# 🚢 modelship
> Ship machine learning models in minutes, not months
[](https://pypi.org/project/modelship/)
[](https://pypi.org/project/modelship/)
[](https://github.com/datalpia/modelship/actions/workflows/ci-cd.yml)
[](https://github.com/datalpia/modelship/blob/main/LICENSE)
`modelship` is a utility application to ease wrapping and deploying machine learning models
by autogenerating applications, leveraging modern standards such as ONNX and WebAssembly.
## Demo
Examples of static web applications generated with `modelship` from ONNX models:
- `housing`: housing price prediction model (regression)
- Live: https://datalpia.github.io/modelship/demo/housing/
- Source: [demo/housing](demo/housing)
- `sentiment`: movie review sentiment analysis (binary classification)
- Live: https://datalpia.github.io/modelship/demo/sentiment/
- Source: [demo/sentiment](demo/sentiment)
## Features
- ONNX model support
- Generate a static web application with autogenerated form
## Installation
Using `pip` (or any other Python package manager):
```bash
pip install modelship
```
Using `uvx`:
```bash
uvx modelship
```
## Usage
### Model metadata
Every model must be described with some basic metadata for conversions to work properly.
Here is the YAML schema:
```yaml
name: Model Name
description: Model description
inputs:
float_input:
name: Float Input Name
type: float32
shape: [null, 1]
min: 10
max: 100
step: 1
default: 50
string_input:
name: String Input Name
type: string
shape: [null]
outputs:
float_output:
name: Float Output Name
type: float32
shape: [null, 1]
string_output:
name: String Output Name
type: string
shape: [null]
```
Input fields:
- `name`: `str`
- `type`: `Literal["float32", "string"]`
- `shape`: `list[int | None]`
- (optional) `min`: `float`
- (optional) `max`: `float`
- (optional) `step`: `float`
- (optional) `defaut`: `float | str`
Output fields:
- `name`: `str`
- `type`: `Literal["float32", "string"]`
- `shape`: `list[int | None]`
### Static web application generation
Provide an ONNX model with its YAML metadata description, and `modelship`
will generate a static web application with an autogenerated HTML form,
performing model inference using ONNX Runtime Web (WebAssembly):
```bash
$ modelship static --output dist --metadata model/metadata.yml model/model.onnx
```
The resulting static application in `dist` can now be deployed on any static
hosting provider (GitHub Pages, GitLab Pages, Cloudflare Pages, S3, Vercel)!
## License
Licensed under [Apache License 2.0](LICENSE)
Copyright (c) 2025 - present Romain Clement / Datalpia
Raw data
{
"_id": null,
"home_page": null,
"name": "modelship",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.14,>=3.10",
"maintainer_email": null,
"keywords": "deployment, machine-learning, onnx, webassembly",
"author": null,
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/ed/51/00dcdf5fdd884bafea42a09d4caaf35ff08b74334307d81cd943f9bb738d/modelship-0.2.0.tar.gz",
"platform": null,
"description": "# \ud83d\udea2 modelship\n\n> Ship machine learning models in minutes, not months\n\n[](https://pypi.org/project/modelship/)\n[](https://pypi.org/project/modelship/)\n[](https://github.com/datalpia/modelship/actions/workflows/ci-cd.yml)\n[](https://github.com/datalpia/modelship/blob/main/LICENSE)\n\n`modelship` is a utility application to ease wrapping and deploying machine learning models\nby autogenerating applications, leveraging modern standards such as ONNX and WebAssembly.\n\n## Demo\n\nExamples of static web applications generated with `modelship` from ONNX models:\n\n- `housing`: housing price prediction model (regression)\n - Live: https://datalpia.github.io/modelship/demo/housing/\n - Source: [demo/housing](demo/housing)\n- `sentiment`: movie review sentiment analysis (binary classification)\n - Live: https://datalpia.github.io/modelship/demo/sentiment/\n - Source: [demo/sentiment](demo/sentiment)\n\n## Features\n\n- ONNX model support\n- Generate a static web application with autogenerated form\n\n## Installation\n\nUsing `pip` (or any other Python package manager):\n\n```bash\npip install modelship\n```\n\nUsing `uvx`:\n\n```bash\nuvx modelship\n```\n\n## Usage\n\n### Model metadata\n\nEvery model must be described with some basic metadata for conversions to work properly.\n\nHere is the YAML schema:\n\n```yaml\nname: Model Name\ndescription: Model description\ninputs:\n float_input:\n name: Float Input Name\n type: float32\n shape: [null, 1]\n min: 10\n max: 100\n step: 1\n default: 50\n string_input:\n name: String Input Name\n type: string\n shape: [null]\noutputs:\n float_output:\n name: Float Output Name\n type: float32\n shape: [null, 1]\n string_output:\n name: String Output Name\n type: string\n shape: [null]\n```\n\nInput fields:\n- `name`: `str`\n- `type`: `Literal[\"float32\", \"string\"]`\n- `shape`: `list[int | None]`\n- (optional) `min`: `float`\n- (optional) `max`: `float`\n- (optional) `step`: `float`\n- (optional) `defaut`: `float | str`\n\nOutput fields:\n- `name`: `str`\n- `type`: `Literal[\"float32\", \"string\"]`\n- `shape`: `list[int | None]`\n\n### Static web application generation\n\nProvide an ONNX model with its YAML metadata description, and `modelship`\nwill generate a static web application with an autogenerated HTML form,\nperforming model inference using ONNX Runtime Web (WebAssembly):\n\n```bash\n$ modelship static --output dist --metadata model/metadata.yml model/model.onnx\n```\n\nThe resulting static application in `dist` can now be deployed on any static\nhosting provider (GitHub Pages, GitLab Pages, Cloudflare Pages, S3, Vercel)!\n\n## License\n\nLicensed under [Apache License 2.0](LICENSE)\n\nCopyright (c) 2025 - present Romain Clement / Datalpia\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "Ship machine learning models in minutes, not months",
"version": "0.2.0",
"project_urls": null,
"split_keywords": [
"deployment",
" machine-learning",
" onnx",
" webassembly"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "33587ea068f4092cc3d2131577471b68db7bce87c79bc4403d477e3133294266",
"md5": "b9a6106b65a302b1e00c877428ccc126",
"sha256": "74783a0a32241188175e9af40d0c9b296923ac73f31182315b0f922e5e2f19eb"
},
"downloads": -1,
"filename": "modelship-0.2.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "b9a6106b65a302b1e00c877428ccc126",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.14,>=3.10",
"size": 6109951,
"upload_time": "2025-10-14T22:40:00",
"upload_time_iso_8601": "2025-10-14T22:40:00.136877Z",
"url": "https://files.pythonhosted.org/packages/33/58/7ea068f4092cc3d2131577471b68db7bce87c79bc4403d477e3133294266/modelship-0.2.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "ed5100dcdf5fdd884bafea42a09d4caaf35ff08b74334307d81cd943f9bb738d",
"md5": "f29b35a66204ee6fb5df6eb247845571",
"sha256": "2c67d93440726ac8bf841a1f679e0fb0486f75a5a93ed6c46fdbf8cf5f147c16"
},
"downloads": -1,
"filename": "modelship-0.2.0.tar.gz",
"has_sig": false,
"md5_digest": "f29b35a66204ee6fb5df6eb247845571",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.14,>=3.10",
"size": 6600329,
"upload_time": "2025-10-14T22:40:02",
"upload_time_iso_8601": "2025-10-14T22:40:02.372561Z",
"url": "https://files.pythonhosted.org/packages/ed/51/00dcdf5fdd884bafea42a09d4caaf35ff08b74334307d81cd943f9bb738d/modelship-0.2.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-14 22:40:02",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "modelship"
}
JSON