Search…
Quickstart
Quickstart guide to start using Konduit-Serving
Konduit-Serving is a framework-agnostic model serving solution focused on deploying machine learning pipelines to production. The Python SDK allows data scientists to quickly test machine learning deployment scenarios, bridging the gap between data science teams and DevOps.
Before running these commands, set up Konduit Serving according to the installation instructions on the Building From Source and Installation page:

Configuration Files

Konduit Serving configuration files consist of serving, steps and client components. Save the configuration below as a text file named hello-world.yaml in your current directory:
1
serving:
2
http_port: 1337
3
input_data_format: NUMPY
4
output_data_format: NUMPY
5
steps:
6
python_step:
7
type: PYTHON
8
python_code: |
9
first += 2
10
second = first
11
python_inputs:
12
first: NDARRAY
13
python_outputs:
14
second: NDARRAY
15
client:
16
port: 1337
Copied!
The pages in this section show you how to start and interact with a Konduit Serving instance. For these examples, the Konduit Serving instance and client are on the same machine.
For quick experimentation, check out the quickstart for the command line interface (CLI):
To access additional options, you will want to configure Konduit Serving instances with the Python SDK. Start with the Python quickstart:
Copy link