### Install ShellGPT with LiteLLM

Source: https://github.com/ther1d/shell_gpt/wiki/Azure

Installs the ShellGPT package with LiteLLM support, enabling communication with various LLM backends. This is the initial step for integrating LiteLLM.

```shell
pip install shell-gpt[litellm]
```

--------------------------------

### Provide Go learning advice and example using heredoc

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Demonstrates using a heredoc (`<< EOF`) to provide multiple lines of input to ShellGPT, asking for learning advice and a code example for Golang.

```shell
sgpt << EOF
What is the best way to lear Golang?
Provide simple hello world example.
EOF
# -> The best way to learn Golang...

```

--------------------------------

### Example JSON Output from Custom Role

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Provides an example of the JSON output generated by the `json_generator` custom role, demonstrating the structure and content expected for user, password, email, and address.

```json
{
  "user": "JohnDoe",
  "password": "p@ssw0rd",
  "email": "johndoe@example.com",
  "address": {
    "street": "123 Main St",
    "city": "Anytown",
    "state": "CA",
    "zip": "12345"
  }
}
```

--------------------------------

### Start Ollama API Server

Source: https://github.com/ther1d/shell_gpt/wiki/Ollama

This command starts the Ollama API server, making the locally hosted language models available for use by other applications.

```shell
ollama serve
```

--------------------------------

### Dockerfile for ShellGPT with Ollama

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

This Dockerfile sets up an environment to run ShellGPT using Ollama. It installs Python, configures necessary environment variables like the default model and API base URL, installs the 'litellm' package, and sets the entrypoint to 'sgpt'.

```dockerfile
FROM python:3-slim

ENV DEFAULT_MODEL=ollama/mistral:7b-instruct-v0.2-q4_K_M
ENV API_BASE_URL=http://10.10.10.10:11434
ENV USE_LITELLM=true
ENV OPENAI_API_KEY=bad_key
ENV SHELL_INTERACTION=false
ENV PRETTIFY_MARKDOWN=false
ENV OS_NAME="Arch Linux"
ENV SHELL_NAME=auto

WORKDIR /app
COPY . /app

RUN apt-get update && apt-get install -y gcc
RUN pip install --no-cache /app[litellm] && mkdir -p /tmp/shell_gpt

VOLUME /tmp/shell_gpt

ENTRYPOINT ["sgpt"]
```

--------------------------------

### Install ShellGPT using pip

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

This snippet shows how to install the ShellGPT package using pip. It's a straightforward Python package installation.

```shell
pip install shell-gpt
```

--------------------------------

### Runtime Configuration File Example

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Illustrates the structure and content of the runtime configuration file (`~/.config/shell_gpt/.sgptrc`). It shows various parameters that can be set, such as API keys, cache settings, default models, and paths.

```text
# API key, also it is possible to define OPENAI_API_KEY env.
OPENAI_API_KEY=your_api_key
# Base URL of the backend server. If "default" URL will be resolved based on --model.
API_BASE_URL=default
# Max amount of cached message per chat session.
CHAT_CACHE_LENGTH=100
# Chat cache folder.
CHAT_CACHE_PATH=/tmp/shell_gpt/chat_cache
# Request cache length (amount).
CACHE_LENGTH=100
# Request cache folder.
CACHE_PATH=/tmp/shell_gpt/cache
# Request timeout in seconds.
REQUEST_TIMEOUT=60
# Default OpenAI model to use.
DEFAULT_MODEL=gpt-4o
# Default color for shell and code completions.
DEFAULT_COLOR=magenta
# When in --shell mode, default to "Y" for no input.
DEFAULT_EXECUTE_SHELL_CMD=false
# Disable streaming of responses
DISABLE_STREAMING=false
# The pygment theme to view markdown (default/describe role).
CODE_THEME=default
# Path to a directory with functions.
OPENAI_FUNCTIONS_PATH=/Users/user/.config/shell_gpt/functions
# Print output of functions when LLM uses them.
SHOW_FUNCTIONS_OUTPUT=false
# Allows LLM to use functions.
OPENAI_USE_FUNCTIONS=true
# Enforce LiteLLM usage (for local LLMs).
USE_LITELLM=false
```

--------------------------------

### Install ShellGPT with LiteLLM Support

Source: https://github.com/ther1d/shell_gpt/wiki/Ollama

This command installs the ShellGPT package with the necessary dependencies to support LiteLLM, enabling communication with local LLM backends.

```shell
pip install "shell-gpt[litellm]"
```

--------------------------------

### Generate Docker command with ShellGPT

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Illustrates generating a Docker command to start an Nginx container and mount a local HTML file using ShellGPT.

```shell
sgpt -s "start nginx container, mount ./index.html"
# -> docker run -d -p 80:80 -v $(pwd)/index.html:/usr/share/nginx/html/index.html nginx
# -> [E]xecute, [D]escribe, [A]bort: e
```

--------------------------------

### Install ShellGPT Dependencies

Source: https://github.com/ther1d/shell_gpt/blob/main/CONTRIBUTING.md

This command installs the ShellGPT project dependencies, including development and testing packages. The '-e' flag installs the package in editable mode, and '.[dev,test]' specifies the extra dependencies to install.

```Shell
pip install -e ."[dev,test]"
```

--------------------------------

### Compile ShellGPT Binary with PyInstaller

Source: https://github.com/ther1d/shell_gpt/wiki/Home

This snippet demonstrates how to build a single executable binary for the ShellGPT application using PyInstaller. It includes cloning the repository, setting up a virtual environment, installing dependencies, and running PyInstaller to create the binary.

```shell
git clone https://github.com/TheR1D/shell_gpt.git
cd shell_gpt
python3 -m venv venv
source venv/bin/activate
pip install pyinstaller
pip install -e .
cd sgpt
pyinstaller --onefile app.py
```

--------------------------------

### Run ShellGPT with Azure Backend

Source: https://github.com/ther1d/shell_gpt/wiki/Azure

Executes ShellGPT using the Azure backend with a specified model deployment and a sample prompt. This command demonstrates how to interact with ShellGPT after the setup is complete.

```shell
sgpt --model azure/<your_deployment_name> --no-functions "Hi Azure"
```

--------------------------------

### Start Chat Session and Make a Request

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Explains how to start a chat session with a specific name (`conversation_1`) and make a request to the language model. Subsequent requests with the same session name will maintain the conversation context.

```shell
sgpt --chat conversation_1 "please remember my favorite number: 4"
sgpt --chat conversation_1 "what would be my favorite number + 4?"
```

--------------------------------

### Install Ollama on Linux/WSL2

Source: https://github.com/ther1d/shell_gpt/wiki/Ollama

This command downloads and executes the Ollama installation script for Linux and Windows Subsystem for Linux 2 environments.

```shell
curl https://ollama.ai/install.sh | sh
```

--------------------------------

### Run Shell GPT Docker Container

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

This snippet demonstrates how to run the Shell GPT Docker container. It includes setting the OpenAI API key, operating system name, shell name, and mounting a volume for cache storage. It also shows an example command to execute.

```shell
docker run --rm \
           --env OPENAI_API_KEY=api_key \
           --env OS_NAME=$(uname -s) \
           --env SHELL_NAME=$(echo $SHELL) \
           --volume gpt-cache:/tmp/shell_gpt \
       ghcr.io/ther1d/shell_gpt -s "update my system"
```

--------------------------------

### Initiate Chat Session with Code Generation

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Demonstrates starting a chat session (`conversation_2`) and simultaneously requesting code generation for making a request to localhost using Python.

```shell
sgpt --chat conversation_2 --code "make a request to localhost using python"
```

```python
import requests

response = requests.get('http://localhost')
print(response.text)
```

--------------------------------

### Analyze docker logs with ShellGPT

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Shows how to pipe `docker logs` output to ShellGPT to analyze logs, find errors, and get potential solutions.

```shell
docker logs -n 20 my_app | sgpt "check logs, find errors, provide possible solutions"
```

--------------------------------

### Start REPL Mode with Initial Prompt from File

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Initiates a REPL mode session with an initial prompt loaded from a file. The content of the specified file (e.g., 'my_app.py') is fed as the initial input to the GPT model.

```shell
sgpt --repl temp < my_app.py
```

--------------------------------

### Install Default Shell GPT Functions

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Installs the default set of functions provided by Shell GPT. These functions can be used by the LLM to execute system tasks and interact with the user's environment.

```shell
sgpt --install-functions
```

--------------------------------

### Shell GPT Docker Alias and Usage

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

This section provides an example of creating a Docker alias for Shell GPT for easier command execution. It also shows how to set the OpenAI API key and interact with the tool using chat functionality.

```shell
alias sgpt="docker run --rm --volume gpt-cache:/tmp/shell_gpt --env OPENAI_API_KEY --env OS_NAME=$(uname -s) --env SHELL_NAME=$(echo $SHELL) ghcr.io/ther1d/shell_gpt"
export OPENAI_API_KEY="your OPENAI API key"
sgpt --chat rainbow "what are the colors of a rainbow"
sgpt --chat rainbow "inverse the list of your last answer"
sgpt --chat rainbow "translate your last answer in french"
```

--------------------------------

### Pull Mistral LLM Model with Ollama

Source: https://github.com/ther1d/shell_gpt/wiki/Ollama

This command downloads the 'mistral:7b-instruct' language model using Ollama. The download and installation process may take some time.

```shell
ollama pull mistral:7b-instruct
```

--------------------------------

### Generate OS-specific system update command

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Shows how ShellGPT generates an appropriate system update command based on the operating system. Examples for macOS and Ubuntu are provided.

```shell
sgpt -s "update my system"
# -> sudo softwareupdate -i -a
# -> [E]xecute, [D]escribe, [A]bort: e
```

```shell
sgpt -s "update my system"
# -> sudo apt update && sudo apt upgrade -y
# -> [E]xecute, [D]escribe, [A]bort: e
```

--------------------------------

### Start REPL Mode Chat Session

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Initiates an interactive chat session with GPT models in REPL mode. A unique session name can be provided, or 'temp' can be used for a temporary session. This mode shares the underlying object with chat mode, allowing for seamless transitions between them.

```shell
sgpt --repl temp
```

--------------------------------

### Iterative Shell Command Generation in Chat Mode

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Illustrates how to use shell_gpt in a chat mode (`conversation_3`) to iteratively generate and refine shell commands, starting with listing files, sorting them, concatenating them with FFmpeg, and finally converting the output to MP3.

```shell
sgpt --chat conversation_3 --shell "what is in current folder"
sgpt --chat conversation_3 "Sort by name"
sgpt --chat conversation_3 "Concatenate them using FFMPEG"
sgpt --chat conversation_3 "Convert the resulting file into an MP3"
```

--------------------------------

### LLM Handles Function Execution Errors and Retries

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Shows how Shell GPT and the LLM can handle errors during function execution. If a command fails (e.g., due to a missing tool like `jq`), the LLM can attempt to resolve the issue, such as installing the missing tool, and then retry the original command.

```shell
sgpt "parse /tmp/test.json file using jq and return only email value"
# -> @FunctionCall execute_shell_command(shell_command="jq -r '.email' /tmp/test.json")
# -> It appears that jq is not installed on the system. Let me try to install it using brew.
# -> @FunctionCall execute_shell_command(shell_command="brew install jq")
# -> jq has been successfully installed. Let me try to parse the file again.
```

--------------------------------

### Ask about shell redirects using here-string

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Shows how to use a here-string (`<<<`) to pass a single line of input to ShellGPT, asking about learning shell redirects.

```shell
sgpt <<< "What is the best way to learn shell redirects?"
# -> The best way to learn shell redirects is through...

```

--------------------------------

### Test ShellGPT with Ollama Backend

Source: https://github.com/ther1d/shell_gpt/wiki/Ollama

This command tests the ShellGPT integration with the Ollama backend by querying the 'ollama/mistral:7b-instruct' model. It requires a valid OpenAI API key or a placeholder string if not using OpenAI.

```shell
sgpt --model ollama/mistral:7b-instruct  "Who are you?"
```

--------------------------------

### Configure ShellGPT for LiteLLM

Source: https://github.com/ther1d/shell_gpt/wiki/Azure

Sets up the ShellGPT configuration file to enforce LiteLLM usage and provides a placeholder for the Azure OpenAI API key. This configuration is crucial for directing ShellGPT to use LiteLLM.

```text
USE_LITELLM=true
OPENAI_API_KEY=YOUR_AZURE_KEY
```

--------------------------------

### Enable Request Caching

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Demonstrates how to enable request caching using the `--cache` option for `sgpt` requests to the OpenAI API. This speeds up subsequent identical queries by retrieving results from local storage.

```shell
sgpt "what are the colors of a rainbow"
```

--------------------------------

### Create and Activate Python Virtual Environment

Source: https://github.com/ther1d/shell_gpt/blob/main/CONTRIBUTING.md

This snippet demonstrates how to create a Python virtual environment named 'env' and activate it using the 'source' command. This is a standard practice for isolating project dependencies.

```Shell
python -m venv env && source ./env/bin/activate
```

--------------------------------

### Chain Function Calls in Shell GPT

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Illustrates chaining multiple function calls in a single prompt to perform sequential actions, such as playing music and opening a URL. This highlights the tool's ability to handle complex workflows.

```shell
sgpt "Play music and open hacker news"
```

--------------------------------

### Build Shell GPT Docker Image

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

This command shows how to build a custom Docker image for the Shell GPT project using the provided Dockerfile.

```shell
docker build -t sgpt .
```

--------------------------------

### Execute general query with ShellGPT

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Basic usage of ShellGPT to answer a general knowledge question. The output is the AI-generated answer.

```shell
sgpt "What is the fibonacci sequence"
# -> The Fibonacci sequence is a series of numbers where each number ...
```

--------------------------------

### Execute Shell Command with jq

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Demonstrates executing a shell command using `jq` to extract the email from a JSON file. This showcases direct command execution within the tool.

```shell
sgpt "execute_shell_command(shell_command=\"jq -r '.email' /tmp/test.json\")"
```

--------------------------------

### Summarize document using input redirection

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Illustrates using input redirection (`<`) to pass the content of a file to ShellGPT for summarization.

```shell
sgpt "summarise" < document.txt
# -> The document discusses the impact...
```

--------------------------------

### Create Custom Role for JSON Generation

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Shows how to create a custom role named `json_generator` with a specific description to ensure responses are always in valid JSON format. It also demonstrates using the role to generate structured data.

```shell
sgpt --create-role json_generator
# Enter role description: Provide only valid json as response.
```

```shell
sgpt --role json_generator "random: user, password, email, address"
```

--------------------------------

### Generate Python Code and Save to File

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Illustrates how to generate Python code using shell_gpt and redirect the output to a file (`fizz_buzz.py`). It also shows how to execute the saved Python script.

```shell
sgpt --code "solve classic fizz buzz problem using Python" > fizz_buzz.py
python fizz_buzz.py
```

--------------------------------

### Execute Shell Command and Pipe to Clipboard

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Demonstrates how to execute a shell command generated by shell_gpt and pipe its output to `pbcopy` to save it to the clipboard. The `--no-interaction` flag is used to disable interactive mode and print the command directly to standard output.

```shell
sgpt -s "find all json files in current folder" --no-interaction | pbcopy
```

--------------------------------

### Generate ffmpeg command for video concatenation

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Shows how to use ShellGPT to generate an `ffmpeg` command for combining multiple video files into one, excluding audio.

```shell
sgpt -s "ffmpeg combine $(ls -m) into one video file without audio."
# -> ffmpeg -i 1.mp4 -i 2.mp4 -i 3.mp4 -filter_complex "[0:v] [1:v] [2:v] concat=n=3:v=1 [v]" -map "[v]" out.mp4
```

--------------------------------

### Generate Comments for Python Code

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Demonstrates piping existing Python code to shell_gpt with the `--code` option to generate comments for each line of the code.

```shell
cat fizz_buzz.py | sgpt --code "Generate comments for each line of my code"
```

```python
# Loop through numbers 1 to 100
for i in range(1, 101):
    # Check if number is divisible by both 3 and 5
    if i % 3 == 0 and i % 5 == 0:
        # Print "FizzBuzz" if number is divisible by both 3 and 5
        print("FizzBuzz")
    # Check if number is divisible by 3
    elif i % 3 == 0:
        # Print "Fizz" if number is divisible by 3
        print("Fizz")
    # Check if number is divisible by 5
    elif i % 5 == 0:
        # Print "Buzz" if number is divisible by 5
        print("Buzz")
    # If number is not divisible by 3 or 5, print the number itself
    else:
        print(i)
```

--------------------------------

### Execute Shell Commands in REPL Mode

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Enables REPL mode to interactively execute shell commands. Users can type commands directly or use 'e' to execute, and 'd' to describe them. This is useful for interactive shell command execution and code generation.

```shell
sgpt --repl temp --shell
```

--------------------------------

### LLM Executes Custom Shell Command Function

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Illustrates how the LLM can invoke a custom function, such as `execute_shell_command`, to perform actions like listing files in a directory. The output of the function is then presented to the user.

```shell
sgpt "What are the files in /tmp folder?"
# -> @FunctionCall execute_shell_command(shell_command="ls /tmp")
# -> The /tmp folder contains the following files and directories:
# -> test.txt
# -> test.json
```

--------------------------------

### Provide Multiline Prompt in REPL Mode

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Allows users to input multiline prompts in REPL mode using triple quotes. This is useful for providing complex instructions or code snippets to the GPT model for explanation or execution.

```shell
sgpt --repl temp
>>> """
... Explain following code:
... import random
... print(random.randint(1, 10))
... """
```

--------------------------------

### Generate git commit message from diff

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Demonstrates using ShellGPT to generate a git commit message by piping the output of `git diff` to the `sgpt` command.

```shell
git diff | sgpt "Generate git commit message, for my changes"
# -> Added main feature details into README.md
```

--------------------------------

### Generate curl command with piped JSON data

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Demonstrates using ShellGPT with piped JSON data to generate a `curl` command for a POST request.

```shell
sgpt -s "POST localhost with" < data.json
# -> curl -X POST -H "Content-Type: application/json" -d '{"a": 1, "b": 2}' http://localhost
# -> [E]xecute, [D]escribe, [A]bort: e
```

--------------------------------

### Generate shell command with ShellGPT

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Demonstrates generating a shell command to find all JSON files in the current directory using ShellGPT. The `--shell` or `-s` flag is used for this purpose.

```shell
sgpt --shell "find all json files in current folder"
# -> find . -type f -name "*.json"
# -> [E]xecute, [D]escribe, [A]bort: e
```

--------------------------------

### Generate Python Code for FizzBuzz

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Shows how to use the `--code` parameter to generate Python code for the classic FizzBuzz problem. The generated code iterates from 1 to 100 and prints 'Fizz', 'Buzz', or 'FizzBuzz' based on divisibility rules.

```shell
sgpt --code "solve fizz buzz problem using python"
```

```python
for i in range(1, 101):
    if i % 3 == 0 and i % 5 == 0:
        print("FizzBuzz")
    elif i % 3 == 0:
        print("Fizz")
    elif i % 5 == 0:
        print("Buzz")
    else:
        print(i)
```

--------------------------------

### Show Specific Chat Session History

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Demonstrates how to display the complete message history for a specific chat session by using the `--show-chat` option followed by the session name.

```shell
sgpt --show-chat conversation_1
```

--------------------------------

### Set Azure Environment Variables for LiteLLM

Source: https://github.com/ther1d/shell_gpt/wiki/Azure

Exports environment variables required for LiteLLM to connect to the Azure OpenAI service. These variables include the API base URL, API version, and optional token/type for authentication.

```shell
export AZURE_API_BASE=YOUR_API_BASE
export AZURE_API_VERSION=YOUR_API_VERSION
export AZURE_AD_TOKEN=YOUR_TOKEN # Optional
export AZURE_API_TYPE=YOUR_API_TYPE # Optional
```

--------------------------------

### Use ShellGPT with Ollama Default Model

Source: https://github.com/ther1d/shell_gpt/wiki/Ollama

This command uses ShellGPT with the default model configured in the .sgptrc file, which should be set to an Ollama model like 'ollama/mistral:7b-instruct' for local LLM usage.

```shell
sgpt "Hello Ollama"
```

--------------------------------

### Define Custom Function for Shell Command Execution

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Demonstrates how to define a custom Python function for Shell GPT to execute shell commands. The function uses Pydantic and Instructor to define the schema and execution logic, returning the command's exit code and output.

```python
# execute_shell_command.py
import subprocess
from pydantic import Field
from instructor import OpenAISchema


class Function(OpenAISchema):
    """
    Executes a shell command and returns the output (result).
    """
    shell_command: str = Field(..., example="ls -la", descriptions="Shell command to execute.")

    class Config:
        title = "execute_shell_command"

    @classmethod
    def execute(cls, shell_command: str) -> str:
        result = subprocess.run(shell_command.split(), capture_output=True, text=True)
        return f"Exit code: {result.returncode}, Output:\n{result.stdout}"
```

--------------------------------

### Add Caching to Python Request in Chat Session

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Shows how to continue a chat session (`conversation_2`) by requesting an enhancement to the previously generated Python code, specifically adding caching functionality using the `cachecontrol` library.

```shell
sgpt --chat conversation_2 --code "add caching"
```

```python
import requests
from cachecontrol import CacheControl

sess = requests.session()
cached_sess = CacheControl(sess)

response = cached_sess.get('http://localhost')
print(response.text)
```

--------------------------------

### List All Chat Sessions

Source: https://github.com/ther1d/shell_gpt/blob/main/README.md

Provides the command to list all active chat sessions managed by shell_gpt. This is useful for reviewing and managing conversation history.

```shell
sgpt --list-chats
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.