Experimental collaboration tool to use multiple AI personnel together equipped with instructed function calls.
Project description
Jam.AI
Create Jam session with AI
Jam is an experimental collaboration tool to use multiple AI personnel together equipped with instructed function calls.
Quick Start
from jam import Jam
from jam.personnel import BasicPersonnel
from jam.instrument import PromptPainter
from jam.persistence import SQLitePersistence
jam_room = Jam(
members=[
BasicPersonnel.from_json('example/personnel/albert-einstein.json'),
BasicPersonnel.from_json('example/personnel/stephen-hawking.json')
],
instruments=[
PromptPainter()
],
persistence=SQLitePersistence()
)
prompt = jam_room.compose(
message='Give me a question',
multi=True
)
Installation
pip install jam-ai --upgrade
You need to use Pip to install jam. Conda package is currently unavailable.
Requirements
- Python >= 3.8
- OpenAI
Extra Requirements for Function Calls
- Requests
- Stability SDK
- Pillow
Author
- Abhishta Gatya (Email) - Software and Machine Learning Engineer
Project details
Release history Release notifications | RSS feed
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-0.1.5.tar.gz
(19.3 kB
view details)
Built Distribution
jam_ai-0.1.5-py3-none-any.whl
(30.0 kB
view details)
File details
Details for the file jam_ai-0.1.5.tar.gz
.
File metadata
- Download URL: jam_ai-0.1.5.tar.gz
- Upload date:
- Size: 19.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | a8cc4fc781bd2e2a66277e4537e50a0acf5c4a811515543e83520fce604fefc8 |
|
MD5 | fb2d33c67f4b4c1e5e4164cdfebc857b |
|
BLAKE2b-256 | 51052b00cafe3193e930dea536fc67db9df985718c23dc8444acd330973e73c8 |
File details
Details for the file jam_ai-0.1.5-py3-none-any.whl
.
File metadata
- Download URL: jam_ai-0.1.5-py3-none-any.whl
- Upload date:
- Size: 30.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | c6dc4afd4ce4edaa91c8fabf9bd776683aa197a19d0abc573e4b1b56885e8d0e |
|
MD5 | 4a33198164efc1104de56c7399af863b |
|
BLAKE2b-256 | b47a68b4548cd4b0620435523da48d97b4fbbb704cc5e1dec252ad955f9b3d88 |