Skip to content

fix: Remove unnecessary pandas import from multimodal datasets preview module. #5957

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
copybara-service merged 1 commit into from
Oct 24, 2025
Merged

fix: Remove unnecessary pandas import from multimodal datasets preview module. #5957

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
9 changes: 5 additions & 4 deletions google/cloud/aiplatform/preview/datasets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,8 @@
#

import dataclasses
import io
import json
from typing import Dict, List, Optional, Tuple
import uuid

Expand All @@ -32,7 +34,6 @@
from vertexai import generative_models
from vertexai.generative_models import _generative_models
from vertexai.preview import prompts
import pandas

from google.protobuf import field_mask_pb2
from google.protobuf import struct_pb2
Expand Down Expand Up @@ -758,7 +759,7 @@ def from_bigquery(
def from_pandas(
cls,
*,
dataframe: pandas.DataFrame,
dataframe: "pandas.DataFrame", # type: ignore # noqa: F821
target_table_id: Optional[str] = None,
display_name: Optional[str] = None,
project: Optional[str] = None,
Expand Down Expand Up @@ -1077,15 +1078,15 @@ def from_gemini_request_jsonl(

jsonl_string = blob.download_as_text()
lines = [line.strip() for line in jsonl_string.splitlines() if line.strip()]
df = pandas.DataFrame(lines, columns=[request_column_name])
json_string = json.dumps({request_column_name: lines})

session_options = bigframes.BigQueryOptions(
credentials=credentials,
project=project,
location=location,
)
with bigframes.connect(session_options) as session:
temp_bigframes_df = session.read_pandas(df)
temp_bigframes_df = session.read_json(io.StringIO(json_string))
temp_bigframes_df[request_column_name] = bigframes.bigquery.parse_json(
temp_bigframes_df[request_column_name]
)
Expand Down
14 changes: 8 additions & 6 deletions tests/unit/aiplatform/test_multimodal_datasets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -584,9 +584,10 @@ def test_create_dataset_from_gemini_request_jsonl(
mock_bucket.blob.assert_called_once_with("test-file.jsonl")
mock_blob.download_as_text.assert_called_once()

pandas.testing.assert_frame_equal(
session_mock.read_pandas.call_args[0][0],
pandas.DataFrame({"requests": ["json_line_1", "json_line_2"]}),
session_mock.read_json.assert_called_once()
assert (
session_mock.read_json.call_args[0][0].getvalue()
== '{"requests": ["json_line_1", "json_line_2"]}'
)
bq_client_mock.return_value.copy_table.assert_called_once_with(
sources=mock.ANY,
Expand Down Expand Up @@ -636,9 +637,10 @@ def test_create_dataset_from_gemini_request_jsonl_without_target_table_id(
mock_bucket.blob.assert_called_once_with("test-file.jsonl")
mock_blob.download_as_text.assert_called_once()

pandas.testing.assert_frame_equal(
session_mock.read_pandas.call_args[0][0],
pandas.DataFrame({"requests": ["json_line_1", "json_line_2"]}),
session_mock.read_json.assert_called_once()
assert (
session_mock.read_json.call_args[0][0].getvalue()
== '{"requests": ["json_line_1", "json_line_2"]}'
)

# Assert that the default BQ dataset is created
Expand Down