explaingit

seldonio/seldon-core

4,748GoAudience · dataComplexity · 5/5Setup · hard

TLDR

Platform for deploying trained machine learning models as live web endpoints on Kubernetes, with built-in A/B testing, outlier detection, explainability, and monitoring via Prometheus and Grafana.

Mindmap

mindmap
  root((Seldon Core))
    What it does
      Serve ML models
      Scale predictions
      Monitor accuracy
    Built-in features
      A/B testing
      Outlier detection
      Explainability
      Distributed tracing
    Tech stack
      Kubernetes
      Helm
      Prometheus and Grafana
    Cloud support
      AWS and Azure
      Google Cloud
      OpenShift
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Things people build with this

USE CASE 1

Deploy a trained scikit-learn or PyTorch model as a REST endpoint that scales with traffic on a Kubernetes cluster.

USE CASE 2

Run A/B tests splitting traffic between two model versions to compare their prediction quality on real users.

USE CASE 3

Add an outlier detector that flags unusual inputs before they reach a production model to protect prediction quality.

USE CASE 4

Monitor model accuracy and request metrics with built-in Prometheus and Grafana dashboards without custom instrumentation.

Tech stack

GoPythonKubernetesHelmTensorFlowPyTorchPrometheusGrafana

Getting it running

Difficulty · hard Time to first run · 1day+

Requires a running Kubernetes cluster and Helm, you need a cloud provider account or a local kind/minikube setup before any model can be deployed.

In plain English

Seldon Core is a platform for taking trained machine learning models and turning them into live services that other software can call over the internet. If you have a model trained in Python, Java, TensorFlow, PyTorch, or a handful of other frameworks, Seldon Core wraps it up and exposes it as a web endpoint that accepts requests and returns predictions. The whole system runs on Kubernetes, which is an infrastructure layer for managing many containers at once across cloud servers. The core idea is that putting a model into production is harder than training it. You need to handle incoming traffic, scale up when requests spike, keep logs, monitor accuracy over time, and roll out new versions without breaking things. Seldon Core packages all of that machinery. It has been installed over two million times and is used by organizations that run thousands of models simultaneously. It works on AWS, Azure, Google Cloud, Alibaba Cloud, DigitalOcean, and OpenShift, so teams are not locked into one provider. Beyond basic serving, the project adds several built-in capabilities. You can run A/B tests that split traffic between two versions of a model to see which performs better. You can add outlier detectors that flag unusual inputs before they reach the model. You can attach explainers that produce a reason for each prediction. All requests and responses can be logged to Elasticsearch for auditing, and metrics flow to Prometheus and Grafana for dashboards and alerts. Distributed tracing via Jaeger lets engineers see exactly how long each step in a multi-model pipeline takes. Version 2 of Seldon Core is now available and the project recommends new users start there. Version 1, which the bulk of the documentation covers, is still supported. Installation for V1 is done through Helm, a Kubernetes package manager, using a single command that sets up the operator in a dedicated namespace. Once installed, you deploy a model by writing a short configuration file that names the model type and points to the model file stored in cloud object storage. The project is open source and maintained by Seldon. There is an active Slack community, fortnightly video calls, and a public issue tracker for bugs and feature requests.

Copy-paste prompts

Prompt 1
I have a trained scikit-learn model saved as a .pkl file and want to serve it as a REST API using Seldon Core on Kubernetes. Show me the Helm install command and the SeldonDeployment YAML to deploy it.
Prompt 2
Using Seldon Core, how do I configure an A/B test that routes 80% of traffic to my current model and 20% to a new candidate, and what metrics tell me which performs better?
Prompt 3
Show me how to attach a model explainer to a Seldon Core deployment so that every prediction response includes a human-readable reason for why the model returned that result.
Open on GitHub → Explain another repo

← seldonio on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.