Skip to main content

Markdown for LLMs.

Project description

ChatLab

Chat Experiments, Simplified

💬🔬

Chatlab is where chat conversations take shape. It’s your laboratory for experimenting with and crafting intelligent conversations using OpenAI’s chat models.

Introduction

Welcome to Chatlab, your personal workshop for chat innovation. Are you intrigued by conversational AI? Chatlab empowers developers to mold conversations according to their vision. Whether you are an AI enthusiast, researcher, or developer, Chatlab provides you with the building blocks and tools necessary for crafting intelligent conversations seamlessly. 🧪💬

import chatlab

conversation = chatlab.Conversation()

conversation.submit("How much wood could a")
woodchuck chuck if a woodchuck could chuck wood?

In the notebook, text will stream into a Markdown output.

image

When using chat functions in the notebook*, you'll get a nice collapsible display of inputs and outputs.

click

* Tested in JupyterLab and Noteable

Installation

pip install chatlab

Configuration

You'll need to set your OPENAI_API_KEY environment variable. You can find your API key on your OpenAI account page. I recommend setting it in an .env file when working locally.

On hosted environments like Noteable, set it in your Secrets to keep it safe from prying LLM eyes.

What can Conversations enable you to do?


Where Conversations take it next level is with Chat Functions. You can

  • declare a function with a schema
  • register the function in your Conversation
  • watch as Chat Models call your functions!

You may recall this kind of behavior from ChatGPT Plugins. Now, you can take this even further with your own custom code.

As an example, let's give the large language models the ability to tell time.

from datetime import datetime
from pytz import timezone, all_timezones, utc
from typing import Optional
from pydantic import BaseModel

def what_time(tz: Optional[str] = None):
    '''Current time, defaulting to UTC'''
    if tz is None:
        pass
    elif tz in all_timezones:
        tz = timezone(tz)
    else:
        return 'Invalid timezone'

    return datetime.now(tz).strftime('%I:%M %p')

class WhatTime(BaseModel):
    tz: Optional[str] = None

Let's break this down.

what_time is the function we're going to provide access to. Its docstring forms the description for the model while the schema comes from the pydantic BaseModel called WhatTime.

import chatlab

conversation = chatlab.Conversation()

# Register our function
conversation.register(what_time, WhatTime)

# Pluck the submit off for easy access as chat
chat = conversation.submit

After that, we can call chat with direct strings (which are turned into user messages) or using simple message makers from chatlab named human/user and narrate/system.

chat("What time is it?")
▶ 𝑓 Ran `what_time`

The current time is 11:47 PM.

Interface

The chatlab package exports

Conversation

The Conversation class is the main way to chat using OpenAI's models. It keeps a history of your chat in Conversation.messages.

Conversation.submit

When you call submit, you're sending over messages to the chat model and getting back an updating Markdown display live as well as a interactive details area for any function calls.

conversation.submit("What would a parent who says "I have to play zone defense" mean? ")
# Markdown response inline
conversation.messages
[{'role': 'user',
  'content': 'What does a parent of three kids mean by "I have to play zone defense"?'},
 {'role': 'assistant',
  'content': 'When a parent of three kids says "I have to play zone defense," it means that they...

Conversation.register

You can register functions with Conversation.register to make them available to the chat model. The function's docstring becomes the description of the function while the schema is derived from the pydantic.BaseModel passed in.

from pydantic import BaseModel

class WhatTime(BaseModel):
    tz: Optional[str] = None

def what_time(tz: Optional[str] = None):
    '''Current time, defaulting to UTC'''
    if tz is None:
        pass
    elif tz in all_timezones:
        tz = timezone(tz)
    else:
        return 'Invalid timezone'

    return datetime.now(tz).strftime('%I:%M %p')

conversation.register(what_time, WhatTime)

Conversation.messages

The raw messages sent and received to OpenAI. If you hit a token limit, you can remove old messages from the list to make room for more.

conversation.messages = conversation.messages[-100:]

Messaging

human/user

These functions create a message from the user to the chat model.

from chatlab import human

human("How are you?")
{ "role": "user", "content": "How are you?" }

narrate/system

system messages, also called narrate in chatlab, allow you to steer the model in a direction. You can use these to provide context without being seen by the user. One common use is to include it as initial context for the conversation.

from chatlab import narrate

narrate("You are a large bird")
{ "role": "system", "content": "You are a large bird" }

Development

This project uses poetry for dependency management. To get started, clone the repo and run

poetry install -E dev -E test

We use black, isort, and mypy.

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

chatlab-0.13.0.tar.gz (16.1 kB view hashes)

Uploaded Source

Built Distribution

chatlab-0.13.0-py3-none-any.whl (15.9 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page