Unable to launch Chat With RTX - An existing connection was forcibly closed by the remote host

AI & Data Science AI Foundation Models and Endpoints
1

I managed to get Chat with RTX up and running without any issues initially. However, I’ve recently begun encountering a problem where, upon launching the app, I get the error message "An existing connection was forcibly closed by the remote host.

File "C:\Users\user\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\ssl.py", line 1375, in do_handshake 

    self._sslobj.do_handshake() 

ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host

Any ideas on how to fix that?

My system parameters:

13th Gen Intel(R) Core™ i9-13900H 2.60 GHz
64 GB of RAM
RTX 4070, drivers are up to date
Windows 11 23H2, all recent updates installed

No VPN is running

2

The issue is likely the same as one described here

3

Thanks for providing the links! I checked the github discussion you referenced but I had trouble finding the solution in it.

The comment from ArthurZucker “Then I invite you to read this tutorial. Hub is working alright on our ends” redirects to https://saturncloud.io/ homepage.

The comment from Wauplin “Closing this issue as the root problem seemed to come from the firewall.” leads to a discussion about Cisco blocking connections to huggingface? They seem to resolve it after “admin” whitelisted it?

Any suggestions/advice on how I, an end user using this for personal use, can “whitelist” huggingface? I am very unfamiliar with SSL. My AV is literally just windows defender (desktop dedicated for data analysis/gpu tasks). Any help at all is greatly appreciated!

Forgot to include the Traceback:

Traceback (most recent call last):
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\connectionpool.py”, line 793, in urlopen
response = self._make_request(
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\connectionpool.py”, line 491, in _make_request
raise new_e
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\connectionpool.py”, line 467, in _make_request
self._validate_conn(conn)
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\connectionpool.py”, line 1099, in _validate_conn
conn.connect()
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\connection.py”, line 653, in connect
sock_and_verified = _ssl_wrap_socket_and_match_hostname(
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\connection.py”, line 806, in ssl_wrap_socket_and_match_hostname
ssl_sock = ssl_wrap_socket(
File "C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\util\ssl.py", line 465, in ssl_wrap_socket
ssl_sock = ssl_wrap_socket_impl(sock, context, tls_in_tls, server_hostname)
File "C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\util\ssl.py", line 509, in _ssl_wrap_socket_impl
return ssl_context.wrap_socket(sock, server_hostname=server_hostname)
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\ssl.py”, line 513, in wrap_socket
return self.sslsocket_class._create(
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\ssl.py”, line 1104, in _create
self.do_handshake()
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\ssl.py”, line 1375, in do_handshake
self._sslobj.do_handshake()
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\requests\adapters.py”, line 486, in send
resp = conn.urlopen(
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\connectionpool.py”, line 847, in urlopen
retries = retries.increment(
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\util\retry.py”, line 470, in increment
raise reraise(type(error), error, _stacktrace)
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\util\util.py”, line 38, in reraise
raise value.with_traceback(tb)
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\connectionpool.py”, line 793, in urlopen
response = self._make_request(
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\connectionpool.py”, line 491, in _make_request
raise new_e
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\connectionpool.py”, line 467, in _make_request
self._validate_conn(conn)
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\connectionpool.py”, line 1099, in _validate_conn
conn.connect()
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\connection.py”, line 653, in connect
sock_and_verified = _ssl_wrap_socket_and_match_hostname(
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\connection.py”, line 806, in ssl_wrap_socket_and_match_hostname
ssl_sock = ssl_wrap_socket(
File "C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\util\ssl.py", line 465, in ssl_wrap_socket
ssl_sock = ssl_wrap_socket_impl(sock, context, tls_in_tls, server_hostname)
File "C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\urllib3\util\ssl.py", line 509, in _ssl_wrap_socket_impl
return ssl_context.wrap_socket(sock, server_hostname=server_hostname)
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\ssl.py”, line 513, in wrap_socket
return self.sslsocket_class._create(
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\ssl.py”, line 1104, in _create
self.do_handshake()
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\ssl.py”, line 1375, in do_handshake
self._sslobj.do_handshake()
urllib3.exceptions.ProtocolError: (‘Connection aborted.’, ConnectionResetError(10054, ‘An existing connection was forcibly closed by the remote host’, None, 10054, None))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\RAG\trt-llm-rag-windows-main\app.py”, line 114, in
embed_model = HuggingFaceEmbeddings(model_name=embedded_model)
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\langchain\embeddings\huggingface.py”, line 66, in init
self.client = sentence_transformers.SentenceTransformer(
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\sentence_transformers\SentenceTransformer.py”, line 87, in init
snapshot_download(model_name_or_path,
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\sentence_transformers\util.py”, line 442, in snapshot_download
model_info = _api.model_info(repo_id=repo_id, revision=revision, token=token)
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\huggingface_hub\utils_validators.py”, line 118, in _inner_fn
return fn(*args, **kwargs)
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\huggingface_hub\hf_api.py”, line 2219, in model_info
r = get_session().get(path, headers=headers, timeout=timeout, params=params)
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\requests\sessions.py”, line 602, in get
return self.request(“GET”, url, **kwargs)
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\requests\sessions.py”, line 589, in request
resp = self.send(prep, **send_kwargs)
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\requests\sessions.py”, line 703, in send
r = adapter.send(request, **kwargs)
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\huggingface_hub\utils_http.py”, line 67, in send
return super().send(request, *args, **kwargs)
File “C:\Users\j\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\requests\adapters.py”, line 501, in send
raise ConnectionError(err, request=request)
requests.exceptions.ConnectionError: (ProtocolError(‘Connection aborted.’, ConnectionResetError(10054, ‘An existing connection was forcibly closed by the remote host’, None, 10054, None)), ‘(Request ID: 6e8662fd-100e-4e5b-8e52-02b887408bd9)’)

4

As it was suggested in replies to the topic I’ve referenced above, try installing a VPN service or use a mobile hotspot and then start the chat. It may help.

I don’t know a reliable solution. For me the issue just disappeared without any action from my side.

5

I had exactly the same problem and using a VPN fixed it. I’m inside the US (Texas) and using AT&T fiber Internet. No idea why the connections were being blocked but maybe something inside AT&T? Turning off the firewall did NOT fix the problem, only the VPN did. Connected to the ProtonVPN US-CA relay.