154 lines
4.1 KiB
Markdown
154 lines
4.1 KiB
Markdown
# 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](https://github.com/sigoden/argc): A bash command-line framewrok and command runner
|
||
- [jq](https://github.com/jqlang/jq): A JSON processor
|
||
|
||
## Getting Started with AIChat
|
||
|
||
**1. Clone the repository:**
|
||
|
||
```sh
|
||
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**:
|
||
|
||
```sh
|
||
ln -s "$(pwd)" "$(aichat --info | grep functions_dir | awk '{print $2}')"
|
||
# OR
|
||
argc install
|
||
```
|
||
|
||
Don't forget to add the following config to your AIChat `config.yaml` file:
|
||
|
||
```yaml
|
||
function_calling: true
|
||
```
|
||
|
||
AIChat will automatically load `functions.json` and execute commands located in the `./bin` directory based on your prompts.
|
||
|
||
**4. Start using your functions:**
|
||
|
||
Now you can interact with your LLM using natural language prompts that trigger your defined functions.
|
||
|
||
## AIChat Showcases
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
## Writing Your Own Tools
|
||
|
||
Writing tools is super easy, you only need to write functions with comments.
|
||
|
||
`llm-functions` will automatically generate binaries, function declarations, and so on
|
||
|
||
Refer to `./tools/demo_tool.{sh,js,py}` for examples of how to use comments for autogeneration of declarations.
|
||
|
||
### Bash
|
||
|
||
Create a new bashscript in the [./tools/](./tools/) directory (.e.g. `may_execute_command.sh`).
|
||
|
||
```sh
|
||
#!/usr/bin/env bash
|
||
set -e
|
||
|
||
# @describe Runs a shell command.
|
||
# @option --command! The command to execute.
|
||
|
||
main() {
|
||
eval "$argc_command"
|
||
}
|
||
|
||
eval "$(argc --argc-eval "$0" "$@")"
|
||
```
|
||
|
||
### Javascript
|
||
|
||
Create a new javascript in the [./tools/](./tools/) directory (.e.g. `may_execute_js_code.js`).
|
||
|
||
```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/](./tools/) directory (e.g., `may_execute_py_code.py`).
|
||
|
||
```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:
|
||
|
||
```yaml
|
||
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](https://github.com/sigoden/llm-functions/blob/main/LICENSE) file for detailed information. |