Maximum lenght

[Xerizaf]

⚠️ Search for existing issues first ⚠️

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

Which Operating System are you using?

Windows

Which version of Auto-GPT are you using?

Latest Release

GPT-3 or GPT-4?

GPT-3.5

Steps to reproduce 🕹

Continue

Current behavior 😯

This model's maximum context length is 8191 tokens, however you requested 11103 tokens (11103 in your prompt; 0 for the completion). Please reduce your prompt; or completion length.

Expected behavior 🤔

Continue

Your prompt 📝

# Paste your prompt here

Your Logs 📒

<insert your logs here>

[RoyalSWiSH]

Is this in the browse_website command or what were you trying to do?

[HectorNavarroAsymm]

I also have this error:
openai.error.InvalidRequestError: This model's maximum context length is 4097 tokens. However, you requested 69997 tokens (972 in the messages, 69025 in the completion). Please reduce the length of the messages or completion.
I'm running auto gpt from the command prompt ./run.sh, every time I run it I end up having the same error.
It asks if I want to continue with previous task or not, I've tried running it multiple times, I've answered yes and no and always end up with the same error.

I'm running on MacOS, I'm on the stable branch, I already cloned the project again.
I'm looking for a way to clear the LocalCache

[k-boikov]

There are multiple issues opened about that #2801 #2871 #2906

[GoMightyAlgorythmGo]

for me too endless crashes since 4 days and is as old as 2 weeks i made code check it out: #3239 (comment)

[jmj4678]

I'm experiencing the same issue. Reduce the length of your prompt. Hopefully sooner rather than later the conversation with the system will feel more natural. As of now, look at your prompt and look for ways to rephrase it and shorten it. I realized I was using one agent to do two things and simply splitted it into 2 and it "worked". Good luck