def test_search_bad_argument(self):
client = SearchClient("endpoint", "index name", CREDENTIAL)
with pytest.raises(TypeError) as e:
client.search(10)
assert str(
e) == "Expected a SuggestQuery for 'query', but got {}".format(
repr(10))
def test_get_search_simple(self, api_key, endpoint, index_name, **kwargs):
client = SearchClient(endpoint, index_name,
AzureKeyCredential(api_key))
results = list(client.search(search_text="hotel"))
assert len(results) == 7
results = list(client.search(search_text="motel"))
assert len(results) == 2
def test_get_search_counts(self, api_key, endpoint, index_name, **kwargs):
client = SearchClient(endpoint, index_name,
AzureKeyCredential(api_key))
results = client.search(search_text="hotel")
assert results.get_count() is None
results = client.search(search_text="hotel", include_total_count=True)
assert results.get_count() == 7
def test_get_search_coverage(self, api_key, endpoint, index_name,
**kwargs):
client = SearchClient(endpoint, index_name,
AzureKeyCredential(api_key))
results = client.search(search_text="hotel")
assert results.get_coverage() is None
results = client.search(search_text="hotel", minimum_coverage=50.0)
cov = results.get_coverage()
assert isinstance(cov, float)
assert cov >= 50.0
def search(rootdir, Query, index_name, endpoint, key, fnames, vertical):
field_names = ['FileName', 'FilePath', 'Score']
# Create a client
credential = AzureKeyCredential(key)
client = SearchClient(endpoint=endpoint,
index_name=index_name,
credential=credential)
results = client.search(search_text=Query)
df = pd.read_csv('TrackerFiles/{}.csv'.format(vertical))
r = []
for result in results:
if result['FileName'] in fnames:
d = {
'FileName': result['FileName'],
'FilePath': result['FilePath'],
'Score': result['@search.score']
}
r.append(d)
if df.loc[df['FileName'] == str(result['FileName']),
'Intent'].isnull().any():
df.loc[df['FileName'] == str(result['FileName']),
'Intent'] = str(Query)
else:
df.loc[df['FileName'] == str(result['FileName']),
'Intent'] = df.loc[df['FileName'] ==
str(result['FileName']),
'Intent'] + "," + str(Query)
df.to_csv('TrackerFiles/{}.csv'.format(vertical), index=False)
with open(rootdir + 'result.csv', 'w') as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=field_names)
writer.writeheader()
writer.writerows(r)
return rootdir + 'result.csv'
def search_query(search_text, filter_by=None, sort_order=None):
try:
# Create a search client
azure_credential = AzureKeyCredential(search_key)
search_client = SearchClient(search_endpoint, search_index,
azure_credential)
# Submit search query
results = search_client.search(
search_text,
search_mode="all",
include_total_count=True,
filter=filter_by,
order_by=sort_order,
facets=['metadata_author'],
highlight_fields='merged_content-3,imageCaption-3',
select=
"url,metadata_storage_name,metadata_author,metadata_storage_size,"
"metadata_storage_last_modified,language,sentiment,merged_content,"
"keyphrases,locations,imageTags,imageCaption")
return results
except Exception as ex:
raise ex
class SearchDocumentsTest(PerfStressTest):
def __init__(self, arguments):
super().__init__(arguments)
api_key = self.get_from_env("AZURE_SEARCH_API_KEY")
service_endpoint = os.getenv("AZURE_SEARCH_SERVICE_ENDPOINT")
index_name = os.getenv("AZURE_SEARCH_INDEX_NAME")
key = os.getenv("AZURE_SEARCH_API_KEY")
self.service_client = SyncClient(service_endpoint, index_name,
AzureKeyCredential(api_key))
self.async_service_client = AsyncClient(service_endpoint, index_name,
AzureKeyCredential(api_key))
@staticmethod
def add_arguments(parser):
super(SearchDocumentsTest, SearchDocumentsTest).add_arguments(parser)
parser.add_argument(
'--num-documents',
nargs='?',
type=int,
help='The number of results expect to be returned.',
default=-1)
async def global_setup(self):
await super().global_setup()
async def close(self):
await self.async_service_client.close()
await super().close()
def run_sync(self):
if self.args.num_documents == -1:
results = len(self.service_client.search(search_text="luxury"))
else:
results = len(
self.service_client.search(search_text="luxury",
top=self.args.num_documents))
async def run_async(self):
if self.args.num_documents == -1:
results = await self.async_service_client.search(
search_text="luxury")
else:
results = await self.async_service_client.search(
search_text="luxury", top=self.args.num_documents)
count = 0
async for result in results:
count += count
def test_get_search_facets_none(self, api_key, endpoint, index_name,
**kwargs):
client = SearchClient(endpoint, index_name,
AzureKeyCredential(api_key))
select = ("hotelName", "category", "description")
results = client.search(search_text="WiFi", select=",".join(select))
assert results.get_facets() is None
def simple_text_query():
# [START simple_query]
from azure.core.credentials import AzureKeyCredential
from azure.search.documents import SearchClient
search_client = SearchClient(service_endpoint, index_name,
AzureKeyCredential(key))
results = search_client.search(query="spa")
print("Hotels containing 'spa' in the name (or other fields):")
for result in results:
print(" Name: {} (rating {})".format(result["HotelName"],
result["Rating"]))
def test_get_count_reset_continuation_token(self, mock_search_post):
client = SearchClient("endpoint", "index name", CREDENTIAL)
result = client.search(search_text="search text")
assert isinstance(result, ItemPaged)
assert result._page_iterator_class is SearchPageIterator
search_result = SearchDocumentsResult()
search_result.results = [
SearchResult(additional_properties={"key": "val"})
]
mock_search_post.return_value = search_result
result.__next__()
result._first_page_iterator_instance.continuation_token = "fake token"
result.get_count()
assert not result._first_page_iterator_instance.continuation_token
def test_get_search_facets_result(self, api_key, endpoint, index_name, **kwargs):
client = SearchClient(
endpoint, index_name, AzureKeyCredential(api_key)
)
query = SearchQuery(search_text="WiFi", facets=["category"])
query.select("hotelName", "category", "description")
results = client.search(query=query)
assert results.get_facets() == {
"category": [
{"value": "Budget", "count": 4},
{"value": "Luxury", "count": 1},
]
}
def filter_query():
# [START facet_query]
from azure.core.credentials import AzureKeyCredential
from azure.search.documents import SearchClient
search_client = SearchClient(service_endpoint, index_name,
AzureKeyCredential(key))
results = search_client.search(
search_text="WiFi", facets=["Category,count:3", "ParkingIncluded"])
facets = results.get_facets()
print("Catgory facet counts for hotels:")
for facet in facets["Category"]:
print(" {}".format(facet))
def test_search_query_argument(self, mock_search_post):
client = SearchClient("endpoint", "index name", CREDENTIAL)
result = client.search(search_text="search text")
assert isinstance(result, ItemPaged)
assert result._page_iterator_class is SearchPageIterator
search_result = SearchDocumentsResult()
search_result.results = [
SearchResult(additional_properties={"key": "val"})
]
mock_search_post.return_value = search_result
assert not mock_search_post.called
next(result)
assert mock_search_post.called
assert mock_search_post.call_args[0] == ()
assert (mock_search_post.call_args[1]["search_request"].search_text ==
"search text")
def filter_query():
# [START filter_query]
from azure.core.credentials import AzureKeyCredential
from azure.search.documents import SearchClient
from azure.search.documents.models import SearchQuery
search_client = SearchClient(service_endpoint, index_name, AzureKeyCredential(key))
query = SearchQuery(search_text="WiFi")
query.filter("Address/StateProvince eq 'FL' and Address/Country eq 'USA'")
query.select("HotelName", "Rating")
query.order_by("Rating desc")
results = search_client.search(query=query)
print("Florida hotels containing 'WiFi', sorted by Rating:")
for result in results:
print(" Name: {} (rating {})".format(result["HotelName"], result["Rating"]))
def semantic_ranking():
# [START semantic_ranking]
from azure.core.credentials import AzureKeyCredential
from azure.search.documents import SearchClient
endpoint = os.getenv("AZURE_SEARCH_SERVICE_ENDPOINT")
index_name = os.getenv("AZURE_SEARCH_INDEX_NAME")
api_key = os.getenv("AZURE_SEARCH_API_KEY")
credential = AzureKeyCredential(api_key)
client = SearchClient(endpoint=endpoint,
index_name=index_name,
credential=credential)
results = list(
client.search(search_text="luxury",
query_type="semantic",
query_language="en-us"))
for result in results:
print("{}\n{}\n)".format(result["HotelId"], result["HotelName"]))
def test_get_search_filter(self, api_key, endpoint, index_name, **kwargs):
client = SearchClient(endpoint, index_name,
AzureKeyCredential(api_key))
select = ("hotelName", "category", "description")
results = list(
client.search(search_text="WiFi",
filter="category eq 'Budget'",
select=",".join(select),
order_by="hotelName desc"))
assert [x["hotelName"]
for x in results] == sorted([x["hotelName"] for x in results],
reverse=True)
expected = {
"category",
"hotelName",
"description",
"@search.score",
"@search.highlights",
}
assert all(set(x) == expected for x in results)
assert all(x["category"] == "Budget" for x in results)
def query_func(search_query):
endpoint = "https://chatbotsearchservice.search.windows.net/"
admin_key = "4CF0B5C911347AE7BBCBF5B3B8D9212C"
index_name = "hotels-sample-index"
search_client = SearchClient(endpoint=endpoint, index_name=index_name, credential=AzureKeyCredential(admin_key))
features = {
"search_fields":"HotelName",
"select":"HotelName, Rating",
"filter":"Rating gt 4",
"order_by":"Rating desc"}
query_result = search_client.search(
include_total_count=True,
search_text=f"{search_query}",
search_fields=f"{features['search_fields']}",
select=f"{features['select']}",
filter=f"{features['filter']}",
order_by=f"{features['order_by']}")
return query_result
search_index = os.getenv(
"AZURE_SEARCH_INDEX_NAME") # Feel free to use > 1 and switch them out
search_api_key = os.getenv("AZURE_SEARCH_ADMIN_API_KEY")
# UI
title = os.getenv("APPLICATION_NAME")
st.header(title)
q = st.text_input("Search query", "Type your search query here")
st.write("The current search query is:", q)
# Query processing
search_client = SearchClient(
endpoint=search_endpoint,
index_name=search_index,
credential=AzureKeyCredential(search_api_key),
)
results = search_client.search(search_text=q, include_total_count=True)
st.text(f"Total Documents Matching Query: {results.get_count()}")
st.subheader("Results found:")
# print(type(results)) # spoiler: custom Azure Search pagedItem object
for result in results:
# print(result.keys()) # Inspect what you can display
st.text(result[str(list(result.keys())[0])]) # Show first available item