태태개발일지 - 쿼드란트 벡터 db 구축 처음부터 끝까지

쿼드란트 Vector DB 구축

 

1. Qdrant GitHub Releases 페이지에서 맞는 릴리즈 버전 다운로드

 

2. 원하는 위치에 압축풀기

 

3. qdrant.exe 로 실행하기

 

4. 하면 http://localhost:6333/dashboard 들어가면 아무것도 안뜬다.

 

5. https://github.com/qdrant/qdrant-web-ui/releases 여기서 최신 ui 버전 받고 qudrant가 들어있는 폴더안에 파일을 다옮겨야 그래야 ui버전이 뜬다.

Releases · qdrant/qdrant-web-ui

 

 

 실행 화면

 

 

 

 

python으로 벡터 DB에 데이터 밀어넣기

pip install qdrant-client

 

 

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

client = QdrantClient(url="http://localhost:6333")


client.create_collection(
    collection_name="test_collection",
    vectors_config=VectorParams(size=4, distance=Distance.DOT),
)



operation_info = client.upsert(
    collection_name="test_collection",
    wait=True,
    points=[
        PointStruct(id=1, vector=[0.05, 0.61, 0.76, 0.74], payload={"city": "Berlin"}),
        PointStruct(id=2, vector=[0.19, 0.81, 0.75, 0.11], payload={"city": "London"}),
        PointStruct(id=3, vector=[0.36, 0.55, 0.47, 0.94], payload={"city": "Moscow"}),
        PointStruct(id=4, vector=[0.18, 0.01, 0.85, 0.80], payload={"city": "New York"}),
        PointStruct(id=5, vector=[0.24, 0.18, 0.22, 0.44], payload={"city": "Beijing"}),
        PointStruct(id=6, vector=[0.35, 0.08, 0.11, 0.44], payload={"city": "Mumbai"}),
    ],
)

print(operation_info)

search_result = client.query_points(
    collection_name="test_collection",
    query=[0.2, 0.1, 0.9, 0.7],
    with_payload=False,
    limit=3
).points

print(search_result)

 

 

 

결과