Skip to main content

A flexible chatbot framework supporting multiple AI providers

Project description

AriAI

A flexible chatbot framework that supports multiple AI providers (OpenAI and Hugging Face).

Features

  • Support for both OpenAI (GPT-3.5/4) and Hugging Face models
  • Custom system prompts / personalities
  • Conversation memory
  • Rich terminal UI with colored output
  • Easy to use and extend

Installation

  1. Clone this repository:
git clone https://github.com/username/ariai.git
cd ariai
  1. Build and install the package:
python setup.py sdist bdist_wheel
pip install ./dist/ariai-0.1-py3-none-any.whl

Usage

Here's a basic example:

from ariai import AriAI

# Using OpenAI
bot = AriAI(
    provider="openai",
    api_key="YOUR_OPENAI_API_KEY",
    system_prompt="You are a helpful AI assistant."
)

# Or using Hugging Face
bot = AriAI(
    provider="huggingface",
    hf_model="google/flan-t5-base",
    system_prompt="You are a helpful AI assistant."
)

# Start the interactive chat UI
bot.start_ui()

You can also use the chat method directly:

response = bot.chat("Hello, how are you?")
print(response)

Configuration

OpenAI

For OpenAI, you'll need to set your API key. You can either:

  1. Pass it directly to the constructor
  2. Set it as an environment variable: OPENAI_API_KEY

Hugging Face

For Hugging Face, you can specify any model that supports text generation. The default is "google/flan-t5-base".

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.

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

ariai-0.1.0.tar.gz (4.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ariai-0.1.0-py3-none-any.whl (4.1 kB view details)

Uploaded Python 3

File details

Details for the file ariai-0.1.0.tar.gz.

File metadata

  • Download URL: ariai-0.1.0.tar.gz
  • Upload date:
  • Size: 4.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for ariai-0.1.0.tar.gz
Algorithm Hash digest
SHA256 4b07cad6242d428a0cf0550dc5db07b8527760433867d010014c58744149e582
MD5 c51a635ea78f170eec2d40181979bc29
BLAKE2b-256 ede309001b037afa83bf7983810c6eff9407275bb0f896f991b87a0df5fabba3

See more details on using hashes here.

File details

Details for the file ariai-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: ariai-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 4.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for ariai-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 049c1c05cb941db50e618b3d86ebf7b9792769802011714a911c0b5c15be9d76
MD5 340f86189a4c51f316468556d39d7dd8
BLAKE2b-256 db80e6791c0b7874c83f34e0e0e3632ffa034d5757cdced737a8c435e66492aa

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page