Crew AI problem with requests

General
, ,
1

Error Description

When attempting to export a Span batch using the OpenTelemetry SDK, a connection error occurs. The error is manifested as ConnectionResetError: [Errno 104] Connection reset by peer, indicating that the connection was reset by the remote server. This issue occurs when using Crew AI but not when using Langchain.

Logs

2025-04-11 -  - INFO -  Class: GeneralKnowledge Function: crew Message: Crew successfully created.
ERROR:opentelemetry.sdk.trace.export:Exception while exporting Span batch.
Traceback (most recent call last):
  File "urllib3/connectionpool.py", line 716, in urlopen
    httplib_response = self._make_request(
  File "urllib3/connectionpool.py", line 404, in _make_request
    self._validate_conn(conn)
  File "urllib3/connectionpool.py", line 1061, in _validate_conn
    conn.connect()
  File "urllib3/connection.py", line 419, in connect
    self.sock = ssl_wrap_socket(
  File "urllib3/util/ssl_.py", line 458, in ssl_wrap_socket
    ssl_sock = _ssl_wrap_socket_impl(
  File "urllib3/util/ssl_.py", line 502, in _ssl_wrap_socket_impl
    return ssl_context.wrap_socket(sock, server_hostname=server_hostname)
  File "ssl.py", line 455, in wrap_socket
    return self.sslsocket_class._create(
  File "ssl.py", line 1042, in _create
    self.do_handshake()
  File "ssl.py", line 1320, in do_handshake
    self._sslobj.do_handshake()
ConnectionResetError: [Errno 104] Connection reset by peer

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "requests/adapters.py", line 667, in send
    resp = conn.urlopen(
  File "urllib3/connectionpool.py", line 802, in urlopen
    retries = retries.increment(
  File "urllib3/util/retry.py", line 552, in increment
    raise six.reraise(type(error), error, _stacktrace)
  File "six.py", line 769, in reraise
    raise value.with_traceback(tb)
  File "urllib3/connectionpool.py", line 716, in urlopen
    httplib_response = self._make_request(
  File "urllib3/connectionpool.py", line 404, in _make_request
    self._validate_conn(conn)
  File "urllib3/connectionpool.py", line 1061, in _validate_conn
    conn.connect()
  File "urllib3/connection.py", line 419, in connect
    self.sock = ssl_wrap_socket(
  File "urllib3/util/ssl_.py", line 458, in ssl_wrap_socket
    ssl_sock = _ssl_wrap_socket_impl(
  File "urllib3/util/ssl_.py", line 502, in _ssl_wrap_socket_impl
    return ssl_context.wrap_socket(sock, server_hostname=server_hostname)
  File "ssl.py", line 455, in wrap_socket
    return self.sslsocket_class._create(
  File "ssl.py", line 1042, in _create
    self.do_handshake()
  File "ssl.py", line 1320, in do_handshake
    self._sslobj.do_handshake()
urllib3.exceptions.ProtocolError: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "opentelemetry/sdk/trace/export/__init__.py", line 362, in _export_batch
    self.span_exporter.export(self.spans_list[:idx])  # type: ignore
  File "opentelemetry/exporter/otlp/proto/http/trace_exporter/__init__.py", line 189, in export
    return self._export_serialized_spans(serialized_data)
  File "opentelemetry/exporter/otlp/proto/http/trace_exporter/__init__.py", line 159, in _export_serialized_spans
    resp = self._export(serialized_data)
  File "opentelemetry/exporter/otlp/proto/http/trace_exporter/__init__.py", line 133, in _export
    return self._session.post(
  File "requests/sessions.py", line 637, in post
    return self.request("POST", url, data=data, json=json, **kwargs)
  File "requests/sessions.py", line 589, in request
    resp = self.send(prep, **send_kwargs)
  File "requests/sessions.py", line 703, in send
    r = adapter.send(request, **kwargs)
  File "requests/adapters.py", line 682, in send
    raise ConnectionError(err, request=request)
requests.exceptions.ConnectionError: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer')

Attempted Solutions

  • I have tried running the LLM model on both GCP and Azure Open AI, but the same issue persists.
  • This problem occurs only when using Crew AI and not when using Langchain.
  • I am working on the Cloud 9 platform.

Possible Causes and Solutions

  1. Connection Issue: The Connection reset by peer error suggests that the remote server reset the connection. This could be due to network issues or server configuration problems.
  2. SSL/TLS Configuration: Ensure that SSL/TLS certificates and configurations are correctly set up on both the server and client sides.
  3. Retries and Timeouts: Try increasing the number of connection retries and setting longer timeouts in the connection configuration.

If you need further assistance or have additional questions, feel free to ask!

1 Like
2

Welcome!

If you share a minimal version of your code that lets others reproduce the error, you’ll definitely boost your chances of getting people to chime in with their thoughts.

1 Like