Skip to main content

Makes working with OpenAI's GPT API and other LLM's super easy

Project description

JustAI

Package to make working with Large Language models in Python super easy.

Author: Hans-Peter Harmsen (hp@harmsen.nl)
Current version: 3.2.0

Installation

  1. Install the package:
python -m pip install justai
  1. Create an OpenAI acccount (for GPT3.5 / 4) here or an Anthropic account here
  2. Create an OpenAI api key (for Claude) here or an Anthropic api key here
  3. Create a .env file with the following content:
OPENAI_API_KEY=your-openai-api-key
OPENAI_ORGANIZATION=your-openai-organization-id
ANTHROPIC_API_KEY=your-anthropic-api-key

Usage

from justai import Agent

if __name__ == "__main__":
    agent = Agent('gpt-3.5-turbo')
    agent.system = "You are a movie critic. I feed you with movie titles and you give me a review in 50 words."

    message = agent.chat("Forrest Gump")
    print(message)

output

Forrest Gump is an American classic that tells the story of
a man with a kind heart and simple mind who experiences major
events in history. Tom Hanks gives an unforgettable performance, 
making us both laugh and cry. A heartwarming and nostalgic 
movie that still resonates with audiences today.

Other models

Justai can use different types of models:

OpenAI models like GPT-3.5, GPT-4-turbo-preview
Anthropic models like claude-3-opus-20240229 and claude-3-sonnet-20240229
Open source models like Llama2-7b or Mixtral-8x7b-instruct as long as they are in the GGUF format.

The provider is chosen depending on the model name. E.g. if a model name starts with gpt, OpenAI is chosen as the provider. To use an open source model, just pass the full path to the .gguf file as the model name.

Using the examples

Install dependencies:

python -m pip install -r requirements.txt

Basic

python examples/basic.py

Starts an interactive session. In the session you dan chat with GPT-4 or another model.

Returning json

python examples/return_types.py

You can specify a specific return type (like a list of dicts) for the completion. This is useful when you want to extract structured data from the completion.

To define a return type, just pass return_json=True to agent.chat().

See the example code for more details.

Interactive

python examples/interactive.py

Starts an interactive session. In the session you dan chat with GPT-4 or another model.

Special commands

In the interactive mode you can use these special commands which each start with a colon:

Syntax Description
:reset resets the conversation
:load name loads the saved conversation with the specified name
:save name saves the conversation under the specified name
:input filename loads an input from the specified file
:model gpt-4 Sets the AI model
:max_tokens 800 The maximum number of tokens to generate in the completion
:temperature 0.9 What sampling temperature to use, between 0 and 2
:n 1 Specifies the number answers given
:stop ["\n", " Human:", " AI:"] Up to 4 sequences where the API will stop generating further tokens
:bye quits but saves the conversation first
:exit or :quit quits the program

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

justai-3.2.0.tar.gz (23.9 kB view details)

Uploaded Source

Built Distribution

justai-3.2.0-py3-none-any.whl (28.0 kB view details)

Uploaded Python 3

File details

Details for the file justai-3.2.0.tar.gz.

File metadata

  • Download URL: justai-3.2.0.tar.gz
  • Upload date:
  • Size: 23.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.11.3

File hashes

Hashes for justai-3.2.0.tar.gz
Algorithm Hash digest
SHA256 3086138cd1b51e297d0892e12877918683577bdb1eb19fdbd216e0265b294ecc
MD5 36c454437ea40c6676c554887cea30a4
BLAKE2b-256 555f9b9a58a63bd13065e3109c3ac73720b5ae7ef97b8285a3e0bddde59ed698

See more details on using hashes here.

File details

Details for the file justai-3.2.0-py3-none-any.whl.

File metadata

  • Download URL: justai-3.2.0-py3-none-any.whl
  • Upload date:
  • Size: 28.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.11.3

File hashes

Hashes for justai-3.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f3c5aa807afe6debd1321dbbe853d68b00e9bf9716f1c2f89702afc6ecd8b9c7
MD5 36e90f111cf3d084ebac2e99ba6d4438
BLAKE2b-256 965501826c49b380be389b8d18c4429566efc1ecf91b5ef22ac1f0740a743799

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