Skip to main content

Engaging with Multiple AI Agents with Jam.

Project description

Jam.AI

Jam is an experimental collaboration tool to use multiple AI personnel together equipped with instructed function calls.

Create Jam session with AI

View Changelog

Demo

Quick Start

from jam import Jam
from jam.personnel import BasicPersonnel, AutoPersonnel
from jam.instrument import PromptPainter

jam_room = Jam(
    members=[
        BasicPersonnel.from_json(filepath='example/personnel/claude-monet.json'),  # Using custom JSON
        BasicPersonnel.from_preset(name='pablo-picasso'),  # Using example presets from Git
        AutoPersonnel.from_prompt(uid='wkandinsky', prompt='Wassily Kandinsky')  # Using GPT to build prompt
    ],
    instruments=[PromptPainter()]
)

prompt = jam_room.compose(
    message='who are you!',
    multi=True
)

print(prompt) # List of Prompts from Characters

Don't forget to use your credentials. Primarily for OpenAI, the core engine of this project. https://platform.openai.com/account/api-keys

export OPENAI_KEY=YOUR_KEY

Installation

pip install jam-ai --upgrade

You need to use Pip to install jam. Conda package is currently unavailable.

Requirements

  • Python >= 3.8
  • OpenAI
  • Requests
  • Pillow

Extra Requirements for Function Calls

  • Psycopg2
  • PyMySQL
  • Stability SDK

Extension

Optional dependencies to fit any requirement needed.

pip install jam-ai[database] # Using Postgres, MySQL, Redis ...
pip install jam-ai[function] # Using Extended Function Calls requiring SDKs / Packages

For the use of other libraries, please consider to always feed in your API Keys respectively. See below for example.

export STABILITY_KEY=YOUR_STABILITY_AI_KEY # If you are using Stability SDK
export WRITESONIC_KEY=YOUR_WRITE_SONIC_KEY # If you are using WriteSonic API
export CUSTOM_KEY=YOUR_CUSTOM_KEY          # If there are any other added functionalities

Author

  • Abhishta Gatya (Email) - Software and Machine Learning Engineer

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

jam_ai-0.2.1.tar.gz (26.3 kB view details)

Uploaded Source

Built Distribution

jam_ai-0.2.1-py3-none-any.whl (42.7 kB view details)

Uploaded Python 3

File details

Details for the file jam_ai-0.2.1.tar.gz.

File metadata

  • Download URL: jam_ai-0.2.1.tar.gz
  • Upload date:
  • Size: 26.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.6

File hashes

Hashes for jam_ai-0.2.1.tar.gz
Algorithm Hash digest
SHA256 7a8fdbb1ef7eed84e520952f36a161cf6a891519d3c613ef74dc3abed9b14f33
MD5 5e7ba6fce662c2eece6597b3e6515e08
BLAKE2b-256 fd8b2ff9ec3e813524a9a57eeb82cc48976803066ad1d16741b29bea0789e528

See more details on using hashes here.

File details

Details for the file jam_ai-0.2.1-py3-none-any.whl.

File metadata

  • Download URL: jam_ai-0.2.1-py3-none-any.whl
  • Upload date:
  • Size: 42.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.6

File hashes

Hashes for jam_ai-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 68ca73b3296d9837ec4edb7bd7f97d999a2cd0c89c2e53de8966f33b050a48c9
MD5 80622b8f0f675fd53ccadfeef7d4aaa9
BLAKE2b-256 b17f90d58897d257275836ba67867b24b1cace37c6e544b02e53ae7de9b4021f

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