mirror of
https://github.com/james-m-jordan/openai-cookbook.git
synced 2025-05-09 19:32:38 +00:00
Refactor Qdrant notebooks (#556)
* Upgrade Qdrant to 1.3.0 * Adapt the descriptions and run the missing cells
This commit is contained in:
parent
090b1f95ce
commit
3ce532c03c
@ -42,10 +42,35 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 1,
|
||||
"id": "8d8810f9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-29T12:59:21.344233180Z",
|
||||
"start_time": "2023-06-29T12:59:00.815088712Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Collecting qdrant-client\r\n",
|
||||
" ...\r\n",
|
||||
"Successfully installed certifi-2023.5.7 grpcio-1.56.0 grpcio-tools-1.56.0 h11-0.14.0 h2-4.1.0 hpack-4.0.0 httpcore-0.17.2 httpx-0.24.1 hyperframe-6.0.1 numpy-1.25.0 portalocker-2.7.0 protobuf-4.23.3 pydantic-1.10.9 qdrant-client-1.3.1 typing-extensions-4.5.0 urllib3-1.26.16\r\n",
|
||||
"Collecting wget\r\n",
|
||||
" Using cached wget-3.2.zip (10 kB)\r\n",
|
||||
" Preparing metadata (setup.py) ... \u001B[?25ldone\r\n",
|
||||
"\u001B[?25hBuilding wheels for collected packages: wget\r\n",
|
||||
" Building wheel for wget (setup.py) ... \u001B[?25ldone\r\n",
|
||||
"\u001B[?25h Created wheel for wget: filename=wget-3.2-py3-none-any.whl size=9657 sha256=eb5f15f12150fc304e7b14973424f696fa8d95225772bc0cbc0b318bf92e04b9\r\n",
|
||||
" Stored in directory: /home/user/.cache/pip/wheels/04/5f/3e/46cc37c5d698415694d83f607f833f83f0149e49b3af9d0f38\r\n",
|
||||
"Successfully built wget\r\n",
|
||||
"Installing collected packages: wget\r\n",
|
||||
"Successfully installed wget-3.2\r\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# We'll need to install Qdrant client\n",
|
||||
"!pip install qdrant-client\n",
|
||||
@ -58,7 +83,12 @@
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "5be94df6",
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-29T13:00:32.715638041Z",
|
||||
"start_time": "2023-06-29T13:00:31.654032435Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import openai\n",
|
||||
@ -95,10 +125,24 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 5,
|
||||
"id": "5dff8b55",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-29T13:02:47.656128622Z",
|
||||
"start_time": "2023-06-29T13:00:39.079229873Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": "'vector_database_wikipedia_articles_embedded.zip'"
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"embeddings_url = 'https://cdn.openai.com/API/examples/data/vector_database_wikipedia_articles_embedded.zip'\n",
|
||||
"\n",
|
||||
@ -108,9 +152,14 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 6,
|
||||
"id": "21097972",
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-29T13:03:08.268413005Z",
|
||||
"start_time": "2023-06-29T13:02:47.626254476Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import zipfile\n",
|
||||
@ -120,9 +169,14 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 7,
|
||||
"id": "70bbd8ba",
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-29T13:03:28.291797292Z",
|
||||
"start_time": "2023-06-29T13:03:08.269033964Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"article_df = pd.read_csv('../data/vector_database_wikipedia_articles_embedded.csv')"
|
||||
@ -311,7 +365,7 @@
|
||||
"source": [
|
||||
"## Qdrant\n",
|
||||
"\n",
|
||||
"The last vector database we'll consider is **[Qdrant](https://qdrant.tech/)**. This is a high-performant vector search database written in Rust. It offers both on-premise and cloud version, but for the purposes of that example we're going to use the local deployment mode.\n",
|
||||
"**[Qdrant](https://qdrant.tech/)**. is a high-performant vector search database written in Rust. It offers both on-premise and cloud version, but for the purposes of that example we're going to use the local deployment mode.\n",
|
||||
"\n",
|
||||
"Setting everything up will require:\n",
|
||||
"- Spinning up a local instance of Qdrant\n",
|
||||
@ -646,9 +700,9 @@
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "vector_db_split",
|
||||
"name": "python3",
|
||||
"language": "python",
|
||||
"name": "vector_db_split"
|
||||
"display_name": "Python 3 (ipykernel)"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
|
@ -1,7 +1,7 @@
|
||||
version: '3.4'
|
||||
services:
|
||||
qdrant:
|
||||
image: qdrant/qdrant:v1.0.1
|
||||
image: qdrant/qdrant:v1.3.0
|
||||
restart: on-failure
|
||||
ports:
|
||||
- "6333:6333"
|
||||
|
Loading…
x
Reference in New Issue
Block a user