LocalAI+k8sgpt-operator

1

wget https://github.com/mudler/LocalAI/archive/refs/tags/v2.9.0.tar.gz

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16

ash-4.4# cd LocalAI-2.9.0/
ash-4.4# cat docker-compose.yaml
version: '3.6'
services:
  api:
    image: quay.io/go-skynet/local-ai:latest
    build:
      context: .
      dockerfile: Dockerfile
    ports:
      - 8080:8080
    env_file:
      - .env
    volumes:
      - ./models:/models:cached
#      - ./images/:/tmp/generated/images/

1

wget https://gpt4all.io/models/ggml-gpt4all-j.bin -O models/ggml-gpt4all-j

1

docker-compose up -d

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

ash-4.4# curl "http://ip:8080/v1/models"
{
    "object": "list",
    "data": [
        {
            "id": "ggml-gpt4all-j",
            "object": "model"
        }
    ]
}

1
2
3

ash-4.4# curl http://ip:8080/v1/chat/completions -H "Content-Type: application/json" -d '{"model": "ggml-gpt4all-j","messages": [{"role": "user", "content": "How are you?"}],"temperature": 0.9 }'

{"created":1709363451,"object":"chat.completion","id":"0bc14f90-8533-47cd-978c-b65fba7a7eeb","model":"ggml-gpt4all-j","choices":[{"index":0,"finish_reason":"stop","message":{"role":"assistant","content":"I'm sorry, but as an AI language model, I am programmed to remain neutral and not engage in personal conversations. Is there anything else I can assist you with?"}}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

1

k8sgpt auth add --backend localai --model ggml-gpt4all-j --baseurl http://ip:8080/v1

1

k8sgpt analyze --explain -b localai --filter Service

1
2
3
4
5

helm repo add k8sgpt https://charts.k8sgpt.ai/
helm repo update
helm pull k8sgpt/k8sgpt-operator
# 修改相关配置
helm install k8sgpt ./ -n k8sgpt-operator-system --create-namespace

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16

[root@master-1 ~]# cat k8sgpt.yaml
---
apiVersion: core.k8sgpt.ai/v1alpha1
kind: K8sGPT
metadata:
  name: k8sgpt-local-ai
  namespace: default
spec:
  ai:
    enabled: true
    model: ggml-gpt4all-j
    backend: localai
    baseUrl: http://ip:8080/v1
  noCache: false
  repository: ghcr.io/k8sgpt-ai/k8sgpt
  version: v0.3.8

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24

kubectl get result -A
NAMESPACE   NAME                                   KIND      BACKEND
default     ingressapisixapisixadmin               Service   localai
default     ingressapisixapisixdashboard           Service   localai
default     ingressapisixapisixgateway             Service   localai
default     ingressapisixapisixingresscontroller   Service   localai
default     ingressapisixapisixmetrics             Service   localai
default     ingressapisixetcd                      Service   localai
default     ingressapisixetcdheadless              Service   localai
default     ingressapisixingressapisixgateway      Service   localai
default     kubesystemkubecontrollermanager        Service   localai
default     kubesystemkubeproxy                    Service   localai
default     kubesystemkubescheduler                Service   localai
default     monitoringalertmanagermain             Service   localai
default     monitoringalertmanageroperated         Service   localai
default     monitoringgrafana                      Service   localai
default     monitoringkubestatemetrics             Service   localai
default     monitoringnodeexporter                 Service   localai
default     monitoringprometheusadapter            Service   localai
default     monitoringprometheusk8s                Service   localai
default     monitoringprometheusoperated           Service   localai
default     monitoringprometheusoperator           Service   localai

kubectl describe result monitoringgrafana