# Custom Servers

{% hint style="info" %}
**Note**: The Seldon CLI allows you to view information about underlying Seldon resources and make changes to them through the scheduler in non-Kubernetes environments. However, it cannot modify underlying manifests within a Kubernetes cluster. Therefore, using the Seldon CLI for control plane operations in a Kubernetes environment is not recommended. For more details, see [Seldon CLI](/seldon-core-2/resources/apis/cli.md).
{% endhint %}

```python
import os
os.environ["NAMESPACE"] = "seldon-mesh"
```

```python
MESH_IP=!kubectl get svc seldon-mesh -n ${NAMESPACE} -o jsonpath='{.status.loadBalancer.ingress[0].ip}'
MESH_IP=MESH_IP[0]
import os
os.environ['MESH_IP'] = MESH_IP
MESH_IP
```

```
'172.18.255.2'

```

## Custom Server with Capabilities

The `capabilities` field replaces the capabilities from the ServerConfig.

```bash
cat ./servers/custom-mlserver-capabilities.yaml
```

```yaml
apiVersion: mlops.seldon.io/v1alpha1
kind: Server
metadata:
  name: mlserver-134
spec:
  serverConfig: mlserver
  capabilities:
  - mlserver-1.3.4
  podSpec:
    containers:
    - image: seldonio/mlserver:1.3.4
      name: mlserver

```

```bash
kubectl create -f ./servers/custom-mlserver-capabilities.yaml -n ${NAMESPACE}
```

```
server.mlops.seldon.io/mlserver-134 created

```

```bash
kubectl wait --for condition=ready --timeout=300s server --all -n ${NAMESPACE}
```

```
server.mlops.seldon.io/mlserver condition met
server.mlops.seldon.io/mlserver-134 condition met
server.mlops.seldon.io/triton condition met

```

```bash
cat ./models/iris-custom-requirements.yaml
```

```yaml
apiVersion: mlops.seldon.io/v1alpha1
kind: Model
metadata:
  name: iris
spec:
  storageUri: "gs://seldon-models/mlserver/iris"
  requirements:
  - mlserver-1.3.4

```

```bash
kubectl create -f ./models/iris-custom-requirements.yaml -n ${NAMESPACE}
```

```
model.mlops.seldon.io/iris created

```

```bash
kubectl wait --for condition=ready --timeout=300s model --all -n ${NAMESPACE}
```

```
model.mlops.seldon.io/iris condition met

```

```bash
seldon model infer iris --inference-host ${MESH_IP}:80 \
  '{"inputs": [{"name": "predict", "shape": [1, 4], "datatype": "FP32", "data": [[1, 2, 3, 4]]}]}'
```

```json
{
	"model_name": "iris_1",
	"model_version": "1",
	"id": "057ae95c-e6bc-4f57-babf-0817ff171729",
	"parameters": {},
	"outputs": [
		{
			"name": "predict",
			"shape": [
				1,
				1
			],
			"datatype": "INT64",
			"parameters": {
				"content_type": "np"
			},
			"data": [
				2
			]
		}
	]
}

```

```bash
kubectl delete -f ./models/iris-custom-server.yaml -n ${NAMESPACE}
```

```
model.mlops.seldon.io "iris" deleted

```

```bash
kubectl delete -f ./servers/custom-mlserver.yaml -n ${NAMESPACE}
```

```
server.mlops.seldon.io "mlserver-134" deleted

```

## Custom Server with Extra Capabilities

The `extraCapabilities` field extends the existing list from the ServerConfig.

```bash
cat ./servers/custom-mlserver.yaml
```

```yaml
apiVersion: mlops.seldon.io/v1alpha1
kind: Server
metadata:
  name: mlserver-134
spec:
  serverConfig: mlserver
  extraCapabilities:
  - mlserver-1.3.4
  podSpec:
    containers:
    - image: seldonio/mlserver:1.3.4
      name: mlserver

```

```bash
kubectl create -f ./servers/custom-mlserver.yaml -n ${NAMESPACE}
```

```
server.mlops.seldon.io/mlserver-134 created

```

```bash
kubectl wait --for condition=ready --timeout=300s server --all -n ${NAMESPACE}
```

```
server.mlops.seldon.io/mlserver condition met
server.mlops.seldon.io/mlserver-134 condition met
server.mlops.seldon.io/triton condition met

```

```bash
cat ./models/iris-custom-server.yaml
```

```yaml
apiVersion: mlops.seldon.io/v1alpha1
kind: Model
metadata:
  name: iris
spec:
  storageUri: "gs://seldon-models/mlserver/iris"
  server: mlserver-134

```

```bash
kubectl create -f ./models/iris-custom-server.yaml -n ${NAMESPACE}
```

```
model.mlops.seldon.io/iris created

```

```bash
kubectl wait --for condition=ready --timeout=300s model --all -n ${NAMESPACE}
```

```
model.mlops.seldon.io/iris condition met

```

```bash
seldon model infer iris --inference-host ${MESH_IP}:80 \
  '{"inputs": [{"name": "predict", "shape": [1, 4], "datatype": "FP32", "data": [[1, 2, 3, 4]]}]}'
```

```json
{
	"model_name": "iris_1",
	"model_version": "1",
	"id": "a3e17c6c-ee3f-4a51-b890-6fb16385a757",
	"parameters": {},
	"outputs": [
		{
			"name": "predict",
			"shape": [
				1,
				1
			],
			"datatype": "INT64",
			"parameters": {
				"content_type": "np"
			},
			"data": [
				2
			]
		}
	]
}

```

```bash
kubectl delete -f ./models/iris-custom-server.yaml -n ${NAMESPACE}
```

```
model.mlops.seldon.io "iris" deleted

```

```bash
kubectl delete -f ./servers/custom-mlserver.yaml -n ${NAMESPACE}
```

```
server.mlops.seldon.io "mlserver-134" deleted

```

```python
```


---

# 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/user-guide/examples/custom-servers.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.