# Error with Chat with RTX **URL:** \ **Category:** NVIDIA Nemotron\ **Created:** [February 14, 2024, 10:31pm UTC](https://forums.developer.nvidia.com/t/error-with-chat-with-rtx/282880 "2024-02-14T22:31:35Z")\ **Posts on this page:** 14\ **Page:** 1
**Author:** ![Cjay12345](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@Cjay12345](https://forums.developer.nvidia.com/u/Cjay12345)\ **Post date:** [February 14, 2024, 10:31pm UTC](https://forums.developer.nvidia.com/t/error-with-chat-with-rtx/282880/1 "2024-02-14T22:31:35Z")
Running into the following error after the installation of Chat with RTX Windows 11 Pro 13th Gen Intel(R) Core™ i9-13900KF, 3000 Mhz, 24 Core(s), 32 Logical Processor(s) NVIDIA GeForce RTX 4090 Driver: 31.0.15.4609 (updated) Ran as administrator and temp disabled antivirus to prevent conflicts. Used the default directory during installation. Successfull install but powershell error whenever trying to run an instance. > Blockquote Traceback (most recent call last): > File “C:\Users\pasto\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\lib\site-packages\urllib3\connectionpool.py”, line 793, in urlopen > response = self.\_make\_request( > File “C:\Users\pasto\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\lib\site-packages\urllib3\connectionpool.py”, line 491, in \_make\_request > raise new\_e > File “C:\Users\pasto\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\pasto\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\lib\site-packages\urllib3\connectionpool.py”, line 1099, in \_validate\_conn > conn.connect() > File “C:\Users\pasto\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\pasto\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\pasto\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\pasto\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\pasto\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\lib\ssl.py”, line 513, in wrap\_socket > return self.sslsocket\_class.\_create( > File “C:\Users\pasto\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\lib\ssl.py”, line 1104, in \_create > self.do\_handshake() > File “C:\Users\pasto\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 > Blockquote > During handling of the above exception, another exception occurred: > Traceback (most recent call last): > File “C:\Users\pasto\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\lib\site-packages\requests\adapters.py”, line 486, in send > resp = conn.urlopen( > File “C:\Users\pasto\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\lib\site-packages\urllib3\connectionpool.py”, line 847, in urlopen > retries = retries.increment( > File “C:\Users\pasto\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\pasto\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\pasto\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\lib\site-packages\urllib3\connectionpool.py”, line 793, in urlopen > response = self.\_make\_request( > File “C:\Users\pasto\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\lib\site-packages\urllib3\connectionpool.py”, line 491, in \_make\_request > raise new\_e > File “C:\Users\pasto\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\pasto\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\lib\site-packages\urllib3\connectionpool.py”, line 1099, in \_validate\_conn > conn.connect() > File “C:\Users\pasto\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\pasto\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\pasto\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\pasto\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\pasto\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\lib\ssl.py”, line 513, in wrap\_socket > return self.sslsocket\_class.\_create( > File “C:\Users\pasto\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\lib\ssl.py”, line 1104, in \_create > self.do\_handshake() > File “C:\Users\pasto\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)) > Blockquote > During handling of the above exception, another exception occurred: > Traceback (most recent call last): > File “C:\Users\pasto\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\pasto\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\pasto\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\pasto\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\pasto\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\pasto\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\lib\site-packages\huggingface\_hub\hf\_api.py”, line 2084, in model\_info > r = get\_session().get(path, headers=headers, timeout=timeout, params=params) > File “C:\Users\pasto\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\pasto\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\pasto\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\pasto\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\pasto\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: 0c660f0a-112a-4d8c-bea6-c8c6bbf56cd4)’) > Press any key to continue . . . ---
**Author:** ![TomNVIDIA](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/tomnvidia/32/14181_2.png) [@TomNVIDIA](https://forums.developer.nvidia.com/u/TomNVIDIA)\ **Post date:** [February 14, 2024, 10:37pm UTC](https://forums.developer.nvidia.com/t/error-with-chat-with-rtx/282880/2 "2024-02-14T22:37:40Z")
Hello, Please see: [Chat with RTX Installation Failure - Please use the default installation directory](https://forums.developer.nvidia.com/t/chat-with-rtx-installation-failure-please-use-the-default-installation-directory/282860/) ---
**Author:** ![Cjay12345](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@Cjay12345](https://forums.developer.nvidia.com/u/Cjay12345)\ **Post date:** [February 14, 2024, 11:38pm UTC](https://forums.developer.nvidia.com/t/error-with-chat-with-rtx/282880/3 "2024-02-14T23:38:21Z")
Yep it’s in the default installation directory. ---
**Author:** ![codercaspar](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@codercaspar](https://forums.developer.nvidia.com/u/codercaspar)\ **Post date:** [February 15, 2024, 1:19am UTC](https://forums.developer.nvidia.com/t/error-with-chat-with-rtx/282880/4 "2024-02-15T01:19:22Z")
The same Error. Also, I got the prompt when trying to run Chat with RTX "python.exe - Entry Point Not Found The procedure entry point balabala… (a long name of a tensor) could not be located in the dynamic link library …\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\Lib\site-packages\nvidia\cudnn\bin\cudnn\_adv\_infer64\_8.dll …\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\Lib\site-packages\nvidia\cudnn\bin\cudnn\_adv\_train64\_8.dll …\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\Lib\site-packages\nvidia\cudnn\bin\cudnn\_cnn\_infer64\_8.dll …\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\Lib\site-packages\nvidia\cudnn\bin\cudnn\_cnn\_train64\_8.dll " ---
**Author:** ![vicch7](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/vicch7/32/225911_2.png) [@vicch7](https://forums.developer.nvidia.com/u/vicch7)\ **Post date:** [February 15, 2024, 2:52am UTC](https://forums.developer.nvidia.com/t/error-with-chat-with-rtx/282880/5 "2024-02-15T02:52:47Z")
Had the exact error, and I logged the endpoint which could not be connected, it is: [https://huggingface.co/api/models/WhereIsAI/UAE-Large-V1](https://huggingface.co/api/models/WhereIsAI/UAE-Large-V1) Apparently [huggingface.co](http://huggingface.co) has a somewhat questionable SSL certificate, that gets rejected by certain firewalls and I suspect my ISP as well. See [SSL fails and we can't pull from HuggingFaceHub · Issue #25552 · huggingface/transformers · GitHub](https://github.com/huggingface/transformers/issues/25552) The proof is that when trying to access that URL through browser, I sometimes get SSL error as well, though it would succeed on next request somehow. Anyway I think it’s not an issue with Chat with RTX in particular, it’s a problem with connecting to its dependency [huggingface.co](http://huggingface.co) ---
**Author:** ![Cjay12345](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@Cjay12345](https://forums.developer.nvidia.com/u/Cjay12345)\ **Post date:** [February 15, 2024, 4:43am UTC](https://forums.developer.nvidia.com/t/error-with-chat-with-rtx/282880/6 "2024-02-15T04:43:56Z")
Hmmm tried rerunning it off my phone’s hotspot to see if it was a network firewall issue and still no joy. Same 10054 error “An existing connection was forcibly closed by the remote host” ---
**Author:** ![pascu.sorin](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@pascu.sorin](https://forums.developer.nvidia.com/u/pascu.sorin)\ **Post date:** [February 15, 2024, 10:56am UTC](https://forums.developer.nvidia.com/t/error-with-chat-with-rtx/282880/7 "2024-02-15T10:56:54Z")
I managed to finally install it successfully but now when trying to run it I get the following error: Traceback (most recent call last): File “C:\Users\sorin\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\lib\site-packages\langchain\embeddings\huggingface.py”, line 58, in **init** import sentence\_transformers ModuleNotFoundError: No module named ‘sentence\_transformers’ The above exception was the direct cause of the following exception: Traceback (most recent call last): File “C:\Users\sorin\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\sorin\AppData\Local\NVIDIA\ChatWithRTX\env\_nvd\_rag\lib\site-packages\langchain\embeddings\huggingface.py”, line 61, in **init** raise ImportError( ImportError: Could not import sentence\_transformers python package. Please install it with `pip install sentence-transformers`. Any ideas what this could be about? ---
**Author:** ![vicch7](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/vicch7/32/225911_2.png) [@vicch7](https://forums.developer.nvidia.com/u/vicch7)\ **Post date:** [February 16, 2024, 12:47am UTC](https://forums.developer.nvidia.com/t/error-with-chat-with-rtx/282880/8 "2024-02-16T00:47:46Z")
I managed to fix the issue by using a VPN. I think it’s a regional issue so using mobile network won’t be enough. I recommend you try the same if you still have the issue. There are plenty of free services out there. It might be slow, there are several GBs of models to be downloaded when running it for the first time, but it’s still faster than trying all the hacky fixes (regrettably I spent hours on it). ---
**Author:** ![user97688](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@user97688](https://forums.developer.nvidia.com/u/user97688)\ **Post date:** [February 16, 2024, 4:34am UTC](https://forums.developer.nvidia.com/t/error-with-chat-with-rtx/282880/9 "2024-02-16T04:34:34Z")
did you fix this error? ---
**Author:** ![pascu.sorin](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@pascu.sorin](https://forums.developer.nvidia.com/u/pascu.sorin)\ **Post date:** [February 16, 2024, 7:07am UTC](https://forums.developer.nvidia.com/t/error-with-chat-with-rtx/282880/10 "2024-02-16T07:07:31Z")
Unfortunately no. Trying to install the sentence-transformers in the conda env that Chat with RTX uses, just tells me they are up to date. I tried reinstalling all requirements, but that gives me the error that not all dependencies can be resolved and some clashes between versions. So I’m just waiting for a new release or someone smarter than me to find a fix. ---
**Author:** ![wangzhangwu1216](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/wangzhangwu1216/32/316259_2.png) [@wangzhangwu1216](https://forums.developer.nvidia.com/u/wangzhangwu1216)\ **Post date:** [February 16, 2024, 7:43am UTC](https://forums.developer.nvidia.com/t/error-with-chat-with-rtx/282880/11 "2024-02-16T07:43:26Z")
Same concern here, did anyone figure it out? ---
**Author:** ![user97688](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@user97688](https://forums.developer.nvidia.com/u/user97688)\ **Post date:** [February 17, 2024, 3:09am UTC](https://forums.developer.nvidia.com/t/error-with-chat-with-rtx/282880/12 "2024-02-17T03:09:08Z")
I also tried the same thing i force reinstalled the requirements but then tensorrt dll stopped working ---
**Author:** ![stephan.arndt](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@stephan.arndt](https://forums.developer.nvidia.com/u/stephan.arndt)\ **Post date:** [February 18, 2024, 8:39am UTC](https://forums.developer.nvidia.com/t/error-with-chat-with-rtx/282880/13 "2024-02-18T08:39:00Z")
Thank you for this advice, it **worked for me**. I had the exact issue _“ProtocolError(‘Connection aborted.’ … )”_. I downloaded the free version of Proton VPM after a quick browse of [The Best VPN Services for 2023 (pcmag.com)](https://au.pcmag.com/vpn/138/the-best-vpn-services). The quick connect landed me in California (from Australia). Probably saved me hours of frustration. ---
**Author:** ![jaymehta7600](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/jaymehta7600/32/218752_2.png) [@jaymehta7600](https://forums.developer.nvidia.com/u/jaymehta7600)\ **Post date:** [February 18, 2024, 1:36pm UTC](https://forums.developer.nvidia.com/t/error-with-chat-with-rtx/282880/14 "2024-02-18T13:36:37Z")
I keep getting this error while launching: “ModuleNotFoundError: No module named ‘sentence\_transformers’” Anyone solved it?