绝了！k3s (k8s) 安装 ollama 运行 deepseek 全流程揭秘，yaml全公开

# https://cloud.tencent.com/developer/article/2495842 环境变量
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    app: ollama
  name: ollama
  namespace: moonfdd
spec:
  strategy:
    type: Recreate
  replicas: 1
  selector:
    matchLabels:
      app: ollama
  template:
    metadata:
      labels:
        app: ollama
    spec:
      containers:
        - env:
            - name: OLLAMA_HOST
              value: "0.0.0.0"
            - name: OLLAMA_PORT
              value: "11434"
            - name: OLLAMA_NUM_PARALLEL
              value: "20" # 默认是1
            - name: OLLAMA_ORIGINS
              value: "*"
            - name: OLLAMA_MODELS
              value: "/root/.ollama/models"
          image: 'ollama/ollama:0.5.12'
          command: ["ollama", "serve"]
          imagePullPolicy: IfNotPresent
          name: ollama
          volumeMounts:
            - mountPath: /root/.ollama/models/
              name: data
          resources:
            # nvidia.com/gpu: 1
            # memory: "24Gi"
            # limits:
            #   cpu: 200m
            #   memory: 200Mi
            # requests:
            #   cpu: 100m
            #   memory: 100Mi
        - image: 'ollama/ollama:0.5.12'
          command: ["sh", "-c", "while true; do ollama run deepseek-r1:1.5b; sleep 5; done"]
          imagePullPolicy: IfNotPresent
          name: ollamacmd
      volumes:
        - name: data
          hostPath:
            path: /root/k8s/moonfdd/ollama/root/.ollama/models/
            type: DirectoryOrCreate
---
apiVersion: v1
kind: Service
metadata:
  labels:
    app: ollama
  name: ollama
  namespace: moonfdd
spec:
  ports:
    - name: 11434-11434
      port: 11434
      protocol: TCP
      targetPort: 11434
      nodePort: 11434
  selector:
    app: ollama
  type: NodePort

kubectl apply -f ollama.yaml

package main
<p>import (
"bufio"
"bytes"
"encoding/json"
"fmt"
"net/http"
"time"
)</p><p>type Message struct {
Role    string <code>json:"role"
Content string <code>json:"content"</code>
}</p><p>// 修改请求结构体，添加 Stream 字段
type DeepSeekRequest struct {
Model       string    <code>json:"model"</code>
Messages    []Message <code>json:"messages"</code>
MaxTokens   int       <code>json:"max_tokens,omitempty"</code>
Temperature float64   <code>json:"temperature,omitempty"</code>
Stream      bool      <code>json:"stream"</code> // 新增流式控制字段
}</p><p>// 保持其他结构体不变...</p>
                    <div class="aritcle_card">
                        <a class="aritcle_card_img" href="/ai/723">
                            <img src="https://img.php.cn/upload/ai_manual/000/000/000/175679963982777.png" alt="DeepSeek">
                        </a>
                        <div class="aritcle_card_info">
                            <a href="/ai/723">DeepSeek</a>
                            <p>幻方量化公司旗下的开源大模型平台</p>
                            <div class="">
                                <img src="/static/images/card_xiazai.png" alt="DeepSeek">
                                <span>7009</span>
                            </div>
                        </div>
                        <a href="/ai/723" class="aritcle_card_btn">
                            <span>查看详情</span>
                            <img src="/static/images/cardxiayige-3.png" alt="DeepSeek">
                        </a>
                    </div>
                <p>const (
localAPIURL = "<a href="https://www.php.cn/link/d50b2d3afe5ec033d560dd1318b2707b">https://www.php.cn/link/d50b2d3afe5ec033d560dd1318b2707b</a>"
)</p><p>func main() {
fmt.Println("开始")
requestData := DeepSeekRequest{
Model: "deepseek-r1:1.5b",
Messages: []Message{
{
Role:    "user",
Content: "微信公众号 福大大架构师每日一题 是谁",
},
},
MaxTokens:   512000,
Temperature: 1,
Stream:      true, // 启用流式模式
}
requestBody, err := json.Marshal(requestData)
if err != nil {
panic("JSON编码失败: " + err.Error())
}</p><pre class="brush:php;toolbar:false;"><code>// 配置更合理的超时时间
client := &http.Client{
    Transport: &http.Transport{
        DisableKeepAlives: true, // ? 关键设置：禁用连接复用
        MaxIdleConns:      1,
        IdleConnTimeout:   30 * time.Second,
    },
    Timeout: 10 * time.Minute, // 大模型响应时间较长
}

req, err := http.NewRequest("POST", localAPIURL, bytes.NewBuffer(requestBody))
if err != nil {
    panic("创建请求失败: " + err.Error())
}

req.Header.Set("Content-Type", "application/json")
req.Header.Set("Connection", "close") // 显式关闭连接
req.Close = true

resp, err := client.Do(req)
if err != nil {
    panic("请求发送失败: " + err.Error())
}
defer resp.Body.Close()

// 流式响应处理
if resp.StatusCode != http.StatusOK {
    fmt.Printf("请求失败，状态码：%d\n", resp.StatusCode)
    return
}

// 使用 Scanner 逐行读取流式响应
scanner := bufio.NewScanner(resp.Body)
scanner.Buffer(make([]byte, 1024), 10*1024*1024) // 扩大缓冲区
for scanner.Scan() {
    rawData := scanner.Bytes()
    if len(rawData) == 0 {
        continue
    }
    var chunk DeepSeekChunk
    err := json.Unmarshal(rawData[6:], &chunk)
    if err == nil {
        for i := 0; i < len(chunk.Choices); i++ {
            if chunk.Choices[i].Delta.Content != "" {
                fmt.Print(chunk.Choices[i].Delta.Content)
            }
        }
    }
}

if err := scanner.Err(); err != nil {
    fmt.Printf("读取响应时发生错误: %v\n", err)
}</code>