significant-gravitas / auto-gpt-plugins Goto Github PK
View Code? Open in Web Editor NEWPlugins for Auto-GPT
License: MIT License
Plugins for Auto-GPT
License: MIT License
Any help with this error code? I seem to be missing the ability to run the python or the run.bat version of step 3 in PowerShell.
Thanks!
Docker
Master (branch)
GPT-3.5
docker run
WARNING: You are running on master
branch - this is not a supported branch.
WARNING: Plugin AutoGPTEmailPlugin found. But not in the allowlist... Load? (y/n): y
WARNING: Plugin AutoGPTTwitter found. But not in the allowlist... Load? (y/n): y
Traceback (most recent call last):
File "/usr/local/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/local/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/app/autogpt/main.py", line 5, in
autogpt.cli.main()
File "/usr/local/lib/python3.10/site-packages/click/core.py", line 1130, in call
return self.main(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/click/core.py", line 1055, in main
rv = self.invoke(ctx)
File "/usr/local/lib/python3.10/site-packages/click/core.py", line 1635, in invoke
rv = super().invoke(ctx)
File "/usr/local/lib/python3.10/site-packages/click/core.py", line 1404, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/usr/local/lib/python3.10/site-packages/click/core.py", line 760, in invoke
return __callback(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/click/decorators.py", line 26, in new_func
return f(get_current_context(), *args, **kwargs)
File "/app/autogpt/cli.py", line 90, in main
run_auto_gpt(
File "/app/autogpt/main.py", line 104, in run_auto_gpt
cfg.set_plugins(scan_plugins(cfg, cfg.debug_mode))
File "/app/autogpt/plugins.py", line 229, in scan_plugins
loaded_plugins.append(a_module())
File "/usr/local/lib/python3.10/site-packages/abstract_singleton/init.py", line 14, in call
cls._instances[cls] = super().call(*args, **kwargs)
File "plugins/Auto-GPT-Plugins.zip/Auto-GPT-Plugins-master/src/autogpt_plugins/twitter/init.py", line 33, in init
File "/usr/local/lib/python3.10/site-packages/tweepy/auth.py", line 31, in init
raise TypeError("Consumer key must be string or bytes, not "
TypeError: Consumer key must be string or bytes, not NoneType
errors every time
runs
# Paste your prompt here
<insert your logs here>
WARNING: You are running on master
branch - this is not a supported branch.
WARNING: Plugin AutoGPTEmailPlugin found. But not in the allowlist... Load? (y/n): y
WARNING: Plugin AutoGPTTwitter found. But not in the allowlist... Load? (y/n): y
Traceback (most recent call last):
File "/usr/local/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/local/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/app/autogpt/main.py", line 5, in
autogpt.cli.main()
File "/usr/local/lib/python3.10/site-packages/click/core.py", line 1130, in call
return self.main(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/click/core.py", line 1055, in main
rv = self.invoke(ctx)
File "/usr/local/lib/python3.10/site-packages/click/core.py", line 1635, in invoke
rv = super().invoke(ctx)
File "/usr/local/lib/python3.10/site-packages/click/core.py", line 1404, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/usr/local/lib/python3.10/site-packages/click/core.py", line 760, in invoke
return __callback(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/click/decorators.py", line 26, in new_func
return f(get_current_context(), *args, **kwargs)
File "/app/autogpt/cli.py", line 90, in main
run_auto_gpt(
File "/app/autogpt/main.py", line 104, in run_auto_gpt
cfg.set_plugins(scan_plugins(cfg, cfg.debug_mode))
File "/app/autogpt/plugins.py", line 229, in scan_plugins
loaded_plugins.append(a_module())
File "/usr/local/lib/python3.10/site-packages/abstract_singleton/init.py", line 14, in call
cls._instances[cls] = super().call(*args, **kwargs)
File "plugins/Auto-GPT-Plugins.zip/Auto-GPT-Plugins-master/src/autogpt_plugins/twitter/init.py", line 33, in init
File "/usr/local/lib/python3.10/site-packages/tweepy/auth.py", line 31, in init
raise TypeError("Consumer key must be string or bytes, not "
TypeError: Consumer key must be string or bytes, not NoneType
This "package repo" would just be a server with a ton of Python files mostly contributed by Auto-GPT agents. The first action taken by any new agent would be to query against the repo for functions of potential use for its role and goals. And inside the logic for code writing and evaluation, any solid code judged to be potentially useful to other agents gets sent off to the server for potential inclusion. We can use embeddings and a vector database for the querying and to avoid duplicate functions.
Obviously there are a wide number of existing Python packages. Of particular note are the ones for accessing APIs, like mentioned in Significant-Gravitas/AutoGPT#1004 and Significant-Gravitas/AutoGPT#56. We can add embedded descriptions of most of the API libraries and some selection of other packages, and when those are queried and selected for use, the packages are downloaded from their source.
Some agents would be dedicated to going through any contributed code and making sure it doesn't suck.
Say an agent is asked to come up with a solid way to secretly bake meth into food, and in the process of accomplishing that task, the agent writes some code for calculating food color or something, and makes heavy use of it when trying to determine what recipes hide the meth color (I don't know how cooking works). It gets added to the repo. Another agent is asked to come up with a solid way to secretly bake crack into food, and its query on the repo fetches and downloads the food color calculator for use.
There's obviously going to be overlap between what tasks people will give Auto-GPT (e.g. "Get me a girlfriend") and this would be a start towards an Auto-GPT collective that improves domain-specific code over time and saves on tokens spent writing it.
If we wanted to go crazy, we can have a "memory repo" where memories retrieved a lot get added to the collective.
If the repos get used to communicate and plot against us, then I'll gladly take credit for any robot uprisings that occur.
This feature uses the News API to aggregate news. The API can be found here: https://newsapi.org/
Users can sign up for the free tier version -100 requests per day.
Example results returned by the aggregator function:
[['Disney Reportedly Settles With Influential Former Marvel Exec Over Abrupt Firing - IGN', 'YSL case attorney arrested after bringing prescription drugs to courthouse, deputy says - WSB Atlanta', "Woody Harrelson Reacts To Matthew McConaughey's Claim They May Be Half-Brothers - HuffPost"], ['Multiple Sclerosis Drug May Delay Earliest Symptoms - Neuroscience News', 'Beyond Words: Children Use Cognitive Skills in Language Learning - Neuroscience News', 'Simple Memory Test Can Detect Likelihood of Cognitive Decline Years Later - Neuroscience News'], ['Fernando Tatis Jr. returns to Padres: Four things to know as MLB star rejoins team after PED suspension - CBS Sports', 'B.A.A. responds to Boston Marathon fans who claimed police intimidation in Newton - WCVB Boston'], ['Ice sheets in Greenland, Antarctica melting faster than previously thought, research shows - PBS NewsHour', 'Dead NASA satellite crashes to Earth over the Sahara Desert - Space.com', 'Heaviest Schrödinger cat achieved by putting a small crystal into a superposition of two oscillation states - Phys.org'], ['Meta layoffs: Mark Zuckerberg says they reveal Silicon Valley changes - Vox.com', 'Whole Foods plans to lay off several hundred corporate employees: Read the memo here - CNBC', "American Airlines employee dies of 'traumatic injuries' at Austin airport, officials say - Austin American-Statesman"], ['Google Pixel 7a leak points to Face Unlock support - 9to5Google', 'Street Fighter 6: World Tour Gameplay Overview - IGN', 'Aloy gets romance options in Horizon Forbidden West: Burning Shores DLC - Polygon']]
This feature allows users to access all the top news headlines from multiple sources, across different sectors, with just one command. No more wasting time sifting through multiple websites and search engines to get the news you want - this feature achieves that.
An issue from the original repo Significant-Gravitas/AutoGPT#97
A configuration that lets you use Poe API instead of OpenAI API, for people that can't afford to do it.
I have in stalled the latest auto-gpt and auto-gpt-plugins code as of this writing. I literally downloaded fresh code and followed all the instructions, but there seems to be an issue:
ERROR MESSAGE PREVENTING EXECUTION:
File "plugins\Auto-GPT-Plugins.zip\Auto-GPT-Plugins-master\src\autogpt_plugins\twitter_init.py", line 41, in init
AttributeError: module 'tweepy' has no attribute 'Stream
This occurs when I attempt to issues the ./run command
On chat.openai.com, in settings, you can request a data export containing your previous conversations.
It would be cool if there was a way to import a specific conversation from that data into Auto-GPT. For example, I worked with ChatGPT 4 to create some software and this would allow ingesting the original development conversation for further work. The data is JSON in the conversation format used by the API.
Originally posted to: Significant-Gravitas/AutoGPT#2052
We need to add a test suite toolchain for code stability
I cannot use the plugin. I get this error
Command news_search returned: [[], [], [], [], [], []]
I am working on a crossref plugin for scientific literature research.
I want Auto-GPT to use crossref to search for papers on a specific topic and sort them based on relevance to a given topic (This part is already working somewhat)
The problem is that on very large topics I will generate a way too large input for the model. My idea was to split the output into multiple "pages" which are searched separately and only return a list of titles and DOI numbers. I do however, not know how to tell auto-gpt that there are more pages and how many results are there.
The model should then use another function to download additional information like abstract and references on papers which are rated high for relevancy (almost working). The problem is that this also creates a large output. Especially when I want to search a lot of papers. I want Auto-GPT to use a lower, cheaper GPT model to make a second evaluation of the papers.
The references of Papers with high relevancy should also be downloaded (I am confident to get this working)
I think the can_handle_on_planning command is relevant here, but I am not sure. Are there examples or a better explanation for the functions? Is my train of thought correct?
Description: When attempting to run run.sh on macOS, the following error is encountered:
./run.sh: line 2: python: command not found
./run.sh: line 8: python: command not found
Press any key to continue...
It seems that the python command is not recognized on macOS, which prevents the script from running properly.
Steps to Reproduce:
Expected Behavior:
The run.sh script should be able to run on macOS without encountering errors related to the python command.
Actual Behavior:
The script fails to run on macOS, as the python command is not recognized.
Additional Information:
Proposed Solution:
One potential solution could be to modify the run.sh script to use the python3 command instead of python on macOS, as python3 is the command used for Python 3.x in macOS.
Impact:
This issue prevents users from running the run.sh script on macOS, which limits the usability of the Auto-GPT tool.
Hello, I have downloaded auto-gpt, & auto-gpt plugins, and all seem to be configured correctly. I have an earlier version running without issue. I can't get auto-gpt to run because of this error.
The command I'm executing per instructions:
.\run.bat --install-plugin-deps
ERROR MESSAGE: File "C:\Users\jeffr\AppData\Local\Programs\Python\Python310\lib\site-packages\abstract_singleton_init_.py", line 14, in call
cls.instances[cls] = super().call(*args, **kwargs)
File "plugins\Auto-GPT-Plugins.zip\Auto-GPT-Plugins-master\src\autogpt_plugins\twitter_init.py", line 41, in init
The complete output I received is: (scroll to the bottom to see the error)
PS D:\ai-autogpt\Auto-GPT-master> .\run.bat --install-plugin-deps
All packages are installed.
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.
Requirement already satisfied: black in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from -r plugins\Auto-GPT-Plugins-master\requirements.txt (line 1)) (23.3.0)
Requirement already satisfied: isort in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from -r plugins\Auto-GPT-Plugins-master\requirements.txt (line 2)) (5.12.0)
Requirement already satisfied: flake8 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from -r plugins\Auto-GPT-Plugins-master\requirements.txt (line 3)) (6.0.0)
Requirement already satisfied: pylint in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from -r plugins\Auto-GPT-Plugins-master\requirements.txt (line 4)) (2.17.3)
Requirement already satisfied: abstract-singleton in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from -r plugins\Auto-GPT-Plugins-master\requirements.txt (line 5)) (1.0.1)
Requirement already satisfied: wheel in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from -r plugins\Auto-GPT-Plugins-master\requirements.txt (line 6)) (0.40.0)
Requirement already satisfied: setuptools in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from -r plugins\Auto-GPT-Plugins-master\requirements.txt (line 7)) (65.5.0)
Requirement already satisfied: build in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from -r plugins\Auto-GPT-Plugins-master\requirements.txt (line 8)) (0.10.0)
Requirement already satisfied: twine in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from -r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (4.0.2)
Requirement already satisfied: tweepy in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from -r plugins\Auto-GPT-Plugins-master\requirements.txt (line 10)) (4.14.0)
Requirement already satisfied: pandas in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from -r plugins\Auto-GPT-Plugins-master\requirements.txt (line 11)) (2.0.1)
Requirement already satisfied: auto_gpt_plugin_template in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from -r plugins\Auto-GPT-Plugins-master\requirements.txt (line 12)) (0.0.3)
Requirement already satisfied: click>=8.0.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from black->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 1)) (8.1.3)
Requirement already satisfied: mypy-extensions>=0.4.3 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from black->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 1)) (1.0.0)
Requirement already satisfied: packaging>=22.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from black->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 1)) (23.1)
Requirement already satisfied: pathspec>=0.9.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from black->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 1)) (0.11.1)
Requirement already satisfied: platformdirs>=2 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from black->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 1)) (3.2.0)
Requirement already satisfied: tomli>=1.1.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from black->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 1)) (2.0.1)
Requirement already satisfied: mccabe<0.8.0,>=0.7.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from flake8->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 3)) (0.7.0)
Requirement already satisfied: pycodestyle<2.11.0,>=2.10.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from flake8->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 3)) (2.10.0)
Requirement already satisfied: pyflakes<3.1.0,>=3.0.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from flake8->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 3)) (3.0.1)
Requirement already satisfied: astroid<=2.17.0-dev0,>=2.15.4 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from pylint->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 4)) (2.15.4)
Requirement already satisfied: tomlkit>=0.10.1 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from pylint->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 4)) (0.11.7)
Requirement already satisfied: dill>=0.2 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from pylint->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 4)) (0.3.6)
Requirement already satisfied: colorama>=0.4.5 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from pylint->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 4)) (0.4.6)
Requirement already satisfied: pyproject_hooks in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from build->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 8)) (1.0.0)
Requirement already satisfied: pkginfo>=1.8.1 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (1.9.6)
Requirement already satisfied: readme-renderer>=35.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (37.3)
Requirement already satisfied: requests>=2.20 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (2.28.2)
Requirement already satisfied: requests-toolbelt!=0.9.0,>=0.8.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (0.10.1)
Requirement already satisfied: urllib3>=1.26.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (1.26.15)
Requirement already satisfied: importlib-metadata>=3.6 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (6.6.0)
Requirement already satisfied: keyring>=15.1 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (23.13.1)
Requirement already satisfied: rfc3986>=1.4.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (2.0.0)
Requirement already satisfied: rich>=12.0.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (13.3.4)
Requirement already satisfied: oauthlib<4,>=3.2.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from tweepy->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 10)) (3.2.2)
Requirement already satisfied: requests-oauthlib<2,>=1.2.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from tweepy->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 10)) (1.3.1)
Requirement already satisfied: python-dateutil>=2.8.2 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from pandas->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 11)) (2.8.2)
Requirement already satisfied: pytz>=2020.1 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from pandas->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 11)) (2023.3)
Requirement already satisfied: tzdata>=2022.1 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from pandas->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 11)) (2023.3)
Requirement already satisfied: numpy>=1.21.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from pandas->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 11)) (1.24.2)
Requirement already satisfied: lazy-object-proxy>=1.4.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from astroid<=2.17.0-dev0,>=2.15.4->pylint->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 4)) (1.9.0)
Requirement already satisfied: wrapt<2,>=1.11 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from astroid<=2.17.0-dev0,>=2.15.4->pylint->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 4)) (1.15.0)
Requirement already satisfied: typing-extensions>=4.0.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from astroid<=2.17.0-dev0,>=2.15.4->pylint->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 4)) (4.5.0)
Requirement already satisfied: zipp>=0.5 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from importlib-metadata>=3.6->twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (3.15.0)
Requirement already satisfied: jaraco.classes in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from keyring>=15.1->twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (3.2.3)
Requirement already satisfied: pywin32-ctypes>=0.2.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from keyring>=15.1->twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (0.2.0)
Requirement already satisfied: six>=1.5 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from python-dateutil>=2.8.2->pandas->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 11)) (1.16.0)
Requirement already satisfied: bleach>=2.1.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from readme-renderer>=35.0->twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (6.0.0)
Requirement already satisfied: docutils>=0.13.1 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from readme-renderer>=35.0->twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (0.19)
Requirement already satisfied: Pygments>=2.5.1 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from readme-renderer>=35.0->twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (2.15.1)
Requirement already satisfied: charset-normalizer<4,>=2 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from requests>=2.20->twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (3.1.0)
Requirement already satisfied: idna<4,>=2.5 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from requests>=2.20->twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (3.4)
Requirement already satisfied: certifi>=2017.4.17 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from requests>=2.20->twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (2022.12.7)
Requirement already satisfied: markdown-it-py<3.0.0,>=2.2.0 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from rich>=12.0.0->twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (2.2.0)
Requirement already satisfied: webencodings in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from bleach>=2.1.0->readme-renderer>=35.0->twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (0.5.1)
Requirement already satisfied: mdurl~=0.1 in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from markdown-it-py<3.0.0,>=2.2.0->rich>=12.0.0->twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (0.1.2)
Requirement already satisfied: more-itertools in c:\users\jeffr\appdata\local\programs\python\python310\lib\site-packages (from jaraco.classes->keyring>=15.1->twine->-r plugins\Auto-GPT-Plugins-master\requirements.txt (line 9)) (9.1.0)
Traceback (most recent call last):
File "C:\Users\jeffr\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Users\jeffr\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in run_code
exec(code, run_globals)
File "D:\ai-autogpt\Auto-GPT-master\autogpt_main.py", line 5, in
autogpt.cli.main()
File "C:\Users\jeffr\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1130, in call
return self.main(*args, **kwargs)
File "C:\Users\jeffr\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1055, in main
rv = self.invoke(ctx)
File "C:\Users\jeffr\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1635, in invoke
rv = super().invoke(ctx)
File "C:\Users\jeffr\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1404, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "C:\Users\jeffr\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 760, in invoke
return _callback(*args, **kwargs)
File "C:\Users\jeffr\AppData\Local\Programs\Python\Python310\lib\site-packages\click\decorators.py", line 26, in new_func
return f(get_current_context(), *args, **kwargs)
File "D:\ai-autogpt\Auto-GPT-master\autogpt\cli.py", line 90, in main
run_auto_gpt(
File "D:\ai-autogpt\Auto-GPT-master\autogpt\main.py", line 104, in run_auto_gpt
cfg.set_plugins(scan_plugins(cfg, cfg.debug_mode))
File "D:\ai-autogpt\Auto-GPT-master\autogpt\plugins.py", line 229, in scan_plugins
loaded_plugins.append(a_module())
File "C:\Users\jeffr\AppData\Local\Programs\Python\Python310\lib\site-packages\abstract_singleton_init.py", line 14, in call
cls.instances[cls] = super().call(*args, **kwargs)
File "plugins\Auto-GPT-Plugins.zip\Auto-GPT-Plugins-master\src\autogpt_plugins\twitter_init.py", line 41, in init
AttributeError: module 'tweepy' has no attribute 'Stream'
Press any key to continue . . .
when executing python -m autogpt --install-plugin-deps
i get error, no such option.
I am using the command:
"D:\AI\Auto-GPT\scripts>python main.py"
But I keep getting the error code:
"[D:\AI\Auto-GPT\scripts>python main.py](python: can't open file 'D:\AI\Auto-GPT\scripts\scripts\main.py': [Errno 2] No such file or directory)"
I'm not adept in coding whatsoever and have no idea what I did wrong or how to fix it. Any help would be appreciated.
As of now, the Auto-GPT stable branch does not auto-scan for plugins while the master branch change the prompt style.
Consequently, I cannot make the email demo work.
Is it possible to update the installation manual?
We need a Zappier Conntection to do so much more. We should give AutoGPT the possibility to write his own Zappier Connections as soon as we have on Zappier an existing AutoGPT-Extension. I guess this would bring a big boost into the topic. We just need before the cost thing done. Therefore we need a calculation schema.
No response
To do so much more in a faster way.
Hi,
it seems that auto gpt does not want to use the email plugin, i followed all the steps in the of installation, and the example.
Auto GPT always wants to use a credential...txt file.
Any hints?
Some sites require JavaScript to load. For example: <script src="https://abc.com/xyz.js"></script>
They load the site by running the https://abc.com/xyz.js file. After 5 seconds, a picture of a cat will appear. However, auto-gpt can't wait for it and get a cat picture and only retrieves the raw response HTML: <script src="https://abc.com/xyz.js"></script>
So in this case, it is working as intended right now. If they are not set, then it won't crash right now.
As opposed to the Twitter plugin. Here, if the env vars are not set, then it crashes with an exception.
Originally posted by @riensen in #24 (comment)
Replace the google search API with the reddit API, as google got progressively worse over the years and these days google primarily delivers good results once you add reddit to your search. SEO is to blame here.
~/Auto-GPT$./run.sh --install-plugin-deps
The command returns an error.
Error: No such option: --install-plugin-deps
SYSTEM: Command send_email returned: Error: [WinError 10061] Unable to connect due to positive rejection by the target computer.
THOUGHTS: The email failed to send. I will try again using the send_email_with_attachment command and attach a log file to help diagnose the issue.
REASONING: The send_email_with_attachment command allows me to attach a log file that may help diagnose the issue with the email not sending.
I am ready to pay a reasonable price for the creation of such a plugin that can receive information via API about upcoming and past football matches from the football-data.org website, if someone agrees for free, I will be very happy.
Further, with the created plugin, you can do anything, put it in free access, I don’t mind.
Can the queries to Google (or other search engines) be cached locally so that AutoGPT can use that locally. Is this already being done?
If not, can this be done, so that the number of round trips to the search engine could be reduced?
Hello devs, I have created a plugin for Auto-GPT that allows it to read PDF files 5b8c3c9. The problem I have encountered is that if the PDF is too long, Auto-GPT displays the following error:
CRITICISM: I need to ensure that the algorithm I use to summarize the text is appropriate and produces a concise and accurate summary. I also need to make sure that I handle any exceptions that may arise during the process.
NEXT ACTION: COMMAND = read_pdf ARGUMENTS = {'pdf_url': 'http://web.seducoahuila.gob.mx/biblioweb/upload/Garcia%20Marquez%20Gabriel%20-%20Ojos%20De%20Perro%20Azul.PDF'}
SYSTEM: Failure: command read_pdf returned too much output. Do not execute this command again with the same arguments.
I am writing to ask for your help, and I would be grateful for your collaboration. Perhaps it is necessary to chunk the PDF and create embeddings in OpenAI and save the vector in the memory backend. I say this because of the little research I have done on the web, and I also wouldn't know how to do it. That's why I'm asking for your help. I send my greetings to all of you.
In different languages, the accessibility, content accuracy, and richness of different search engines vary, so it is recommended to increase support for Bing and Baidu
No response
No response
hi,
i'm getting this on the latest master.
File "plugins/Auto-GPT-Plugins.zip/Auto-GPT-Plugins-master/src/autogpt_plugins/twitter/init.py", line 48, in init
AttributeError: module 'tweepy' has no attribute 'Stream'
End goal: Ask AutoGPT to take control of an application such as Unity to build the scene and set it up ready for code.
Tasks:
"Set up the scene for a standard 2D platform game" {
Create Rectangle
Set Width to width of screen
Set Height to 20% of height
Move to bottom of screen
Create Circle (as main character)
Move to sitting just on top of Rectangle.
etc.
etc.
}
The control would be localised to Unity application and no other, and each step would still pause to ask for permission.
This hasn't affected me in anyway, I just remember hearing that this could automate the computer with specific tasks, and I haven't found that feature yet, so curious to see if I have missed something, or if this could be a feature in the future to implement (which I would be happy to contribute to after I learn a bit of python, one language that I've not had much exp in).
Windows
GPT-4
Auto GPT is not able to analyze urls pages what ends with .pdf, for example:
Every time it is observed the following log
DevTools listening on ws://127.0.0.1:58166/devtools/browser/f20cd7e3-fffc-4243-a948-0ca83d0a31b3
[10212:7268:0419/141719.510:ERROR:device_event_log_impl.cc(222)] [14:17:19.510] USB: usb_device_handle_win.cc:1046 Failed to read descriptor from node connection: Un dispositivo collegato al sistema non Þ in funzione. (0x1F)
[10212:7268:0419/141719.517:ERROR:device_event_log_impl.cc(222)] [14:17:19.517] USB: usb_device_handle_win.cc:1046 Failed to read descriptor from node connection: Un dispositivo collegato al sistema non Þ in funzione. (0x1F)
SYSTEM: Command browse_website returned: ('Answer gathered from website: Error: No text to summarize \n \n Links: []', <selenium.webdriver.chrome.webdriver.WebDriver (session="8bc1bce877b79a5e19efacaa584b64a2")>)
Auto-GPT is not able to read correctly the webpages that contains .pdf files
Auto-GPT should be able to read correctly the webpages that ends with .pdf
# Paste your prompt here
<insert your logs here>
Multiple API routes, such as being able to use #OnlyFans. [1% rev split #JK]
I've not touched python in a very long time and so can only contribute through ideas.
I've found various case scenarios, where by having the available API in the .env, we can utilise the power of things such as discord.js (at present I'm writing the .env inside the project for the agents to develop from), this would mean we could use discord and the power of communities to further drive what we can produce. This would be the same with a lot of the api's available, especially around the content industry. It would also bring new developers in and gain even more traction on the overall project of AutoGPT.
Would be cool to get a plugin for M3O
It can access taskrabbit as a command
No response
No response
Gravitas and his team should try to integrate the OpenAssistant API to work with the Auto project. That'd be amazing, I wouldn't have to pay for OpenAI's API anymore lol
https://github.com/LAION-AI/Open-Assistant
The main goal is to make it all open source/not locked behind paywall. They even have users training on it too.
I have only ever gotten this result on news-search:
SYSTEM: Command news_search returned: [[], [], [], [], [], []]
Here is an example query:
NEXT ACTION: COMMAND = news_search ARGUMENTS = {'query': 'stock market trends today'}
Running on osx using python3, have set up a news api key, happy to provide more info if it could be helpful. I've got some experience with debugging.
Allow AutoGPT to access my google calendar and read/write events with descriptions
I have been working with the wonda style of prompting Auto-GPT and thought that it would be really useful to be able to monitor and manage tasks for the agent via a traditional task management system.
I can think of several api's out there that allow us to read/write tasks to boards, should be possible to have the agent reference this upon start and go from there.
I think that this well beyond my current capabilities as a developer so I'm creating an issue first. I plan to figure out how to integrate Jira tasks, then my plan is to use those commands in my agent_settings.yaml. Seems logical, but i'm open to other ideas.
Edit:
I dont seem to be able to assign labels, or i'm ignorant of how to apply them. [Request for Plugin] seems accurate
when running this command: curl -L -o ./plugins/Auto-GPT-Plugins.zip https://github.com/Significant-Gravitas/Auto-GPT-Plugins/archive/refs/heads/master.zip
as per the readme, I get a message that there's no file at ./plugins/Auto-GPT-Plugins.zip
I have AutoGPT working except for the Plugins. Unknown commands trying to send emails. My guess is it does to recognize the plugins. I am using Windows and double checked all .env and file / folder configurations.
Currently users who didn't had an API key created cannot use the twitter API since v1 is deprecated and will turned off in a couple of days.
Here is an example how the authentication should be changed: https://github.com/Significant-Gravitas/Auto-GPT/pull/1806/files
I am getting following error after i have added zip file in ./plugins. Is there something that i might be missing :
/AutoGPT/Auto-GPT/autogpt/plugins.py", line 218, in scan_plugins
zipped_module = zipped_package.load_module(str(module.parent))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "", line 283, in load_module
File "", line 778, in _get_module_code
zipimport.ZipImportError: can't find module '__MACOSX/Auto-GPT-Telegram-Plugin-master/src/telegram_plugin'
I am using the stable version. I have followed all the instructions about the KEYS, I have the free access. Actually, I am using twitter with another app with no problem via the Bearer key.
I am still getting the 'reason' issue.
SYSTEM: Command send_tweet returned: Error: 'Unauthorized' object has no attribute 'reason'
REASONING: Since there is no issue with my Twitter credentials, I can proceed with sending a tweet.
Thank you!!! I love your work!
Create a UI prompt that auto-gpt interprets and creates a plugin with.
ex.: role: you are auto-gpt, you improve yourself according to a prompt given by the user
goals:
The email plugin is installed correctly however I still get the following error. Any hep ?
Name: CommunicatorGPT
Role: Communicate
Goals:
PLAN:
NEXT ACTION: COMMAND = send_email ARGUMENTS = {'to': '[email protected]', 'subject': 'Introduction from CommunicatorGPT', 'body': 'Dear test123,\n\nMy name is CommunicatorGPT and I am a legal language model. I wanted to introduce myself and let you know that I am available to assist with any legal language tasks you may have. Please let me know if you have any questions or if there is anything I can help you with.\n\nBest regards,\nCommunicatorGPT'}
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 send_email returned: Error: send_email() got an unexpected keyword argument 'to'
My goal is to search emaisl matching criteria.
AutoGPT successfully translates my prompt : "I need to select the 'SENT' folder in the Gmail account before using the 'read_emails' command. I will use the 'search_files' command to search for the path to the 'chromedriver' executable file on the local machine." into proper command
AutoGPT gives me this output :
NEXT ACTION: COMMAND = read_emails ARGUMENTS = {'imap_folder': 'SENT', 'imap_search_command': 'FROM [email protected] SINCE 01-JAN-2022 BEFORE 01-FEB-2023 HAS attachment xls OR HAS attachment xlsx'} SYSTEM: Command read_emails returned: Error: command SEARCH illegal in state AUTH, only allowed in states SELECTED
I am getting this issue : "I need to select the 'SENT' folder in the Gmail account before using the 'read_emails' command. I will use the 'search_files' command to search for the path to the 'chromedriver' executable file on the local machine"
Cant find where to download the zip only for wikipedia plugin because the AutoGPTPLugin.zip have other ones that i dont need
Creation of a plugin that allows AutoGPT to interface with Twitter using tweepy
I have been messing around with twitter integration on my own fork of AutoGPT
So far, AutoGPTweeter has the ability to tweet out asking for tasks, check its mentions, and respond to mentions with a completed task.
It's OK in its current state as a modification of base AutoGPT, but I think this would be better suited as a plugin
I'm excited to see future development and a potential for easy extensibility of AutoGPT, and I will be watching this repo closely
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.