Skip to main content

A library to communicate with AI assistants such as ChatGPT, Claude, Copilot, Gemini, HuggingChat, and Pi, and enabling multiagent interactions between them.

Project description

TalkingHeads ๐Ÿ’ฌ

TalkingHeads Documentation

CircleCI Build Status PyPI version Licence: MIT Documentation Status CodeQL Status Code style: black

Welcome to TalkingHeads! ๐Ÿ’ฌ

TalkingHeads is a Python library that serves as an interface for seamless communication with ChatGPT, Claude, Copilot, Gemini, LeChat, HuggingChat, and Pi ๐Ÿค–

By leveraging the power of browser automation, this library enables users to effortlessly interact with online chat agents ๐Ÿš€โœจ

You can utilize more than one agent by using multiagent module, and improve your workflow with an ensemble of models!

Prerequisites ๐Ÿ“‹

  • Install Chrome
  • Register to the provider you would like to use (or not, and use Pi!)

Installation

pip install talkingheads

or from source:

pip install git+https://github.com/ugorsahin/TalkingHeads

Usage

from talkingheads import PiClient

chathead = PiClient()

response = chathead.interact("Hello, how are you today")

print(response)

Features

Features Claude ChatGPT Copilot Gemini LeChat HuggingChat Pi
Use without login โŒ โŒ โœ… โŒ โŒ โŒ โœ…
Login* โž– โœ… โž– โž– โœ… โœ… โž–
Interact โœ… โœ… โœ… โœ… โœ… โœ… โœ…
New Chat โœ… โœ… โœ… โœ… โœ… โœ… โœ…
Regenerate Response โœ… โœ… โŒ โœ… โŒ โŒ โŒ
Custom Interactions โŒ โœ… โŒ โŒ โŒ โŒ โŒ
Search Web โŒ โŒ โœ… โŒ โŒ โœ… โŒ
Plugins โŒ โŒ โœ… โŒ โŒ โŒ โŒ
Switch Model โŒ โœ… โœ…** โŒ โœ… โœ… โœ…
Multimodal (Visual) โœ… โž–*** โœ… โœ… โŒ โŒ โŒ

โœ… (Auto) Save the conversation as csv, h5, html, json, orc, pkl, xlsx, xml

  • โœ… : Functionality exists and implemented
  • โŒ : Functionality does not exist
  • โž– : Fuctionality exists but not implemented

* You should use a user profile and login manually to use Gemini, Claude and Copilot.Please take a look at documentation and FAQ to set up a user profile.

** The modes of Copilot (Creative, Balanced and Precise) are accessible with model switch. However, it is unclear if they are different models.

*** ChatGPT has multimodality, but only for premium users, donate me a premium account if you need that to be implemented!

Issues & Contribution

Feel free to dive in, share your knowledge, and collaborate. I would be happy to answer any questions or accept your contributions. Let me know in issues if you need anything.

Enhancing our documentation would be fantastic and appreciated. Help me improve documentation with your valuable contributions. Please indicate your issue with a tag enclosed by square brackets: [FEATURE], [BUG], [DOCUMENTATION], [QUESTION]. If you don't know what to write you can write [MISC]. I will prioritize issues with tags.

Where is old ChatGPT_Automation library?

You can still run your code to connect ChatGPT, follow the below tutorial

export ChatGPT_UNAME=<your@email>
export ChatGPT_PWD=><password>
from talkingheads import ChatGPTClient

chathead = ChatGPTClient()

response = chathead.interact("Hello, how are you today")

print(response)

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

talkingheads-0.5.3.tar.gz (30.5 kB view details)

Uploaded Source

Built Distribution

talkingheads-0.5.3-py3-none-any.whl (35.0 kB view details)

Uploaded Python 3

File details

Details for the file talkingheads-0.5.3.tar.gz.

File metadata

  • Download URL: talkingheads-0.5.3.tar.gz
  • Upload date:
  • Size: 30.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.10

File hashes

Hashes for talkingheads-0.5.3.tar.gz
Algorithm Hash digest
SHA256 32bb7dc03cea268ee883e7589c63a0ad50f70d5039f9d99907466105f69cd032
MD5 37fcdc0199c96f83b2c6ede319640862
BLAKE2b-256 a76e07efaf00570d549a5b49c4e5ee1666455f9768a5198e95f18d1e8841a0dc

See more details on using hashes here.

File details

Details for the file talkingheads-0.5.3-py3-none-any.whl.

File metadata

File hashes

Hashes for talkingheads-0.5.3-py3-none-any.whl
Algorithm Hash digest
SHA256 b0887253c82682da857b75aee82e0163f42d556c55fdbcdc4f455117804d372c
MD5 82899ab13cdabc6a609e408aa5ef5366
BLAKE2b-256 0ea9edfcc25f9cefe22b60818fee29b7e88928a22d7c0c7d0371055d2f07542d

See more details on using hashes here.

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