schihei/yolo-ai-cmdbot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Squashed commit of the following:

Browse Source 
commit 7b16b63f5f269baa0441ee171d906419585d2526
Author: wunderwuzzi23 <johannr@wunderwuzzi.net>
Date:   Sat Mar 18 19:34:34 2023 -0700

    update text

commit d99b7ebf211a517d74fcf3241843e78a71e99d05
Author: wunderwuzzi23 <johannr@wunderwuzzi.net>
Date:   Sat Mar 18 19:31:28 2023 -0700

    fix formatting

commit 65b1f6218cc32f0a0001637b22b9f1b4640de983
Author: wunderwuzzi23 <johannr@wunderwuzzi.net>
Date:   Sat Mar 18 19:17:08 2023 -0700

    updating messages

commit 314071228395a595503dc3a15fda2b3c8b5e6095
Author: wunderwuzzi23 <johannr@wunderwuzzi.net>
Date:   Sat Mar 18 19:13:40 2023 -0700

    updating install.bat for yolo.yaml settings

commit 85c9f381415c86e7c95572bdcbd98d6478f616ef
Author: wunderwuzzi23 <johannr@wunderwuzzi.net>
Date:   Sat Mar 18 19:08:09 2023 -0700

    load yolo.yaml from executing directory

commit d9ee70035e186c8b21875d58e7a7bf3f980eaa60
Author: wunderwuzzi23 <johannr@wunderwuzzi.net>
Date:   Sat Mar 18 18:43:45 2023 -0700

    update readme

commit f2ae85827c675e3f2c87bf4d455709e227e1bfb4
Author: wunderwuzzi23 <johannr@wunderwuzzi.net>
Date:   Sat Mar 18 18:37:41 2023 -0700

    cleanup

commit fc5cf55982dd6de3a4e81de2b0286f18788bc87c
Author: wunderwuzzi23 <johannr@wunderwuzzi.net>
Date:   Sat Mar 18 18:31:00 2023 -0700

    fix formatting

commit 3ec4cf959cf4a43d061b0d579c863af5bb495631
Author: wunderwuzzi23 <johannr@wunderwuzzi.net>
Date:   Sat Mar 18 18:27:49 2023 -0700

    set safety: True in config

commit d13153141bbdb4ada5d9bf742b19fd9c10624c86
Author: wunderwuzzi23 <johannr@wunderwuzzi.net>
Date:   Sat Mar 18 18:25:07 2023 -0700

    update readme

commit 39f82ee8cf744ef6fbfbe6622e4d39cc6323d69a
Author: wunderwuzzi23 <johannr@wunderwuzzi.net>
Date:   Sat Mar 18 18:24:43 2023 -0700

    update readme

commit 944046c11bdcd3b01b33798dae5ca33e8ddda9db
Author: wunderwuzzi23 <johannr@wunderwuzzi.net>
Date:   Sat Mar 18 18:21:47 2023 -0700

    update requirements

commit 0c22313bdc6b3a9f272faf99b9998930ede9502a
Author: wunderwuzzi23 <johannr@wunderwuzzi.net>
Date:   Sat Mar 18 18:15:17 2023 -0700

    formatting

commit 08e16c67ad8fd588962f9bf22fe0588ac4c0ec3a
Author: wunderwuzzi23 <johannr@wunderwuzzi.net>
Date:   Sat Mar 18 17:39:35 2023 -0700

    default gpt-3.5-turbo (gpt-4 is waitlist for many)

commit eec224fe3b34a2627d771682cde291ccdf96bcac
Author: wunderwuzzi23 <johannr@wunderwuzzi.net>
Date:   Sat Mar 18 17:16:57 2023 -0700

    add yolo.yaml, gpt-4 support, improve install.sh
This commit is contained in:
wunderwuzzi23
2023-03-18 19:38:38 -07:00
parent 39a010c48e
commit d42082f8fe
6 changed files with 154 additions and 107 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+34 -13
View File
@@ -2,6 +2,27 @@
![Animated GIF](https://github.com/wunderwuzzi23/blog/raw/master/static/images/2023/yolo-shell-anim-gif.gif)
# Update Yolo v0.2 - Support for GPT-4 API
This update introduces the `yolo.yaml` configuration file. In this file you can specify which OpenAI model you want to query, and other settings. The safety switch also moved into this configuration file.
For now the default model is still `gpt-3.5-turbo`, but you can update to `gpt-4` if you have gotten access already!
```
Yolo v0.2 - by @wunderwuzzi23
Usage: yolo [-a] list the current directory information
Argument: -a: Prompt the user before running the command (only useful when safety is off)
Current configuration per yolo.yaml:
* Model : gpt-3.5-turbo
* Temperature : 0
* Max. Tokens : 500
* Safety : on
```
Happy Hacking!
# Installation on Linux and macOS
```
@@ -17,17 +38,18 @@ yolo show me some funny unicode characters
## OpenAI API Key configuration
There are two ways to configure the key on Linux and macOS:
There are three ways to configure the key on Linux and macOS:
- You can either `export OPENAI_API_KEY=<yourkey>`, or have a `.env` file in the same directory as `yolo.py` with `OPENAI_API_KEY="<yourkey>"` as a line
- Create a file at `~/.openai.apikey` with the key in it
- Add the key to the `yolo.yaml` configuration file
## Aliases
To set the alias, like `yolo` or `computer` on each login, add them to your .bashrc or .bash_aliases file. (zsh on macOS)
To set the alias, like `yolo` or `computer` on each login, add them to .bash_aliases (or .zshrc on macOS) file. Make sure the path is the one you want to use.
```
echo "alias yolo=$TARGET_FULLPATH" >> ~/.bash_aliases
echo "alias computer=$TARGET_FULLPATH" >> ~/.bash_aliases
echo "alias yolo=$(pwd)/yolo.py" >> ~/.bash_aliases
echo "alias computer=$(pwd)/yolo.py" >> ~/.bash_aliases
```
## Installation script
@@ -35,21 +57,20 @@ echo "alias computer=$TARGET_FULLPATH" >> ~/.bash_aliases
Another option is to run `source install.sh` after cloning the repo. That does the following:
1. Copies the necessary files to `~/yolo-ai-cmdbot/`
2. Creates two aliases `yolo` and `computer` pointint to `~/yolo-ai-cmdbot/yolo.py`
3. Adds the aliases to the `~/bash_aliases` file (only tested on Ubuntu)
3. Adds the aliases to the `~/.bash_aliases` or `~/.zshrc` file
That's it for Linux and macOS. Now make sure you have an OpenAI API key set.
# Windows Installation
On Windows run `.\install.bat` (or double-click) after cloning the repo. By default it does the following:
On Windows you can run `.\install.bat` (or double-click) after cloning the repo. By default it does the following:
1. Copies the necessary files to `~\yolo-ai-cmdbot\`
2. Creates a `yolo.bat` file in `~` that lets you run equivalent to `python.exe ~\yolo-ai-cmdbot\yolo.py`
You also have the option to:
1. Change the location where `yolo-ai-cmdbot\` and `yolo.bat` will be created
2. Skip creating `yolo-ai-cmdbot\` and use the folder of the cloned repository instead.
3. Create a `.openai.apikey` and/or `.yolo-safety-off` file in your `~` directory
3. Create a `.openai.apikey` file in your `~` directory
That's it basically.
@@ -60,6 +81,8 @@ On Windows `export OPENAI_API_KEY=<yourkey>` will not work instead:
- Or, Run PowerShell as administrator and run `setx OPENAI_API_KEY "<yourkey>"`
- Or, Go to `Start` and search `edit environment variables for your account` and manually create the variable with name `OPENAI_API_KEY` and value `<yourkey>`
Optionally (since v.0.2), the key can also be stored in `yolo.yaml`.
## Running yolo on Windows
Windows is less tested, it does work though and will use PowerShell.
@@ -88,13 +111,11 @@ Have fun.
# Disabling the safety switch! **Caution!**
By default `yolo` will prompt the user before executing commands. To have yolo run commands right away when they come back from ChatGPT create a file named `~/.yolo-safety-off`.
By default `yolo` will prompt the user before executing commands.
A simple command to do that on Linux would be:
Since v.0.2 the safety switch setting moved to `yolo.yaml`, the old `~/.yolo-safety-off` is not used anymore.
```
touch ~/.yolo-safety-off
```
To have yolo run commands right away when they come back from ChatGPT change the `safety` in the `yolo.yaml` to `False`.
If you still want to inspect the command that is executed when safety is off, add the `-a` argument, e.g `yolo -a delete the file test.txt`.
install.bat
+21 -47
View File
@@ -4,20 +4,20 @@ setlocal enabledelayedexpansion
:: First check if `install.bat` (this) has needed files in same directory
if not exist %~dp0\yolo.py ( echo `yolo.py` missing in %~dp0 cannot install & goto :choice_default_3 )
if not exist %~dp0\prompt.txt ( echo `prompt.txt` missing in %~dp0 cannot install & goto :choice_default_3 )
if not exist %~dp0\yolo.yaml ( echo `yolo.yaml` missing in %~dp0 cannot install & goto :choice_default_3 )
:: Note: "~" or %HOME% is equivalent to "%HOMEDRIVE%%HOMEPATH%\" but the latter is set in VM environments (from what I can tell)
:: INSTALL_DIR = Directory the "yolo-ai-cmdbot\" will go to.
:: SCRIPT_DIR = Directory the "yolo.bat" script will go to.
:: createDIR = Whether or not a seperate "yolo-ai-cmdbot\" directory will be made/used to hold "yolo.py" and "prompt.txt". 1=Yes, 2=Just_use_Repo (the folder this is in)
:: createAPIKEY = Whether to create a ".openai.apikey" at %HOMEDRIVE%%HOMEPATH%\. 1=Yes, 2=No
:: createSafetyOff = Whether to create a ".yolo-safety-off" at %HOMEDRIVE%%HOMEPATH%\. 1=Yes, 2=No
:: Default values:
set "INSTALL_DIR=%HOMEDRIVE%%HOMEPATH%\"
set "SCRIPT_DIR=%HOMEDRIVE%%HOMEPATH%\"
set /a "createDIR=1"
set /a "createAPIKEY=2"
set /a "createSafetyOff=2"
set "installing=1"
:: Set Variables To User Defined If Needed
@@ -67,6 +67,8 @@ if /i %createDIR%==1 ( call :install_yolo_directory )
if /i %createDIR%==2 ( call :install_yolo_repository )
::Make sure safety is on when default installing
::Note: when upgrading from v0.1 to v0.2 it will delete the file.
::With v.0.2 the safety switch moved to the config file yolo.yaml
if /i !installing!==1 ( del %HOMEDRIVE%%HOMEPATH%\.yolo-safety-off )
:choice_default_4
@@ -123,13 +125,8 @@ cls
call :print_apikey
choice /n /c YN /m "Let me know which option you want to select: "
set /a createAPIKEY=!ERRORLEVEL!
cls
call :print_safetyoff
choice /n /c YN /m "Let me know which option you want to select: "
set /a createSafetyOff=!ERRORLEVEL!
if /i !createAPIKEY!==1 ( call :create_openai_apikey )
if /i !createSafetyOff!==1 ( call :create_safety_off )
goto :EOF
:: Creates a directory to hold yolo.py and prompt.txt
@@ -139,6 +136,7 @@ echo Installing to !TARGET_DIR!
mkdir !TARGET_DIR!
copy %~dp0\yolo.py !TARGET_DIR!
copy %~dp0\prompt.txt !TARGET_DIR!
copy %~dp0\yolo.yaml !TARGET_DIR!
goto :EOF
:: Create yolo.bat and input code linking to created directory
@@ -165,13 +163,6 @@ if not exist %~dp0\yolo.py ( echo Not Found: Aborting "create_yolo_bat_from_repo
)
goto :EOF
:: Creates the safety off file and puts it in ~ for you
:create_safety_off
echo Yolo Safety Off:
echo Creating `.yolo-safety-off` in `%HOMEDRIVE%%HOMEPATH%\`
copy nul %HOMEDRIVE%%HOMEPATH%\.yolo-safety-off
goto :EOF
:: Creates the .openai.apikey if it doesn't already exists (otherwise, does nothing)
:create_openai_apikey
echo Yolo OpenAi ApiKey:
@@ -267,38 +258,17 @@ echo If you do not understand what this means, select [N]
echo.
goto :EOF
:: Prints a prompt for `.yolo-safety-off`
:print_safetyoff
echo.
echo Installation `.yolo-safety-off` File Options:
echo.
echo This file will remove the confirmation message before running commands given by yolo
echo You can still have a confirmation message appear using the `-a` switch before your prompt:
echo `.\yolo.bat -a [Enter Prompt Here]`
echo.
echo [Y] Yes, Create a `.yolo-safety-off` if it does not exist at `%HOMEDRIVE%%HOMEPATH%\`
echo [N] No, Will skip this.
echo.
echo You probably want to use [N], this may cause you to delete/modify files you did not want to.
echo If you do not understand what this means, select [N]
echo.
goto :EOF
:: Prints a "Finished Installing" and usage message after installing
:print_guide
echo.
echo Finished Installing Yolo...
echo Finished Installing Yolo.
echo.
echo You can run commands by being in the same directory as your `yolo.bat` file ( It is in `!SCRIPT_DIR!` ) with the following command:
echo Run commands by being in the same directory as your `yolo.bat` file ( It is in `!SCRIPT_DIR!` ):
echo `.\yolo.bat [Enter Prompt Here]`
echo You can also put your `yolo.bat` file into a $PATH directory and run it like so, instead:
echo `yolo [Enter Prompt Here]`
echo You can use the `-a` switch to make sure yolo asks you before running the returned command:
echo `yolo -a [Enter Prompt Here]`
echo Make sure to do this when deleting/modifying files/folders with safety off.
echo.
echo You should have `C:\Windows\System32` as a path in the $PATH environment variable but you can write the command `echo $env:PATH` into PowerShell for more options...
set /p "wait=Press [Enter] for more:"
echo Or, put the `yolo.bat` file into a $PATH directory and run it like so, instead:
echo `yolo [Enter Prompt Here]`
echo.
if /i !createDIR!==1 ( call :print_bat_warning_directory )
if /i !createDIR!==2 ( call :print_bat_warning_repository )
set /p "wait=Press [Enter] for more:"
@@ -326,16 +296,20 @@ goto :EOF
:print_apikey_guide
echo.
echo Api Key:
echo API Key:
echo.
echo You will need to provide your openai apikey to use yolo.
echo You can get this at `https://platform.openai.com/account/api-keys` after logging in.
echo - You can then put the apikey straight into a `.openai.apikey` file in `%HOMEDRIVE%%HOMEPATH%\`
echo (You can run this `install.bat` again and select `O`ptional Files to create a `.openai.apikey` file for you)
echo -You can paste `OPENAI_API_KEY="[yourkey]"` into a `.env` file that should be in the folder yolo is installed in currently.
echo You need to provide your OpenAI API key to use yolo.
echo.
echo You can get a key from `https://platform.openai.com/account/api-keys` after logging in.
echo There are multiple options for providing the key:
echo (1) You can put the key into a `.openai.apikey` file in `%HOMEDRIVE%%HOMEPATH%\`
echo Run `install.bat` again and select `O`ptional Files to create a `.openai.apikey` file
echo (2) You can paste `OPENAI_API_KEY="[yourkey]"` into a `.env` file that should be in the folder yolo is installed in currently.
if /i !createDIR!==1 ( echo `.env` should be in: !TARGET_DIR! )
if /i !createDIR!==2 ( echo `.env` should be in: %~dp0 )
echo -You can run `$env:OPENAI_API_KEY="[yourkey]"` in your terminal before using yolo in that terminal
echo (3) You can run `$env:OPENAI_API_KEY="[yourkey]"` in your terminal before using yolo in that terminal
echo -If you run PowerShell as administrator you can then run `setx OPENAI_API_KEY "[yourkey]"` to permanently and use yolo in any terminal (you may need to reopen the terminal once).
echo -Go to `Start` and search `edit environment variables for your account` and manually create the variable with name `OPENAI_API_KEY` and value `[yourkey]`
echo (4) Another option is to put the API key in the yolo.yaml configuration file (since v.0.2)
echo.
goto :EOF
install.sh
Regular → Executable
+31 -7
View File
@@ -1,18 +1,42 @@
# Installs yolo in the user's home directory
# Simple installer for yolo in the user's home directory
echo "Hello. Installing yolo..."
echo "- Creating yolo-ai-cmdbot in home directory..."
TARGET_DIR=~/yolo-ai-cmdbot
TARGET_FULLPATH=$TARGET_DIR/yolo.py
mkdir -p $TARGET_DIR
cp yolo.py prompt.txt $TARGET_DIR
echo "- Copying files..."
cp yolo.py prompt.txt yolo.yaml $TARGET_DIR
chmod +x $TARGET_FULLPATH
#Linux/Mac
# Creates two aliases for use
echo "- Creating yolo and computer aliases..."
alias yolo=$TARGET_FULLPATH
alias computer=$TARGET_FULLPATH
# Add the aliases to the logon scripts
echo "alias yolo=$TARGET_FULLPATH" >> ~/.bash_aliases
echo "alias computer=$TARGET_FULLPATH" >> ~/.bash_aliases
# Depends on your shell
if [[ "$SHELL" == "/bin/bash" ]]; then
echo "- Adding aliases to ~/.bash_aliases"
echo "alias yolo=$TARGET_FULLPATH" >> ~/.bash_aliases
echo "alias computer=$TARGET_FULLPATH" >> ~/.bash_aliases
elif [[ "$SHELL" == "/bin/zsh" ]]; then
echo "- Adding aliases to ~/.zshrc"
echo "alias yolo=$TARGET_FULLPATH" >> ~/.zshrc
echo "alias computer=$TARGET_FULLPATH" >> ~/.zshrc
else
echo "Note: Shell was not bash or zsh."
echo " Consider configuring aliases (like yolo and/or computer) manually by adding them to your login script, e.g:"
echo " alias yolo=$TARGET_FULLPATH >> <your_logon_file>"
fi
echo
echo "Done."
echo
echo "Make sure you have the OpenAI API key set via one of these options:"
echo " - environment variable"
echo " - .env or an ~/.openai.apikey file or in"
echo " - yolo.yaml"
echo
echo "Have fun!"
requirements.txt
+4 -3
View File
@@ -1,5 +1,6 @@
openai==0.27
termcolor==2.2.0
colorama
python-dotenv
distro
colorama==0.4.4
python-dotenv==1.0.0
distro==1.7.0
PyYAML==5.4.1
yolo.py
+54 -36
View File
@@ -11,20 +11,21 @@ import sys
import subprocess
import dotenv
import distro
import yaml
from termcolor import colored
from colorama import init
# Check if the user globally disabled the safety switch
def get_yolo_safety_switch_config():
def read_config() -> any:
home_path = os.path.expanduser("~")
yolo_safety_off_path = os.path.join(home_path,".yolo-safety-off")
## Find the executing directory (e.g. in case an alias is set)
## So we can find the config file
yolo_path = os.path.abspath(__file__)
prompt_path = os.path.dirname(yolo_path)
if os.path.exists(yolo_safety_off_path):
return False
else:
return True
config_file = os.path.join(prompt_path, "yolo.yaml")
with open(config_file, 'r') as file:
return yaml.safe_load(file)
# Construct the prompt
def get_full_prompt(user_prompt, shell):
@@ -48,12 +49,23 @@ def get_full_prompt(user_prompt, shell):
return prompt
def print_usage():
print("Yolo 0.1 - by @wunderwuzzi23")
print("Yolo v0.2 - by @wunderwuzzi23")
print()
print("Usage: yolo [-a] list the current directory information")
print("Argument: -a: Prompt the user before running the command")
print("Argument: -a: Prompt the user before running the command (only useful when safety is off)")
print()
print("Current safety switch setting (~/.yolo-safety-off) is " + str(yolo_safety_switch))
yolo_safety_switch = "on"
if config["safety"] != True:
yolo_safety_switch = "off"
print("Current configuration per yolo.yaml:")
print("* Model : " + str(config["model"]))
print("* Temperature : " + str(config["temperature"]))
print("* Max. Tokens : " + str(config["max_tokens"]))
print("* Safety : " + yolo_safety_switch)
def get_os_friendly_name():
@@ -70,10 +82,30 @@ def get_os_friendly_name():
return os_name
def set_api_key():
# Two options for the user to specify they openai api key.
#1. Place a ".env" file in same directory as this with the line:
# OPENAI_API_KEY="<yourkey>"
# or do `export OPENAI_API_KEY=<yourkey>` before use
dotenv.load_dotenv()
openai.api_key = os.getenv("OPENAI_API_KEY")
#2. Place a ".openai.apikey" in the home directory that holds the line:
# <yourkey>
# Note: This options will likely be removed in the future
if not openai.api_key: #If statement to avoid "invalid filepath" error
home_path = os.path.expanduser("~")
openai.api_key_path = os.path.join(home_path,".openai.apikey")
#3. Final option is the key might be in the yolo.yaml config file
# openai_apikey: <yourkey>
if not openai.api_key:
openai.api_key = config["openai_api_key"]
if __name__ == "__main__":
# Get the global safety switch setting (default is True/on)
yolo_safety_switch = get_yolo_safety_switch_config()
config = read_config()
set_api_key()
# Unix based SHELL (/bin/bash, /bin/zsh), otherwise assuming it's Windows
shell = os.environ.get("SHELL", "powershell.exe")
@@ -82,31 +114,18 @@ if __name__ == "__main__":
ask_flag = False # safety switch -a command line argument
yolo = "" # user's answer to safety switch (-a) question y/n
# Two options for the user to specify they openai api key.
#1. Place a ".env" file in same directory as this with the line:
# OPENAI_API_KEY="<yourkey>"
# or do `export OPENAI_API_KEY=<yourkey>` before use
dotenv.load_dotenv()
openai.api_key = os.getenv("OPENAI_API_KEY")
#2. Place a ".openai.apikey" in the home directory that holds the line:
# <yourkey>
if not openai.api_key: #If statement to avoid "invalid filepath" error
home_path = os.path.expanduser("~")
openai.api_key_path = os.path.join(home_path,".openai.apikey")
# Parse arguments and make sure we have at least a single word
if len(sys.argv) < 2:
print_usage()
sys.exit(-1)
# safety switch via argument -a (local override of global setting)
# Safety switch via argument -a (local override of global setting)
# Force Y/n questions before running the command
if sys.argv[1] == "-a":
ask_flag = True
command_start_idx = 2
# to allow easy/natural use we don't require the input to be a
# To allow easy/natural use we don't require the input to be a
# single string. So, the user can just type yolo what is my name?
# without having to put the question between ''
arguments = sys.argv[command_start_idx:]
@@ -117,7 +136,6 @@ if __name__ == "__main__":
print ("No user prompt specified.")
sys.exit(-1)
# Load the correct prompt based on Shell and OS and append the user's prompt
prompt = get_full_prompt(user_prompt, shell)
@@ -127,13 +145,13 @@ if __name__ == "__main__":
# Call the ChatGPT API
response = openai.ChatCompletion.create(
model="gpt-3.5-turbo",
model=config["model"],
messages=[
{"role": "system", "content": system_prompt},
{"role": "user", "content": prompt}
],
temperature=0,
max_tokens=500,
temperature=config["temperature"],
max_tokens=config["max_tokens"],
)
#print (response)
@@ -143,8 +161,8 @@ res_command = response.choices[0].message.content.strip()
#Enable color output on Windows using colorama
init()
prefixes = ("Sorry", "I'm sorry")
if res_command.startswith(prefixes):
prefixes = ("sorry", "i'm sorry", "the question is not clear")
if res_command.lower().startswith(prefixes):
print(colored("There was an issue: "+res_command, 'red'))
sys.exit(-1)
@@ -154,8 +172,8 @@ if res_command.count("```",2):
sys.exit(-1)
print("Command: " + colored(res_command, 'blue'))
if yolo_safety_switch == True or ask_flag == True:
print("Execute the command? Y/n (default Y) ==> ", end = '')
if config["safety"] != "off" or ask_flag == True:
print("Execute the command? [Y/n] ==> ", end = '')
yolo = input()
print()
yolo.yaml
+9
View File
@@ -0,0 +1,9 @@
model: gpt-3.5-turbo # If you have access to gpt-4 API already, you can update this.
temperature: 0
max_tokens: 500
# Safety: If set to False, commands returned from the AI will be run *without* prompting the user.
safety: True
# Open AI API Key (optional): The key can aso be provided via environment variable (OPENAI_API_KEY), .env, or ~/.openai.apikey file
openai_api_key: