kacperlukawski

kacperlukawski

import multiprocessing
import tempfile
import time
from pathlib import Path
from urllib.request import urlretrieve

import h5py
from qdrant_client import QdrantClient
from qdrant_client.conversions.common_types import VectorParams
from qdrant_client.http.models import Distance, SearchRequest

kacperlukawski

from qdrant_client import QdrantClient
from qdrant_client.conversions.common_types import VectorParams

client = QdrantClient("localhost", 6333)
client.recreate_collection(
    collection_name="test_collection",
    vectors_config=VectorParams(size=4, distance=Distance.EUCLID),
)

kacperlukawski

vectors = [
    [.1, .0, .0, .0],
    [.0, .1, .0, .0],
    [.0, .0, .1, .0],
    [.0, .0, .0, .1],
    [.1, .0, .1, .0],
    [.0, .1, .0, .1],
    [.1, .1, .0, .0],
    [.0, .0, .1, .1],
    [.1, .1, .1, .1],

kacperlukawski

results = client.search_batch(
    collection_name="test_collection",
    requests=[
        SearchRequest(
            vector=[0., 0., 2., 0.],
            limit=1,
        ),
        SearchRequest(
            vector=[0., 0., 0., 0.01],
            with_vector=True,

kacperlukawski

kacperlukawski

from qdrant_client import QdrantClient
from qdrant_client.http.models import VectorParams, Distance

client = QdrantClient()
client.recreate_collection(
   collection_name="multiple_vectors",
   vectors_config={
       "title": VectorParams(
           size=100,
           distance=Distance.EUCLID,

kacperlukawski

client.recreate_collection(
   collection_name="single_vector",
   vectors_config=VectorParams(
       size=100,
       distance=Distance.COSINE,
   )
)

kacperlukawski

from datasets import load_dataset

dataset = load_dataset("ChristophSchuhmann/MS_COCO_2017_URL_TEXT")

kacperlukawski

import pandas as pd

dataset_df = pd.DataFrame(dataset["train"])