From 4435255b04332c4242fb1bb0640326b339d89db9 Mon Sep 17 00:00:00 2001 From: Rakesh Jain Date: Fri, 14 Nov 2025 20:03:09 +0000 Subject: [PATCH] Sample data sometimes fails --- be/app/lakeviewer.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/be/app/lakeviewer.py b/be/app/lakeviewer.py index 21eec4b..f433e56 100644 --- a/be/app/lakeviewer.py +++ b/be/app/lakeviewer.py @@ -6,6 +6,7 @@ import pandas as pd import pyarrow as pa import daft +from daft.context import get_context import humanize import pyarrow.compute as pc import numpy as np @@ -117,7 +118,7 @@ def get_sample_data(self, table, sql, limit=50): and "total-data-files" in curr_snapshot.summary.keys() and int(curr_snapshot.summary["total-data-files"]) > 200 ): - optimized_plan = df._builder.optimize()._builder.repr_ascii( + optimized_plan = df._builder.optimize(get_context().daft_execution_config)._builder.repr_ascii( simple=False ) logging.info(optimized_plan) @@ -256,4 +257,4 @@ def get_gcp_access_token(service_account_file, scopes): request = Request() credentials.refresh(request) # Forces token refresh if needed - return credentials \ No newline at end of file + return credentials