Skip to content

Fix assignment of template field in __init__ in weaviate #36908

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
potiuk merged 1 commit into from
Jan 20, 2024
Merged

Fix assignment of template field in __init__ in weaviate #36908

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
10 changes: 5 additions & 5 deletions airflow/providers/weaviate/hooks/weaviate.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -183,7 +183,7 @@ def create_schema(self, schema_json: dict[str, Any] | str) -> None:
client.schema.create(schema_json)

@staticmethod
def _convert_dataframe_to_list(data: list[dict[str, Any]] | pd.DataFrame) -> list[dict[str, Any]]:
def _convert_dataframe_to_list(data: list[dict[str, Any]] | pd.DataFrame | None) -> list[dict[str, Any]]:
"""Helper function to convert dataframe to list of dicts.

In scenario where Pandas isn't installed and we pass data as a list of dictionaries, importing
Expand Down Expand Up @@ -382,7 +382,7 @@ def check_subset_of_schema(self, classes_objects: list) -> bool:
def batch_data(
self,
class_name: str,
data: list[dict[str, Any]] | pd.DataFrame,
data: list[dict[str, Any]] | pd.DataFrame | None,
batch_config_params: dict[str, Any] | None = None,
vector_col: str = "Vector",
uuid_col: str = "id",
Expand All @@ -401,7 +401,7 @@ def batch_data(
:param retry_attempts_per_object: number of time to try in case of failure before giving up.
:param tenant: The tenant to which the object will be added.
"""
data = self._convert_dataframe_to_list(data)
converted_data = self._convert_dataframe_to_list(data)
total_results = 0
error_results = 0
insertion_errors: list = []
Expand Down Expand Up @@ -437,7 +437,7 @@ def _process_batch_errors(

self.log.info(
"Total Objects %s / Objects %s successfully inserted and Objects %s had errors.",
len(data),
len(converted_data),
total_results,
error_results,
)
Expand All @@ -460,7 +460,7 @@ def _process_batch_errors(
client.batch.configure(**batch_config_params)
with client.batch as batch:
# Batch import all data
for index, data_obj in enumerate(data):
for index, data_obj in enumerate(converted_data):
for attempt in Retrying(
stop=stop_after_attempt(retry_attempts_per_object),
retry=(
Expand Down
7 changes: 3 additions & 4 deletions airflow/providers/weaviate/operators/weaviate.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,17 +74,16 @@ def __init__(
self.input_json = input_json
self.uuid_column = uuid_column
self.tenant = tenant
if input_data is not None:
self.input_data = input_data
elif input_json is not None:
self.input_data = input_data
if (self.input_data is None) and (input_json is not None):
warnings.warn(
"Passing 'input_json' to WeaviateIngestOperator is deprecated and"
" you should use 'input_data' instead",
AirflowProviderDeprecationWarning,
stacklevel=2,
)
self.input_data = input_json
else:
elif self.input_data is None and input_json is None:
raise TypeError("Either input_json or input_data is required")

@cached_property
Expand Down