A python client to interact with Machine Learning microservices hosted on Lift Wing
Project description
Liftwing Python Package
Make request to machine learning models hosted on Lift Wing - the Wikimedia Foundation's ML model serving platform
The LiftWing python package works as a client for developers making API requests. With this package developers will be able to import their desired API and make requests to it.
Installation
Install the python package named liftwing using pip:
pip install liftwing
After installing the package you can list the available models
python -m liftwing
Using the package
We can make requests to a model server:
from liftwing import RevertRiskAPIModel
client = RevertRiskAPIModel()
result = client.request(payload={"lang": "en", "rev_id": "123456"})
print(result)
Result:
{
"model_name":"revertrisk-language-agnostic",
"model_version":"3",
"wiki_db":"enwiki",
"revision_id":"123456",
"output":{
"prediction":false,
"probabilities":{
"true":0.25512129068374634,
"false":0.7448787093162537
}
}
}
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file liftwing-0.1.1.tar.gz.
File metadata
- Download URL: liftwing-0.1.1.tar.gz
- Upload date:
- Size: 5.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
06340dace2c442e8d801729e3aece0ea20d83b7fa39d7acd925f0fc1c3511423
|
|
| MD5 |
16d7f8673a38befb9a0b69cb48e5ec0e
|
|
| BLAKE2b-256 |
3c964640dc14a4055d4a1efa05450d576c18cf73d1b3ecc787a16ff12b0b9f7a
|
File details
Details for the file liftwing-0.1.1-py3-none-any.whl.
File metadata
- Download URL: liftwing-0.1.1-py3-none-any.whl
- Upload date:
- Size: 8.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f45cbdc82a3c19d86f8b17f5dfb2bc39e893f563eb051d0eedeccb6a120e67cd
|
|
| MD5 |
28045f541498cad397bfaff4faecaa7f
|
|
| BLAKE2b-256 |
b3e9be91a85b4ad2907dbd8e1322b628835073d61489c0fb27ad63334023d87a
|