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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
|
# coding: utf-8
# -------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project root for
# license information.
# --------------------------------------------------------------------------
"""
FILE: sample_vector_search.py
DESCRIPTION:
This sample demonstrates how to get search results from a basic search text
from an Azure Search index.
USAGE:
python sample_vector_search.py
Set the environment variables with your own values before running the sample:
1) AZURE_SEARCH_SERVICE_ENDPOINT - the endpoint of your Azure Cognitive Search service
2) AZURE_SEARCH_INDEX_NAME - the name of your search index (e.g. "hotels-sample-index")
3) AZURE_SEARCH_API_KEY - your search API key
"""
import os
from azure.core.credentials import AzureKeyCredential
from azure.search.documents import SearchClient
from azure.search.documents.indexes import SearchIndexClient
from azure.search.documents.models import VectorizedQuery
service_endpoint = os.environ["AZURE_SEARCH_SERVICE_ENDPOINT"]
index_name = os.environ["AZURE_SEARCH_INDEX_NAME"]
key = os.environ["AZURE_SEARCH_API_KEY"]
def get_embeddings(text: str):
# There are a few ways to get embeddings. This is just one example.
import openai
open_ai_endpoint = os.getenv("OpenAIEndpoint")
open_ai_key = os.getenv("OpenAIKey")
client = openai.AzureOpenAI(
azure_endpoint=open_ai_endpoint,
api_key=open_ai_key,
api_version="2023-09-01-preview",
)
embedding = client.embeddings.create(input=[text], model="text-embedding-ada-002")
return embedding.data[0].embedding
def get_hotel_index(name: str):
from azure.search.documents.indexes.models import (
SearchIndex,
SearchField,
SearchFieldDataType,
SimpleField,
SearchableField,
VectorSearch,
VectorSearchProfile,
HnswAlgorithmConfiguration,
)
fields = [
SimpleField(name="hotelId", type=SearchFieldDataType.String, key=True),
SearchableField(
name="hotelName",
type=SearchFieldDataType.String,
sortable=True,
filterable=True,
),
SearchableField(name="description", type=SearchFieldDataType.String),
SearchField(
name="descriptionVector",
type=SearchFieldDataType.Collection(SearchFieldDataType.Single),
searchable=True,
vector_search_dimensions=1536,
vector_search_profile_name="my-vector-config",
),
SearchableField(
name="category",
type=SearchFieldDataType.String,
sortable=True,
filterable=True,
facetable=True,
),
]
vector_search = VectorSearch(
profiles=[VectorSearchProfile(name="my-vector-config", algorithm_configuration_name="my-algorithms-config")],
algorithms=[HnswAlgorithmConfiguration(name="my-algorithms-config")],
)
return SearchIndex(name=name, fields=fields, vector_search=vector_search)
def get_hotel_documents():
docs = [
{
"hotelId": "1",
"hotelName": "Fancy Stay",
"description": "Best hotel in town if you like luxury hotels.",
"descriptionVector": get_embeddings("Best hotel in town if you like luxury hotels."),
"category": "Luxury",
},
{
"hotelId": "2",
"hotelName": "Roach Motel",
"description": "Cheapest hotel in town. Infact, a motel.",
"descriptionVector": get_embeddings("Cheapest hotel in town. Infact, a motel."),
"category": "Budget",
},
{
"hotelId": "3",
"hotelName": "EconoStay",
"description": "Very popular hotel in town.",
"descriptionVector": get_embeddings("Very popular hotel in town."),
"category": "Budget",
},
{
"hotelId": "4",
"hotelName": "Modern Stay",
"description": "Modern architecture, very polite staff and very clean. Also very affordable.",
"descriptionVector": get_embeddings(
"Modern architecture, very polite staff and very clean. Also very affordable."
),
"category": "Luxury",
},
{
"hotelId": "5",
"hotelName": "Secret Point",
"description": "One of the best hotel in town. The hotel is ideally located on the main commercial artery of the city in the heart of New York.",
"descriptionVector": get_embeddings(
"One of the best hotel in town. The hotel is ideally located on the main commercial artery of the city in the heart of New York."
),
"category": "Boutique",
},
]
return docs
def single_vector_search():
# [START single_vector_search]
query = "Top hotels in town"
search_client = SearchClient(service_endpoint, index_name, AzureKeyCredential(key))
vector_query = VectorizedQuery(vector=get_embeddings(query), k_nearest_neighbors=3, fields="descriptionVector")
results = search_client.search(
vector_queries=[vector_query],
select=["hotelId", "hotelName"],
)
for result in results:
print(result)
# [END single_vector_search]
def single_vector_search_with_filter():
# [START single_vector_search_with_filter]
query = "Top hotels in town"
search_client = SearchClient(service_endpoint, index_name, AzureKeyCredential(key))
vector_query = VectorizedQuery(vector=get_embeddings(query), k_nearest_neighbors=3, fields="descriptionVector")
results = search_client.search(
search_text="",
vector_queries=[vector_query],
filter="category eq 'Luxury'",
select=["hotelId", "hotelName"],
)
for result in results:
print(result)
# [END single_vector_search_with_filter]
def simple_hybrid_search():
# [START simple_hybrid_search]
query = "Top hotels in town"
search_client = SearchClient(service_endpoint, index_name, AzureKeyCredential(key))
vector_query = VectorizedQuery(vector=get_embeddings(query), k_nearest_neighbors=3, fields="descriptionVector")
results = search_client.search(
search_text=query,
vector_queries=[vector_query],
select=["hotelId", "hotelName"],
)
for result in results:
print(result)
# [END simple_hybrid_search]
if __name__ == "__main__":
credential = AzureKeyCredential(key)
index_client = SearchIndexClient(service_endpoint, credential)
index = get_hotel_index(index_name)
index_client.create_index(index)
client = SearchClient(service_endpoint, index_name, credential)
hotel_docs = get_hotel_documents()
client.upload_documents(documents=hotel_docs)
single_vector_search()
single_vector_search_with_filter()
simple_hybrid_search()
|
