You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
379 lines
11 KiB
Plaintext
379 lines
11 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Using MyScale as a vector database for OpenAI embeddings\n",
|
|
"\n",
|
|
"This notebook provides a step-by-step guide on using MyScale as a vector database for OpenAI embeddings. The process includes:\n",
|
|
"\n",
|
|
"1. Utilizing precomputed embeddings generated by OpenAI API.\n",
|
|
"2. Storing these embeddings in a cloud instance of MyScale.\n",
|
|
"3. Converting raw text query to an embedding using OpenAI API.\n",
|
|
"4. Leveraging MyScale to perform nearest neighbor search within the created collection.\n",
|
|
"\n",
|
|
"### What is MyScale\n",
|
|
"\n",
|
|
"[MyScale](https://myscale.com) is a database built on Clickhouse that combines vector search and SQL analytics to offer a high-performance, streamlined, and fully managed experience. It's designed to facilitate joint queries and analyses on both structured and vector data, with comprehensive SQL support for all data processing.\n",
|
|
"\n",
|
|
"\n",
|
|
"### Deployment options\n",
|
|
"\n",
|
|
"- Deploy and execute vector search with SQL on your cluster within two minutes by using [MyScale Console](https://console.myscale.com).\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Prerequisites\n",
|
|
"\n",
|
|
"To follow this guide, you will need to have the following:\n",
|
|
"\n",
|
|
"1. A MyScale cluster deployed by following the [quickstart guide](https://docs.myscale.com/en/quickstart/).\n",
|
|
"2. The 'clickhouse-connect' library to interact with MyScale.\n",
|
|
"3. An [OpenAI API key](https://beta.openai.com/account/api-keys) for vectorization of queries."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Install requirements\n",
|
|
"\n",
|
|
"This notebook requires the `openai`, `clickhouse-connect`, as well as some other dependencies. Use the following command to install them:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2023-02-16T12:05:05.718972Z",
|
|
"start_time": "2023-02-16T12:04:30.434820Z"
|
|
},
|
|
"pycharm": {
|
|
"is_executing": true
|
|
}
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"! pip install openai clickhouse-connect wget pandas"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Prepare your OpenAI API key\n",
|
|
"\n",
|
|
"To use the OpenAI API, you'll need to set up an API key. If you don't have one already, you can obtain it from [OpenAI](https://platform.openai.com/account/api-keys)."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2023-02-16T12:05:05.730338Z",
|
|
"start_time": "2023-02-16T12:05:05.723351Z"
|
|
}
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"import openai\n",
|
|
"\n",
|
|
"# get API key from on OpenAI website\n",
|
|
"openai.api_key = \"OPENAI_API_KEY\"\n",
|
|
"\n",
|
|
"# check we have authenticated\n",
|
|
"openai.Engine.list()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Connect to MyScale\n",
|
|
"\n",
|
|
"Follow the [connections details](https://docs.myscale.com/en/cluster-management/) section to retrieve the cluster host, username, and password information from the MyScale console, and use it to create a connection to your cluster as shown below:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2023-02-16T12:05:06.827143Z",
|
|
"start_time": "2023-02-16T12:05:05.733771Z"
|
|
}
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"import clickhouse_connect\n",
|
|
"\n",
|
|
"# initialize client\n",
|
|
"client = clickhouse_connect.get_client(host='YOUR_CLUSTER_HOST', port=8443, username='YOUR_USERNAME', password='YOUR_CLUSTER_PASSWORD')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Load data"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"We need to load the dataset of precomputed vector embeddings for Wikipedia articles provided by OpenAI. Use the `wget` package to download the dataset."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2023-02-16T12:05:37.371951Z",
|
|
"start_time": "2023-02-16T12:05:06.851634Z"
|
|
},
|
|
"pycharm": {
|
|
"is_executing": true
|
|
}
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"import wget\n",
|
|
"\n",
|
|
"embeddings_url = \"https://cdn.openai.com/API/examples/data/vector_database_wikipedia_articles_embedded.zip\"\n",
|
|
"\n",
|
|
"# The file is ~700 MB so this will take some time\n",
|
|
"wget.download(embeddings_url)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"After the download is complete, extract the file using the `zipfile` package:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2023-02-16T12:06:01.538851Z",
|
|
"start_time": "2023-02-16T12:05:37.376042Z"
|
|
}
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"import zipfile\n",
|
|
"\n",
|
|
"with zipfile.ZipFile(\"vector_database_wikipedia_articles_embedded.zip\", \"r\") as zip_ref:\n",
|
|
" zip_ref.extractall(\"../data\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Now, we can load the data from `vector_database_wikipedia_articles_embedded.csv` into a Pandas DataFrame:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"\n",
|
|
"from ast import literal_eval\n",
|
|
"\n",
|
|
"# read data from csv\n",
|
|
"article_df = pd.read_csv('../data/vector_database_wikipedia_articles_embedded.csv')\n",
|
|
"article_df = article_df[['id', 'url', 'title', 'text', 'content_vector']]\n",
|
|
"\n",
|
|
"# read vectors from strings back into a list\n",
|
|
"article_df[\"content_vector\"] = article_df.content_vector.apply(literal_eval)\n",
|
|
"article_df.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Index data\n",
|
|
"\n",
|
|
"We will create an SQL table called `articles` in MyScale to store the embeddings data. The table will include a vector index with a cosine distance metric and a constraint for the length of the embeddings. Use the following code to create and insert data into the articles table:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2023-02-16T12:17:36.366066Z",
|
|
"start_time": "2023-02-16T12:17:35.486872Z"
|
|
}
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# create articles table with vector index\n",
|
|
"embedding_len=len(article_df['content_vector'][0]) # 1536\n",
|
|
"\n",
|
|
"client.command(f\"\"\"\n",
|
|
"CREATE TABLE IF NOT EXISTS default.articles\n",
|
|
"(\n",
|
|
" id UInt64,\n",
|
|
" url String,\n",
|
|
" title String,\n",
|
|
" text String,\n",
|
|
" content_vector Array(Float32),\n",
|
|
" CONSTRAINT cons_vector_len CHECK length(content_vector) = {embedding_len},\n",
|
|
" VECTOR INDEX article_content_index content_vector TYPE HNSWFLAT('metric_type=Cosine')\n",
|
|
")\n",
|
|
"ENGINE = MergeTree ORDER BY id\n",
|
|
"\"\"\")\n",
|
|
"\n",
|
|
"# insert data into the table in batches\n",
|
|
"from tqdm.auto import tqdm\n",
|
|
"\n",
|
|
"batch_size = 100\n",
|
|
"total_records = len(article_df)\n",
|
|
"\n",
|
|
"# upload data in batches\n",
|
|
"data = article_df.to_records(index=False).tolist()\n",
|
|
"column_names = article_df.columns.tolist() \n",
|
|
"\n",
|
|
"for i in tqdm(range(0, total_records, batch_size)):\n",
|
|
" i_end = min(i + batch_size, total_records)\n",
|
|
" client.insert(\"default.articles\", data[i:i_end], column_names=column_names)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"We need to check the build status of the vector index before proceeding with the search, as it is automatically built in the background."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"articles count: 25000\n",
|
|
"index build status: Built\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# check count of inserted data\n",
|
|
"print(f\"articles count: {client.command('SELECT count(*) FROM default.articles')}\")\n",
|
|
"\n",
|
|
"# check the status of the vector index, make sure vector index is ready with 'Built' status\n",
|
|
"get_index_status=\"SELECT status FROM system.vector_indices WHERE name='article_content_index'\"\n",
|
|
"print(f\"index build status: {client.command(get_index_status)}\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Search data\n",
|
|
"\n",
|
|
"Once indexed in MyScale, we can perform vector search to find similar content. First, we will use the OpenAI API to generate embeddings for our query. Then, we will perform the vector search using MyScale."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {
|
|
"ExecuteTime": {
|
|
"end_time": "2023-02-16T12:30:39.379566Z",
|
|
"start_time": "2023-02-16T12:30:38.031041Z"
|
|
}
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"1 Battle of Bannockburn\n",
|
|
"2 Wars of Scottish Independence\n",
|
|
"3 1651\n",
|
|
"4 First War of Scottish Independence\n",
|
|
"5 Robert I of Scotland\n",
|
|
"6 841\n",
|
|
"7 1716\n",
|
|
"8 1314\n",
|
|
"9 1263\n",
|
|
"10 William Wallace\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"import openai\n",
|
|
"\n",
|
|
"query = \"Famous battles in Scottish history\"\n",
|
|
"\n",
|
|
"# creates embedding vector from user query\n",
|
|
"embed = openai.Embedding.create(\n",
|
|
" input=query,\n",
|
|
" model=\"text-embedding-3-small\",\n",
|
|
")[\"data\"][0][\"embedding\"]\n",
|
|
"\n",
|
|
"# query the database to find the top K similar content to the given query\n",
|
|
"top_k = 10\n",
|
|
"results = client.query(f\"\"\"\n",
|
|
"SELECT id, url, title, distance(content_vector, {embed}) as dist\n",
|
|
"FROM default.articles\n",
|
|
"ORDER BY dist\n",
|
|
"LIMIT {top_k}\n",
|
|
"\"\"\")\n",
|
|
"\n",
|
|
"# display results\n",
|
|
"for i, r in enumerate(results.named_results()):\n",
|
|
" print(i+1, r['title'])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.9.16"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 1
|
|
}
|