forked from testcontainers/testcontainers-python
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathexample_basic.py
More file actions
149 lines (128 loc) · 5.26 KB
/
example_basic.py
File metadata and controls
149 lines (128 loc) · 5.26 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
import json
from datetime import datetime
import numpy as np
from qdrant_client import QdrantClient
from qdrant_client.http import models
from testcontainers.qdrant import QdrantContainer
def basic_example():
with QdrantContainer() as qdrant:
# Get connection parameters
host = qdrant.get_container_host_ip()
port = qdrant.get_exposed_port(qdrant.port)
# Create Qdrant client
client = QdrantClient(host=host, port=port)
print("Connected to Qdrant")
# Create collection
collection_name = "test_collection"
vector_size = 128
client.create_collection(
collection_name=collection_name,
vectors_config=models.VectorParams(size=vector_size, distance=models.Distance.COSINE),
)
print(f"Created collection: {collection_name}")
# Generate test vectors and payloads
num_vectors = 5
vectors = np.random.rand(num_vectors, vector_size).tolist()
payloads = [
{
"text": "AI and machine learning are transforming industries",
"category": "Technology",
"tags": ["AI", "ML", "innovation"],
"timestamp": datetime.utcnow().isoformat(),
},
{
"text": "New study reveals benefits of meditation",
"category": "Health",
"tags": ["wellness", "mental health"],
"timestamp": datetime.utcnow().isoformat(),
},
{
"text": "Global warming reaches critical levels",
"category": "Environment",
"tags": ["climate", "sustainability"],
"timestamp": datetime.utcnow().isoformat(),
},
{
"text": "Stock market shows strong growth",
"category": "Finance",
"tags": ["investing", "markets"],
"timestamp": datetime.utcnow().isoformat(),
},
{
"text": "New restaurant opens in downtown",
"category": "Food",
"tags": ["dining", "local"],
"timestamp": datetime.utcnow().isoformat(),
},
]
# Upload vectors with payloads
client.upsert(
collection_name=collection_name,
points=models.Batch(ids=list(range(num_vectors)), vectors=vectors, payloads=payloads),
)
print("Uploaded vectors with payloads")
# Search vectors
search_result = client.search(collection_name=collection_name, query_vector=vectors[0], limit=3)
print("\nSearch results:")
for scored_point in search_result:
print(
json.dumps(
{"id": scored_point.id, "score": scored_point.score, "payload": scored_point.payload}, indent=2
)
)
# Filtered search
filter_result = client.search(
collection_name=collection_name,
query_vector=vectors[0],
query_filter=models.Filter(
must=[models.FieldCondition(key="category", match=models.MatchValue(value="Technology"))]
),
limit=2,
)
print("\nFiltered search results:")
for scored_point in filter_result:
print(
json.dumps(
{"id": scored_point.id, "score": scored_point.score, "payload": scored_point.payload}, indent=2
)
)
# Create payload index
client.create_payload_index(
collection_name=collection_name, field_name="category", field_schema=models.PayloadFieldSchema.KEYWORD
)
print("\nCreated payload index on category field")
# Create vector index
client.create_payload_index(
collection_name=collection_name, field_name="tags", field_schema=models.PayloadFieldSchema.KEYWORD
)
print("Created payload index on tags field")
# Scroll through collection
scroll_result = client.scroll(collection_name=collection_name, limit=10, with_payload=True, with_vectors=True)
print("\nScrolled through collection:")
for point in scroll_result[0]:
print(json.dumps({"id": point.id, "payload": point.payload}, indent=2))
# Get collection info
collection_info = client.get_collection(collection_name)
print("\nCollection info:")
print(
json.dumps(
{
"name": collection_info.name,
"vectors_count": collection_info.vectors_count,
"points_count": collection_info.points_count,
"status": collection_info.status,
},
indent=2,
)
)
# Update payload
client.set_payload(collection_name=collection_name, payload={"new_field": "updated value"}, points=[0, 1])
print("\nUpdated payload for points 0 and 1")
# Delete points
client.delete(collection_name=collection_name, points_selector=models.PointIdsList(points=[4]))
print("Deleted point with id 4")
# Clean up
client.delete_collection(collection_name)
print("\nDeleted collection")
if __name__ == "__main__":
basic_example()