Skip to content

fix: context list handling #474

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: context list handling #474

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
11 changes: 8 additions & 3 deletions src/openlayer/lib/core/base_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,9 @@ class OpenlayerModel(abc.ABC):
def run_from_cli(self) -> None:
"""Run the model from the command line."""
parser = argparse.ArgumentParser(description="Run data through a model.")
parser.add_argument("--dataset-path", type=str, required=True, help="Path to the dataset")
parser.add_argument(
"--dataset-path", type=str, required=True, help="Path to the dataset"
)
parser.add_argument(
"--output-dir",
type=str,
Expand Down Expand Up @@ -85,7 +87,9 @@ def run_batch_from_df(self, df: pd.DataFrame) -> Tuple[pd.DataFrame, dict]:
# Filter row_dict to only include keys that are valid parameters
# for the 'run' method
row_dict = row.to_dict()
filtered_kwargs = {k: v for k, v in row_dict.items() if k in run_signature.parameters}
filtered_kwargs = {
k: v for k, v in row_dict.items() if k in run_signature.parameters
}

# Call the run method with filtered kwargs
output = self.run(**filtered_kwargs)
Expand All @@ -108,7 +112,8 @@ def run_batch_from_df(self, df: pd.DataFrame) -> Tuple[pd.DataFrame, dict]:
if "tokens" in processed_trace:
df.at[index, "tokens"] = processed_trace["tokens"]
if "context" in processed_trace:
df.at[index, "context"] = processed_trace["context"]
# Convert the context list to a string to avoid pandas issues
df.at[index, "context"] = json.dumps(processed_trace["context"])

config = {
"outputColumnName": "output",
Expand Down