python-tgpt 0.0.7

Interact with AI without API key

python-tgpt

AI for all

>>> import tgpt
>>> bot = tgpt.TGPT()
>>> bot.chat('Hello there')
"  Hello! It's nice to meet you. Is there something I can help you with or would you like to chat?"
>>> 

This project allows you to interact with AI (LLaMA) without API Key.

The name python-tgpt is inherited from it's parent project tgpt which runs on golang.

Prerequisite

• Python>=3.9

Installation and usage

Installation

Pick either of the following ways to get started.

1. From pypi:

pip install python-tgpt

2. Direct from source

pip install git+https://github.com/Simatwa/python-tgpt.git

3. Clone and Install

git clone https://github.com/Simatwa/python-tgpt.git
cd python-tgpt
pip install .

Usage

This package features a ready to use commandline interface.

• Quick response python -m tgpt generate "<Your prompt>"

• Interactive mode python -m tgpt interactive "<Kickoff prompt though not a must>"

Instead of python -m tgpt, you can as well just use tgpt

As from version 0.0.6, generate is the default command. So something like this will still work. tgpt "<Your prompt>"

Developer Docs

1. Generate a quick response

from tgpt import TGPT
bot = TGPT()
resp = bot.chat('<Your prompt>')
print(resp)
# Output : How may I help you.

2. Get back whole response

from tgpt import TGPT
bot = TGPT()
resp = bot.ask('<Your Prompt')
print(resp)
# Output
"""
{'completion': "I'm so excited to share with you the incredible experiences...", 'stop_reason': None, 'truncated': False, 'stop': None, 'model': 'llama-2-13b-chat', 'log_id': 'cmpl-3NmRt5A5Djqo2jXtXLBwJ2', 'exception': None}
"""

Stream Response

Just add parameter stream with value true.

1. Text Generated only

from tgpt import TGPT
bot = TGPT()
resp = bot.chat('<Your prompt>', stream=True)
for value in resp:
    print(value)
# output
"""
How may
How may I help 
How may I help you
How may I help you today?
"""

2. Whole Response

from tgpt import TGPT
bot = TGPT()
resp = bot.ask('<Your Prompt>', stream=True)
for value in resp:
    print(value)
# Output
"""
{'completion': "I'm so", 'stop_reason': None, 'truncated': False, 'stop': None, 'model': 'llama-2-13b-chat', 'log_id': 'cmpl-3NmRt5A5Djqo2jXtXLBwxx', 'exception': None}

{'completion': "I'm so excited to share with.", 'stop_reason': None, 'truncated': False, 'stop': None, 'model': 'llama-2-13b-chat', 'log_id': 'cmpl-3NmRt5A5Djqo2jXtXLBwxx', 'exception': None}

{'completion': "I'm so excited to share with you the incredible ", 'stop_reason': None, 'truncated': False, 'stop': None, 'model': 'llama-2-13b-chat', 'log_id': 'cmpl-3NmRt5A5Djqo2jXtXLBwxx', 'exception': None}

{'completion': "I'm so excited to share with you the incredible experiences...", 'stop_reason': None, 'truncated': False, 'stop': None, 'model': 'llama-2-13b-chat', 'log_id': 'cmpl-3NmRt5A5Djqo2jXtXLBwxx', 'exception': None}
"""

• To get better feedback, you can make use of optimizers using parameter optimizer with values (code or system_command)

from tgpt import TGPT
bot = TGPT()
resp = bot.ask('<Your Prompt>', optimizer='code')
print(resp)

Note : As of v0.0.7, chatting conversationally has been featured (Experimental) : bot = tgpt.TGPT(is_conversation=True) at console just append flag --conversation. NB: Tends to fail after relative lengthy chat.

Acknowledgements

1. tgpt
2. You