Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Instruments not available to agent in docker container... v0.7.1 #223

Open
devnull75 opened this issue Oct 29, 2024 · 3 comments
Open

Instruments not available to agent in docker container... v0.7.1 #223

devnull75 opened this issue Oct 29, 2024 · 3 comments

Comments

@devnull75
Copy link

Cannot get the default yt_download instrument or custom instruments to load...

instruments

Please see attached image for details.

@devnull75 devnull75 changed the title Instruments not available to agent in docker container... Instruments not available to agent in docker container... v0.7.1 Oct 29, 2024
@Zeroocooloverride
Copy link

check if you have uncomment (without #) docker host port , etc in initialized.py

@Zeroocooloverride
Copy link

Zeroocooloverride commented Oct 30, 2024

I just deploy in Vercel and Google clouds and was installed straight forward, if you are using Linux without docker.desktop may be quiet Trekkie, better another environment

@Zeroocooloverride
Copy link

Well, if you will prompt an agent to climb a wall at least give the stair. Long history short: Just download any bash or python app that do so, and then rute the path of the app with the agent. Other way, with maybe less chance, is giving the task of create an app that download videos from YouTube (of course you must do a better prompt than this). You may need go gradual in what you ask cause you'll miss do many things, if you don't prompt properly the agent in each step or in order to achieves tasks bit more complex or without having the necessaries tools. Example: wrong prompt: -you ask to the agent: Connect to my face....
-Agent: ??????
Good Prompt: "Connect to Facebook on host: xxxxx Port: xxxxx, user: xxxxxxxPassword:xxxxxx, and send back any request of Catpcha"

First make sure that the agent have the right tools for the task you will command. Just need configure properly one time and then goes alone. ( need guidance till you get happy with the results.
This Error happen's each time that the Agent want to use "code_execution_tool" or in another task is working?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants