Cassandra Driver Exception: Unable to connect to the metadata service

Question

I am playing around with some self-paced learning for creating and configuring LLMs for personal use. In this scenario, I am trying to connect to AstraDB to store the headlines from a sample of news articles in a vector database

The python code is below:

ASTRA_DB_SECURE_BUNDLE_PATH = <INSERT PATH>.zip #This is in a zip file downloaded from AstraDB
ASTRA_DB_APPLICATION_TOKEN = <INSERT TOKEN>
ASTRA_DB_CLIENT_ID = <INSERT CLIENT_ID>
ASTRA_DB_CLIENT_SECRET = <INSERT CLIENT_SECRET>
ASTRA_DB_KEYSPACE_NAME = <INSERT KEYSPACE NAME>
OPEN_API_KEY = <INSERT OPENAI KEY>

from langchain.vectorstores.cassandra import Cassandra
from langchain.indexes.vectorstore import VectorStoreIndexWrapper
from langchain.llms import OpenAI
from langchain.embeddings import OpenAIEmbeddings

from cassandra.cluster import Cluster
from cassandra.auth import PlainTextAuthProvider

from datasets import load_dataset

cloud_config= {
'secure_connect_bundle': ASTRA_DB_SECURE_BUNDLE_PATH
}
auth_provider = PlainTextAuthProvider(ASTRA_DB_CLIENT_ID, ASTRA_DB_CLIENT_SECRET)
cluster = Cluster(cloud=cloud_config, auth_provider=auth_provider)
astraSession = cluster.connect()

llm = OpenAI(openai_api_key=OPEN_API_KEY)
myEmbedding = OpenAIEmbeddings(openai_api_key=OPEN_API_KEY)

myCassandraVStore = Cassandra(
    embedding = myEmbedding,
    session = astraSession,
    keyspace = ASTRA_DB_KEYSPACE_NAME,
    table_name = "qa_mini_demo",
)

print("loading data from huggingface")
myDataset = load_dataset("Biddls/Onion_News", split = "train")
headlines = myDataset["text"][:50]

print("\nGenerating embeddings and storing in AstraDB")
myCassandraVStore.add_texts(headlines)

print("Inserted %i headlines.\n" % len(headlines))

When I run the file I receive the following error:

Traceback (most recent call last):
  File "C:\PATH\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\cassandra\datastax\cloud\__init__.py", line 138, in read_metadata_info
    response = urlopen(url, context=config.ssl_context, timeout=timeout)
  File "C:\PATH\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\urllib\request.py", line 216, in urlopen
    return opener.open(url, data, timeout)
  File "C:\PATH\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\urllib\request.py", line 519, in open
    response = self._open(req, data)
  File "C:\PATH\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\urllib\request.py", line 536, in _open
    result = self._call_chain(self.handle_open, protocol, protocol +
  File "C:\PATH\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\urllib\request.py", line 496, in _call_chain
    result = func(*args)
  File "C:\PATH\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\urllib\request.py", line 1391, in https_open
    return self.do_open(http.client.HTTPSConnection, req,
  File "C:\PATH\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\urllib\request.py", line 1352, in do_open
    r = h.getresponse()
  File "C:\PATH\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\http\client.py", line 1375, in getresponse
    response.begin()
  File "C:\PATH\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\http\client.py", line 318, in begin
    version, status, reason = self._read_status()
  File "C:\PATH\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\http\client.py", line 279, in _read_status
    line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
  File "C:\PATH\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\socket.py", line 705, in readinto
    return self._sock.recv_into(b)
  File "C:\PATH\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\ssl.py", line 1274, in recv_into
    return self.read(nbytes, buffer)
  File "C:\PATH\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\ssl.py", line 1130, in read
    return self._sslobj.read(len, buffer)
TimeoutError: The read operation timed out

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\PATH\", line 22, in <module>    
    cluster = Cluster(cloud=cloud_config, auth_provider=auth_provider)
  File "cassandra\cluster.py", line 1132, in cassandra.cluster.Cluster.__init__
  File "C:\PATH\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\cassandra\datastax\cloud\__init__.py", line 92, in get_cloud_config        
    config = read_metadata_info(config, cloud_config)
  File "C:\PATH\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\cassandra\datastax\cloud\__init__.py", line 141, in read_metadata_info     
    raise DriverException("Unable to connect to the metadata service at %s. "
cassandra.DriverException: Unable to connect to the metadata service at https://3b3b9a1d-bb70-4078-8d4f-5b0e69e5a4b3-us-east1.db.astra.datastax.com:29080/metadata. Check the cluster status in the cloud console.

I have double, triple, and quadruple-checked that the cluster is active. My guess is that the timeout error is creating a problem, maybe because of a slow internet connection, but I do not know how to run a test with different lengths of time.

Appreciate any insight here.

Answer 1

How about if you update it as follows?

from cassandra.cluster import Cluster, ExecutionProfile, EXEC_PROFILE_DEFAULT, ProtocolVersion
...
cloud_config= {
  'secure_connect_bundle': ASTRA_DB_SECURE_BUNDLE_PATH,
  'connect_timeout': 30
}
profile = ExecutionProfile(request_timeout=30)
cluster = Cluster(cloud=cloud_config, auth_provider=auth_provider, protocol_version=ProtocolVersion.V4, execution_profiles={EXEC_PROFILE_DEFAULT: profile})
...