Pipeline should be improved to limit CPU usage on page renders

Author: jakep-allenai

olmocr/pipeline.py

@@ -14,7 +14,7 @@
 import sys
 import tempfile
 import time
-from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
+from concurrent.futures import ThreadPoolExecutor, as_completed
 from concurrent.futures.process import BrokenProcessPool
 from dataclasses import dataclass
 from functools import cache

olmocr/version.py

@@ -2,7 +2,7 @@
 _MINOR = "3"
 # On main and in a nightly release the patch should be one ahead of the last
 # released build.
-_PATCH = "1"
+_PATCH = "2"
 # This is mainly for nightly builds which have the suffix ".dev$DATE". See
 # https://semver.org/#is-v123-a-semantic-version for the semantics.
 _SUFFIX = ""