async def create_indexer():
# create an index
index_name = "hotels"
fields = [
SimpleField(name="hotelId", type=SearchFieldDataType.String, key=True),
SimpleField(name="baseRate", type=SearchFieldDataType.Double)
]
index = SearchIndex(name=index_name, fields=fields)
ind_client = SearchIndexerClient(service_endpoint, AzureKeyCredential(key))
async with ind_client:
await ind_client.create_index(index)
# [START create_indexer_async]
# create a datasource
container = SearchIndexerDataContainer(name='searchcontainer')
data_source_connection = SearchIndexerDataSourceConnection(
name="indexer-datasource",
type="azureblob",
connection_string=connection_string,
container=container)
async with ind_client:
data_source = await ind_client.create_data_source_connection(
data_source_connection)
# create an indexer
indexer = SearchIndexer(name="async-sample-indexer",
data_source_name="async-indexer-datasource",
target_index_name="indexer-hotels")
async with indexers_client:
result = await indexers_client.create_indexer(indexer)
print("Create new Indexer - async-sample-indexer")
async def _prepare_indexer(self, endpoint, api_key, name="sample-indexer", ds_name="sample-datasource", id_name="hotels"):
con_str = self.settings.AZURE_STORAGE_CONNECTION_STRING
self.scrubber.register_name_pair(con_str, 'connection_string')
container = SearchIndexerDataContainer(name='searchcontainer')
data_source_connection = SearchIndexerDataSourceConnection(
name=ds_name,
type="azureblob",
connection_string=con_str,
container=container
)
ds_client = SearchIndexerClient(endpoint, AzureKeyCredential(api_key))
ds = await ds_client.create_data_source_connection(data_source_connection)
index_name = id_name
fields = [
{
"name": "hotelId",
"type": "Edm.String",
"key": True,
"searchable": False
}]
index = SearchIndex(name=index_name, fields=fields)
ind_client = SearchIndexClient(endpoint, AzureKeyCredential(api_key))
ind = await ind_client.create_index(index)
return SearchIndexer(name=name, data_source_name=ds.name, target_index_name=ind.name)
def sample_indexer_workflow():
# Now that we have a datasource and an index, we can create an indexer.
skillset_name = _create_skillset().name
print("Skillset is created")
ds_name = _create_datasource().name
print("Data source is created")
ind_name = _create_index().name
print("Index is created")
# we pass the data source, skillsets and targeted index to build an indexer
parameters = IndexingParameters(configuration={"parsingMode": "jsonArray"})
indexer = SearchIndexer(
name="hotel-data-indexer",
data_source_name=ds_name,
target_index_name=ind_name,
skillset_name=skillset_name,
parameters=parameters
)
indexer_client = SearchIndexerClient(service_endpoint, AzureKeyCredential(key))
indexer_client.create_indexer(indexer) # create the indexer
# to get an indexer
result = indexer_client.get_indexer("hotel-data-indexer")
print(result)
# To run an indexer, we can use run_indexer()
indexer_client.run_indexer(result.name)
# Using create or update to schedule an indexer
schedule = IndexingSchedule(interval=datetime.timedelta(hours=24))
result.schedule = schedule
updated_indexer = indexer_client.create_or_update_indexer(result)
print(updated_indexer)
# get the status of an indexer
indexer_client.get_indexer_status(updated_indexer.name)
def _prepare_indexer(self, client, index_client, storage_cs, name,
container_name):
data_source_connection = SearchIndexerDataSourceConnection(
name=f"{name}-ds",
type="azureblob",
connection_string=storage_cs,
container=SearchIndexerDataContainer(name=container_name))
ds = client.create_data_source_connection(data_source_connection)
fields = [{
"name": "hotelId",
"type": "Edm.String",
"key": True,
"searchable": False
}]
index = SearchIndex(name=f"{name}-hotels", fields=fields)
ind = index_client.create_index(index)
return SearchIndexer(name=name,
data_source_name=ds.name,
target_index_name=ind.name)