Skip to main content

A python based DIANA Client for interacting with the DIANA server with higher level apis.

Project description

DIANA Client

This is a python client for the DIANA REST API. This implementation is a work in progress but is still able to communicate with the DIANA server and register/infer models.

from diana_client import HTTPClient

client = HTTPClient(
  diana_server_url = "https://diana.distributive.network",
  model_registry_url = "https://models.diana.distributive.network"
)

print(f"Can we connect? {client.check_diana_server_connection()}")

#### Register a Model

response = client.register_model(
    model_name = "my_model",
    model_path = "./my_model.onnx",
    preprocess_path = "./preprocess.py",
    postprocess_path = "./postprocess.py",
    password = "my_password",
    language = "python",
    packages = ["numpy", "pandas", "opencv-python"]
)

print(response.text) ### Model registered successfully!

#### Infer a Model

response = client.infer(
    inputs = files, # a list of the bytes of each input
    model_name = "my_model",
    slice_batch = 1, # number of inputs per slice
    inference_id = "my_inference_id", # An identifier for the inference
    compute_group_info = "joinKey/joinSecret" # The compute group info for the inference
)

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

diana_client-0.2.2.tar.gz (4.6 kB view hashes)

Uploaded Source

Built Distribution

diana_client-0.2.2-py3-none-any.whl (5.3 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