pjlab-adg / drivelikeahuman Goto Github PK
View Code? Open in Web Editor NEWDrive Like a Human: Rethinking Autonomous Driving with Large Language Models
License: MIT License
Drive Like a Human: Rethinking Autonomous Driving with Large Language Models
License: MIT License
Do we really need to interact with the AD system for several cycles ?
If so, the questions we asked the AD system must influence the results.
哥,为什么我录的视频只有两三秒?我用的是openai,不是azure;然后就会出现这个问题。
laneID, vid = inputs.replace(' ', '').split(',')
ValueError: not enough values to unpack (expected 2, got 1)
Does your project support the replacement of large language models, such as replacing gpt3.5 in the project with the ChatGlm3 large model? Because our school does not have the conditions to unlock the restrictions of gpt3.5, that is, it does not have a credit card to upgrade the openai account. Thank you.
Hi, thank you so much for your amazing work! I'm experimenting with the CaseReasoning
ipynb, where a few weeks ago, it's able to run smoothly locally. Yet now, when I try to run client = Client("http://llama-adapter.opengvlab.com/")
, it generates an error
ValueError: Could not get Gradio config from: http://llama-adapter.opengvlab.com/
And it appears that http://llama-adapter.opengvlab.com/ is now down? Do you happen to know any updates to this? Thank you so much!
Hi, your work is amazing! However I have notice that I use chatgpt to grenerate the thought, will often return "Observation: Check your output and make sure it conforms the format instructions!"
Have you tried other ways to better constrain the output of large models?
I would like to ask why your experimental data is not reflected in the paper, such as the success rate of 30s in the environment of road 4 and density 1,We look forward to hearing from you!
Thank you for the open source spirit, and the ideas in the paper are great,However, I have always had a problem in running your code, and I have asked questions several times, but the problem has not been solved, so I would like to ask you in detail.Here is the same code as yours
The results are as follows
Just keep stuck like this, and then wait until the final decision is made before running, and then keep stuck waiting for running,
I was wondering if this is normal, because I saw how smooth your demo videos were
So the question was raised,I think there are the following anomalies in conda, and I will list them one by one. Please kindly help me to see which aspects are the problems
It is probably the above exceptions, which have warning errors, and there are many repeated reasoning processes, I do not know whether these problems cause the simulator to stall and not run smoothly,I would really appreciate your help!!!
Description:
I encountered an issue when trying to record videos in my environment using the gymnasium.wrappers. RecordVideo wrapper. I receive an error indicating that the fps value is of NoneType when the code tries to save the video. Do I need to specify a specific frame rate (fps) when initializing the environment or in the configuration?
Steps to Reproduce:
Expected Behavior:
The video should save successfully without any errors.
Actual Behavior:
A TypeError is thrown indicating that the fps value is NoneType.
Error Logs:
Traceback (most recent call last):
File "E:\DriveLikeAHuman-main\DriveLikeAHuman-main\HELLM.py", line 107, in
obs, reward, done, info, _ = env.step(output["action_id"])
File "C:\Users\ASUS\anaconda3\lib\site-packages\gymnasium\wrappers\record_video.py", line 180, in step
self.close_video_recorder()
File "C:\Users\ASUS\anaconda3\lib\site-packages\gymnasium\wrappers\record_video.py", line 193, in close_video_recorder
self.video_recorder.close()
File "C:\Users\ASUS\anaconda3\lib\site-packages\gymnasium\wrappers\monitoring\video_recorder.py", line 161, in close
clip.write_videofile(self.path, logger=moviepy_logger)
File "C:\Users\ASUS\anaconda3\lib\site-packages\decorator.py", line 232, in fun
return caller(func, *(extras + args), **kw)
File "C:\Users\ASUS\anaconda3\lib\site-packages\moviepy\decorators.py", line 54, in requires_duration
return f(clip, *a, **k)
File "C:\Users\ASUS\anaconda3\lib\site-packages\decorator.py", line 232, in fun
return caller(func, *(extras + args), **kw)
File "C:\Users\ASUS\anaconda3\lib\site-packages\moviepy\decorators.py", line 135, in use_clip_fps_by_default
return f(clip, *new_a, **new_kw)
File "C:\Users\ASUS\anaconda3\lib\site-packages\decorator.py", line 232, in fun
return caller(func, *(extras + args), **kw)
File "C:\Users\ASUS\anaconda3\lib\site-packages\moviepy\decorators.py", line 22, in convert_masks_to_RGB
return f(clip, *a, **k)
File "C:\Users\ASUS\anaconda3\lib\site-packages\moviepy\video\VideoClip.py", line 300, in write_videofile
ffmpeg_write_video(self, filename, fps, codec,
File "C:\Users\ASUS\anaconda3\lib\site-packages\moviepy\video\io\ffmpeg_writer.py", line 213, in ffmpeg_write_video
with FFMPEG_VideoWriter(filename, clip.size, fps, codec = codec,
File "C:\Users\ASUS\anaconda3\lib\site-packages\moviepy\video\io\ffmpeg_writer.py", line 88, in init
'-r', '%.02f' % fps,
TypeError: must be real number, not NoneType
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "E:\DriveLikeAHuman-main\DriveLikeAHuman-main\HELLM.py", line 111, in
env.close()
File "C:\Users\ASUS\anaconda3\lib\site-packages\gymnasium\wrappers\record_video.py", line 217, in close
self.close_video_recorder()
File "C:\Users\ASUS\anaconda3\lib\site-packages\gymnasium\wrappers\record_video.py", line 193, in close_video_recorder
self.video_recorder.close()
File "C:\Users\ASUS\anaconda3\lib\site-packages\gymnasium\wrappers\monitoring\video_recorder.py", line 161, in close
clip.write_videofile(self.path, logger=moviepy_logger)
File "C:\Users\ASUS\anaconda3\lib\site-packages\decorator.py", line 232, in fun
return caller(func, *(extras + args), **kw)
File "C:\Users\ASUS\anaconda3\lib\site-packages\moviepy\decorators.py", line 54, in requires_duration
return f(clip, *a, **k)
File "C:\Users\ASUS\anaconda3\lib\site-packages\decorator.py", line 232, in fun
return caller(func, *(extras + args), **kw)
File "C:\Users\ASUS\anaconda3\lib\site-packages\moviepy\decorators.py", line 135, in use_clip_fps_by_default
return f(clip, *new_a, **new_kw)
File "C:\Users\ASUS\anaconda3\lib\site-packages\decorator.py", line 232, in fun
return caller(func, *(extras + args), **kw)
File "C:\Users\ASUS\anaconda3\lib\site-packages\moviepy\decorators.py", line 22, in convert_masks_to_RGB
return f(clip, *a, **k)
File "C:\Users\ASUS\anaconda3\lib\site-packages\moviepy\video\VideoClip.py", line 300, in write_videofile
ffmpeg_write_video(self, filename, fps, codec,
File "C:\Users\ASUS\anaconda3\lib\site-packages\moviepy\video\io\ffmpeg_writer.py", line 213, in ffmpeg_write_video
with FFMPEG_VideoWriter(filename, clip.size, fps, codec = codec,
File "C:\Users\ASUS\anaconda3\lib\site-packages\moviepy\video\io\ffmpeg_writer.py", line 88, in init
'-r', '%.02f' % fps,
TypeError: must be real number, not NoneType
Moviepy - Building video E:\DriveLikeAHuman-main\DriveLikeAHuman-main\results-video\highwayv0-episode-0.mp4.
Moviepy - Writing video E:\DriveLikeAHuman-main\DriveLikeAHuman-main\results-video\highwayv0-episode-0.mp4
Moviepy - Building video E:\DriveLikeAHuman-main\DriveLikeAHuman-main\results-video\highwayv0-episode-0.mp4.
Moviepy - Writing video E:\DriveLikeAHuman-main\DriveLikeAHuman-main\results-video\highwayv0-episode-0.mp4
C:\Users\ASUS\anaconda3\lib\site-packages\gymnasium\wrappers\monitoring\video_recorder.py:182: UserWarning: WARN: Unable to save last video! Did you call close()?
Environment:
OS: [Windows 11]
Python Version: [3.10.13]
gymnasium version: [0.29.1]
moviepy version: [1.0.3]
IDE: [PyCharm 2023.2.1 (Professional Edition)]
Hi there,
Thanks for sharing this great work.
The code worked well when I first tried it one month ago. However, I tried it yesterday and got the Rate Limit Error from the Openai API after running up to 10 frames; therefore, the simulation terminated. I wonder whether you have had the same error as mine recently and any thoughts on this error. Looking forward to your reply.
Best,
Yixuan
Where are the 'Self-reflection' and 'Memories' modules mentioned in the paper?
Is it possible for us to use GPT-4 model (with GPT-4 API key in config file) in this project?
I have tried to replace the API key with a GPT-4 one in config.yaml
and set the model_name
of the llm
in HELLM.py
as below:
os.environ["OPENAI_API_KEY"] = OPENAI_CONFIG['OPENAI_KEY'] llm = ChatOpenAI( temperature=0, model_name='gpt-4-0613', max_tokens=1024, request_timeout=60 )
But we got error:
openai.error.InvalidRequestError: The model:
gpt-4-0613 does not exist
Thank you in advance for any helpful insight!
Hi,
This is Haowei and thanks for the open source code. When I am trying to run the repo, I encountered the following errors:
Exception has occurred: InvalidRequestError
This model's maximum context length is 4097 tokens. However, you requested 4270 tokens (3246 in the messages, 1024 in the completion). Please reduce the length of the messages or completion.
I am currently using OS Windows 11, Python 3.9.13 Anaconda, and Openai API (rather than the Azure API). I was wondering if you could help solve this issue. Please let me know if other information is required.
Thanks.
When I save the result of video, I have a problem:
Example:
Error:
> Finished chain.
Moviepy - Building video /data/GitHub/DriveLikeAHuman/results-video/highwayv0-episode-0.mp4.
Moviepy - Writing video /data/GitHub/DriveLikeAHuman/results-video/highwayv0-episode-0.mp4
Moviepy - Done !
Moviepy - video ready /data/GitHub/DriveLikeAHuman/results-video/highwayv0-episode-0.mp4
---------------------------------------------------------------------------
TimeoutError Traceback (most recent call last)
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/urllib3/connection.py:203, in HTTPConnection._new_conn(self)
202 try:
--> 203 sock = connection.create_connection(
204 (self._dns_host, self.port),
205 self.timeout,
206 source_address=self.source_address,
207 socket_options=self.socket_options,
208 )
209 except socket.gaierror as e:
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/urllib3/util/connection.py:85, in create_connection(address, timeout, source_address, socket_options)
84 try:
---> 85 raise err
86 finally:
87 # Break explicitly a reference cycle
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/urllib3/util/connection.py:73, in create_connection(address, timeout, source_address, socket_options)
72 sock.bind(source_address)
---> 73 sock.connect(sa)
74 # Break explicitly a reference cycle
TimeoutError: [Errno 110] Connection timed out
The above exception was the direct cause of the following exception:
ConnectTimeoutError Traceback (most recent call last)
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/urllib3/connectionpool.py:790, in HTTPConnectionPool.urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, preload_content, decode_content, **response_kw)
789 # Make the request on the HTTPConnection object
--> 790 response = self._make_request(
791 conn,
792 method,
793 url,
794 timeout=timeout_obj,
795 body=body,
796 headers=headers,
797 chunked=chunked,
798 retries=retries,
799 response_conn=response_conn,
800 preload_content=preload_content,
801 decode_content=decode_content,
802 **response_kw,
803 )
805 # Everything went great!
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/urllib3/connectionpool.py:491, in HTTPConnectionPool._make_request(self, conn, method, url, body, headers, retries, timeout, chunked, response_conn, preload_content, decode_content, enforce_content_length)
490 new_e = _wrap_proxy_error(new_e, conn.proxy.scheme)
--> 491 raise new_e
493 # conn.request() calls http.client.*.request, not the method in
494 # urllib3.request. It also calls makefile (recv) on the socket.
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/urllib3/connectionpool.py:467, in HTTPConnectionPool._make_request(self, conn, method, url, body, headers, retries, timeout, chunked, response_conn, preload_content, decode_content, enforce_content_length)
466 try:
--> 467 self._validate_conn(conn)
468 except (SocketTimeout, BaseSSLError) as e:
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/urllib3/connectionpool.py:1092, in HTTPSConnectionPool._validate_conn(self, conn)
1091 if conn.is_closed:
-> 1092 conn.connect()
1094 if not conn.is_verified:
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/urllib3/connection.py:611, in HTTPSConnection.connect(self)
610 sock: socket.socket | ssl.SSLSocket
--> 611 self.sock = sock = self._new_conn()
612 server_hostname: str = self.host
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/urllib3/connection.py:212, in HTTPConnection._new_conn(self)
211 except SocketTimeout as e:
--> 212 raise ConnectTimeoutError(
213 self,
214 f"Connection to {self.host} timed out. (connect timeout={self.timeout})",
215 ) from e
217 except OSError as e:
ConnectTimeoutError: (<urllib3.connection.HTTPSConnection object at 0x7f0c0bb01480>, 'Connection to openaipublic.blob.core.windows.net timed out. (connect timeout=None)')
The above exception was the direct cause of the following exception:
MaxRetryError Traceback (most recent call last)
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/requests/adapters.py:486, in HTTPAdapter.send(self, request, stream, timeout, verify, cert, proxies)
485 try:
--> 486 resp = conn.urlopen(
487 method=request.method,
488 url=url,
489 body=request.body,
490 headers=request.headers,
491 redirect=False,
492 assert_same_host=False,
493 preload_content=False,
494 decode_content=False,
495 retries=self.max_retries,
496 timeout=timeout,
497 chunked=chunked,
498 )
500 except (ProtocolError, OSError) as err:
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/urllib3/connectionpool.py:844, in HTTPConnectionPool.urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, preload_content, decode_content, **response_kw)
842 new_e = ProtocolError("Connection aborted.", new_e)
--> 844 retries = retries.increment(
845 method, url, error=new_e, _pool=self, _stacktrace=sys.exc_info()[2]
846 )
847 retries.sleep()
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/urllib3/util/retry.py:515, in Retry.increment(self, method, url, response, error, _pool, _stacktrace)
514 reason = error or ResponseError(cause)
--> 515 raise MaxRetryError(_pool, url, reason) from reason # type: ignore[arg-type]
517 log.debug("Incremented Retry for (url='%s'): %r", url, new_retry)
MaxRetryError: HTTPSConnectionPool(host='openaipublic.blob.core.windows.net', port=443): Max retries exceeded with url: /encodings/cl100k_base.tiktoken (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x7f0c0bb01480>, 'Connection to openaipublic.blob.core.windows.net timed out. (connect timeout=None)'))
During handling of the above exception, another exception occurred:
ConnectTimeout Traceback (most recent call last)
File /data/GitHub/DriveLikeAHuman/HELLM.py:105
103 while not (done or truncated):
104 sce.upateVehicles(obs, frame)
--> 105 DA.agentRun(output)
106 da_output = DA.exportThoughts()
107 output = outputParser.agentRun(da_output)
File /data/GitHub/DriveLikeAHuman/LLMDriver/driverAgent.py:72, in DriverAgent.agentRun(self, last_step_decision)
70 last_step_explanation = "Not available"
71 with get_openai_callback() as cb:
---> 72 self.agent.run(
73 f"""
74 You, the 'ego' car, are now driving a car on a highway. You have already drive for {self.sce.frame} seconds.
75 The decision you made LAST time step was `{last_step_action}`. Your explanation was `{last_step_explanation}`.
76 Here is the current scenario: \n ```json\n{self.sce.export2json()}\n```\n.
77 Please make decision for the `ego` car. You have to describe the state of the `ego`, then analyze the possible actions, and finally output your decision.
78
79 There are several rules you need to follow when you drive on a highway:
80 {TRAFFIC_RULES}
81
82 Here are your attentions points:
83 {DECISION_CAUTIONS}
84
85 Let's think step by step. Once you made a final decision, output it in the following format: \n
86 ```
87 Final Answer:
88 "decision":{{"ego car's decision, ONE of the available actions"}},
89 "expalanations":{{"your explaination about your decision, described your suggestions to the driver"}}
90 ``` \n
91 """,
92 callbacks=[self.ch]
93 )
94 print(cb)
95 print('[cyan]Final decision:[/cyan]')
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/langchain/chains/base.py:315, in Chain.run(self, callbacks, tags, metadata, *args, **kwargs)
313 if len(args) != 1:
314 raise ValueError("`run` supports only one positional argument.")
--> 315 return self(args[0], callbacks=callbacks, tags=tags, metadata=metadata)[
316 _output_key
317 ]
319 if kwargs and not args:
320 return self(kwargs, callbacks=callbacks, tags=tags, metadata=metadata)[
321 _output_key
322 ]
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/langchain/chains/base.py:183, in Chain.__call__(self, inputs, return_only_outputs, callbacks, tags, metadata, include_run_info)
181 raise e
182 run_manager.on_chain_end(outputs)
--> 183 final_outputs: Dict[str, Any] = self.prep_outputs(
184 inputs, outputs, return_only_outputs
185 )
186 if include_run_info:
187 final_outputs[RUN_KEY] = RunInfo(run_id=run_manager.run_id)
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/langchain/chains/base.py:257, in Chain.prep_outputs(self, inputs, outputs, return_only_outputs)
255 self._validate_outputs(outputs)
256 if self.memory is not None:
--> 257 self.memory.save_context(inputs, outputs)
258 if return_only_outputs:
259 return outputs
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/langchain/memory/token_buffer.py:48, in ConversationTokenBufferMemory.save_context(self, inputs, outputs)
46 # Prune buffer if it exceeds max token limit
47 buffer = self.chat_memory.messages
---> 48 curr_buffer_length = self.llm.get_num_tokens_from_messages(buffer)
49 if curr_buffer_length > self.max_token_limit:
50 pruned_memory = []
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/langchain/chat_models/openai.py:499, in ChatOpenAI.get_num_tokens_from_messages(self, messages)
497 if sys.version_info[1] <= 7:
498 return super().get_num_tokens_from_messages(messages)
--> 499 model, encoding = self._get_encoding_model()
500 if model.startswith("gpt-3.5-turbo"):
501 # every message follows <im_start>{role/name}\n{content}<im_end>\n
502 tokens_per_message = 4
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/langchain/chat_models/openai.py:477, in ChatOpenAI._get_encoding_model(self)
475 # Returns the number of tokens used by a list of messages.
476 try:
--> 477 encoding = tiktoken_.encoding_for_model(model)
478 except KeyError:
479 logger.warning("Warning: model not found. Using cl100k_base encoding.")
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/tiktoken/model.py:67, in encoding_for_model(model_name)
65 for model_prefix, model_encoding_name in MODEL_PREFIX_TO_ENCODING.items():
66 if model_name.startswith(model_prefix):
---> 67 return get_encoding(model_encoding_name)
69 if encoding_name is None:
70 raise KeyError(
71 f"Could not automatically map {model_name} to a tokeniser. "
72 "Please use `tiktok.get_encoding` to explicitly get the tokeniser you expect."
73 ) from None
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/tiktoken/registry.py:63, in get_encoding(encoding_name)
60 raise ValueError(f"Unknown encoding {encoding_name}")
62 constructor = ENCODING_CONSTRUCTORS[encoding_name]
---> 63 enc = Encoding(**constructor())
64 ENCODINGS[encoding_name] = enc
65 return enc
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/tiktoken_ext/openai_public.py:64, in cl100k_base()
63 def cl100k_base():
---> 64 mergeable_ranks = load_tiktoken_bpe(
65 "https://openaipublic.blob.core.windows.net/encodings/cl100k_base.tiktoken"
66 )
67 special_tokens = {
68 ENDOFTEXT: 100257,
69 FIM_PREFIX: 100258,
(...)
72 ENDOFPROMPT: 100276,
73 }
74 return {
75 "name": "cl100k_base",
76 "pat_str": r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}{1,3}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+""",
77 "mergeable_ranks": mergeable_ranks,
78 "special_tokens": special_tokens,
79 }
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/tiktoken/load.py:116, in load_tiktoken_bpe(tiktoken_bpe_file)
114 def load_tiktoken_bpe(tiktoken_bpe_file: str) -> dict[bytes, int]:
115 # NB: do not add caching to this function
--> 116 contents = read_file_cached(tiktoken_bpe_file)
117 return {
118 base64.b64decode(token): int(rank)
119 for token, rank in (line.split() for line in contents.splitlines() if line)
120 }
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/tiktoken/load.py:48, in read_file_cached(blobpath)
45 with open(cache_path, "rb") as f:
46 return f.read()
---> 48 contents = read_file(blobpath)
50 os.makedirs(cache_dir, exist_ok=True)
51 tmp_filename = cache_path + "." + str(uuid.uuid4()) + ".tmp"
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/tiktoken/load.py:24, in read_file(blobpath)
22 return f.read()
23 # avoiding blobfile for public files helps avoid auth issues, like MFA prompts
---> 24 resp = requests.get(blobpath)
25 resp.raise_for_status()
26 return resp.content
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/requests/api.py:73, in get(url, params, **kwargs)
62 def get(url, params=None, **kwargs):
63 r"""Sends a GET request.
64
65 :param url: URL for the new :class:`Request` object.
(...)
70 :rtype: requests.Response
71 """
---> 73 return request("get", url, params=params, **kwargs)
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/requests/api.py:59, in request(method, url, **kwargs)
55 # By using the 'with' statement we are sure the session is closed, thus we
56 # avoid leaving sockets open which can trigger a ResourceWarning in some
57 # cases, and look like a memory leak in others.
58 with sessions.Session() as session:
---> 59 return session.request(method=method, url=url, **kwargs)
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/requests/sessions.py:589, in Session.request(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)
584 send_kwargs = {
585 "timeout": timeout,
586 "allow_redirects": allow_redirects,
587 }
588 send_kwargs.update(settings)
--> 589 resp = self.send(prep, **send_kwargs)
591 return resp
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/requests/sessions.py:703, in Session.send(self, request, **kwargs)
700 start = preferred_clock()
702 # Send the request
--> 703 r = adapter.send(request, **kwargs)
705 # Total elapsed time of the request (approximately)
706 elapsed = preferred_clock() - start
File ~/anaconda3/envs/llama/lib/python3.10/site-packages/requests/adapters.py:507, in HTTPAdapter.send(self, request, stream, timeout, verify, cert, proxies)
504 if isinstance(e.reason, ConnectTimeoutError):
505 # TODO: Remove this in 3.0.0: see #2811
506 if not isinstance(e.reason, NewConnectionError):
--> 507 raise ConnectTimeout(e, request=request)
509 if isinstance(e.reason, ResponseError):
510 raise RetryError(e, request=request)
ConnectTimeout: HTTPSConnectionPool(host='openaipublic.blob.core.windows.net', port=443): Max retries exceeded with url: /encodings/cl100k_base.tiktoken (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x7f0c0bb01480>, 'Connection to openaipublic.blob.core.windows.net timed out. (connect timeout=None)'))
MY Version:
python==3.10
urllib3==2.0.4
moviepy==1.0.3
tiktoken==0.4.0
I guess it may be a problem with the urllib3 version, my current version is urllib3==2.0.4,
I would like to ask your the version of urllib3 , python, moviepy and tiktoken.
Thank you.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.