Activity
Mon
Wed
Fri
Sun
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
What is this?
Less
More

Memberships

AI Automation Society

208.5k members • Free

Ai Automation Vault

14.5k members • Free

AI Developer Accelerator

10.8k members • Free

2 contributions to AI Developer Accelerator
Problems with OpenAI Connection
I had asked for help on trying to get my hierarchical ai newsletter from Brandon's video up and running. I did not understand all the error message but it seems to come down to my connection to openai. When I use OpenAIGPT4 = ChatOpenAI(model = "gpt-4") in the program, I get this message at the end of a long error string: File "/Users/terrybyrd/Library/Caches/pypoetry/virtualenvs/ai-newsletter2-Qzdo-5fg-py3.12/lib/python3.12/site-packages/openai/_base_client.py", line 1020, in _request raise self._make_status_error_from_response(err.response) from None openai.NotFoundError: Error code: 404 - {'error': {'message': 'The model `gpt-4` does not exist or you do not have access to it.', 'type': 'invalid_request_error', 'param': None, 'code': 'model_not_found'}} Whe I use OpenAIGPT4 = ChatOpenAI(model="gpt-3.5-turbo", I get this error at the end of the error string: File "/Users/terrybyrd/Library/Caches/pypoetry/virtualenvs/ai-newsletter2-Qzdo-5fg-py3.12/lib/python3.12/site-packages/openai/_base_client.py", line 1020, in _request raise self._make_status_error_from_response(err.response) from None openai.RateLimitError: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}} I have more than enough to satisfy this request in my OpenAI account ($18.00) and none of it seems to be used when I run this crew. There could be some other problems with the program but I suspect all of the other problems start with this failure. Any thoughts on this?
0 likes • May '24
@Mick Wright Hey, Mark, thanks for your response. Yes, it is a little confusing about just what ChatGPT is doing. I have listened to several analysis and there does not seem to be a consensus on just what is happening. I have gone back and used some other LLMs on some of these programs and they seem to be operating fine. I will take the advice you guys have given me and see what happens. Thanks again for your help.
0 likes • May '24
@Mick Wright It seems like there is no cost to using Groq and Llama3 on the sample programs and the programs that Brandon presents in his video. What is your experience in using these? It seems like it would be good combination for simple and intermediate tasks from my limited viewpoint.
Help with CrewAI and Python
I need help from anyone in the community who can answer my question. I have been following Brandon video on building a travel planner from his video for Crewai beginners. I downloaded python 3.11.9 as it seems that he says you should use a version less than 3.12. I followed his instructions to the letter but I am still getting some type(s) of errors when I run the application. The error starts like this: "> Entering new CrewAgentExecutor chain... Exception in thread Thread-1 (_execute): Traceback (most recent call last): File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/threading.py", line 1045, in _bootstrap_inner self.run() File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/threading.py", line 982, in run ..." and end like this: " File "/Users/terrybyrd/Library/Caches/pypoetry/virtualenvs/ai-news-letter-8g0Q9LeX-py3.11/lib/python3.11/site-packages/crewai/crew.py", line 242, in _run_hierarchical_process task_output = task.execute( ^^^^^^^^^^^^^ File "/Users/terrybyrd/Library/Caches/pypoetry/virtualenvs/ai-news-letter-8g0Q9LeX-py3.11/lib/python3.11/site-packages/crewai/task.py", line 93, in execute context.append(task.output.result) ^^^^^^^^^^^^^^^^^^ AttributeError: 'NoneType' object has no attribute 'result'" Now I could put the entire error output up but it is long. I understand programming fairly well but have been away from it for a while. I am not familiar with all the packages and independencies of these packages but I am picking it up as I go along. Any suggestions to solving my problem will be very much appreciated. Thanks.
0 likes • May '24
@Tyson Benson async_execution is enabled like in Brandon's video. This is the code for Brandon's hierarchical example. I put in a few print statements to see if certain points in the main.py file was being reached. I guess I did not put the correct ending of the error message: Here it is if this help: File "/Users/terrybyrd/Library/Caches/pypoetry/virtualenvs/ai-newsletter-Qzdo-5fg-py3.12/lib/python3.12/site-packages/openai/_base_client.py", line 1020, in _request raise self._make_status_error_from_response(err.response) from None openai.NotFoundError: Error code: 404 - {'error': {'message': 'The model `gpt-4` does not exist or you do not have access to it.', 'type': 'invalid_request_error', 'param': None, 'code': 'model_not_found'}}
0 likes • May '24
I was saying that I put a few print statements to see if some of the calls were being made to the tasks and agents and that seem to be working.
1-2 of 2
Terry Byrd
1
4points to level up
@terry-byrd-7829
Retired MIS Professor. I taught MIS courses at Florida State University and Auburn University.

Active 114d ago
Joined May 13, 2024
Auburn, AL 36830
Powered by