Auto-GPT Command evaluate_code returned: Error: The model: `gpt-4` does not exist

Khnaz35 commented 1 year ago

⚠️ Search for existing issues first ⚠️

[X] I have searched the existing issues, and there is no existing issue for my problem

Which Operating System are you using?

MacOS

Which version of Auto-GPT are you using?

Latest Release

GPT-3 or GPT-4?

GPT-4

Steps to reproduce 🕹

MacBook-Pro-2:Auto-GPT khnaz35 $ docker run -it --env-file=/Users/desktop/Auto-GPT/.env -v $PWD/auto_gpt_workspace:/home/appuser/auto_gpt_workspace autogpt Warning: The file 'auto-gpt.json' does not exist. Local memory would not be saved to a file. NEWS: ::UPDATED:: Welcome to Auto-GPT! We'll keep you informed of the latest news and features by printing messages here. If you don't wish to see this message, you can run Auto-GPT with the --skip-news flag Welcome to Auto-GPT! run with '--help' for more information. Create an AI-Assistant: Enter the name of your AI and its role below. Entering nothing will load defaults. Name your AI: For example, 'Entrepreneur-GPT' AI Name: Entrepreneur-GPT 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.' Entrepreneur-GPT is: 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: How many GPT agents are available?

Current behavior 😯

Using memory of type: LocalCache Using Browser: chrome THOUGHTS: I think I should start by listing the available GPT agents to see what resources I have available. REASONING: Listing the available GPT agents will give me an idea of what tasks I can delegate to them and what resources I have available to me. PLAN:

List available GPT agents CRITICISM: I need to ensure that I am delegating tasks effectively and not overloading any one agent with too many tasks. NEXT ACTION: COMMAND = list_agents ARGUMENTS = {} Enter 'y' to authorise command, 'y -N' to run N continuous commands, 'n' to exit program, or enter feedback for ... Input:y -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= SYSTEM: Command list_agents returned: List of agents: THOUGHTS: I think I should start a new GPT agent to help me with my tasks. REASONING: Starting a new GPT agent will allow me to delegate tasks to it and free up my own resources. PLAN:
Start a new GPT agent CRITICISM: I need to ensure that I am giving the agent clear and concise tasks to complete, and that I am not overloading it with too many tasks. NEXT ACTION: COMMAND = start_agent ARGUMENTS = {'name': 'task_agent', 'task': 'Assist with simple tasks', 'prompt': 'What task would you like me to complete?'} Enter 'y' to authorise command, 'y -N' to run N continuous commands, 'n' to exit program, or enter feedback for ... Input:y -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= SYSTEM: Command start_agent returned: Agent task_agent created with key 0. First response: As an AI language model, I do not have any specific task for you to complete. However, if you have any questions or need assistance with anything, feel free to ask and I will do my best to help you. THOUGHTS: I should ask the new GPT agent to search for the number of agents I have available. REASONING: Asking the new GPT agent to search for the number of agents I have available will give me an idea of how many resources I have available. PLAN:
Ask task_agent to search for the number of agents available CRITICISM: I need to ensure that I am giving the agent clear and concise tasks to complete, and that I am not overloading it with too many tasks. NEXT ACTION: COMMAND = message_agent ARGUMENTS = {'key': 0, 'message': 'Please search for the number of agents I have available.'} Enter 'y' to authorise command, 'y -N' to run N continuous commands, 'n' to exit program, or enter feedback for ... Input:

Expected behavior 🤔

Should list the available agent from my .env files. I have these settings available. `

SMART_LLM_MODEL - Smart language model (Default: gpt-4)

FAST_LLM_MODEL - Fast language model (Default: gpt-3.5-turbo)

SMART_LLM_MODEL=gpt-4 FAST_LLM_MODEL=gpt-3.5-turbo

LLM MODEL SETTINGS

FAST_TOKEN_LIMIT - Fast token limit for OpenAI (Default: 4000)

SMART_TOKEN_LIMIT - Smart token limit for OpenAI (Default: 8000)

When using --gpt3only this needs to be set to 4000.

FAST_TOKEN_LIMIT=4000 SMART_TOKEN_LIMIT=8000`

Also i have paid account setup for my use case

Your prompt 📝

# Paste your prompt here

How many GPT agents are available?

Also i don't see the file ai_settings.yaml file

Your Logs 📒

<insert your logs here>

I am not seeing the log/activity.log

manuel919 commented 1 year ago

I assume you do not have access to the model GPT4, yet. You can join the waitlist here: https://openai.com/waitlist/gpt-4-api Alternatively just use GPT3.5 by calling python -m autogpt --gpt3only

Khnaz35 commented 1 year ago

Might be that's an issue even after setting up the paid account its not allowing access to gtp-4, Btw i do have access to chatgpt plus though.

Also can you confirm that why it still doesn't list the other user agent ?

SMART_LLM_MODEL=gpt-4 FAST_LLM_MODEL=gpt-3.5-turbo Because my prompt was "How many GPT agents are available?" I also tried with "How many GPT agents I do have?"

manuel919 commented 1 year ago

Yeah, chatgpt plus gives you access to gpt4 via their chat interface. But not via API, which is required for auto gpt.

You could also set SMART_LLM_MODEL to the same value as FAST_LLM_MODEL

bradiosd commented 1 year ago

I had access to message_agent on 20/21 of April and now I am getting the error that the OP is getting. They seem to have taken my GPT4 access away?

Significant-Gravitas / AutoGPT