ssl.SSLCertVerificationError when running for first time

[mgug01]

⚠️ Search for existing issues first ⚠️

• [X] I have searched the existing issues, and there is no existing issue for my problem

Which Operating System are you using?

MacOS

GPT-3 or GPT-4?

GPT-3.5

Steps to reproduce 🕹

Installed all dependencies as required, edited .env as required, ran python -m autogpt, followed prompts and received below error.

Current behavior 😯

Initial prompts work as expected, but after setting goals and beginning to run the following error appears causing the process to fail:

Using memory of type: 
 LocalCache
Using Browser:  chrome
Traceback (most recent call last):
...
ssl.SSLCertVerificationError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self signed certificate in certificate chain (_ssl.c:997)

Expected behavior 🤔

No response

Your prompt 📝

python -m autogpt

Your Logs 📒

2023-04-19 12:22:53,215 INFO Welcome to Auto-GPT!  Enter the name of your AI and its role below. Entering nothing will load defaults.
2023-04-19 12:22:53,624 INFO Name your AI:  For example, 'Entrepreneur-GPT'
2023-04-19 12:23:17,652 INFO Entrepreneur-GPT here! I am at your service.
2023-04-19 12:23:17,848 INFO Describe your AI's role:  For example, 'an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth.'
2023-04-19 12:24:08,586 INFO Enter up to 5 goals for your AI:  For example: 
Increase net worth, Grow Twitter Account, Develop and manage multiple businesses autonomously'
2023-04-19 12:27:47,754 INFO FAILED TO CONNECT TO PINECONE HTTPSConnectionPool(host='controller.asia-southeast1-gcp.pinecone.io', port=443): Max retries exceeded with url: /actions/whoami (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self signed certificate in certificate chain (_ssl.c:997)')))
2023-04-19 12:27:48,417 INFO DOUBLE CHECK CONFIGURATION Please ensure you have setup and configured Pinecone properly for use.You can check out https://github.com/Torantulino/Auto-GPT#-pinecone-api-key-setup to ensure you've set up everything correctly.
2023-04-19 12:28:19,512 INFO Welcome back!  Would you like me to return to being Entrepreneur-GPT?
2023-04-19 12:28:26,319 INFO Using memory of type: LocalCache
2023-04-19 12:28:26,525 INFO Using Browser: chrome
2023-04-19 12:30:03,984 INFO Welcome back!  Would you like me to return to being Entrepreneur-GPT?
2023-04-19 12:30:05,338 INFO Using memory of type: LocalCache
2023-04-19 12:30:05,497 INFO Using Browser: firefox
2023-04-19 14:00:11,912 INFO Welcome back!  Would you like me to return to being Entrepreneur-GPT?
2023-04-19 14:00:13,884 INFO Using memory of type: LocalCache
2023-04-19 14:00:14,063 INFO Using Browser: firefox
2023-04-19 14:39:47,396 INFO Welcome back!  Would you like me to return to being Entrepreneur-GPT?
2023-04-19 14:39:49,352 INFO Using memory of type: LocalCache
2023-04-19 14:39:49,504 INFO Using Browser: firefox
2023-04-19 14:42:52,116 INFO Welcome back!  Would you like me to return to being Entrepreneur-GPT?
2023-04-19 14:42:53,618 INFO Using memory of type: LocalCache
2023-04-19 14:42:53,743 INFO Using Browser: firefox
2023-04-19 14:44:50,176 INFO Welcome back!  Would you like me to return to being Entrepreneur-GPT?
2023-04-19 14:44:51,365 INFO Using memory of type: LocalCache
2023-04-19 14:44:51,514 INFO Using Browser: chrome
2023-04-19 14:53:52,366 INFO Welcome back!  Would you like me to return to being Entrepreneur-GPT?
2023-04-19 14:53:56,153 INFO Welcome to Auto-GPT!  Enter the name of your AI and its role below. Entering nothing will load defaults.
2023-04-19 14:53:56,601 INFO Name your AI:  For example, 'Entrepreneur-GPT'
2023-04-19 14:53:59,707 INFO Test here! I am at your service.
2023-04-19 14:53:59,908 INFO Describe your AI's role:  For example, 'an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth.'
2023-04-19 14:54:07,932 INFO Enter up to 5 goals for your AI:  For example: 
Increase net worth, Grow Twitter Account, Develop and manage multiple businesses autonomously'
2023-04-19 14:54:36,962 INFO Using memory of type: LocalCache
2023-04-19 14:54:37,133 INFO Using Browser: chrome

[k-boikov]

python version?

[mgug01]

python version?

Currently on 3.10.5. I installed the requirements within a venv. Also- on a Mac OS 13.3.1

[k-boikov]

I think you should read this https://stackoverflow.com/a/42334357

[ntindle]

Are you using a proxy?

[ilannn]

I've experienced this same error when trying to run auto-gpt over docker on a Mac M1 (using the docker-compose in the repo). No proxy configured.

Edit Exception traceback

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 "/home/appuser/autogpt/__main__.py", line 5, in <module>
    autogpt.cli.main()
  File "/home/appuser/.local/lib/python3.10/site-packages/click/core.py", line 1130, in __call__
    return self.main(*args, **kwargs)
  File "/home/appuser/.local/lib/python3.10/site-packages/click/core.py", line 1055, in main
    rv = self.invoke(ctx)
  File "/home/appuser/.local/lib/python3.10/site-packages/click/core.py", line 1635, in invoke
    rv = super().invoke(ctx)
  File "/home/appuser/.local/lib/python3.10/site-packages/click/core.py", line 1404, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/home/appuser/.local/lib/python3.10/site-packages/click/core.py", line 760, in invoke
    return __callback(*args, **kwargs)
  File "/home/appuser/.local/lib/python3.10/site-packages/click/decorators.py", line 26, in new_func
    return f(get_current_context(), *args, **kwargs)
  File "/home/appuser/autogpt/cli.py", line 151, in main
    agent.start_interaction_loop()
  File "/home/appuser/autogpt/agent/agent.py", line 75, in start_interaction_loop
    assistant_reply = chat_with_ai(
  File "/home/appuser/autogpt/chat.py", line 159, in chat_with_ai
    assistant_reply = create_chat_completion(
  File "/home/appuser/autogpt/llm_utils.py", line 93, in create_chat_completion
    response = openai.ChatCompletion.create(
  File "/home/appuser/.local/lib/python3.10/site-packages/openai/api_resources/chat_completion.py", line 25, in create
    return super().create(*args, **kwargs)
  File "/home/appuser/.local/lib/python3.10/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
    response, _, api_key = requestor.request(
  File "/home/appuser/.local/lib/python3.10/site-packages/openai/api_requestor.py", line 216, in request
    result = self.request_raw(
  File "/home/appuser/.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: HTTPSConnectionPool(host='api.openai.com', port=443): Max retries exceeded with url: /v1/chat/completions (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self signed certificate in certificate chain (_ssl.c:1007)')))

The issue doesn't seem to be in firing https requests. I tried running requests.get("https://google.com") and it worked.

[ilannn]

Looking at more references across the web, it might have been related to my corporate VPN, the fact was running the solution inside the python:3.10 container, or the fact that it was running on my M1 Mac.

I managed to overcome this issue by following the following comment: https://community.openai.com/t/ssl-certificate-verify-failed/32442/47