llm-functions/README.md

LLM Functions

This project allows you to enhance large language models (LLMs) with custom functions written in bash/js/python. Imagine your LLM being able to execute system commands, access web APIs, or perform other complex tasks – all triggered by simple, natural language prompts.

Prerequisites

Make sure you have the following tools installed:

• argc: A bash command-line framewrok and command runner
• jq: A JSON processor

Getting Started with AIChat

1. Clone the repository:

git clone https://github.com/sigoden/llm-functions

2. Build tools and bots:

• Create a ./tools.txt file with each tool filename on a new line.

get_current_weather.sh
may_execute_py_code.py

• Create a ./bots.txt file with each bot name on a new line.

todo-sh
hackernews

• Run argc build to build functions declarations files (functions.json) and binaries (./bin) for tools and bots.

3. Configure your AIChat:

Symlink this repo directory to aichat functions_dir:

ln -s "$(pwd)" "$(aichat --info | grep functions_dir | awk '{print $2}')"
# OR
argc install

Don't forget to add the following config to your AIChat config.yaml file:

function_calling: true

AIChat will automatically load functions.json and execute commands located in the ./bin directory based on your prompts.

4. Start using your functions:

Now you can interact with your LLM using natural language prompts that trigger your defined functions.

AIChat Showcases

Writing Your Own Tools

Writing tools is super easy, you only need to write functions with comments.

llm-functions will automatically generate binaries, function declarations, and so on

Refer to ./tools/demo_tool.{sh,js,py} for examples of how to use comments for autogeneration of declarations.

Bash

Create a new bashscript in the ./tools/ directory (.e.g. may_execute_command.sh).

#!/usr/bin/env bash
set -e

# @describe Runs a shell command.
# @option --command! The command to execute.

main() {
    eval "$argc_command"
}

eval "$(argc --argc-eval "$0" "$@")"

Javascript

Create a new javascript in the ./tools/ directory (.e.g. may_execute_js_code.js).

/**
 * Runs the javascript code in node.js.
 * @typedef {Object} Args
 * @property {string} code - Javascript code to execute, such as `console.log("hello world")`
 * @param {Args} args
 */
exports.main = function main({ code }) {
  eval(code);
}

Python

Create a new python script in the ./tools/ directory (e.g., may_execute_py_code.py).

def main(code: str):
    """Runs the python code.
    Args:
        code: Python code to execute, such as `print("hello world")`
    """
    exec(code)

Writing Bots

Bot = Prompt + Tools (Function Callings) + Knowndge (RAG). It's also known as OpenAI's GPTs.

The bot has the following folder structure:

└── bots
    └── mybot
        ├── embeddings/                     # Contains RAG files for knownledge
        ├── functions.json                  # Function declarations file (Auto-generated)
        ├── index.yaml                      # Bot definition file
        └── tools.{sh,js,py}                # Bot tools script

The bot definition file (index.yaml) defines crucial aspects of your bot:

name: TestBot                             
description: This is test bot
version: v0.1.0
instructions: You are a test bot to ... 
conversation_starters:
  - What can you do?

Refer to ./bots/todo-{sh,js,py} for examples of how to implement a bot.

License

The project is under the MIT License, Refer to the LICENSE file for detailed information.