Chat Experiments, Simplified
💬🔬
ChatLab is a Python package that makes it easy to experiment with OpenAI's chat models. It provides a simple interface for chatting with the models and a way to register functions that can be called from the chat model.
Best yet, it's interactive in the notebook!
- Learning the Basics
- Recommend and Visualize Color Palettes
- Introduction to the Function Registry
- Creating Knowledge Graphs with Pydantic
- Direct Parallel Function Calling
- Let the Model do some Data Science
import chatlab
import random
def flip_a_coin():
'''Returns heads or tails'''
return random.choice(['heads', 'tails'])
chat = chatlab.Chat()
chat.register(flip_a_coin)
await chat("Please flip a coin for me")𝑓 Ran `flip_a_coin`
Input:
{}Output:
"tails"It landed on tails!In the notebook, text will stream into a Markdown output and function inputs and outputs are a nice collapsible display, like with ChatGPT Plugins.
TODO: Include GIF/mp4 of this in action
pip install chatlabYou'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 notebook environments, set it in your Secrets to keep it safe from prying LLM eyes.
💬
Where Chats take it next level is with Chat Functions. You can
- declare a function
- register the function in your
Chat - 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] = NoneLet'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
chat = chatlab.Chat()
# Register our function
chat.register(what_time, WhatTime)After that, we can call chat with direct strings (which are turned into user messages) or using simple message makers from chatlab named user and system.
await chat("What time is it?")𝑓 Ran `what_time`
Input:
{}Output:
"11:19 AM"The current time is 11:19 AM.The chatlab package exports
The Chat class is the main way to chat using OpenAI's models. It keeps a history of your chat in Chat.messages.
submit is how you send all the currently built up messages over to OpenAI. Markdown output will display responses from the assistant.
await chat.submit('What would a parent who says "I have to play zone defense" mean? ')
# Markdown response inline
chat.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...You can register functions with Chat.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')
chat.register(what_time, WhatTime)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.
chat.messages = chat.messages[-100:]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?" }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" }This project uses poetry for dependency management. To get started, clone the repo and run
poetry install -E dev -E testWe use ruff and mypy.
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent