Skip to main content

A Pyodide python http client library and utilities for communicating with Triton Inference Server (based on tritonclient from NVIDIA)

Project description

Triton HTTP Client for Pyodide

A Pyodide python http client library and utilities for communicating with Triton Inference Server (based on tritonclient from NVIDIA).

This is a simplified implemetation of the triton client from NVIDIA, it is mainly made for running in the web browser with pyodide. It only implement the http client, and most of the API remains the same but changed into async.

Usage

You can used it in Pyodide based environment, for example: Pyodide console or JupyterLite.

For example in a JupyterLite notebook, you can install the client by running:

import micropip
micropip.install("pyotritonclient")

If you want to use outside pyodide, run pip install pyotritonclient. However, please note that you will need to provide your own http_client class.

To execute the model, we provide utility functions to make it much easier:

import numpy as np
from pyotritonclient import get_config, execute_model

# obtain the model config
config = await get_config('https://triton.imjoy.io', 'cellpose-cyto')

# create fake input tensors
input0 = np.zeros([2, 349, 467], dtype='float32')
input1 = np.array([30], dtype='float32')
# run inference
results = await execute_model([input0, input1], config=config)

You can access the lower level api, see the test example.

You can also find the official client examples demonstrate how to use the package to issue request to triton inference server. However, please notice that you will need to change the http client code into async style. For example, instead of doing client.infer(...), you need to do await client.infer(...).

The http client code is forked from triton client git repo since commit b3005f9db154247a4c792633e54f25f35ccadff0.

Server setup

Since we access the server from the browser environment which typically has more security restrictions, it is important that the server is configured to enable browser access.

Please make sure you configured following aspects:

  • The server must provide HTTPS endpoints instead of HTTP
  • The server should send the following headers:
    • Access-Control-Allow-Headers: Inference-Header-Content-Length,Accept-Encoding,Content-Encoding,Access-Control-Allow-Headers
    • Access-Control-Expose-Headers: Inference-Header-Content-Length,Range,Origin,Content-Type
    • Access-Control-Allow-Methods: GET,HEAD,OPTIONS,PUT,POST
    • Access-Control-Allow-Origin: * (This is optional depending on whether you want to support CORS)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pyotritonclient-0.1.2.tar.gz (18.4 kB view details)

Uploaded Source

Built Distribution

pyotritonclient-0.1.2-py3-none-any.whl (19.6 kB view details)

Uploaded Python 3

File details

Details for the file pyotritonclient-0.1.2.tar.gz.

File metadata

  • Download URL: pyotritonclient-0.1.2.tar.gz
  • Upload date:
  • Size: 18.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.2 CPython/3.9.5

File hashes

Hashes for pyotritonclient-0.1.2.tar.gz
Algorithm Hash digest
SHA256 f8f914486bdab5550cb28b07c53459b9ca728cbe111af79ac726088518097058
MD5 e5fede34df1254072cd0b0bde3c695e3
BLAKE2b-256 f78ea310adad9337848af7cb3595056cb794c2cd4067c55358a536d5adca18f2

See more details on using hashes here.

File details

Details for the file pyotritonclient-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: pyotritonclient-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 19.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.2 CPython/3.9.5

File hashes

Hashes for pyotritonclient-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 32431a355b1b6310cc8d19cb00781d390f903bccdb78ed049b97ac27dcdb7054
MD5 29dfc8690404345d9fcb6d48d0314f68
BLAKE2b-256 8c73a6c6a5c7013ce81cafbc03333e9eea0a441d2b4a20104c77e28f6c020728

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page