diff --git a/transforms/language/pdf2parquet/python/src/pdf2parquet_transform.py b/transforms/language/pdf2parquet/python/src/pdf2parquet_transform.py
index 0f5de10c0..20ef49dc3 100644
--- a/transforms/language/pdf2parquet/python/src/pdf2parquet_transform.py
+++ b/transforms/language/pdf2parquet/python/src/pdf2parquet_transform.py
@@ -24,6 +24,7 @@
 import filetype
 import pandas as pd
 import pyarrow as pa
+import numpy as np
 from data_processing.transform import AbstractBinaryTransform, TransformConfiguration
 from data_processing.utils import TransformUtils, get_logger, str2bool
 from data_processing.utils.cli_utils import CLIArgumentProvider
@@ -237,7 +238,7 @@ def _convert_pdf2parquet(
         num_pages = len(doc.pages)
         num_tables = len(doc.tables)
         num_doc_elements = len(doc.texts)
-        document_hash = doc.origin.binary_hash
+        document_hash = np.uint64(doc.origin.binary_hash)
 
         self._update_metrics(num_pages=num_pages, elapse_time=elapse_time)
 
diff --git a/transforms/language/pdf2parquet/python/test-data/expected/archive1.parquet b/transforms/language/pdf2parquet/python/test-data/expected/archive1.parquet
index 907fb3803..f68ff66e1 100644
Binary files a/transforms/language/pdf2parquet/python/test-data/expected/archive1.parquet and b/transforms/language/pdf2parquet/python/test-data/expected/archive1.parquet differ
diff --git a/transforms/language/pdf2parquet/python/test-data/expected/metadata.json b/transforms/language/pdf2parquet/python/test-data/expected/metadata.json
index b9a535098..330ee3a5c 100644
--- a/transforms/language/pdf2parquet/python/test-data/expected/metadata.json
+++ b/transforms/language/pdf2parquet/python/test-data/expected/metadata.json
@@ -5,8 +5,8 @@
     "job name": "pdf2parquet",
     "job type": "pure python",
     "job id": "job_id",
-    "start_time": "2024-10-29 14:17:59",
-    "end_time": "2024-10-29 14:18:05",
+    "start_time": "2024-11-11 21:04:30",
+    "end_time": "2024-11-11 21:04:38",
     "status": "success"
   },
   "code": {
@@ -15,6 +15,7 @@
     "path": "path"
   },
   "job_input_params": {
+    "batch_size": -1,
     "artifacts_path": null,
     "contents_type": "text/markdown",
     "do_table_structure": true,
@@ -28,23 +29,25 @@
     "random_samples": -1,
     "files_to_use": [
       ".pdf",
+      ".docx",
+      ".pptx",
       ".zip"
     ],
     "num_processors": 0
   },
   "execution_stats": {
-    "cpus": 16.8,
+    "cpus": 21.1,
     "gpus": 0,
-    "memory": 31.22,
+    "memory": 32.09,
     "object_store": 0,
-    "execution time, min": 0.108
+    "execution time, min": 0.139
   },
   "job_output_stats": {
     "source_files": 2,
     "source_size": 605137,
     "result_files": 2,
-    "result_size": 33044,
-    "processing_time": 6.478,
+    "result_size": 32939,
+    "processing_time": 5.596,
     "nrows": 3,
     "nsuccess": 3,
     "nfail": 0,
diff --git a/transforms/language/pdf2parquet/python/test-data/expected/redp5110-ch1.parquet b/transforms/language/pdf2parquet/python/test-data/expected/redp5110-ch1.parquet
index 39613b1d1..17a7cf950 100644
Binary files a/transforms/language/pdf2parquet/python/test-data/expected/redp5110-ch1.parquet and b/transforms/language/pdf2parquet/python/test-data/expected/redp5110-ch1.parquet differ
diff --git a/transforms/language/pdf2parquet/python/test-data/expected_batch/metadata.json b/transforms/language/pdf2parquet/python/test-data/expected_batch/metadata.json
index f8f9ad71a..32023e56a 100644
--- a/transforms/language/pdf2parquet/python/test-data/expected_batch/metadata.json
+++ b/transforms/language/pdf2parquet/python/test-data/expected_batch/metadata.json
@@ -5,8 +5,8 @@
     "job name": "pdf2parquet",
     "job type": "pure python",
     "job id": "job_id",
-    "start_time": "2024-10-31 13:14:39",
-    "end_time": "2024-10-31 13:16:41",
+    "start_time": "2024-11-11 21:06:08",
+    "end_time": "2024-11-11 21:06:14",
     "status": "success"
   },
   "code": {
@@ -36,22 +36,22 @@
     "num_processors": 0
   },
   "execution_stats": {
-    "cpus": 39.0,
+    "cpus": 21.5,
     "gpus": 0,
-    "memory": 29.87,
+    "memory": 32.19,
     "object_store": 0,
-    "execution time, min": 2.029
+    "execution time, min": 0.1
   },
   "job_output_stats": {
     "source_files": 2,
     "source_size": 605137,
     "result_files": 1,
-    "processing_time": 3.888,
+    "processing_time": 3.353,
     "nrows": 3,
     "nsuccess": 3,
     "nfail": 0,
     "nskip": 0,
-    "result_size": 27200
+    "result_size": 27147
   },
   "source": {
     "name": "/Users/dol/codes/data-prep-kit/transforms/language/pdf2parquet/python/test-data/input",
diff --git a/transforms/language/pdf2parquet/python/test-data/expected_batch/redp5110-ch1.parquet b/transforms/language/pdf2parquet/python/test-data/expected_batch/redp5110-ch1.parquet
index 3e9ba12c7..c29b5db0e 100644
Binary files a/transforms/language/pdf2parquet/python/test-data/expected_batch/redp5110-ch1.parquet and b/transforms/language/pdf2parquet/python/test-data/expected_batch/redp5110-ch1.parquet differ
diff --git a/transforms/language/pdf2parquet/python/test-data/expected_json/archive1.parquet b/transforms/language/pdf2parquet/python/test-data/expected_json/archive1.parquet
index 7f34e1ba8..42b0a245d 100644
Binary files a/transforms/language/pdf2parquet/python/test-data/expected_json/archive1.parquet and b/transforms/language/pdf2parquet/python/test-data/expected_json/archive1.parquet differ
diff --git a/transforms/language/pdf2parquet/python/test-data/expected_json/metadata.json b/transforms/language/pdf2parquet/python/test-data/expected_json/metadata.json
index 04bec2b88..ed05c6b34 100644
--- a/transforms/language/pdf2parquet/python/test-data/expected_json/metadata.json
+++ b/transforms/language/pdf2parquet/python/test-data/expected_json/metadata.json
@@ -5,8 +5,8 @@
     "job name": "pdf2parquet",
     "job type": "pure python",
     "job id": "job_id",
-    "start_time": "2024-10-29 14:20:01",
-    "end_time": "2024-10-29 14:20:07",
+    "start_time": "2024-11-11 21:05:31",
+    "end_time": "2024-11-11 21:05:36",
     "status": "success"
   },
   "code": {
@@ -15,6 +15,7 @@
     "path": "path"
   },
   "job_input_params": {
+    "batch_size": -1,
     "artifacts_path": null,
     "contents_type": "application/json",
     "do_table_structure": true,
@@ -28,23 +29,25 @@
     "random_samples": -1,
     "files_to_use": [
       ".pdf",
+      ".docx",
+      ".pptx",
       ".zip"
     ],
     "num_processors": 0
   },
   "execution_stats": {
-    "cpus": 18.0,
+    "cpus": 21.4,
     "gpus": 0,
-    "memory": 30.77,
+    "memory": 32.33,
     "object_store": 0,
-    "execution time, min": 0.105
+    "execution time, min": 0.096
   },
   "job_output_stats": {
     "source_files": 2,
     "source_size": 605137,
     "result_files": 2,
-    "result_size": 22953,
-    "processing_time": 6.282,
+    "result_size": 22850,
+    "processing_time": 3.229,
     "nrows": 3,
     "nsuccess": 3,
     "nfail": 0,
diff --git a/transforms/language/pdf2parquet/python/test-data/expected_json/redp5110-ch1.parquet b/transforms/language/pdf2parquet/python/test-data/expected_json/redp5110-ch1.parquet
index 32905aa74..0f4bda73e 100644
Binary files a/transforms/language/pdf2parquet/python/test-data/expected_json/redp5110-ch1.parquet and b/transforms/language/pdf2parquet/python/test-data/expected_json/redp5110-ch1.parquet differ
diff --git a/transforms/language/pdf2parquet/python/test-data/expected_md_no_table_no_ocr/archive1.parquet b/transforms/language/pdf2parquet/python/test-data/expected_md_no_table_no_ocr/archive1.parquet
index 9fec2cd2d..32bfa6d00 100644
Binary files a/transforms/language/pdf2parquet/python/test-data/expected_md_no_table_no_ocr/archive1.parquet and b/transforms/language/pdf2parquet/python/test-data/expected_md_no_table_no_ocr/archive1.parquet differ
diff --git a/transforms/language/pdf2parquet/python/test-data/expected_md_no_table_no_ocr/metadata.json b/transforms/language/pdf2parquet/python/test-data/expected_md_no_table_no_ocr/metadata.json
index bf5c9e12a..e8a3894bf 100644
--- a/transforms/language/pdf2parquet/python/test-data/expected_md_no_table_no_ocr/metadata.json
+++ b/transforms/language/pdf2parquet/python/test-data/expected_md_no_table_no_ocr/metadata.json
@@ -5,8 +5,8 @@
     "job name": "pdf2parquet",
     "job type": "pure python",
     "job id": "job_id",
-    "start_time": "2024-10-29 14:19:30",
-    "end_time": "2024-10-29 14:19:33",
+    "start_time": "2024-11-11 21:05:04",
+    "end_time": "2024-11-11 21:05:06",
     "status": "success"
   },
   "code": {
@@ -15,6 +15,7 @@
     "path": "path"
   },
   "job_input_params": {
+    "batch_size": -1,
     "artifacts_path": null,
     "contents_type": "text/markdown",
     "do_table_structure": false,
@@ -28,23 +29,25 @@
     "random_samples": -1,
     "files_to_use": [
       ".pdf",
+      ".docx",
+      ".pptx",
       ".zip"
     ],
     "num_processors": 0
   },
   "execution_stats": {
-    "cpus": 17.3,
+    "cpus": 21.6,
     "gpus": 0,
-    "memory": 28.85,
+    "memory": 29.57,
     "object_store": 0,
-    "execution time, min": 0.043
+    "execution time, min": 0.041
   },
   "job_output_stats": {
     "source_files": 2,
     "source_size": 605137,
     "result_files": 2,
-    "result_size": 29659,
-    "processing_time": 2.554,
+    "result_size": 29555,
+    "processing_time": 1.997,
     "nrows": 3,
     "nsuccess": 3,
     "nfail": 0,
diff --git a/transforms/language/pdf2parquet/python/test-data/expected_md_no_table_no_ocr/redp5110-ch1.parquet b/transforms/language/pdf2parquet/python/test-data/expected_md_no_table_no_ocr/redp5110-ch1.parquet
index 69bc4e421..db8b58790 100644
Binary files a/transforms/language/pdf2parquet/python/test-data/expected_md_no_table_no_ocr/redp5110-ch1.parquet and b/transforms/language/pdf2parquet/python/test-data/expected_md_no_table_no_ocr/redp5110-ch1.parquet differ
diff --git a/transforms/language/pdf2parquet/ray/test-data/expected/archive1.parquet b/transforms/language/pdf2parquet/ray/test-data/expected/archive1.parquet
index 907fb3803..f68ff66e1 100644
Binary files a/transforms/language/pdf2parquet/ray/test-data/expected/archive1.parquet and b/transforms/language/pdf2parquet/ray/test-data/expected/archive1.parquet differ
diff --git a/transforms/language/pdf2parquet/ray/test-data/expected/metadata.json b/transforms/language/pdf2parquet/ray/test-data/expected/metadata.json
index b9a535098..330ee3a5c 100644
--- a/transforms/language/pdf2parquet/ray/test-data/expected/metadata.json
+++ b/transforms/language/pdf2parquet/ray/test-data/expected/metadata.json
@@ -5,8 +5,8 @@
     "job name": "pdf2parquet",
     "job type": "pure python",
     "job id": "job_id",
-    "start_time": "2024-10-29 14:17:59",
-    "end_time": "2024-10-29 14:18:05",
+    "start_time": "2024-11-11 21:04:30",
+    "end_time": "2024-11-11 21:04:38",
     "status": "success"
   },
   "code": {
@@ -15,6 +15,7 @@
     "path": "path"
   },
   "job_input_params": {
+    "batch_size": -1,
     "artifacts_path": null,
     "contents_type": "text/markdown",
     "do_table_structure": true,
@@ -28,23 +29,25 @@
     "random_samples": -1,
     "files_to_use": [
       ".pdf",
+      ".docx",
+      ".pptx",
       ".zip"
     ],
     "num_processors": 0
   },
   "execution_stats": {
-    "cpus": 16.8,
+    "cpus": 21.1,
     "gpus": 0,
-    "memory": 31.22,
+    "memory": 32.09,
     "object_store": 0,
-    "execution time, min": 0.108
+    "execution time, min": 0.139
   },
   "job_output_stats": {
     "source_files": 2,
     "source_size": 605137,
     "result_files": 2,
-    "result_size": 33044,
-    "processing_time": 6.478,
+    "result_size": 32939,
+    "processing_time": 5.596,
     "nrows": 3,
     "nsuccess": 3,
     "nfail": 0,
diff --git a/transforms/language/pdf2parquet/ray/test-data/expected/redp5110-ch1.parquet b/transforms/language/pdf2parquet/ray/test-data/expected/redp5110-ch1.parquet
index 39613b1d1..17a7cf950 100644
Binary files a/transforms/language/pdf2parquet/ray/test-data/expected/redp5110-ch1.parquet and b/transforms/language/pdf2parquet/ray/test-data/expected/redp5110-ch1.parquet differ