Aflight: simple Arrow Flight API builder/runner
Loosely inspired by Flask
TL;DR
Server:
Create app.py
import aflight
app = aflight.Aflight()
@app.command("predict")
def predict(batch):
result = do_something_with(batch)
return [result]
To Run:
aflight
Client:
from aflight.client import predict
data = some_pandas_data()
print(predict(data))
Why?
Current kserve, torch/serve etc. APIs are too reliant on HTTP request/response paradigm
Using Arrow as a data format and Arrow Flight as a service API produces a much better interface:
- standard
- has schema
- fast
- columnar
- batch-able
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
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 aflight-0.2.4-py3-none-any.whl.
File metadata
- Download URL: aflight-0.2.4-py3-none-any.whl
- Upload date:
- Size: 7.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/4.0.2 CPython/3.9.16
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
436217ddff6390afe37f691f09cef54cdeac1c7f992e38f93a9fb58307cebb32
|
|
| MD5 |
c1498599e063b13be99dcae590026fcb
|
|
| BLAKE2b-256 |
fb48b0697b34868188293934aff0ddf2a80ef29460679f3fa4794fa9338d70f0
|
