Archytas: A Tools Interface for AI Agents

Implementation of the ReAct (Reason & Action) framework for Large Language Model (LLM) agents. Mainly targeting OpenAI's GPT-4.

Easily create tools from simple python functions or classes with the @tool decorator. A tools list can then be passed to the ReActAgent which will automagially generate a prompt for the LLM containing usage instructions for each tool, as well as manage the ReAct decision loop while the LLM performs its task.

Tools can be anything from internet searches to custom interpreters for your domain. Archytas provides a few built-in demo tools e.g. datetime, fibonacci numbers, and a simple calculator.

Quicksart

# make sure poetry is installed
pip install poetry

# clone and install
git clone git@github.com:jataware/archytas.git
cd archytas
poetry install

# make sure OPENAI_API_KEY var is set
# or set openai_key in .openai.toml
export OPENAI_API_KEY="sk-..."

# run demo
poetry run chat-repl

Simple Usage

Import pre-made tools from the tools module

from archytas.react import ReActAgent, FailedTaskError
from archytas.tools import datetime_tool, fib_n, calculator

from easyrepl import REPL

# create the agent with the tools list
some_tools = [datetime_tool, fib_n, calculator]
agent = ReActAgent(tools=some_tools+[mytool], verbose=True)

# REPL to interact with agent
for query in REPL()
    try:
        answer = agent.react(query)
        print(answer)
    except FailedTaskError as e:
        print(f"Error: {e}")

Built-in Tools

(TODO)

ask_user
datetime
timestamp
fib_n
calculator
...

Custom Tools

(TODO)

from archytas.tools import tool

@tool()
def example_tool(arg1:int, arg2:str='', arg3:dict=None) -> int:
    """
    Simple 1 sentence description of the tool

    More detailed description of the tool. This can be multiple lines.
    Explain more what the tool does, and what it is used for.

    Args:
        arg1 (int): Description of the first argument.
        arg2 (str): Description of the second argument. Defaults to ''.
        arg3 (dict): Description of the third argument. Defaults to {}.

    Returns:
        int: Description of the return value

    Examples:
        >>> example_tool(1, 'hello', {'a': 1, 'b': 2})
        3
        >>> example_tool(2, 'world', {'a': 1, 'b': 2})
        4
    """
    return 42

# TODO: class tool example

Release files for archytas 0.2.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for archytas 0.2.2
File	Size	Uploaded
archytas-0.2.2.tar.gz	25.0 kB	Apr 18, 2023	Details

Built distribution (wheel)

Table of built distributions (wheels) for archytas 0.2.2
File	Interpreter	ABI	Platform	Reset
archytas-0.2.2-py3-none-any.whl 27.4 kB Apr 18, 2023	Python 3	none	any	Details

Total release size: 52.3 kB

Release files / archytas-0.2.2.tar.gz

Download URL	archytas-0.2.2.tar.gz
Size	25.0 kB
Tags	Source
SHA-256 checksum How to use checksums	`9b324c05a983a7ec623ef1ec686a036316a25aa05aa9c87074889a69a8a37c32`
BLAKE2b-256 checksum How to use checksums	`3c75f2309f05228f8a67533564c7233497a92a41810f8dabec58abc84c17cb27`
Upload date	Apr 18, 2023
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`poetry/1.4.1 CPython/3.10.11 Linux/5.15.0-1035-azure`

Release files / archytas-0.2.2-py3-none-any.whl

Download URL	archytas-0.2.2-py3-none-any.whl
Size	27.4 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`491fcffaae13c04bac1cd438d32b3fd3f98f6a43f4b2bb6d96b37fbcc422ce0a`
BLAKE2b-256 checksum How to use checksums	`ea175b8df98681b8fe2c0db0cac8c764d5017e43a49509ebfb3be4366421fd2e`
Upload date	Apr 18, 2023
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`poetry/1.4.1 CPython/3.10.11 Linux/5.15.0-1035-azure`