qdrant_quickstart_collection_create_upsert_and_vector_search.py

1from qdrant_client import QdrantClient
2from qdrant_client.models import VectorParams, Distance
3
4# Initialize the client
5# Use ":memory:" for a transient in-memory database
6client = QdrantClient(host="localhost", port=6333)
7
8# 1. Create a collection
9client.create_collection(
10    collection_name="test_collection",
11    vectors_config=VectorParams(size=4, distance=Distance.DOT),
12)
13
14# 2. Add vectors with payload
15operation_info = client.upsert(
16    collection_name="test_collection",
17    wait=True,
18    points=[
19        {"id": 1, "vector": [0.05, 0.61, 0.76, 0.74], "payload": {"city": "Berlin"}},
20        {"id": 2, "vector": [0.19, 0.81, 0.75, 0.11], "payload": {"city": "London"}},
21        {"id": 3, "vector": [0.36, 0.55, 0.47, 0.94], "payload": {"city": "Moscow"}},
22        {"id": 4, "vector": [0.18, 0.01, 0.85, 0.80], "payload": {"city": "New York"}},
23        {"id": 5, "vector": [0.24, 0.18, 0.22, 0.44], "payload": {"city": "Tokyo"}},
24        {"id": 6, "vector": [0.35, 0.08, 0.11, 0.44], "payload": {"city": "Mumbai"}},
25    ],
26)
27
28# 3. Run a search query
29search_result = client.search(
30    collection_name="test_collection",
31    query_vector=[0.2, 0.1, 0.9, 0.7],
32    limit=3
33)
34
35for result in search_result:
36    print(f"ID: {result.id}, Score: {result.score}, Payload: {result.payload}")