Added notes where users can consider adding thread pool to speed up upsert operation

pull/1077/head
Colin Jarvis 2 years ago
parent 1912234327
commit ed17c4c1b9

@ -476,6 +476,7 @@
],
"source": [
"# Upsert content vectors in content namespace\n",
"# NOTE: Using a thread pool here can accelerate this upsert operation\n",
"print(\"Uploading vectors to content namespace..\")\n",
"for batch_df in df_batcher(article_df):\n",
" index.upsert(vectors=zip(batch_df.vector_id, batch_df.content_vector), namespace='content')"
@ -497,6 +498,7 @@
],
"source": [
"# Upsert title vectors in title namespace\n",
"# NOTE: Using a thread pool here can accelerate this upsert operation\n",
"print(\"Uploading vectors to title namespace..\")\n",
"for batch_df in df_batcher(article_df):\n",
" index.upsert(vectors=zip(batch_df.vector_id, batch_df.title_vector), namespace='title')"
@ -841,6 +843,7 @@
" data_objects.append((v['title'],v['text'],v['title_vector'],v['vector_id']))\n",
"\n",
"# Upsert into article schema\n",
"# NOTE: Using a thread pool here can accelerate this upsert operation\n",
"print(\"Uploading vectors to article schema..\")\n",
"uuids = []\n",
"for articles in data_objects:\n",

Loading…
Cancel
Save