Metadata-Version: 2.1
Name: elangai
Version: 1.0.0
Summary: Inference Engine Platform on Edge Device.
Home-page: https://www.elang.ai/
Author: elangai Developer
Author-email: resha.alfahsi@techbros.io
License: UNKNOWN
Platform: UNKNOWN
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: Other/Proprietary License
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
Classifier: Programming Language :: Python :: 3.6
Description-Content-Type: text/markdown
Requires-Dist: typer

# elangai

`elangai` is an inference engine platform designed for but not limited to the edge device. This SDK includes the main components of `elangai`.


## Installation


### Prerequisite

Before installing `elangai`, users have to install the following components:

* TensorRT >= **7.0.0.11**
* TensorFlow >= **2.5.0**
* ONNXRuntime >= **1.5.2**

Otherwise, `elangai` won't work as intended.


### Install

`elangai` could be installed by following command.

    pip3 install elangai


## Quick Guide


### Make Your Own AI App

Using the following command on terminal, you could easily generate the AI app.

    elangai generate myapp


### Dissect Your AI Model

Use the following command to examine the input and output tensor information of your AI model.

    elangai model-dissector /path/to/your/model.onnx


Currently supports `.onnx` and `.tflite` file only.


### Convert Your AI Model to `.trt` File

`elangai` only supports `.tflite` and `.trt` file inference. Use the following command to convert `.onnx` model to `.trt` file.

    elangai model-converter --src /path/to/model.onnx  --dst /path/to/model.trt


Currently supports `.onnx` file conversion only.


