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
Other
167.51k stars 44.25k forks source link

Stop Thinking When Using Command : clone_repository #3521

Closed Mozartismee closed 1 year ago

Mozartismee commented 1 year ago

⚠️ Search for existing issues first ⚠️

Which Operating System are you using?

MacOS

Which version of Auto-GPT are you using?

Stable (branch)

GPT-3 or GPT-4?

GPT-4

Steps to reproduce 🕹

I asked Auto-GPT to summarize concepts related to transformer architecture from a website and perform translation. During the process, Auto-GPT decided to clone a project to facilitate the task.

Current behavior 😯

Auto-GPT cloned the repository to the auto_gpt_workspace directory.

Expected behavior 🤔

I expect the repository to be cloned successfully to the specified path. Autogpt should continue my required tasks but it stops during cloning the repository and gives no any response.

Your Logs 📒

(env) vernunft@VernunftdeMacBook-Air Auto-GPT % python -m autogpt
NEWS:  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 # INCLUDED COMMAND 'send_tweet' IS DEPRICATED, AND WILL BE REMOVED IN THE NEXT STABLE RELEASE Base Twitter functionality (and more) is now covered by plugins: https://github.com/Significant-Gravitas/Auto-GPT-Plugins ## Changes to Docker configuration The workdir has been changed from /home/appuser to /app. Be sure to update any volume mounts accordingly.
Welcome back!  Would you like me to return to being Explainer?
Continue with the last settings?
Name:  Explainer
Role:  expain the document about transformer architecture
Goals: ['browse https://jalammar.github.io/illustrated-transformer/', 'break down concepts in understandable peices', 'translate these results into accurate traditional chinese', 'output all your explain and translation into a file ', 'file should be stored in /Users/vernunft/Auto-GPT/auto_gpt_workspace']
Continue (y/n): y
Using memory of type:  LocalCache
Using Browser:  chrome
 THOUGHTS:  I suggest we start by browsing the website https://jalammar.github.io/illustrated-transformer/ to get a better understanding of the transformer architecture.
REASONING:  Browsing the website will give us a better understanding of the transformer architecture, which will help us break down the concepts into understandable pieces and translate them into accurate traditional Chinese.
PLAN: 
-  Browse the website https://jalammar.github.io/illustrated-transformer/
-  Break down the concepts into understandable pieces
-  Translate the concepts into accurate traditional Chinese
-  Output all explanations and translations into a file
CRITICISM:  I need to ensure that I am accurately translating the concepts into traditional Chinese and that I am breaking down the concepts into understandable pieces.
NEXT ACTION:  COMMAND = browse_website ARGUMENTS = {'url': 'https://jalammar.github.io/illustrated-transformer/', 'question': 'What is the transformer architecture?'}
Enter 'y' to authorise command, 'y -N' to run N continuous commands, 'n' to exit program, or enter feedback for ...
Input:y -5
-=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= 
[WDM] - Downloading: 100%|██████████████████| 8.04M/8.04M [00:17<00:00, 495kB/s]
SYSTEM:  Command browse_website returned: Error: [Errno 13] Permission denied: '/Users/vernunft/.wdm/drivers/chromedriver/mac_arm64/112.0.5615.49/driver.zip'
 THOUGHTS:  Let's use Google search to find a resource that explains the transformer architecture.
REASONING:  Google search will allow us to find a variety of resources that explain the transformer architecture, which will help us break down the concepts into understandable pieces and translate them into accurate traditional Chinese.
PLAN: 
-  Use Google search to find a resource that explains the transformer architecture
-  Break down the concepts into understandable pieces
-  Translate the concepts into accurate traditional Chinese
-  Output all explanations and translations into a file
CRITICISM:  I need to ensure that I am accurately translating the concepts into traditional Chinese and that I am breaking down the concepts into understandable pieces.
NEXT ACTION:  COMMAND = google ARGUMENTS = {'input': 'transformer architecture explanation'}
SYSTEM:  Command google returned: ['https://towardsdatascience.com/illustrated-guide-to-transformers-step-by-step-explanation-f74876522bc0', 'https://jalammar.github.io/illustrated-transformer/', 'https://machinelearningmastery.com/the-transformer-model/', 'https://builtin.com/artificial-intelligence/transformer-neural-network', 'https://neptune.ai/blog/comprehensive-guide-to-transformers', 'https://en.wikipedia.org/wiki/Transformer_(machine_learning_model)', 'https://medium.com/inside-machine-learning/what-is-a-transformer-d07dd1fbec04', 'https://datagen.tech/guides/computer-vision/transformer-architecture/']
 THOUGHTS:  Let's browse the first link returned by the Google search, which is https://towardsdatascience.com/illustrated-guide-to-transformers-step-by-step-explanation-f74876522bc0. This website provides a step-by-step explanation of the transformer architecture, which will help us break down the concepts into understandable pieces and translate them into accurate traditional Chinese.
REASONING:  Browsing this website will provide us with a step-by-step explanation of the transformer architecture, which will help us break down the concepts into understandable pieces and translate them into accurate traditional Chinese.
PLAN: 
-  Browse the website https://towardsdatascience.com/illustrated-guide-to-transformers-step-by-step-explanation-f74876522bc0
-  Break down the concepts into understandable pieces
-  Translate the concepts into accurate traditional Chinese
-  Output all explanations and translations into a file
CRITICISM:  I need to ensure that I am accurately translating the concepts into traditional Chinese and that I am breaking down the concepts into understandable pieces.
NEXT ACTION:  COMMAND = browse_website ARGUMENTS = {'url': 'https://towardsdatascience.com/illustrated-guide-to-transformers-step-by-step-explanation-f74876522bc0', 'question': 'What is the transformer architecture?'}
[WDM] - Downloading: 100%|██████████████████| 8.04M/8.04M [00:13<00:00, 603kB/s]
SYSTEM:  Command browse_website returned: Error: [Errno 13] Permission denied: '/Users/vernunft/.wdm/drivers/chromedriver/mac_arm64/112.0.5615.49/driver.zip'
 THOUGHTS:  Let's use Google search to find a resource that explains the transformer architecture.
REASONING:  Google search will allow us to find a variety of resources that explain the transformer architecture, which will help us break down the concepts into understandable pieces and translate them into accurate traditional Chinese.
PLAN: 
-  Use Google search to find a resource that explains the transformer architecture
-  Break down the concepts into understandable pieces
-  Translate the concepts into accurate traditional Chinese
-  Output all explanations and translations into a file
CRITICISM:  I need to ensure that I am accurately translating the concepts into traditional Chinese and that I am breaking down the concepts into understandable pieces.
NEXT ACTION:  COMMAND = google ARGUMENTS = {'input': 'transformer architecture explanation'}
SYSTEM:  Command google returned: ['https://towardsdatascience.com/illustrated-guide-to-transformers-step-by-step-explanation-f74876522bc0', 'https://jalammar.github.io/illustrated-transformer/', 'https://machinelearningmastery.com/the-transformer-model/', 'https://builtin.com/artificial-intelligence/transformer-neural-network', 'https://neptune.ai/blog/comprehensive-guide-to-transformers', 'https://en.wikipedia.org/wiki/Transformer_(machine_learning_model)', 'https://medium.com/inside-machine-learning/what-is-a-transformer-d07dd1fbec04', 'https://datagen.tech/guides/computer-vision/transformer-architecture/']
 THOUGHTS:  Let's browse the first link returned by the Google search, which is https://towardsdatascience.com/illustrated-guide-to-transformers-step-by-step-explanation-f74876522bc0. This website provides a step-by-step explanation of the transformer architecture, which will help us break down the concepts into understandable pieces and translate them into accurate traditional Chinese.
REASONING:  Browsing this website will provide us with a step-by-step explanation of the transformer architecture, which will help us break down the concepts into understandable pieces and translate them into accurate traditional Chinese.
PLAN: 
-  Browse the website https://towardsdatascience.com/illustrated-guide-to-transformers-step-by-step-explanation-f74876522bc0
-  Break down the concepts into understandable pieces
-  Translate the concepts into accurate traditional Chinese
-  Output all explanations and translations into a file
CRITICISM:  I need to ensure that I am accurately translating the concepts into traditional Chinese and that I am breaking down the concepts into understandable pieces.
NEXT ACTION:  COMMAND = browse_website ARGUMENTS = {'url': 'https://towardsdatascience.com/illustrated-guide-to-transformers-step-by-step-explanation-f74876522bc0', 'question': 'What is the transformer architecture?'}
[WDM] - Downloading: 100%|██████████████████| 8.04M/8.04M [00:14<00:00, 599kB/s]
SYSTEM:  Command browse_website returned: Error: [Errno 13] Permission denied: '/Users/vernunft/.wdm/drivers/chromedriver/mac_arm64/112.0.5615.49/driver.zip'
 THOUGHTS:  Let's use Google search to find a resource that explains the transformer architecture.
REASONING:  Google search will allow us to find a variety of resources that explain the transformer architecture, which will help us break down the concepts into understandable pieces and translate them into accurate traditional Chinese.
PLAN: 
-  Use Google search to find a resource that explains the transformer architecture
-  Break down the concepts into understandable pieces
-  Translate the concepts into accurate traditional Chinese
-  Output all explanations and translations into a file
CRITICISM:  I need to ensure that I am accurately translating the concepts into traditional Chinese and that I am breaking down the concepts into understandable pieces.
NEXT ACTION:  COMMAND = google ARGUMENTS = {'input': 'transformer architecture explanation'}
Enter 'y' to authorise command, 'y -N' to run N continuous commands, 'n' to exit program, or enter feedback for ...
Input:y -5
-=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= 
SYSTEM:  Command google returned: ['https://towardsdatascience.com/illustrated-guide-to-transformers-step-by-step-explanation-f74876522bc0', 'https://jalammar.github.io/illustrated-transformer/', 'https://machinelearningmastery.com/the-transformer-model/', 'https://builtin.com/artificial-intelligence/transformer-neural-network', 'https://neptune.ai/blog/comprehensive-guide-to-transformers', 'https://en.wikipedia.org/wiki/Transformer_(machine_learning_model)', 'https://medium.com/inside-machine-learning/what-is-a-transformer-d07dd1fbec04', 'https://datagen.tech/guides/computer-vision/transformer-architecture/']
 THOUGHTS:  Let's browse the website https://jalammar.github.io/illustrated-transformer/ to get a better understanding of the transformer architecture.
REASONING:  Browsing the website will allow us to see visualizations and explanations of the transformer architecture, which will help us break down the concepts into understandable pieces and translate them into accurate traditional Chinese.
PLAN: 
-  Browse the website https://jalammar.github.io/illustrated-transformer/
-  Break down the concepts into understandable pieces
-  Translate the concepts into accurate traditional Chinese
-  Output all explanations and translations into a file
CRITICISM:  I need to ensure that I am accurately translating the concepts into traditional Chinese and that I am breaking down the concepts into understandable pieces.
NEXT ACTION:  COMMAND = browse_website ARGUMENTS = {'url': 'https://jalammar.github.io/illustrated-transformer/', 'question': 'What is the transformer architecture?'}
[WDM] - Downloading: 100%|██████████████████| 8.04M/8.04M [00:14<00:00, 589kB/s]SYSTEM:  Command browse_website returned: Error: [Errno 13] Permission denied: '/Users/vernunft/.wdm/drivers/chromedriver/mac_arm64/112.0.5615.49/driver.zip'
 THOUGHTS:  Let's use the 'clone_repository' command to clone the repository containing the website and then open the HTML file locally.
REASONING:  Cloning the repository will allow us to access the website files and open the HTML file locally without needing to use a browser.
PLAN: 
-  Clone the repository containing the website
-  Open the HTML file locally
-  Break down the concepts into understandable pieces
-  Translate the concepts into accurate traditional Chinese
-  Output all explanations and translations into a file
CRITICISM:  I need to ensure that I am accurately translating the concepts into traditional Chinese and that I am breaking down the concepts into understandable pieces.
NEXT ACTION:  COMMAND = clone_repository ARGUMENTS = {'repository_url': 'https://github.com/jalammar/jalammar.github.io.git', 'clone_path': '/Users/vernunft/Auto-GPT/auto_gpt_workspace/transformer_website'}
vaisov commented 1 year ago

So where's the error? Can't see it in the log.

Mozartismee commented 1 year ago

Sorry, I apologize for not providing a more specific description of my issue earlier. I've attempted the process numerous times, but it always comes to a halt at that point.

k-boikov commented 1 year ago

The issue that I see is with your chromedriver, seems like you dont have permissions to use it. Normally what solves that is running it in headless mode. What do you have set for HEADLESS_BROWSER in you .env? Also have you tried using the master branch?

github-actions[bot] commented 1 year ago

This issue has automatically been marked as stale because it has not had any activity in the last 50 days. You can unstale it by commenting or removing the label. Otherwise, this issue will be closed in 10 days.

github-actions[bot] commented 1 year ago

This issue was closed automatically because it has been stale for 10 days with no activity.