diff --git a/apis/python/src/tiledbvcf/dask_functions.py b/apis/python/src/tiledbvcf/dask_functions.py
index 9e0cd86be..71952b15e 100644
--- a/apis/python/src/tiledbvcf/dask_functions.py
+++ b/apis/python/src/tiledbvcf/dask_functions.py
@@ -1,4 +1,6 @@
 import dask
+
+dask.config.set({"dataframe.query-planning": False})
 import dask.dataframe
 
 import pyarrow as pa
diff --git a/apis/python/tests/test_dask.py b/apis/python/tests/test_dask.py
index 28259fa73..a1fd35a67 100644
--- a/apis/python/tests/test_dask.py
+++ b/apis/python/tests/test_dask.py
@@ -5,6 +5,8 @@
 import tiledbvcf
 
 import dask
+
+dask.config.set({"dataframe.query-planning": False})
 import dask.distributed
 
 # Directory containing this file
diff --git a/documentation/how-to/perform-distributed-queries-with-dask.md b/documentation/how-to/perform-distributed-queries-with-dask.md
index 673835824..1054892d5 100644
--- a/documentation/how-to/perform-distributed-queries-with-dask.md
+++ b/documentation/how-to/perform-distributed-queries-with-dask.md
@@ -10,6 +10,8 @@ You can use the `tiledbvcf` package's Dask integration to partition read operati
 import tiledbvcf
 import dask
 
+dask.config.set({'dataframe.query-planning': False})
+
 ds = tiledbvcf.Dataset('my-large-dataset', mode='r')
 dask_df = ds.read_dask(attrs=['sample_name', 'pos_start', 'pos_end'],
                        bed_file='very-large-bedfile.bed',