OperationalError: Error connecting to Elasticsearch: elasticsearch-dbapi - elasticsearch

Question

I am trying to connect to Elasticsearch using the elasticsearch-dbapi library. I want to be able to execute SQL queries on my Elasticsearch cluster.
However, I keep getting this error when I attempt to run a query,
---------------------------------------------------------------------------
gaierror Traceback (most recent call last)
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\urllib3\connection.py:174, in HTTPConnection._new_conn(self)
173 try:
--> 174 conn = connection.create_connection(
175 (self._dns_host, self.port), self.timeout, **extra_kw
176 )
178 except SocketTimeout:
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\urllib3\util\connection.py:72, in create_connection(address, timeout, source_address, socket_options)
68 return six.raise_from(
69 LocationParseError(u"'%s', label empty or too long" % host), None
70 )
---> 72 for res in socket.getaddrinfo(host, port, family, socket.SOCK_STREAM):
73 af, socktype, proto, canonname, sa = res
File ~\Anaconda3\envs\elasticsearch\lib\socket.py:955, in getaddrinfo(host, port, family, type, proto, flags)
954 addrlist = []
--> 955 for res in _socket.getaddrinfo(host, port, family, type, proto, flags):
956 af, socktype, proto, canonname, sa = res
gaierror: [Errno 11001] getaddrinfo failed
During handling of the above exception, another exception occurred:
NewConnectionError Traceback (most recent call last)
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\elasticsearch\connection\http_urllib3.py:251, in Urllib3HttpConnection.perform_request(self, method, url, params, body, timeout, ignore, headers)
249 request_headers["content-encoding"] = "gzip"
--> 251 response = self.pool.urlopen(
252 method, url, body, retries=Retry(False), headers=request_headers, **kw
253 )
254 duration = time.time() - start
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\urllib3\connectionpool.py:787, in HTTPConnectionPool.urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)
785 e = ProtocolError("Connection aborted.", e)
--> 787 retries = retries.increment(
788 method, url, error=e, _pool=self, _stacktrace=sys.exc_info()[2]
789 )
790 retries.sleep()
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\urllib3\util\retry.py:525, in Retry.increment(self, method, url, response, error, _pool, _stacktrace)
523 if self.total is False and error:
524 # Disabled, indicate to re-raise the error.
--> 525 raise six.reraise(type(error), error, _stacktrace)
527 total = self.total
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\urllib3\packages\six.py:770, in reraise(tp, value, tb)
769 raise value.with_traceback(tb)
--> 770 raise value
771 finally:
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\urllib3\connectionpool.py:703, in HTTPConnectionPool.urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)
702 # Make the request on the httplib connection object.
--> 703 httplib_response = self._make_request(
704 conn,
705 method,
706 url,
707 timeout=timeout_obj,
708 body=body,
709 headers=headers,
710 chunked=chunked,
711 )
713 # If we're going to release the connection in ``finally:``, then
714 # the response doesn't need to know about the connection. Otherwise
715 # it will also try to release it and we'll have a double-release
716 # mess.
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\urllib3\connectionpool.py:386, in HTTPConnectionPool._make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw)
385 try:
--> 386 self._validate_conn(conn)
387 except (SocketTimeout, BaseSSLError) as e:
388 # Py2 raises this as a BaseSSLError, Py3 raises it as socket timeout.
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\urllib3\connectionpool.py:1042, in HTTPSConnectionPool._validate_conn(self, conn)
1041 if not getattr(conn, "sock", None): # AppEngine might not have `.sock`
-> 1042 conn.connect()
1044 if not conn.is_verified:
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\urllib3\connection.py:358, in HTTPSConnection.connect(self)
356 def connect(self):
357 # Add certificate verification
--> 358 self.sock = conn = self._new_conn()
359 hostname = self.host
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\urllib3\connection.py:186, in HTTPConnection._new_conn(self)
185 except SocketError as e:
--> 186 raise NewConnectionError(
187 self, "Failed to establish a new connection: %s" % e
188 )
190 return conn
NewConnectionError: <urllib3.connection.HTTPSConnection object at 0x00000236CF7A3D60>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed
During handling of the above exception, another exception occurred:
ConnectionError Traceback (most recent call last)
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\es\baseapi.py:318, in BaseCursor.elastic_query(self, query)
317 try:
--> 318 response = self.es.transport.perform_request("POST", path, body=payload)
319 except es_exceptions.ConnectionError:
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\elasticsearch\transport.py:413, in Transport.perform_request(self, method, url, headers, params, body)
412 if attempt == self.max_retries:
--> 413 raise e
414 else:
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\elasticsearch\transport.py:381, in Transport.perform_request(self, method, url, headers, params, body)
380 try:
--> 381 status, headers_response, data = connection.perform_request(
382 method,
383 url,
384 params,
385 body,
386 headers=headers,
387 ignore=ignore,
388 timeout=timeout,
389 )
391 except TransportError as e:
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\elasticsearch\connection\http_urllib3.py:266, in Urllib3HttpConnection.perform_request(self, method, url, params, body, timeout, ignore, headers)
265 raise ConnectionTimeout("TIMEOUT", str(e), e)
--> 266 raise ConnectionError("N/A", str(e), e)
268 # raise warnings if any from the 'Warnings' header.
ConnectionError: ConnectionError(<urllib3.connection.HTTPSConnection object at 0x00000236CF7A3D60>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed) caused by: NewConnectionError(<urllib3.connection.HTTPSConnection object at 0x00000236CF7A3D60>: Failed to establish a new connection: [Errno 11001] getaddrinfo failed)
During handling of the above exception, another exception occurred:
OperationalError Traceback (most recent call last)
Input In [16], in <cell line: 2>()
1 curs = conn.cursor()
----> 2 curs.execute(
3 "select * from kibana_sample_data_ecommerce LIMIT 10"
4 )
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\es\baseapi.py:36, in check_closed.<locals>.wrap(self, *args, **kwargs)
32 if self.closed:
33 raise exceptions.Error(
34 "{klass} already closed".format(klass=self.__class__.__name__)
35 )
---> 36 return f(self, *args, **kwargs)
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\es\elastic\api.py:158, in Cursor.execute(self, operation, parameters)
155 return self.get_array_type_columns(re_table_name[1])
157 query = apply_parameters(operation, parameters)
--> 158 results = self.elastic_query(query)
159 # We need a list of tuples
160 rows = [tuple(row) for row in results.get("rows", [])]
File ~\Anaconda3\envs\elasticsearch\lib\site-packages\es\baseapi.py:320, in BaseCursor.elastic_query(self, query)
318 response = self.es.transport.perform_request("POST", path, body=payload)
319 except es_exceptions.ConnectionError:
--> 320 raise exceptions.OperationalError("Error connecting to Elasticsearch")
321 except es_exceptions.RequestError as ex:
322 raise exceptions.ProgrammingError(f"Error ({ex.error}): {ex.info}")
OperationalError: Error connecting to Elasticsearch
This is what my code looks like,
from es.elastic.api import connect
conn = connect(
host='https://<endpoint-alias>.es.eastus2.azure.elastic-cloud.com',
port=9200,
scheme="https",
user='elastic',
password='<password>'
)
curs = conn.cursor()
curs.execute(
"select * from kibana_sample_data_ecommerce LIMIT 10"
)
What exactly is the problem here?
Note: I am using the elasticsearch-dbapi package because although it is possible to execute SQL queries using elasticsearch, there does not seem to be an option to scan through all of the results. I want to access all the hits that are returned by a query.
However, when I tried connecting using elasticsearch, it worked without any problem. But, I used the Cloud ID to establish the connection. Is there some issue with the host that I have used?