Closed SteakSmoothie closed 1 year ago
same is happening to me- i am trying to fitget with it right now
same here. after a long time it came back with a "RuntimeError: Failed to get response after 10 retries". I have chatgpt plus.
Post ai_settings.yaml file in your problem description
Same. Someone has broken the latest master build.
Nope, I just stopped and restarted mine, it still works:
only thing weird is when starting start_bot.py you have to do it like: python ./autogpt/start_bot.py --gpt3only But doing that implies that clone_repository clones everything into . and outside of the workplace
Many programmers are working on getting these bugs/features implemented. I have noticed this occurring, especially with selenium. There will be corrections in the future.
Nope, I just stopped and restarted mine, it still works:
What interface is that? I'm running mine in my terminal
I am also running mine in terminal and having the same problem
same problem Wireless looping thinking
Same problem here - I entered debugging mode and I keep getting this message. Anyone know what might be causing this? I believe it is related to the OpenAI API - I've tried several different newly generated APIs from OpenAI and still etting the same result
Nope, I just stopped and restarted mine, it still works:
What interface is that? I'm running mine in my terminal
I was curious, too. It looks like it's the version of Auto-GPT mentioned in their screen shots.. it's a telegram bot https://github.com/Wladastic/Auto-GPT
I have the same issue. Not sure if it's related, but I get the following warning when I restart it:
"Warning: The file 'AutoGpt.json' does not exist. Local memory would not be saved to a file."
+1 - mine is stuck thinking as well.
Stuck on loading too - I just tried giving it simple prompts;
Goal 1: come up with a math question
Goal 2: solve the answer
Goal 3: print the question and answer to a text file
Goal 4: shut down
Stuck on Thinking...
Same issue here
PS D:\testProject\autoGPT\Auto-GPT> python -m autogpt --debug Warning: The file 'AutoGpt.json' does not exist.Local memory would not be saved to a file. Debug Mode: ENABLED Welcome back! Would you like me to return to being bili? Continue with the last settings? Name: bili Role: 分析游戏行业趋势 Goals: ["游戏行业的发展历史'", '游戏的多元化趋势', '游戏行业未来的方向', '完成5000字的文章', '程序结束'] Continue (y/n): y Using memory of type: LocalCache Using Browser: chrome Token limit: 4000 Memory Stats: (0, (0, 1536)) Token limit: 4000 Send Token Count: 959 Tokens remaining for response: 3041 ------------ CONTEXT SENT TO AI --------------- System: The current time and date is Mon Apr 17 13:13:05 2023
System: This reminds you of these events from your past:
User: Determine which next command to use, and respond using the format specified above:
----------- END OF CONTEXT ---------------- Creating chat completion with model gpt-3.5-turbo, temperature 0.0, max_tokens 3041 Error: Reached rate limit, passing... Error: API Bad gateway. Waiting 4 seconds... Error: Reached rate limit, passing... Error: API Bad gateway. Waiting 8 seconds... Error: Reached rate limit, passing... Error: API Bad gateway. Waiting 16 seconds... Error: Reached rate limit, passing... Error: API Bad gateway. Waiting 32 seconds... | Thinking...
When I run in debug mode, the above error occurs. I asked GPT4 about this question and here is its answer:
This output shows that Auto-GPT is encountering issues while trying to interact with the GPT-3.5-turbo model. Specifically, these errors indicate that the API rate limit has been reached and a "Bad Gateway" error is occurring while trying to access it. This could be due to API server overload or other issues.
In this case, you can try the following solutions:
1.Retry after waiting for some time. This might give the API server time to resolve the overload issue. 2.Check your API key and configuration for correctness. Ensure that you are using the correct API key and adhering to the proper rate limits. 3.Check the Auto-GPT GitHub repository for any known issues or updates available. Updating to the latest version might resolve the problem. 4.If the issue persists, you can try contacting the developers of Auto-GPT to report the problem and seek assistance.
Hi,
I'm also stuck in the same "Thinking" status. I have executed the gpt3only option, does it mean there is no limit, right? Any could solve this issue?
That's because you don't have a paid plan for the OpenAI API, regardless of whether you have ChatGPT Plus or not.
https://github.com/Significant-Gravitas/Auto-GPT#openai-api-keys-configuration
That's because you don't have a paid plan for the OpenAI API, regardless of whether you have ChatGPT Plus or not.
Ah, I assumed Pro implied "paid plan". Thanks for pointing this out :)
EDIT: Can now confirm, I setup a paid plan, generated a new API key and the stuck "Thinking..." problem went away.
So, there is no option of a no-tokens use (completely free)?
@raul-parada Seems to be the case, yes.
@lamafab so If I don't have a paid plan, only free plan. still thinking ?
Closing as resolved
I have the same exact problem, but it persists even if i have a paid account with gpt4 approved
@BoccheseGiacomo please post your log
你有成功跑出结果吗?我用的是gpt4,不存在rate limit,但是还是不行
according to the previous answer, it is whether you paid plan for openai API that matters, but not gpt3 or gpt4
That's a shame... Might be a good idea to add this detail in the project requirements, no? Also, why is Auto-GPT dependent on a paid API even when --gpt3only is used?
@GeneralMidiRotkiv it's in the installation instructions in big fat letters: https://significant-gravitas.github.io/Auto-GPT/installation/#openai-api-keys-configuration
Why we strongly advise to get a paid plan? Because this: https://platform.openai.com/docs/guides/rate-limits/overview#:~:text=Free%20trial%20users,RPM%0A40%2C000%20TPM
@Pwuts thanks for the reply. I saw the hint ultimately, but since I already had the API keys and (seemingly) everything else I needed to get started, I didn't bother to check the installation explanations until after I spent some time trying to get it to run. I just think that a little hint inside 'requirements' or 'quickstart' of Readme.md would help avoid this in the future. Still, it's very easy to set up and very interesting, so thanks for the work you guys put in, I don't want to sound ungrateful ;)
@GeneralMidiRotkivestá nas instruções de instalação em letras grandes: https://significant-gravitas.github.io/Auto-GPT/installation/#openai-api-keys-configuration
Por que é altamente recomendável obter um plano pago? Porque isso: https://platform.openai.com/docs/guides/rate-limits/overview#:~:text=Free%20trial%20users,RPM%0A40%2C000%20TPM
@GeneralMidiRotkivestá nas instruções de instalação em letras grandes: https://significant-gravitas.github.io/Auto-GPT/installation/#openai-api-keys-configuration Por que é altamente recomendável obter um plano pago? Porque isso: https://platform.openai.com/docs/guides/rate-limits/overview#:~:text=Free%20trial%20users,RPM%0A40%2C000%20TPM
TWO COMPANIES IN PARTNERSHIP TO MAKE MORE MONEY, THAT'S IT!
If you want to use gpt to it's full extend, they charge for that. That's how businesses work. Them offering free trials is already pretty amazing. If you want to use auto-gpt you can also use a local llm model, the setup is harder though.
But do not confuse open source projects with being a company, we all contribute for free here.
@GeneralMidiRotkivestá nas instruções de instalação em letras grandes: https://significant-gravitas.github.io/Auto-GPT/installation/#openai-api-keys-configuration Por que é altamente recomendável obter um plano pago? Porque isso: https://platform.openai.com/docs/guides/rate-limits/overview#:~:text=Free%20trial%20users,RPM%0A40%2C000%20TPM
DUAS EMPRESAS EM PARCERIA PARA GANHAR MAIS DINHEIRO, ISSO ISSO!
Se você quiser usar o gpt em sua extensão total, eles cobram por isso. É assim que as empresas funcionam. Oferecer testes gratuitos já é incrível. Se você quiser usar o auto-gpt, também pode usar um modelo llm local, embora a configuração seja mais difícil.
Mas não confunda projetos open source com ser uma empresa, todos nós contribuímos de graça aqui.
Next step is it, integrate the llama
⚠️ Search for existing issues first ⚠️
GPT-3 or GPT-4
Steps to reproduce 🕹
I have it installed and when I enter any prompt, it just says "thinking..." and never stops loading.
Current behavior 😯
It never stops generating a response and never actually produces anything.
Expected behavior 🤔
No response
Your prompt 📝