in enumerate(read_rows):
row_ts, feature_data = read_row
result_row = result_rows[row_idx]
if feature_data is None:
for feature_name in requested_features:
feature_ref = (f"{table.name}__{feature_name}"
if full_feature_names else feature_name)
result_row.statuses[
feature_ref] = GetOnlineFeaturesResponse.FieldStatus.NOT_FOUND
else:
for feature_name in feature_data:
feature_ref = (f"{table.name}__{feature_name}"
if full_feature_names else feature_name)
if feature_name in requested_features:
result_row.fields[feature_ref].CopyFrom(
feature_data[feature_name])
result_row.statuses[
feature_ref] = GetOnlineFeaturesResponse.FieldStatus.PRESENT
return OnlineResponse(
GetOnlineFeaturesResponse(field_values=result_rows))
def get_online_features(
self,
features: Union[List[str], FeatureService],
entity_rows: List[Dict[str, Any]],
feature_refs: Optional[List[str]] = None,
full_feature_names: bool = False,
) -> OnlineResponse:
"""
Retrieves the latest online feature data.
Note: This method will download the full feature registry the first time it is run. If you are using a
remote registry like GCS or S3 then that may take a few seconds. The registry remains cached up to a TTL
duration (which can be set to infinity). If the cached registry is stale (more time than the TTL has
passed), then a new registry will be downloaded synchronously by this method. This download may
introduce latency to online feature retrieval. In order to avoid synchronous downloads, please call
refresh_registry() prior to the TTL being reached. Remember it is possible to set the cache TTL to
infinity (cache forever).
Args:
features: List of feature references that will be returned for each entity.
Each feature reference should have the following format:
"feature_table:feature" where "feature_table" & "feature" refer to
the feature and feature table names respectively.
Only the feature name is required.
entity_rows: A list of dictionaries where each key-value is an entity-name, entity-value pair.
Returns:
OnlineResponse containing the feature data in records.
Raises:
Exception: No entity with the specified name exists.
Examples:
Materialize all features into the online store over the interval
from 3 hours ago to 10 minutes ago, and then retrieve these online features.
>>> from feast import FeatureStore, RepoConfig
>>> fs = FeatureStore(repo_path="feature_repo")
>>> online_response = fs.get_online_features(
... features=[
... "driver_hourly_stats:conv_rate",
... "driver_hourly_stats:acc_rate",
... "driver_hourly_stats:avg_daily_trips",
... ],
... entity_rows=[{"driver_id": 1001}, {"driver_id": 1002}, {"driver_id": 1003}, {"driver_id": 1004}],
... )
>>> online_response_dict = online_response.to_dict()
"""
_feature_refs = self._get_features(features, feature_refs)
all_feature_views = self._list_feature_views(allow_cache=True,
hide_dummy_entity=False)
all_on_demand_feature_views = self._registry.list_on_demand_feature_views(
project=self.project, allow_cache=True)
_validate_feature_refs(_feature_refs, full_feature_names)
grouped_refs, grouped_odfv_refs = _group_feature_refs(
_feature_refs, all_feature_views, all_on_demand_feature_views)
if len(grouped_odfv_refs) > 0:
log_event(UsageEvent.GET_ONLINE_FEATURES_WITH_ODFV)
feature_views = list(view for view, _ in grouped_refs)
entityless_case = DUMMY_ENTITY_NAME in [
entity_name for feature_view in feature_views
for entity_name in feature_view.entities
]
provider = self._get_provider()
entities = self._list_entities(allow_cache=True,
hide_dummy_entity=False)
entity_name_to_join_key_map = {}
for entity in entities:
entity_name_to_join_key_map[entity.name] = entity.join_key
needed_request_data_features = self._get_needed_request_data_features(
grouped_odfv_refs)
join_key_rows = []
request_data_features: Dict[str, List[Any]] = {}
# Entity rows may be either entities or request data.
for row in entity_rows:
join_key_row = {}
for entity_name, entity_value in row.items():
# Found request data
if entity_name in needed_request_data_features:
if entity_name not in request_data_features:
request_data_features[entity_name] = []
request_data_features[entity_name].append(entity_value)
continue
try:
join_key = entity_name_to_join_key_map[entity_name]
except KeyError:
raise EntityNotFoundException(entity_name, self.project)
join_key_row[join_key] = entity_value
if entityless_case:
join_key_row[DUMMY_ENTITY_ID] = DUMMY_ENTITY_VAL
if len(join_key_row) > 0:
# May be empty if this entity row was request data
join_key_rows.append(join_key_row)
if len(needed_request_data_features) != len(
request_data_features.keys()):
raise RequestDataNotFoundInEntityRowsException(
feature_names=needed_request_data_features)
entity_row_proto_list = _infer_online_entity_rows(join_key_rows)
union_of_entity_keys: List[EntityKeyProto] = []
result_rows: List[GetOnlineFeaturesResponse.FieldValues] = []
for entity_row_proto in entity_row_proto_list:
# Create a list of entity keys to filter down for each feature view at lookup time.
union_of_entity_keys.append(_entity_row_to_key(entity_row_proto))
# Also create entity values to append to the result
result_rows.append(_entity_row_to_field_values(entity_row_proto))
# Add more feature values to the existing result rows for the request data features
for feature_name, feature_values in request_data_features.items():
for row_idx, feature_value in enumerate(feature_values):
result_row = result_rows[row_idx]
result_row.fields[feature_name].CopyFrom(
python_value_to_proto_value(feature_value))
result_row.statuses[
feature_name] = GetOnlineFeaturesResponse.FieldStatus.PRESENT
for table, requested_features in grouped_refs:
self._populate_result_rows_from_feature_view(
entity_name_to_join_key_map,
full_feature_names,
provider,
requested_features,
result_rows,
table,
union_of_entity_keys,
)
initial_response = OnlineResponse(
GetOnlineFeaturesResponse(field_values=result_rows))
return self._augment_response_with_on_demand_transforms(
_feature_refs, full_feature_names, initial_response, result_rows)
