search

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
166.52k stars 44.06k forks source link

RuntimeError: Failed to get response after 5 retries #1389

Closed ishaoshupai closed 1 year ago

ishaoshupai commented 1 year ago

Duplicates

Steps to reproduce 🕹

Welcome to Auto-GPT! Enter the name of your AI and its role below. Entering nothing will load defaults. Name your AI: For example, 'Entrepreneur-GPT' AI Name: student student here! I am at your service. 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.' student is: improve english skills Enter up to 5 goals for your AI: For example: Increase net worth, Grow Twitter Account, Develop and manage multiple businesses autonomously' Enter nothing to load defaults, enter nothing when finished. Goal 1: improve speaking skills Goal 2: imporve writting skills Goal 3: improve reading skills Goal 4: Using memory of type: LocalCache Traceback (most recent call last): File "D:\Auto-GPT-master\scripts\main.py", line 465, in main() File "D:\Auto-GPT-master\scripts\main.py", line 328, in main agent.start_interaction_loop() File "D:\Auto-GPT-master\scripts\main.py", line 369, in start_interaction_loop assistant_reply = chat.chat_with_ai( ^^^^^^^^^^^^^^^^^^ File "D:\Auto-GPT-master\scripts\chat.py", line 126, in chat_with_ai assistant_reply = create_chat_completion( ^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Auto-GPT-master\scripts\llm_utils.py", line 50, in create_chat_completion raise RuntimeError("Failed to get response after 5 retries") RuntimeError: Failed to get response after 5 retries

Current behavior 😯

RuntimeError: Failed to get response after 5 retries

Expected behavior 🤔

No response

Your prompt 📝

No response

rebroad commented 1 year ago

I'm also getting this. I added the --debug option and it's telling me I'm exceeding my API rate limit, but I don't know why this is happening.

fxlee888 commented 1 year ago

Same issue here. I added a payment to my openai account (not chatgpt plus account) and the errors messages are gone! Need to add "paid account on openAI" in the prerequisite..

xavier-hou commented 1 year ago

Same issue here. I added a payment to my openai account (not chatgpt plus account) and the errors messages are gone! Need to add "paid account on openAI" in the prerequisite..

Really??...

viniciusarruda commented 1 year ago

It seems it is getting from the environment variable instead of the .env file. Set you OPENAI_API_KEY environment variable to a valid API key and test it. It worked here!

utribedi commented 1 year ago

Same issue here. I added a payment to my openai account (not chatgpt plus account) and the errors messages are gone! Need to add "paid account on openAI" in the prerequisite..

Tried this, still doesn't work

IngeniozIT commented 1 year ago

Even though I hadn't done any request with my trial plan (and thus didn't exceed any quota), it started working once I switched to a paid plan.

aaronjrodrigues commented 1 year ago

I am getting this error as well

aaronjrodrigues commented 1 year ago

How exactly do you do this?

fxlee888 commented 1 year ago

Have you created a new API key after upgrading paid plan ?

utribedi commented 1 year ago

Have you created a new API key after upgrading paid plan ?

This was precisely the issue. Works perfectly now. Thanks for pointing it out @fxlee888

fylim commented 1 year ago

Yeah upgrading to paid plan and creating a new API key appears to be working

CharlieAlphaFox commented 1 year ago

A paid plan per query is different from ChatGPT plus. Ensure the membership status under the settings has a charge per API call. I also set a hard and a soft limit in USDs per month so that it doesnt charge me more than I can pay, the default is something like $120 and $96 for hard and soft limits.