Can't run <step-count> about generative_agents HOT 13 CLOSED

in reverie.py , import traceback , then add traceback.print_exc() before print ("Error."),save file and restart python reverie.py

you will see more detail info about your error
my is "openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details."

from generative_agents.

same problem

from generative_agents.

I also meet the same problem.

`python reverie.py
Enter the name of the forked simulation: base_the_ville_isabella_maria_klaus
Enter the name of the new simulation: test-simulation
Note: The agents in this simulation package are computational
constructs powered by generative agents architecture and LLM. We
clarify that these agents lack human-like agency, consciousness,
and independent decision-making.

Enter option: run 100
Error.
Enter option: run 1000
Error.
Enter option: `

from generative_agents.

in reverie.py , import traceback , then add traceback.print_exc() before print ("Error."),save file and restart python reverie.py

you will see more detail info about your error my is "openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details."

I have the same error. Is this need GPT-4 API? How can I use GPT-3.5 API to replace?

from generative_agents.

in reverie.py , import traceback , then add traceback.print_exc() before print ("Error."),save file and restart python reverie.py
you will see more detail info about your error my is "openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details."

I have the same error. Is this need GPT-4 API? How can I use GPT-3.5 API to replace?

I have replaced the old API with a new one (GPT3.5) and it seems to be working properly.
But the new problem is that there is only output in Termin , I can't see the Simulation on my browser

from generative_agents.

in reverie.py , import traceback , then add traceback.print_exc() before print ("Error."),save file and restart python reverie.py

you will see more detail info about your error my is "openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details."

I added the code and got the error.
openai.error.RateLimitError: Rate limit reached for default-text-embedding-ada-002 in organization org-1SwtoMrxxx on requests per min. Limit: 3 / min. Please try again in 20s. Contact us through our help center at help.openai.com if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method.
I input run 1, but it still throws this error.
Can the call frequency be modified?

from generative_agents.

in reverie.py , import traceback , then add traceback.print_exc() before print ("Error."),save file and restart python reverie.py
you will see more detail info about your error my is "openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details."

I added the code and got the error. openai.error.RateLimitError: Rate limit reached for default-text-embedding-ada-002 in organization org-1SwtoMrxxx on requests per min. Limit: 3 / min. Please try again in 20s. Contact us through our help center at help.openai.com if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method. I input run 1, but it still throws this error. Can the call frequency be modified?

You can through inserting a time.sleep(0.5) in "generative_agents/reverie/backend_server/persona/prompt_template/gpt_structure.py, line 278" to control the call frequency. It's a simple way. run 1, it still sent many messages to chatgpt. For example, every character will sent a message to chatgpt.

from generative_agents.

maybe the issue from running out of the quota😂

from generative_agents.

maybe the issue from running out of the quota😂

I'm the same. How can I solve it

from generative_agents.

maybe the issue from running out of the quota😂

I think your account balance has been used up, and you need to subscribe to OpenAI or replace the API key.

from generative_agents.

in reverie.py , import traceback , then add traceback.print_exc() before print ("Error."),save file and restart python reverie.py
you will see more detail info about your error my is "openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details."

I added the code and got the error. openai.error.RateLimitError: Rate limit reached for default-text-embedding-ada-002 in organization org-1SwtoMrxxx on requests per min. Limit: 3 / min. Please try again in 20s. Contact us through our help center at help.openai.com if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method. I input run 1, but it still throws this error. Can the call frequency be modified?

same error

from generative_agents.

in reverie.py , import traceback , then add traceback.print_exc() before print ("Error."),save file and restart python reverie.py
you will see more detail info about your error my is "openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details."

I added the code and got the error. openai.error.RateLimitError: Rate limit reached for default-text-embedding-ada-002 in organization org-1SwtoMrxxx on requests per min. Limit: 3 / min. Please try again in 20s. Contact us through our help center at help.openai.com if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method. I input run 1, but it still throws this error. Can the call frequency be modified?

same error

you should add a payment (credit card), the free account have Rate limit (3 / min), it's not enough for this project.

from generative_agents.

maybe the issue from running out of the quota😂

I think the FREE account can't support this project because of the Rate limit (3/min). I ran 10 times (about 2 min) and it cost me $1.5. This project will generate a large number of API requests in a short period of time.

from generative_agents.