PkgFoundry
Catalog PyPI
Back to packageRELEASE DETAILS

1.19.0

PyPI

aihandler

AI Handler: An engine which wraps certain huggingface models

aichatchatbot
Published14 Jul 2023
Direct dependencies35
Transitive dependenciesNot calculated

README

Version 1.19.0 documentation

AI Handler

Upload Python Package Discord GitHub GitHub last commit GitHub issues GitHub closed issues GitHub pull requests GitHub closed pull requests

This is a simple framework for running AI models. It makes use of the huggingface API which gives you a queue, threading, a simple API, and the ability to run Stable Diffusion and LLMs seamlessly from your local hardware.

This is not intended to be used as a standalone application.

It can easily be extended and used to power interfaces or it can be run from the command line.

AI Handler is a work in progress. It powers two projects at the moment, but may not be ready for general use.

Installation

This is a work in progress.

Pre-requisites

System requirements

  • Windows 10+
  • Python 3.10.8
  • pip 23.0.1
  • CUDA toolkit 11.7
  • CUDNN 8.6.0.163
  • Cuda capable GPU
  • 16gb+ ram

For Windows, follow windows branch instructions

Install

pip install https://github.com/w4ffl35/diffusers/archive/refs/tags/v0.15.0.ckpt_fix_0.0.1.tar.gz
pip install aihandler

Optional

These are optional instructions for installing TensorRT and Deepspeed for Windows

Install Tensor RT:
  1. Download TensorRT-8.4.3.1.Windows10.x86_64.cuda-11.6.cudnn8.4
  2. Git clone TensorRT 8.4.3.1
  3. Follow their instructions to build TensorRT-8.4.3.1 python wheel
  4. Install TensorRT pip install tensorrt-*.whl
Install Deepspeed:
  1. Git clone Deepspeed 0.8.1
  2. Follow their instructions to build Deepspeed python wheel
  3. Install Deepspeed `pip install deepspeed-*.whl

Environment variables

  • AIRUNNER_ENVIRONMENT - dev or prod. Defaults to dev. This controls the LOG_LEVEL
  • LOG_LEVEL - FATAL for production, DEBUG for development. Override this to force a log level

Huggingface variables

Offline mode

These environment variables keep you offline until you need to download a model. This prevents unwanted online access and speeds up usage of huggingface libraries.

  • DISABLE_TELEMETRY Keep this set to 1 at all times. Huggingface collects minimal telemetry when downloading a model from their repository but this will keep it disabled. See more info in this github thread
  • HF_HUB_OFFLINE When loading a diffusers model, huggingface libraries will attempt to download an updated cache before running the model. This prevents that check from happening (long with a boolean passed to load_pretrained see the runner.py file for examples)
  • TRANSFORMERS_OFFLINE Similar to HF_HUB_OFFLINE but for transformers models

Downloads & popularity

Awaiting observations

No metric observations yet

Download counts and popularity will appear here as the collector receives them.

Declared dependencies 35

Native requirements
35 direct targetsNot calculated transitive count
Package / targetRequirementRelationship
einops
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
einops (==0.6.0)runtime
ninja
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
ninja (==1.11.1)runtime
JIT
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
JIT (==0.2.7)runtime
tqdm
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
tqdm (==4.65.0)runtime
omegaconf
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
omegaconf (==2.3.0)runtime
accelerate
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
accelerate (==0.20.3)runtime
controlnet-aux
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
controlnet-aux (==0.0.6)runtime
huggingface-hub
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
huggingface-hub (==0.16.3)runtime
numpy
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
numpy (==1.23.5)runtime
Pillow
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
Pillow (==9.5.0)runtime
pip
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
pip (==23.1.2)runtime
PyQt6
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
PyQt6 (==6.4.2)runtime
PyQt6-Qt6
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
PyQt6-Qt6 (==6.4.3)runtime
PyQt6-sip
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
PyQt6-sip (==13.4.1)runtime
pyqtdarktheme
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
pyqtdarktheme (==2.1.0)runtime
pyre-extensions
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
pyre-extensions (==0.0.29)runtime
lightning
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
lightning (==2.0.2)runtime
requests
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
requests (==2.31.0)runtime
requests-oauthlib
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
requests-oauthlib (==1.3.1)runtime
safetensors
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
safetensors (==0.3.1)runtime
scipy
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
scipy (==1.10.1)runtime
tensorflow
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
tensorflow (==2.12.0)runtime
tokenizers
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
tokenizers (==0.13.3)runtime
charset-normalizer
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
charset-normalizer (==3.1.0)runtime
opencv-python
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
opencv-python (==4.8.0.74)runtime
setuptools
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
setuptools (==67.7.2)runtime
typing-extensions
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
typing-extensions (==4.5.0)runtime
urllib3
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
urllib3 (==1.26.15)runtime
diffusers
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
diffusers (==0.18.2)runtime
transformers
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
transformers (==4.30.1)runtime
compel
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
compel (==1.2.1)runtime
sympy
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
sympy (==1.12.0)runtime
regex
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
regexruntime
matplotlib
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
matplotlib (==3.7.2)runtime
invisible-watermark
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": "",
  "evaluation": "NOT_EVALUATED"
}
invisible-watermark (==0.2.0)runtime

Distribution files

2 collected
aihandler-1.19.0-py3-none-any.whl

bdist_wheel · 59.84 KB · Python py3

Source file
aihandler-1.19.0.tar.gz

sdist · 53.25 KB · Python source

Source file

Repository

PENDING
capsize-games/aihandler

Shared repository data · GitHub

License detected in repository
Not collected

Metadata history

Meaningful changes
Current collected state Current

Observed since 21 Oct, 10:51 UTC

No superseded metadata states collected. Unchanged observations do not create new revisions.

Record identity

package_version:ff9b9724dfd6b96e447e5efffce60ca663d796de201a2f34e861914f7c438f7b

Other collected versions

View all collected versions →