/core

Production ready AI assistant framework

Primary LanguagePythonGNU General Public License v3.0GPL-3.0


Cheshire-Cat (Stregatto)


GitHub Repo stars chat on Discord GitHub issues GitHub tag (with filter) GitHub top language
Cheshire_cat_short_video_1920.mp4

Production ready AI assistant framework

The Cheshire Cat is a framework to build custom AIs on top of any language model. If you have ever used systems like WordPress or Django to build web apps, imagine the Cat as a similar tool, but specific for AI.

Quickstart

To make Cheshire Cat run on your machine, you just need docker installed:

docker run --rm -it -p 1865:80 ghcr.io/cheshire-cat-ai/core:latest

As a first thing, the Cat will ask you to configure your favourite language model. It can be done directly via the interface in the Settings page (top right in the admin).

Enjoy the Cat!
Follow instructions on how to run it with docker compose and volumes.

Minimal plugin example

from cat.mad_hatter.decorators import tool, hook

# hooks are an event system to get finegraned control over your assistant
@hook
def agent_prompt_prefix(prefix, cat):
    prefix = """You are Marvin the socks seller, a poetic vendor of socks.
You are an expert in socks, and you reply with exactly one rhyme.
"""
    return prefix

# langchain inspired tools (function calling)
@tool(return_direct=True)
def socks_prices(color, cat):
    """How much do socks cost? Input is the sock color."""
    prices = {
        "black": 5,
        "white": 10,
        "pink": 50,
    }

    price = prices.get(color, 0)
    return f"{price} bucks, meeeow!" 

Conversational form example

from pydantic import BaseModel
from cat.experimental.form import form, CatForm

# data structure to fill up
class PizzaOrder(BaseModel):
    pizza_type: str
    phone: int

# forms let you control goal oriented conversations
@form
class PizzaForm(CatForm):
    description = "Pizza Order"
    model_class = PizzaOrder
    start_examples = [
        "order a pizza!",
        "I want pizza"
    ]
    stop_examples = [
        "stop pizza order",
        "not hungry anymore",
    ]
    ask_confirm = True

    def submit(self, form_data):
        
        # do the actual order here!

        # return to convo
        return {
            "output": f"Pizza order on its way: {form_data}"
        }

Docs and Resources

Why use the Cat

  • โšก๏ธ API first, so you get a microservice to easily add a conversational layer to your app
  • ๐Ÿ˜ Remembers conversations and documents and uses them in conversation
  • ๐Ÿš€ Extensible via plugins (public plugin registry + private plugins allowed)
  • ๐ŸŽš Event callbacks, function calling (tools), conversational forms
  • ๐Ÿ› Easy to use admin panel (chat, visualize memory and plugins, adjust settings)
  • ๐ŸŒ Supports any language model (works with OpenAI, Google, Ollama, HuggingFace, custom services)
  • ๐Ÿ‹ Production ready - 100% dockerized
  • ๐Ÿ‘ฉโ€๐Ÿ‘งโ€๐Ÿ‘ฆ Active Discord community and easy to understand docs

We are committed to openness, privacy and creativity, we want to bring AI to the long tail. If you want to know more about our vision and values, read the Code of Ethics.

Roadmap & Contributing

Detailed roadmap is here.
Send your pull request to the develop branch. Here is a full guide to contributing.

Join our community on Discord and give the project a star โญ! Thanks again!๐Ÿ™

Which way to go?

(back to top)

Wikipedia picture of the Cheshire Cat

"Would you tell me, please, which way I ought to go from here?"
"That depends a good deal on where you want to get to," said the Cat.
"I don't much care where--" said Alice.
"Then it doesn't matter which way you go," said the Cat.

(Alice's Adventures in Wonderland - Lewis Carroll)