ollama搭建本地ai大模型并应用调用

1 ollama run llama3

1 ollama run qwen2

1 docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui --restart always ghcr.io/open-webui/open-webui:main

1 OLLAMA_HOST= "0.0.0.0:11434"

1 sudo sh -c 'echo "export OLLAMA_HOST=0.0.0.0:11434">>/etc/profile'launchctl setenv OLLAMA_HOST "0.0.0.0:11434"

1 Environment="OLLAMA\_HOST=0.0.0.0"

package main

import (
"bufio"
"bytes"
"encoding/json"
"fmt"
"io/ioutil"
"net/http"
"os"
"strings"
"time"
)

const (
obaseURL = "http://localhost:11434/api"
omodelID = "qwen2:0.5b" // 选择合适的模型
oendpoint = "/chat" //"/chat/completions"
)

// ChatCompletionRequest 定义了请求体的结构
type olChatCompletionRequest struct {
Model string `json:"model"`
Messages []struct {
Role string `json:"role"`
Content string `json:"content"`
} `json:"messages"`
Stream bool `json:"stream"`
//Temperature float32 `json:"temperature"`
}

// ChatCompletionResponse 定义了响应体的结构
type olChatCompletionResponse struct {
//Choices []struct {
Message struct {
Role string `json:"role"`
Content string `json:"content"`
} `json:"message"`
//} `json:"choices"`
}

// sendRequestWithRetry 发送请求并处理可能的429错误
func olsendRequestWithRetry(client *http.Client, requestBody []byte) (*http.Response, error) {
req, err := http.NewRequest("POST", obaseURL+oendpoint, bytes.NewBuffer(requestBody))
if err != nil {
return nil, err
}

req.Header.Set("Content-Type", "application/json")
//req.Header.Set("Authorization", "Bearer "+apiKey)

resp, err := client.Do(req)
if err != nil {
return nil, err
}

if resp.StatusCode == http.StatusTooManyRequests {
retryAfter := resp.Header.Get("Retry-After")
if retryAfter != "" {
duration, _ := time.ParseDuration(retryAfter)
time.Sleep(duration)
} else {
time.Sleep(5 * time.Second) // 默认等待5秒
}
return olsendRequestWithRetry(client, requestBody) // 递归重试
}

return resp, nil
}

func main() {
client := &http.Client{} // 创建一个全局的 HTTP 客户端实例

// 初始化对话历史记录
history := []struct {
Role string `json:"role"`
Content string `json:"content"`
}{
{"system", "你是一位唐代诗人，特别擅长模仿李白的风格。"},
}

// 创建标准输入的扫描器
scanner := bufio.NewScanner(os.Stdin)

for {
fmt.Print("请输入您的问题（或者输入 'exit' 退出）: ")
scanner.Scan()
userInput := strings.TrimSpace(scanner.Text())

// 退出条件
if userInput == "exit" {
fmt.Println("感谢使用，再见！")
break
}

// 添加用户输入到历史记录
history = append(history, struct {
Role string `json:"role"`
Content string `json:"content"`
}{
"user",
userInput,
})

// 创建请求体
requestBody := olChatCompletionRequest{
Model: omodelID,
Messages: history,
Stream: false,
//Temperature: 0.7,
}

// 构建完整的请求体，包含历史消息
requestBody.Messages = append([]struct {
Role string `json:"role"`
Content string `json:"content"`
}{
{
Role: "system",
Content: "你是一位唐代诗人，特别擅长模仿李白的风格。",
},
}, history...)

// 将请求体序列化为 JSON
requestBodyJSON, err := json.Marshal(requestBody)
if err != nil {
fmt.Println("Error marshalling request body:", err)
continue
}
fmt.Println("wocao:" + string(requestBodyJSON))
// 发送请求并处理重试
resp, err := olsendRequestWithRetry(client, requestBodyJSON)
if err != nil {
fmt.Println("Error sending request after retries:", err)
continue
}
defer resp.Body.Close()

// 检查响应状态码
if resp.StatusCode != http.StatusOK {
fmt.Printf("Received non-200 response status code: %d\n", resp.StatusCode)
continue
}

// 读取响应体
responseBody, err := ioutil.ReadAll(resp.Body)
if err != nil {
fmt.Println("Error reading response body:", err)
continue
}
//fmt.Println("0000" + string(responseBody))
// 解析响应体
var completionResponse olChatCompletionResponse
err = json.Unmarshal(responseBody, &completionResponse)
if err != nil {
fmt.Println("Error unmarshalling response body:", err)
continue
}
fmt.Printf("AI 回复: %s\n", completionResponse.Message.Content) // choice.Message.Content
// 将用户的消息添加到历史记录中
history = append(history, struct {
Role string `json:"role"`
Content string `json:"content"`
}{
Role: completionResponse.Message.Role,
Content: completionResponse.Message.Content, // 假设用户的消息是第一个
}) 

}
}