AutoGPT
AutoGPT copied to clipboard
Warning: The file 'auto-gpt.json' does not exist. Local memory would not be saved to a file.
After following all instructions, i get the above warning on running autogpt for the first time.
- Go to autogpt repository
- create auto-gpt.json ex (linux): echo "" > auto-gpt.json
I was able to work around this by creating a text file with this in it:
{}
Save As:
Auto-GPT.json
The error message appears even if the file is present in the directory:
[06:27 PM] bobinson@MacBook-Pro 🖖 [~/src/Auto-GPT]vim auto-gpt.json [06:28 PM] bobinson@MacBook-Pro 🖖 [~/src/Auto-GPT]docker run -it --env-file=./.env -v $PWD/auto_gpt_workspace:/app/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'
I have added a auto_gpt.json file but still getting Same issue on mac m1:
Requirement already satisfied: h11<1,>=0.9.0 in /home/opt/anaconda3/lib/python3.9/site-packages (from wsproto>=0.14->trio-websocket~=0.9->selenium->-r requirements.txt (line 18)) (0.14.0) Warning: The file 'auto-gpt.json' does not exist. Local memory would not be saved to a file. ./run.sh: line 8: 22735 Illegal instruction: 4 python -m autogpt $@ Press any key to continue...
I have added a auto_gpt.json file but still getting Same issue on mac m1:
Requirement already satisfied: h11<1,>=0.9.0 in /home/opt/anaconda3/lib/python3.9/site-packages (from wsproto>=0.14->trio-websocket~=0.9->selenium->-r requirements.txt (line 18)) (0.14.0) Warning: The file 'auto-gpt.json' does not exist. Local memory would not be saved to a file. ./run.sh: line 8: 22735 Illegal instruction: 4 python -m autogpt $@ Press any key to continue...
Can you try running python -m autogpt --debug
?
it doesn't say The file 'auto-gpt.json' does not exist, however it says: Please set your OpenAI API key in .env or as an environment variable. You can get your key from https://platform.openai.com/account/api-keys
although I did set my open api key in .env
Please make sure you are using the proper .env (not the .template) and you don't have any other .env files around.
the error goes away if I create a blank auto-gpt.json file, on my m2 mac. When the code runs, it writes {}
in the file. But wouldn't it be better to just include an empty file in the repo itself if it is important, or am I missing something ?
I did everything in as suggested. It will run in an Command Prompt in Windows, but not in the Docker Desktop.
Known behavior
I did everything in as suggested. It will run in an Command Prompt in Windows, but not in the Docker Desktop.
Use command: podman run --rm -it --name autogpt --env-file=./.env -v $PWD/auto_gpt_workspace:/home/appuser/auto_gpt_workspace -v $PWD/auto_gpt_workspace/auto-gpt.json:/home/appuser/auto-gpt.json significantgravitas/auto-gpt:0.2.2 --continuous