Update usage.md
Alessandro committed
Oct 15, 2024 at 17:19 UTC
c47ef6762cb6bec3a418d72c05f45599741dec6b
1 file changed
+5
-6
docs/usage.md
+5
-6
@@ -76,13 +76,13 @@ app.run(request_handler=NoRequestLoggingWSGIRequestHandler, host="0.0.0.0", port
76
> [!CAUTION]
77
> We believe in safe and ethical AI development, and highly
78
> suggest you to use the Docker container designed for running Agent Zero.
79
+> However, we understand that some users may want to use the code_execution_tool outside of the Docker container.
80
+>
81
> This is a dangerous and untested feature, and we are not responsible for any damage
82
> or illegal activities or legal liabilities caused by the use of this feature.
83
> As you are responsible for your own actions, use this feature only if 100% sure of what you're doing.
82
-<details>
83
-<summary>I accept the risks and want to use this feature.</summary>
84
85
-- If you are a power-user and 100% sure of what you're doing, you can use the code_execution_tool outside of the Docker container by following these steps:
85
+- If you accept the risks, follow these steps:
86
87
88
@@ -90,7 +90,6 @@ app.run(request_handler=NoRequestLoggingWSGIRequestHandler, host="0.0.0.0", port
90
91
2. Comment out lines 56, 57, 58 and 59 in `initialize.py` that sets the `code_execution_tool` SSH connection parameters. Point them to your machine accordingly. This will enable the code_execution_tool for your Agent Zero instance.
92
93
-> [!IMPORTANT]
93
+> [!IMPORTANT]
94
> The `code_exec_ssh_pass` parameter (root user password) has to be provided to
95
-> `initialize.py` for the code_execution_tool to be able to connect to the machine.
96
-</details>
\ No newline at end of file
95
+> `initialize.py` for the code_execution_tool to be able to connect to the machine.
\ No newline at end of file