Significant-Gravitas / AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
https://agpt.co
MIT License
166.1k stars 43.97k forks source link

Keeps Crashing After a Few Responses (Even on Small Chunks, Not Based on Large Chunks) #4115

Closed ZylerKade closed 11 months ago

ZylerKade commented 1 year ago

⚠️ Search for existing issues first ⚠️

Which Operating System are you using?

Devcontainer / Codespace

Which version of Auto-GPT are you using?

Stable (branch)

GPT-3 or GPT-4?

GPT-4

Steps to reproduce 🕹

Running it like normal in VS Code + Container.

It allows me to give it instructions, and begins running like it should for a few minutes.

But after several prompts back and forth, it crashes.

It doesn't seem like chunk size has anything to do with it as it was able to process large chunks fine in a previous prompt before it crashed on a small chunk, but then when I ran it again it crashed after only 3 prompt cycles on a single/small chunk.

First time was able to go through 10 prompt cycles before crashing, second time it was only able to do 3 before crashing.

And yes, I have the Paid API account (which worked beautifully with no issues in AutoGPT v0.2.2, and not to be mistaken with the ChatGPT4 Plus paid account) with GPT-4 API access.

Current behavior 😯

-=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= Text length: 5363 characters Adding chunk 1 / 1 to memory Summarizing chunk 1 / 1 of length 5363 characters, or 1197 tokens Added chunk 1 summary to memory, of length 1053 characters Summarized 1 chunks. SYSTEM: Command browse_website returned: ("Answer gathered from website: The text does not provide information on the top 10 AI blogs to follow in 2021. Instead, it is a website that covers insights, trends, and opinions related to data-driven technologies, including AI, Big Data, and Analytics. The website features articles on various topics related to AI, machine learning, deep learning, computer vision, natural language processing, and more. \n \n Links: [' (https://intellipaat.com/advanced-certification-data-science-artificial-intelligence-iit-madras/?utm_source=AI_popup&utm_medium=popup&utm_campaign=display_AI_popup)', '\n\n (https://presale.tmsnetwork.io/invite?ref=UD00038)', ' (https://www.analyticsinsight.net/)', 'Analytics Insight (https://www.analyticsinsight.net/)', 'Insights (https://www.analyticsinsight.net/category/insights/)']", <selenium.webdriver.chrome.webdriver.WebDriver (session="e37399b072b37790a7279dd5418b9d6b")>) THOUGHTS: The website I browsed did not provide the information I was looking for. I will need to conduct further research to identify other websites and blogs that share daily or weekly content related to the artificial intelligence industry. I will use internet searches and long-term memory management to accomplish this task. REASONING: Since the website I browsed did not provide the information I was looking for, I need to conduct further research to identify other websites and blogs that share daily or weekly content related to the artificial intelligence industry. Internet searches and long-term memory management will help me accomplish this task. PLAN:

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/vscode/.local/lib/python3.10/site-packages/requests/adapters.py", line 486, in send resp = conn.urlopen( File "/home/vscode/.local/lib/python3.10/site-packages/urllib3/connectionpool.py", line 787, in urlopen retries = retries.increment( File "/home/vscode/.local/lib/python3.10/site-packages/urllib3/util/retry.py", line 550, in increment raise six.reraise(type(error), error, _stacktrace) File "/home/vscode/.local/lib/python3.10/site-packages/urllib3/packages/six.py", line 769, in reraise raise value.with_traceback(tb) File "/home/vscode/.local/lib/python3.10/site-packages/urllib3/connectionpool.py", line 703, in urlopen httplib_response = self._make_request( File "/home/vscode/.local/lib/python3.10/site-packages/urllib3/connectionpool.py", line 449, in _make_request six.raise_from(e, None) File "", line 3, in raise_from File "/home/vscode/.local/lib/python3.10/site-packages/urllib3/connectionpool.py", line 444, in _make_request httplib_response = conn.getresponse() File "/usr/local/lib/python3.10/http/client.py", line 1375, in getresponse response.begin() File "/usr/local/lib/python3.10/http/client.py", line 318, in begin version, status, reason = self._read_status() File "/usr/local/lib/python3.10/http/client.py", line 287, in _read_status raise RemoteDisconnected("Remote end closed connection without" urllib3.exceptions.ProtocolError: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response'))

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/vscode/.local/lib/python3.10/site-packages/openai/api_requestor.py", line 516, in request_raw result = _thread_context.session.request( File "/home/vscode/.local/lib/python3.10/site-packages/requests/sessions.py", line 587, in request resp = self.send(prep, send_kwargs) File "/home/vscode/.local/lib/python3.10/site-packages/requests/sessions.py", line 701, in send r = adapter.send(request, kwargs) File "/home/vscode/.local/lib/python3.10/site-packages/requests/adapters.py", line 501, in send raise ConnectionError(err, request=request) requests.exceptions.ConnectionError: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response'))

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "/usr/local/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/usr/local/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/workspace/Auto-GPT/autogpt/main.py", line 5, in autogpt.cli.main() File "/home/vscode/.local/lib/python3.10/site-packages/click/core.py", line 1130, in call return self.main(args, kwargs) File "/home/vscode/.local/lib/python3.10/site-packages/click/core.py", line 1055, in main rv = self.invoke(ctx) File "/home/vscode/.local/lib/python3.10/site-packages/click/core.py", line 1635, in invoke rv = super().invoke(ctx) File "/home/vscode/.local/lib/python3.10/site-packages/click/core.py", line 1404, in invoke return ctx.invoke(self.callback, ctx.params) File "/home/vscode/.local/lib/python3.10/site-packages/click/core.py", line 760, in invoke return __callback(args, kwargs) File "/home/vscode/.local/lib/python3.10/site-packages/click/decorators.py", line 26, in new_func return f(get_current_context(), *args, *kwargs) File "/workspace/Auto-GPT/autogpt/cli.py", line 90, in main run_auto_gpt( File "/workspace/Auto-GPT/autogpt/main.py", line 171, in run_auto_gpt agent.start_interaction_loop() File "/workspace/Auto-GPT/autogpt/agent/agent.py", line 94, in start_interaction_loop assistant_reply = chat_with_ai( File "/workspace/Auto-GPT/autogpt/llm/chat.py", line 237, in chat_with_ai assistant_reply = create_chat_completion( File "/workspace/Auto-GPT/autogpt/llm/llm_utils.py", line 166, in create_chat_completion response = api_manager.create_chat_completion( File "/workspace/Auto-GPT/autogpt/llm/api_manager.py", line 55, in create_chat_completion response = openai.ChatCompletion.create( File "/home/vscode/.local/lib/python3.10/site-packages/openai/api_resources/chat_completion.py", line 25, in create return super().create(args, kwargs) File "/home/vscode/.local/lib/python3.10/site-packages/openai/api_resources/abstract/engine_apiresource.py", line 153, in create response, , api_key = requestor.request( File "/home/vscode/.local/lib/python3.10/site-packages/openai/api_requestor.py", line 216, in request result = self.request_raw( File "/home/vscode/.local/lib/python3.10/site-packages/openai/api_requestor.py", line 528, in request_raw raise error.APIConnectionError( openai.error.APIConnectionError: Error communicating with OpenAI: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response'))

Expected behavior 🤔

Should return results from the web search and determine next steps.

Your prompt 📝


ai_goals:
- Conduct extensive research to identify the top 10 most popular websites and blogs that share daily or weekly content related to the artificial intelligence industry.
 - Analyze the content of each website and blog to ensure that it is relevant, accurate, and up-to-date.
 - Provide a comprehensive list of the top 10 websites and blogs, along with a brief description of each and the type of content they share.
 - Continuously monitor and update the list to ensure that it remains current and relevant.
 - Offer suggestions for additional websites and blogs to add to the list based on your preferences and feedback. 
 - Conduct extensive research to identify the top 10 most popular websites and blogs that share daily or weekly content related to the artificial intelligence industry.
- Analyze the content of each website and blog to ensure that it is relevant, accurate, and up-to-date.
- Provide a comprehensive list of the top 10 websites and blogs, along with a brief description of each and the type of content they share.
- Continuously monitor and update the list to ensure that it remains current and relevant.
- Offer suggestions for additional websites and blogs to add to the list based on your preferences and feedback.
ai_name: AIGPT
ai_role: an autonomous agent that specializes in gathering and analyzing data related to the artificial intelligence industry to provide you with the most up-to-date and relevant information.
api_budget: 0.0

Your Logs 📒


2023-05-11 14:38:07,254 INFO  Text length: 5363 characters
2023-05-11 14:38:08,050 INFO  Adding chunk 1 / 1 to memory
2023-05-11 14:38:08,301 INFO  Summarizing chunk 1 / 1 of length 5363 characters, or 1197 tokens
2023-05-11 14:38:27,538 INFO  Added chunk 1 summary to memory, of length 1053 characters
2023-05-11 14:38:27,729 INFO  Summarized 1 chunks.
2023-05-11 14:38:34,444 INFO SYSTEM:  Command browse_website returned: ("Answer gathered from website: The text does not provide information on the top 10 AI blogs to follow in 2021. Instead, it is a website that covers insights, trends, and opinions related to data-driven technologies, including AI, Big Data, and Analytics. The website features articles on various topics related to AI, machine learning, deep learning, computer vision, natural language processing, and more. \n \n Links: [' (https://intellipaat.com/advanced-certification-data-science-artificial-intelligence-iit-madras/?utm_source=AI_popup&utm_medium=popup&utm_campaign=display_AI_popup)', '\\n\\n (https://presale.tmsnetwork.io/invite?ref=UD00038)', ' (https://www.analyticsinsight.net/)', 'Analytics Insight (https://www.analyticsinsight.net/)', 'Insights (https://www.analyticsinsight.net/category/insights/)']", <selenium.webdriver.chrome.webdriver.WebDriver (session="e37399b072b37790a7279dd5418b9d6b")>)
2023-05-11 14:39:05,922 INFO  THOUGHTS: The website I browsed did not provide the information I was looking for. I will need to conduct further research to identify other websites and blogs that share daily or weekly content related to the artificial intelligence industry. I will use internet searches and long-term memory management to accomplish this task.
2023-05-11 14:39:06,507 INFO REASONING: Since the website I browsed did not provide the information I was looking for, I need to conduct further research to identify other websites and blogs that share daily or weekly content related to the artificial intelligence industry. Internet searches and long-term memory management will help me accomplish this task.
2023-05-11 14:39:07,081 INFO PLAN: 
2023-05-11 14:39:07,149 INFO -  Conduct further research to identify other websites and blogs that share daily or weekly content related to the artificial intelligence industry.
2023-05-11 14:39:07,563 INFO -  Use internet searches and long-term memory management to accomplish this task.
2023-05-11 14:39:07,847 INFO CRITICISM: I need to ensure that I am using my internet searches and long-term memory management efficiently to complete this task in the least number of steps possible.
2023-05-11 14:39:08,318 INFO NEXT ACTION:  COMMAND = browse_website  ARGUMENTS = {'url': 'https://www.analyticsvidhya.com/blog/2021/01/top-10-ai-blogs-to-follow-in-2021/', 'question': 'What are the top 10 AI blogs to follow in 2021?'}
2023-05-11 14:39:08,754 INFO  Enter 'y' to authorise command, 'y -N' to run N continuous commands, 's' to run self-feedback commands'n' to exit program, or enter feedback for ...
2023-05-11 14:39:08,754 INFO  Asking user via keyboard...
2023-05-11 14:39:46,680 INFO -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= 
2023-05-11 14:40:01,750 INFO  Text length: 8138 characters
2023-05-11 14:40:02,403 INFO  Adding chunk 1 / 1 to memory
2023-05-11 14:40:02,644 INFO  Summarizing chunk 1 / 1 of length 8139 characters, or 2770 tokens
2023-05-11 14:40:10,314 INFO  Added chunk 1 summary to memory, of length 378 characters
2023-05-11 14:40:10,536 INFO  Summarized 1 chunks.
2023-05-11 14:40:19,273 INFO SYSTEM:  Command browse_website returned: ("Answer gathered from website: The text does not provide a list of the top 10 AI blogs to follow in 2021. Instead, it describes a website for a data science community that offers various resources related to machine learning, deep learning, NLP, computer vision, data visualization, and data engineering, including courses, articles, guides, podcasts, and job postings. The website also has a blog section where data scientists can write and share their articles. \n \n Links: ['\\n\\n (https://www.analyticsvidhya.com/blog/)', '\\n\\nStart Here\\n (javascript:void(0);)', 'Machine Learning (https://courses.analyticsvidhya.com/courses/Machine-Learning-Certification-Course-for-Beginners?utm_source=blog_navbar&utm_medium=start_here_button)', 'Deep Learning (https://courses.analyticsvidhya.com/courses/getting-started-with-neural-networks?utm_source=blog_navbar&utm_medium=start_here_button)', 'NLP (https://courses.analyticsvidhya.com/courses/Intro-to-NLP?utm_source=blog_navbar&utm_medium=start_here_button)']", <selenium.webdriver.chrome.webdriver.WebDriver (session="377017e1add43582f78b81c7738548fe")>)
2023-05-11 14:40:47,228 INFO  THOUGHTS: The website I browsed did not provide the information I was looking for. I will need to conduct further research to identify other websites and blogs that share daily or weekly content related to the artificial intelligence industry. I will use internet searches and long-term memory management to accomplish this task.
2023-05-11 14:40:47,787 INFO REASONING: Since the website I browsed did not provide the information I was looking for, I need to conduct further research to identify other websites and blogs that share daily or weekly content related to the artificial intelligence industry. Internet searches and long-term memory management will help me accomplish this task.
2023-05-11 14:40:48,342 INFO PLAN: 
2023-05-11 14:40:48,420 INFO -  Conduct further research to identify other websites and blogs that share daily or weekly content related to the artificial intelligence industry.
2023-05-11 14:40:48,847 INFO -  Use internet searches and long-term memory management to accomplish this task.
2023-05-11 14:40:49,067 INFO CRITICISM: I need to ensure that I am using my internet searches and long-term memory management efficiently to complete this task in the least number of steps possible.
2023-05-11 14:40:49,541 INFO NEXT ACTION:  COMMAND = browse_website  ARGUMENTS = {'url': 'https://emerj.com/ai-sector-overviews/top-ai-blogs-to-follow/', 'question': 'What are the top 10 AI blogs to follow in 2021?'}
2023-05-11 14:41:02,995 INFO  Text length: 3598 characters
2023-05-11 14:41:03,561 INFO  Adding chunk 1 / 1 to memory
2023-05-11 14:41:04,068 INFO  Summarizing chunk 1 / 1 of length 3602 characters, or 765 tokens
2023-05-11 14:41:11,360 INFO  Added chunk 1 summary to memory, of length 413 characters
2023-05-11 14:41:11,494 INFO  Summarized 1 chunks.
2023-05-11 14:41:15,179 INFO SYSTEM:  Command browse_website returned: ("Answer gathered from website: The text does not provide a list of the top 10 AI blogs to follow in 2021. It discusses the services and resources offered by Emerj Artificial Intelligence Research and recent developments in AI. \n \n Links: ['   (https://emerj.com/)', 'Insights (https://emerj.com/ai-sector-overviews/top-ai-blogs-to-follow/)', 'AI in Industries (https://emerj.com/ai-in-industry/)', 'Explore AI by IndustryPLUS (https://emerj.com/membership-matrix/)', 'Consumer goods (https://emerj.com/ai-in-industry/consumer-goods/)']", <selenium.webdriver.chrome.webdriver.WebDriver (session="38ecc2a1f541248ce52c7551751e9d2e")>)
github-actions[bot] commented 11 months ago

This issue has automatically been marked as stale because it has not had any activity in the last 50 days. You can unstale it by commenting or removing the label. Otherwise, this issue will be closed in 10 days.

github-actions[bot] commented 11 months ago

This issue was closed automatically because it has been stale for 10 days with no activity.