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 works both in the browser with Pyodide Python or the native Python. It only implement the http client, and most of the API remains the similar but changed into async and with additional utility functions.

Usage

To use it in Python, you need to first install it with pip:

pip install pyotritonclient

For Pyodide-based Python environment, for example: JupyterLite or Pyodide console, you can install the client by running the following python code:

import micropip
micropip.install("pyotritonclient")

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-0.1.7.tar.gz (18.8 kB view hashes)

Uploaded Source

Built Distribution

pyotritonclient-0.1.7-py3-none-any.whl (20.8 kB view hashes)

Uploaded Python 3

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