From ed17c4c1b9c012d49dc213825013bef9a72f42ed Mon Sep 17 00:00:00 2001 From: Colin Jarvis Date: Wed, 11 Jan 2023 04:04:16 -0800 Subject: [PATCH] Added notes where users can consider adding thread pool to speed up upsert operation --- examples/vector_databases/Vector_db_introduction.ipynb | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/examples/vector_databases/Vector_db_introduction.ipynb b/examples/vector_databases/Vector_db_introduction.ipynb index 723dbe49..9eebfe0f 100644 --- a/examples/vector_databases/Vector_db_introduction.ipynb +++ b/examples/vector_databases/Vector_db_introduction.ipynb @@ -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')" @@ -841,13 +843,14 @@ " 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", " uuid = client.data_object.create(\n", " {\n", - " \"title\": articles[0],\n", - " \"content\": articles[1]\n", + " \"title\": articles[0],\n", + " \"content\": articles[1]\n", " },\n", " \"Article\",\n", " vector=articles[2]\n",