Skip to content

Commit 9f292bb

Browse files
authored
Disable prometheus by default (#416)
Signed-off-by: kerthcet <[email protected]>
1 parent 0fa89a0 commit 9f292bb

File tree

3 files changed

+15
-8
lines changed

3 files changed

+15
-8
lines changed

chart/values.global.yaml

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -32,14 +32,14 @@ leaderWorkerSet:
3232

3333
prometheus:
3434
# Prometheus is required to enable smart routing.
35-
enabled: true
35+
enabled: false
3636

3737
open-webui:
3838
enabled: true
3939
persistence:
4040
enabled: false
4141
enableOpenaiApi: true
42-
# Assumes the OpenAI-compatible API is exposed via the Envoy AI Gateway. Please replace this value if you
42+
# Assumes the OpenAI-compatible API is exposed via the Envoy AI Gateway. Please replace this value if you
4343
# deployed the envoy-ai-gateway example to a namespace other than "default".
4444
openaiBaseApiUrl: "http://envoy-default-default-envoy-ai-gateway-dbec795a.llmaz-system.svc.cluster.local/v1"
4545
extraEnvVars:

site/content/en/docs/installation.md

Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -10,11 +10,13 @@ description: >
1010

1111
**Requirements**:
1212

13-
- Kubernetes version >= 1.26. LWS requires Kubernetes version **v1.26 or higher**. If you are using a lower Kubernetes version and most of your workloads rely on single-node inference, we may consider replacing LWS with a Deployment-based approach. This fallback plan would involve using Kubernetes Deployments to manage single-node inference workloads efficiently. See [#32](https://github.com/InftyAI/llmaz/issues/32) for more details and updates.
13+
- Kubernetes version >= 1.27.
14+
15+
LWS requires Kubernetes version **v1.27 or higher**. If you are using a lower Kubernetes version and most of your workloads rely on single-node inference, we may consider replacing LWS with a Deployment-based approach. This fallback plan would involve using Kubernetes Deployments to manage single-node inference workloads efficiently. See [#32](https://github.com/InftyAI/llmaz/issues/32) for more details and updates.
1416
- Helm 3, see [installation](https://helm.sh/docs/intro/install/).
15-
- Prometheus, see [installation](https://github.com/InftyAI/llmaz/blob/main/site/content/en/docs/integrations/prometheus-operator.md#install-the-prometheus-operator).
1617

17-
Note: llmaz helm chart will by default install
18+
Note that llmaz helm chart will by default install:
19+
1820
- [LWS](https://github.com/kubernetes-sigs/lws) as the default inference workload in the llmaz-system, if you *already installed it * or *want to deploy it in other namespaces* , append `--set leaderWorkerSet.enabled=false` to the command below.
1921
- [Envoy Gateway](https://github.com/envoyproxy/gateway) and [Envoy AI Gateway](https://github.com/envoyproxy/ai-gateway) as the frontier in the llmaz-system, if you *already installed these two components* or *want to deploy in other namespaces* , append `--set envoy-gateway.enabled=false --set envoy-ai-gateway.enabled=false` to the command below.
2022
- [Open WebUI](https://github.com/open-webui/open-webui) as the default chatbot, if you want to disable it, append `--set open-webui.enabled=false` to the command below.

site/content/en/docs/integrations/prometheus-operator.md

Lines changed: 8 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -3,19 +3,24 @@ title: Prometheus Operator
33
weight: 3
44
---
55

6-
Currently, llmaz has already integrated metrics. This document provides deployment steps explaining how to install and configure Prometheus Operator in a Kubernetes cluster.
6+
This document provides deployment steps to install and configure Prometheus Operator in a Kubernetes cluster.
77

88
### Install the prometheus operator
99

10-
Please follow the [documentation](https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/getting-started/installation.md) to install
10+
Please follow the [documentation](https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/getting-started/installation.md) to install prometheus operator or simply run the following command:
11+
12+
```bash
13+
curl -sL https://github.com/prometheus-operator/prometheus-operator/releases/download/v0.81.0/bundle.yaml | kubectl delete -f -
14+
```
15+
16+
Ensure that the Prometheus Operator Pod is running successfully.
1117

1218
```bash
1319
# Installing the prometheus operator
1420
root@VM-0-5-ubuntu:/home/ubuntu# kubectl get pods
1521
NAME READY STATUS RESTARTS AGE
1622
prometheus-operator-55b5c96cf8-jl2nx 1/1 Running 0 12s
1723
```
18-
Ensure that the Prometheus Operator Pod is running successfully.
1924

2025
### Install the ServiceMonitor CR for llmaz
2126

0 commit comments

Comments
 (0)