# Getting Started

{% hint style="info" %}
Some dependencies may require that the (virtual) machines on which you deploy, support the SSE4.2\
instruction set or x86-64-v2 microarchitecture. If `lscpu | grep sse4_2` does not return anything on\
your machine, your CPU is not compatible, and you may need to update the (virtual) host's CPU.
{% endhint %}

Seldon Core can be installed either with Docker Compose or with Kubernetes:

* [Install locally with Docker Compose](/seldon-core-2/v2.8/getting-started/docker-installation.md)
* [Install onto a Kubernetes cluster](/seldon-core-2/v2.8/getting-started/kubernetes-installation.md)

Once installed:

* Try the existing [examples](/seldon-core-2/v2.8/examples.md).
* Train and deploy your own [model artifact](/seldon-core-2/v2.8/models/inference-artifacts.md#saving-model-artifacts).

## Core Concepts

There are three core resources you will use:

* [Models](/seldon-core-2/v2.8/models.md) - for deploying single machine learning models, custom transformation\
  logic, drift detectors and outliers detectors.
* [Pipelines](/seldon-core-2/v2.8/pipelines.md) - for connecting together flows of data transformations between Models\
  with a synchronous path and multiple asynchronous paths.
* [Experiments](/seldon-core-2/v2.8/experiments.md) - for testing new versions of models

By default the standard installation will deploy MLServer and Triton inference servers which provide\
support for a wide range of machine learning model artifacts including Tensorflow models, PyTorch models,\
SKlearn models, XGBoost models, ONNX models, TensorRT models, custom python models and many more. For\
advanced use, the creation of new inference servers is manged by two resources:

* [Servers](/seldon-core-2/v2.8/servers.md) - for deploying sets of replicas of core inference servers (MLServer or Triton by default).
* [ServerConfigs](/seldon-core-2/v2.8/kubernetes/resources/serverconfig.md) - for defining server configurations including custom servers.

## API for Inference

Once deployed models can be called using the [Seldon V2 inference protocol](/seldon-core-2/v2.8/apis/inference/v2.md). This\
protocol created by Seldon, NVIDIA and the KServe projects is supported by MLServer and Triton inference\
servers amingst others and allows REST and gRPC calls to your model.

Your model is exposed via our internal Envoy gateway. If you wish to expose your models in Kubernetes\
outside the cluster you are free to use any Service Mesh or Ingress technology. Various examples are provided\
for service mesh integration.

## Inference Metrics

Metrics are exposed for scraping by Prometheus. For Kubernetes we provide example instructions for using kube-prometheus.

## Pipeline requirements

Pipelines are built upon Kafka streaming technology.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.seldon.ai/seldon-core-2/v2.8/getting-started.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.