cutecutecat

conda create -n data PYTHON=3.11
conda activate data
conda install conda-forge::pgvector-python numpy pytorch::faiss-cpu conda-forge::psycopg tqdm

EXPORT OMP_WAIT_POLICY=PASSIVE

python sample_kmeans_export.py \
  --url "postgresql://postgres:123@localhost:5432/postgres" \
 --table embeddings2 \

cutecutecat

Guide to creating a 2-layer index

Warning

The VectorChord v0.5.2 is recommended.

Please see step 4 for more information.

Step 1 - Train the bottom layer (Layer 2)

You can still use the original script.

cutecutecat

How to use the LAION-400m benchmark scripts

Preset

• Machine G: with nvidia GPU, such like A10 to build external K-means, with minimum hardware requirements:
  • at least 120GB memory
• Machine D: An instance like i7ie.2xlarge to do the benchmark, with minimum hardware requirements:
  • at least 4000G NVME SSD
  • at least 64GB memory
  • at least 8 vcpus

cutecutecat

from matplotlib import ticker
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

QPS = [13.42, 12.32, 11.23, 8.75, 27.65, 25.36, 20.41, 16.66]

original_data = {
    "acc": [

cutecutecat

import argparse
import datetime
import logging
import math

import psutil
import numpy as np
import psycopg
from tqdm import tqdm
from pgvector.psycopg import register_vector

cutecutecat

import seaborn as sns
import matplotlib.pyplot as plt


qps = [25.69, 18.91, 17.13, 16.18, 14.45, 7.24, 4.51]
recall = [0.9079, 0.9461, 0.9497, 0.9535, 0.9608, 0.9650, 0.9672]
p99_latency = [148.25, 260.68, 269.5, 302.29, 456.09, 1042.41, 1675.42]

fig, (ax1, ax3) = plt.subplots(1, 2, figsize=(12, 5), gridspec_kw={'width_ratios': [20, 7]})

cutecutecat

from os.path import join
import os
import time
import argparse
from pathlib import Path
from tqdm import tqdm

import psycopg
import h5py
from pgvecto_rs.psycopg import register_vector

cutecutecat

import numpy as np
from pgvecto_rs.psycopg import register_vector
import psycopg

# generate random data
rows = 100000
dimensions = 128
embeddings = np.random.rand(rows, dimensions)
categories = np.random.randint(100, size=rows).tolist()
queries = np.random.rand(10, dimensions)