Skip to main content

Orpheus Desktop AI Assistant powered by GPT-4, GPT-4o, GPT-4V, GPT-3.5, DALL-E 3, Llama 3, Mistral, Gemini, Claude, Langchain LLMs, Llama-index, Whisper with chatbot, assistant, text completion, vision and image generation, internet access, chat with files, commands and code execution, file upload and download, and more.

Project description

oDAIa - Desktop AI Assistant

Overview

oDAIa is a Desktop AI Assistant that interacts with OpenAI language models, including GPT-4, GPT-4 Vision, and GPT-3.5, through the OpenAI API. It supports alternative LLMs via Langchain and Llama-index, such as models on HuggingFace, Llama 3, Mistral, Google Gemini, and Anthropic Claude.

The assistant offers modes like chat, completions, and image tasks using DALL-E 3 and GPT-4 Vision. It has filesystem capabilities, can generate and run Python code, execute system commands, and manage file transfers. It also supports web searches.

For audio interactions, oDAIa includes speech synthesis using Microsoft Azure, Google, Eleven Labs, and OpenAI Text-To-Speech services.

JGWill Orpheus Desktop AI Assistant Aim to include Creative Orientation in Prompt Engineering and more

Installation

pip install -U odaia

Usage

odaia

Features

JGWill Creative Practicionners features

TODO

  • Learn about engineering prompting of autonomous mode (normal and extended 241028)

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

odaia-2.3.5.tar.gz (6.3 MB view details)

Uploaded Source

Built Distribution

odaia-2.3.5-py3-none-any.whl (7.5 MB view details)

Uploaded Python 3

File details

Details for the file odaia-2.3.5.tar.gz.

File metadata

  • Download URL: odaia-2.3.5.tar.gz
  • Upload date:
  • Size: 6.3 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.15

File hashes

Hashes for odaia-2.3.5.tar.gz
Algorithm Hash digest
SHA256 88cce6f0d0c7969770c290974c431948048c37d984498f6ffdff67ebeb5b554f
MD5 3178cc5056772d082ff97889b526a290
BLAKE2b-256 b7f260613ffa84b66e42bba8c4a5458b4ae2d7bf0fa98090cf7e596e83c00c33

See more details on using hashes here.

File details

Details for the file odaia-2.3.5-py3-none-any.whl.

File metadata

  • Download URL: odaia-2.3.5-py3-none-any.whl
  • Upload date:
  • Size: 7.5 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.15

File hashes

Hashes for odaia-2.3.5-py3-none-any.whl
Algorithm Hash digest
SHA256 57ab45310d13b32cf941e66bae6ac664098115d32ddc9aeee39488887196d0a4
MD5 52273a8760a4faf228b2195fed21637b
BLAKE2b-256 9996e384cf32b6889beae579a19303c792f2731f9a0559c12e5b39ed35fad824

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