We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
2 parents f6f3d49 + aaf252c commit 3745b99Copy full SHA for 3745b99
hivemind_etl/mediawiki/etl.py
@@ -103,7 +103,9 @@ def load(self, documents: list[Document]) -> None:
103
)
104
105
# Process batches in parallel using ThreadPoolExecutor
106
- batch_size = 1000
+ # TODO: Revert to larger batch size once llama-index loading issue is resolved
107
+ # See: https://github.com/TogetherCrew/temporal-worker-python/issues/60
108
+ batch_size = 1
109
batches = [documents[i:i + batch_size] for i in range(0, len(documents), batch_size)]
110
111
with ThreadPoolExecutor(max_workers=10) as executor:
0 commit comments