jim/openai-cookbook
1
0
Fork 0
mirror of https://github.com/james-m-jordan/openai-cookbook.git synced 2025-05-09 19:32:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Colin Jarvis 2023-01-11 04:04:16 -08:00
parent 21ca5a9555
commit fb18b7f6c2
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
examples/vector_databases/Vector_db_introduction.ipynb
View File

@ -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",