redis缓存替换+pgvector向量替换

.env

@@ -9,4 +9,7 @@ OPENAI_FREQUENCY_PENALTY=0
 TOKENIZER_BASE_URL=http://tokenizer:3002
 
 # frontend 对外端口
-FRONTEND_PORT=3002
+FRONTEND_PORT=1025
+
+# ai-chat-service embedding 配置
+AI_CHAT_EMBEDDING_API_KEY=d51b903546814cc9981d3649a4a899a3.NQOtz3ocRtQwimh9

.gitignore

@@ -1,3 +1,4 @@
 docs
 .workspace.codex
 
+.env

README.md

@@ -33,6 +33,9 @@ docker run -d --name chatgpt-web-backend \
   --openai-presence-penalty 0 \
   --openai-frequency-penalty 0
 
+# ai-chat-backend
+docker build -t ai-chat-backend:1.0.0 .
+
 # chatgpt-web-frontend
 HUSKY=0 pnpm bootstrap
 pnpm dev
@@ -44,43 +47,4 @@ docker build -t tokenizer:1.0.0 .
 
 # keywords-filter
 docker build -t keywords-filter:1.0.0 .
-```
-
-
-## backend
-访问 tokenizer
-```go
-url := fmt.Sprintf("http://127.0.0.1:5000/tokenizer/%s", model)
-// 改成 
-tokenizerBaseURL := os.Getenv("TOKENIZER_BASE_URL")
-if tokenizerBaseURL == "" {
-      tokenizerBaseURL = "http://tokenizer:3002"
-}
-url := fmt.Sprintf("%s/tokenizer/%s", tokenizerBaseURL, model)
-// 直接访问 tokenizer
-```
-
-## frontend
-访问 backend
-```conf
-server {
-  listen 80;
-  server_name localhost;
-
-  root /usr/share/nginx/html;
-  index index.html;
-
-  location / {
-    try_files $uri $uri/ /index.html;
-  }
-
-  location /api/ {
-    proxy_http_version 1.1;
-    proxy_set_header Host $host;
-    proxy_set_header X-Real-IP $remote_addr;
-    proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-    proxy_set_header X-Forwarded-Proto $scheme;
-    proxy_pass http://chatgpt-web-backend:7080/api/;
-  }
-}
 ```

ai-chat-backend/.gitignore

@@ -0,0 +1,3 @@
+dist/
+__pycache__/
+runtime

ai-chat-backend/Dockerfile

@@ -0,0 +1,19 @@
+# 编译阶段
+FROM golang:1.24 AS stage0
+RUN go env -w GOPROXY=https://proxy.golang.com.cn,https://goproxy.cn,direct
+ADD ./ /src/ai-chat-backend
+WORKDIR /src/ai-chat-backend
+RUN CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build -o ai-chat-backend cmd/*.go
+
+FROM alpine:3.18 AS stage1
+ADD ./curl-amd64 /usr/bin/curl
+RUN chmod +x /usr/bin/curl
+LABEL maintainer="nick"
+WORKDIR /app/
+ADD ./dev.config.yaml /app/config.yaml
+ADD ./www /app/www
+COPY --from=stage0 /src/ai-chat-backend/ai-chat-backend ./
+# 指定入口程序
+ENTRYPOINT ["./ai-chat-backend"]
+# 指定容器的启动命令或者入口程序的参数
+CMD ["--config=config.yaml"]

ai-chat-backend/Makefile

@@ -0,0 +1,31 @@
+REGISTRY = arvintian
+PROJECT = chatgpt-web
+BASE_VERSION = v1
+GIT_VERSION = $(shell git rev-parse --short HEAD)
+
+.PHONY: build-local
+build-local:
+	go build -v --ldflags="-w -X main.Version=$(GIT_VERSION)" -o dist/server cmd/*.go
+
+.PHONY: build
+build:
+	mkdir -p dist && docker run --rm -ti -e GOPROXY=https://goproxy.cn,direct -v $(GOPATH):/go -v `pwd`:/app -w /app golang:1.19-alpine \
+	go build -v --ldflags="-w -X main.Version=$(GIT_VERSION)" -o dist/server cmd/*.go
+
+package: build
+	docker build -t $(REGISTRY)/$(PROJECT):$(GIT_VERSION) .
+
+release: package
+	docker tag $(REGISTRY)/$(PROJECT):$(GIT_VERSION) $(REGISTRY)/$(PROJECT):latest
+	docker push $(REGISTRY)/$(PROJECT):$(GIT_VERSION)
+	docker push $(REGISTRY)/$(PROJECT):latest
+
+base:
+	docker build -t $(REGISTRY)/$(PROJECT)-base:$(BASE_VERSION) -f Dockerfile.base .
+
+release-base:
+	docker push $(REGISTRY)/$(PROJECT)-base:$(BASE_VERSION)
+
+clean:
+	rm -rf dist
+	docker images | grep -E "$(REGISTRY)/$(PROJECT)" | grep -v "base"  | awk '{print $$3}' | uniq | xargs -I {} docker rmi --force {}

ai-chat-backend/README.md

@@ -0,0 +1,38 @@
+# ChatGPT-Web
+
+[English](https://github.com/Arvintian/chatgpt-web/blob/main/README_en.md)
+
+使用[Gin](https://github.com/gin-gonic/gin)搭建ChatGPT服务,使用[ChatGPT Web](https://github.com/Chanzhaoyu/chatgpt-web)作为前端
+
+## Usage
+
+[Docker Hub](https://hub.docker.com/repository/docker/arvintian/chatgpt-web/general)
+
+```
+docker run --restart unless-stopped -d --log-opt max-size=50m -p 7080:7080 \
+-e OPENAI_KEY=openai-key \
+-e BASIC_AUTH_USER=user1,user2 \
+-e BASIC_AUTH_PASSWORD=passwd1,passwd2 \
+arvintian/chatgpt-web
+```
+
+- SERVER_PORT 服务端口,默认7080
+- SERVER_HOST 服务监听地址,默认0.0.0.0
+- SOCKS_PROXY socks代理URL,例如socks5://user:password@127.0.0.1:1080
+- BASIC_AUTH_USER 认证用户,多用户英文逗号分隔
+- BASIC_AUTH_PASSWORD 认证用户密码,多用户英文逗号分隔
+- CHAT_SESSION_TTL 会话上下文保持时间,默认30分钟
+- CHAT_MIN_RESPONSE_TOKENS 预留给会话响应的token数,可能导致截断最久的上下文,默认600
+- OPENAI_KEY openai api key,参考OpenAI文档
+- OPENAI_BASE_URL openai api base url,默认https://api.openai.com/v1
+- OPENAI_MODEL 调用模型,默认gpt-3.5-turbo-0301
+- OPENAI_MAX_TOKENS 模型max_tokens参数,参考OpenAI文档
+- OPENAI_TEMPERATURE 模型temperature参数,参考OpenAI文档
+- OPENAI_PRESENCE_PENALTY 模型presence_penalty参数,参考OpenAI文档
+- OPENAI_FREQUENCY_PENALTY 模型frequency_penalty参数,参考OpenAI文档
+
+更详细参数参考: [启动函数](https://github.com/Arvintian/chatgpt-web/blob/main/cmd/main.go#L21)
+
+Tips: 
+- 模型float32参数使用(整型/100)设置,例如: temperature设置0.8,需要设置为80
+- 内置支持了对OPENAI_BASE_URL的正向代理,可以作为OpenAI接口的代理服务器

ai-chat-backend/README_en.md

@@ -0,0 +1,34 @@
+Built ChatGPT service using [Gin](https://github.com/gin-gonic/gin) and [ChatGPT Web](https://github.com/Chanzhaoyu/chatgpt-web) as the front-end. 
+
+## Usage
+
+[Docker Hub](https://hub.docker.com/repository/docker/arvintian/chatgpt-web/general)
+
+```
+docker run --restart unless-stopped -d --log-opt max-size=50m -p 7080:7080 \
+-e OPENAI_KEY=openai-key \
+-e BASIC_AUTH_USER=user1,user2 \
+-e BASIC_AUTH_PASSWORD=passwd1,passwd2 \
+arvintian/chatgpt-web
+```
+
+- SERVER_PORT: Server port, default 7080.
+- SERVER_HOST: Server listen address, default 0.0.0.0.
+- SOCKS_PROXY: Socks proxy URL, for example socks5://user:password@127.0.0.1:1080.
+- BASIC_AUTH_USER: Authentication user, multiple users separated by English commas.
+- BASIC_AUTH_PASSWORD: Authentication user passwords, multiple users separated by English commas.
+- CHAT_SESSION_TTL: Session context retention time, default 30 minutes.
+- CHAT_MIN_RESPONSE_TOKENS: Tokens reserved for session response, may lead to truncation of the longest context, default 600.
+- OPENAI_KEY: OpenAI API key, refer to OpenAI documentation.
+- OPENAI_BASE_URL: OpenAI API base URL, default https://api.openai.com/v1.
+- OPENAI_MODEL: Model called, default gpt-3.5-turbo-0301.
+- OPENAI_MAX_TOKENS: Model max_tokens parameter, refer to OpenAI documentation.
+- OPENAI_TEMPERATURE: Model temperature parameter, refer to OpenAI documentation.
+- OPENAI_PRESENCE_PENALTY: Model presence_penalty parameter, refer to OpenAI documentation.
+- OPENAI_FREQUENCY_PENALTY: Model frequency_penalty parameter, refer to OpenAI documentation.
+
+For more detailed parameters, please refer to the [start function](https://github.com/Arvintian/chatgpt-web/blob/main/cmd/main.go#L21).
+
+Tips: 
+- Use (integer/100) to set the float32 model parameters. For example, if temperature is set to 0.8, it needs to be set to 80.
+- The built-in support for a forward proxy of OPENAI_BASE_URL enables it to function as a proxy server for the OpenAI API.

ai-chat-backend/cmd/main.go

@@ -0,0 +1,128 @@
+package main
+
+import (
+	"ai-chat-backend/pkg/config"
+	"ai-chat-backend/pkg/log"
+	"context"
+	"flag"
+	"fmt"
+	"net/http"
+	"os"
+	"os/signal"
+	"strings"
+	"time"
+
+	"ai-chat-backend/pkg/controllers"
+	"ai-chat-backend/pkg/middlewares"
+	"github.com/gin-gonic/gin"
+)
+
+type ChatGPTWebServer struct {
+	config *config.Config
+	log    log.ILogger
+}
+
+func (r *ChatGPTWebServer) Run(ctx context.Context) error {
+	go r.httpServer(ctx)
+	return nil
+}
+
+func (r *ChatGPTWebServer) httpServer(ctx context.Context) {
+	chatService, err := controllers.NewChatService(r.config, r.log)
+	if err != nil {
+		r.log.Fatal(err)
+	}
+
+	addr := fmt.Sprintf("%s:%d", r.config.Http.IP, r.config.Http.Port)
+	r.log.InfoF("ChatGPT Web Server on: %s", addr)
+	server := &http.Server{
+		Addr: addr,
+	}
+	gin.SetMode(gin.ReleaseMode)
+	entry := gin.Default()
+	entry.Use(middlewares.Cors())
+	chat := entry.Group("/api")
+	if strings.TrimSpace(r.config.BasicAuthUser) != "" {
+		accounts := gin.Accounts{}
+		users := strings.Split(r.config.BasicAuthUser, ",")
+		passwords := strings.Split(r.config.BasicAuthPassword, ",")
+		if len(users) != len(passwords) {
+			r.log.Fatal("basic auth setting error")
+		}
+		for i := 0; i < len(users); i++ {
+			accounts[strings.TrimSpace(users[i])] = strings.TrimSpace(passwords[i])
+		}
+		chat.POST("/chat-process", gin.BasicAuth(accounts), middlewares.RateLimitMiddleware(1, 2), chatService.ChatProcess)
+	} else {
+		chat.POST("/chat-process", middlewares.RateLimitMiddleware(1, 2), chatService.ChatProcess)
+	}
+	chat.POST("/config", func(ctx *gin.Context) {
+		ctx.JSON(200, gin.H{
+			"status": "Success",
+			"data": map[string]string{
+				"apiModel":   "ChatGPTAPI",
+				"socksProxy": "",
+			},
+		})
+	})
+	chat.POST("/session", func(ctx *gin.Context) {
+		ctx.JSON(200, gin.H{
+			"status":  "Success",
+			"message": "",
+			"data": gin.H{
+				"auth": false,
+			},
+		})
+	})
+	chat.GET("/health", func(c *gin.Context) {})
+	fs := http.FileServer(http.Dir(r.config.FrontendPath))
+	entry.NoRoute(func(ctx *gin.Context) {
+		fs.ServeHTTP(ctx.Writer, ctx.Request)
+	})
+	entry.GET("/", func(ctx *gin.Context) {
+		http.ServeFile(ctx.Writer, ctx.Request, r.config.FrontendPath+"/index.html")
+	})
+	server.Handler = entry
+	go func(ctx context.Context) {
+		<-ctx.Done()
+		ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+		defer cancel()
+		if err := server.Shutdown(ctx); err != nil {
+			r.log.InfoF("Server shutdown with error %v", err)
+		}
+	}(ctx)
+	if err := server.ListenAndServe(); err != http.ErrServerClosed {
+		r.log.FatalF("Server listen and serve error %v", err)
+	}
+}
+
+var (
+	configFile = flag.String("config", "dev.config.yaml", "")
+)
+
+func main() {
+	flag.Parse()
+	ctx, stop := signal.NotifyContext(context.Background(), os.Kill, os.Interrupt)
+	defer stop()
+
+	config.InitConfig(*configFile)
+	cnf := config.GetConfig()
+	fmt.Printf("%+v\n", cnf)
+
+	//初始化日志
+	log.SetLevel(cnf.Log.Level)
+	log.SetOutput(log.GetRotateWriter(cnf.Log.LogPath))
+	log.SetPrintCaller(true)
+
+	logger := log.NewLogger()
+	logger.SetLevel(cnf.Log.Level)
+	logger.SetOutput(log.GetRotateWriter(cnf.Log.LogPath))
+	logger.SetPrintCaller(true)
+
+	webServer := &ChatGPTWebServer{
+		config: cnf,
+		log:    logger,
+	}
+	webServer.Run(ctx)
+	<-ctx.Done()
+}

ai-chat-backend/dev.config.yaml

@@ -0,0 +1,37 @@
+http:
+  ip: 0.0.0.0
+  port: 7080
+frontend_path: "www"
+log:
+  level: "info"
+  logPath: "runtime/logs/app.log"
+chat:
+  # 使用的训练模型
+  model: "kimi-k2.5"
+  # 单次请求的上下文总长度,包括：请求消息+响应消息
+  max_tokens: 4096
+  # 表示语言模型输出的随机性和创造性
+  # 取值范围 0 ~ 1，值越大随机性越高
+  temperature: 1.0
+  # 用于生成文本时控制选词的随机程度
+  # 即下一个预测单词考虑的概率范围
+  # 取值范围0 ~ 1
+  top_p: 1.0
+  # 存在惩罚，用于生成文本时控制重复使用单词的程度
+  # 取值范围 0 ~ 1 ，0表示不惩罚，1表示禁止重复
+  presence_penalty: 0
+  # 用于控制模型生成回复时重复单词出现的频率
+  # 取值范围 0~1，值越大表示回复时会更注重避免使用已经出现的单词
+  frequency_penalty: 0
+  # AI助手特征描述
+  bot_desc: "你是一个AI助手，我需要你模拟一名资深的软件工程师来回答我的问题"
+  # 单次请求，保留的响应tokens数量
+  min_response_tokens: 600
+  # 上下文缓存时长，单位s
+  context_ttl: 1800
+  # 上下文消息条数
+  context_len: 4
+dependOn:
+  ai-chat-service:
+    address: "localhost:50055"
+    accessToken: "me256487ang1chubdpdialoud22sev1ozhoguumyqca"

ai-chat-backend/go.mod

@@ -0,0 +1,60 @@
+module ai-chat-backend
+
+go 1.21
+
+toolchain go1.24.2
+
+require (
+	github.com/gin-gonic/gin v1.9.0
+	github.com/google/uuid v1.6.0
+	github.com/sashabaranov/go-openai v1.4.2
+	github.com/sirupsen/logrus v1.9.3
+	github.com/spf13/viper v1.19.0
+	golang.org/x/time v0.5.0
+	google.golang.org/grpc v1.65.0
+	google.golang.org/protobuf v1.34.1
+	gopkg.in/natefinch/lumberjack.v2 v2.2.1
+	k8s.io/klog/v2 v2.60.1
+)
+
+require (
+	github.com/bytedance/sonic v1.8.0 // indirect
+	github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 // indirect
+	github.com/fsnotify/fsnotify v1.7.0 // indirect
+	github.com/gin-contrib/sse v0.1.0 // indirect
+	github.com/go-logr/logr v1.4.1 // indirect
+	github.com/go-playground/locales v0.14.1 // indirect
+	github.com/go-playground/universal-translator v0.18.1 // indirect
+	github.com/go-playground/validator/v10 v10.11.2 // indirect
+	github.com/goccy/go-json v0.10.0 // indirect
+	github.com/hashicorp/hcl v1.0.0 // indirect
+	github.com/json-iterator/go v1.1.12 // indirect
+	github.com/klauspost/cpuid/v2 v2.0.9 // indirect
+	github.com/leodido/go-urn v1.2.1 // indirect
+	github.com/magiconair/properties v1.8.7 // indirect
+	github.com/mattn/go-isatty v0.0.17 // indirect
+	github.com/mitchellh/mapstructure v1.5.0 // indirect
+	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
+	github.com/modern-go/reflect2 v1.0.2 // indirect
+	github.com/pelletier/go-toml/v2 v2.2.2 // indirect
+	github.com/sagikazarmark/locafero v0.4.0 // indirect
+	github.com/sagikazarmark/slog-shim v0.1.0 // indirect
+	github.com/sourcegraph/conc v0.3.0 // indirect
+	github.com/spf13/afero v1.11.0 // indirect
+	github.com/spf13/cast v1.6.0 // indirect
+	github.com/spf13/pflag v1.0.5 // indirect
+	github.com/subosito/gotenv v1.6.0 // indirect
+	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
+	github.com/ugorji/go/codec v1.2.9 // indirect
+	go.uber.org/atomic v1.9.0 // indirect
+	go.uber.org/multierr v1.9.0 // indirect
+	golang.org/x/arch v0.0.0-20210923205945-b76863e36670 // indirect
+	golang.org/x/crypto v0.23.0 // indirect
+	golang.org/x/exp v0.0.0-20230905200255-921286631fa9 // indirect
+	golang.org/x/net v0.25.0 // indirect
+	golang.org/x/sys v0.20.0 // indirect
+	golang.org/x/text v0.15.0 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20240528184218-531527333157 // indirect
+	gopkg.in/ini.v1 v1.67.0 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
+)

ai-chat-backend/go.sum

@@ -0,0 +1,142 @@
+github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=
+github.com/bytedance/sonic v1.8.0 h1:ea0Xadu+sHlu7x5O3gKhRpQ1IKiMrSiHttPF0ybECuA=
+github.com/bytedance/sonic v1.8.0/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZXU064P/U=
+github.com/chenzhuoyu/base64x v0.0.0-20211019084208-fb5309c8db06/go.mod h1:DH46F32mSOjUmXrMHnKwZdA8wcEefY7UVqBKYGjpdQY=
+github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 h1:qSGYFH7+jGhDF8vLC+iwCD4WpbV1EBDSzWkJODFLams=
+github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311/go.mod h1:b583jCggY9gE99b6G5LEC39OIiVsWj+R97kbl5odCEk=
+github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
+github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/frankban/quicktest v1.14.6 h1:7Xjx+VpznH+oBnejlPUj8oUpdxnVs4f8XU8WnHkI4W8=
+github.com/frankban/quicktest v1.14.6/go.mod h1:4ptaffx2x8+WTWXmUCuVU6aPUX1/Mz7zb5vbUoiM6w0=
+github.com/fsnotify/fsnotify v1.7.0 h1:8JEhPFa5W2WU7YfeZzPNqzMP6Lwt7L2715Ggo0nosvA=
+github.com/fsnotify/fsnotify v1.7.0/go.mod h1:40Bi/Hjc2AVfZrqy+aj+yEI+/bRxZnMJyTJwOpGvigM=
+github.com/gin-contrib/sse v0.1.0 h1:Y/yl/+YNO8GZSjAhjMsSuLt29uWRFHdHYUb5lYOV9qE=
+github.com/gin-contrib/sse v0.1.0/go.mod h1:RHrZQHXnP2xjPF+u1gW/2HnVO7nvIa9PG3Gm+fLHvGI=
+github.com/gin-gonic/gin v1.9.0 h1:OjyFBKICoexlu99ctXNR2gg+c5pKrKMuyjgARg9qeY8=
+github.com/gin-gonic/gin v1.9.0/go.mod h1:W1Me9+hsUSyj3CePGrd1/QrKJMSJ1Tu/0hFEH89961k=
+github.com/go-logr/logr v1.2.0/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
+github.com/go-logr/logr v1.4.1 h1:pKouT5E8xu9zeFC39JXRDukb6JFQPXM5p5I91188VAQ=
+github.com/go-logr/logr v1.4.1/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
+github.com/go-playground/assert/v2 v2.2.0 h1:JvknZsQTYeFEAhQwI4qEt9cyV5ONwRHC+lYKSsYSR8s=
+github.com/go-playground/assert/v2 v2.2.0/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
+github.com/go-playground/locales v0.14.1 h1:EWaQ/wswjilfKLTECiXz7Rh+3BjFhfDFKv/oXslEjJA=
+github.com/go-playground/locales v0.14.1/go.mod h1:hxrqLVvrK65+Rwrd5Fc6F2O76J/NuW9t0sjnWqG1slY=
+github.com/go-playground/universal-translator v0.18.1 h1:Bcnm0ZwsGyWbCzImXv+pAJnYK9S473LQFuzCbDbfSFY=
+github.com/go-playground/universal-translator v0.18.1/go.mod h1:xekY+UJKNuX9WP91TpwSH2VMlDf28Uj24BCp08ZFTUY=
+github.com/go-playground/validator/v10 v10.11.2 h1:q3SHpufmypg+erIExEKUmsgmhDTyhcJ38oeKGACXohU=
+github.com/go-playground/validator/v10 v10.11.2/go.mod h1:NieE624vt4SCTJtD87arVLvdmjPAeV8BQlHtMnw9D7s=
+github.com/goccy/go-json v0.10.0 h1:mXKd9Qw4NuzShiRlOXKews24ufknHO7gx30lsDyokKA=
+github.com/goccy/go-json v0.10.0/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
+github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
+github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
+github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
+github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
+github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/hashicorp/hcl v1.0.0 h1:0Anlzjpi4vEasTeNFn2mLJgTSwt0+6sfsiTG8qcWGx4=
+github.com/hashicorp/hcl v1.0.0/go.mod h1:E5yfLk+7swimpb2L/Alb/PJmXilQ/rhwaUYs4T20WEQ=
+github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
+github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
+github.com/klauspost/cpuid/v2 v2.0.9 h1:lgaqFMSdTdQYdZ04uHyN2d/eKdOMyi2YLSvlQIBFYa4=
+github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
+github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
+github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
+github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
+github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
+github.com/leodido/go-urn v1.2.1 h1:BqpAaACuzVSgi/VLzGZIobT2z4v53pjosyNd9Yv6n/w=
+github.com/leodido/go-urn v1.2.1/go.mod h1:zt4jvISO2HfUBqxjfIshjdMTYS56ZS/qv49ictyFfxY=
+github.com/magiconair/properties v1.8.7 h1:IeQXZAiQcpL9mgcAe1Nu6cX9LLw6ExEHKjN0VQdvPDY=
+github.com/magiconair/properties v1.8.7/go.mod h1:Dhd985XPs7jluiymwWYZ0G4Z61jb3vdS329zhj2hYo0=
+github.com/mattn/go-isatty v0.0.17 h1:BTarxUcIeDqL27Mc+vyvdWYSL28zpIhv3RoTdsLMPng=
+github.com/mattn/go-isatty v0.0.17/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
+github.com/mitchellh/mapstructure v1.5.0 h1:jeMsZIYE/09sWLaz43PL7Gy6RuMjD2eJVyuac5Z2hdY=
+github.com/mitchellh/mapstructure v1.5.0/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=
+github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
+github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg=
+github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
+github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
+github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
+github.com/pelletier/go-toml/v2 v2.2.2 h1:aYUidT7k73Pcl9nb2gScu7NSrKCSHIDE89b3+6Wq+LM=
+github.com/pelletier/go-toml/v2 v2.2.2/go.mod h1:1t835xjRzz80PqgE6HHgN2JOsmgYu/h4qDAS4n929Rs=
+github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
+github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/rogpeppe/go-internal v1.9.0 h1:73kH8U+JUqXU8lRuOHeVHaa/SZPifC7BkcraZVejAe8=
+github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs=
+github.com/sagikazarmark/locafero v0.4.0 h1:HApY1R9zGo4DBgr7dqsTH/JJxLTTsOt7u6keLGt6kNQ=
+github.com/sagikazarmark/locafero v0.4.0/go.mod h1:Pe1W6UlPYUk/+wc/6KFhbORCfqzgYEpgQ3O5fPuL3H4=
+github.com/sagikazarmark/slog-shim v0.1.0 h1:diDBnUNK9N/354PgrxMywXnAwEr1QZcOr6gto+ugjYE=
+github.com/sagikazarmark/slog-shim v0.1.0/go.mod h1:SrcSrq8aKtyuqEI1uvTDTK1arOWRIczQRv+GVI1AkeQ=
+github.com/sashabaranov/go-openai v1.4.2 h1:IhacPY7O+ljlBoZRQe9VpsLNm0b4PHa6fOBGA9O4vfc=
+github.com/sashabaranov/go-openai v1.4.2/go.mod h1:lj5b/K+zjTSFxVLijLSTDZuP7adOgerWeFyZLUhAKRg=
+github.com/sirupsen/logrus v1.9.3 h1:dueUQJ1C2q9oE3F7wvmSGAaVtTmUizReu6fjN8uqzbQ=
+github.com/sirupsen/logrus v1.9.3/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ=
+github.com/sourcegraph/conc v0.3.0 h1:OQTbbt6P72L20UqAkXXuLOj79LfEanQ+YQFNpLA9ySo=
+github.com/sourcegraph/conc v0.3.0/go.mod h1:Sdozi7LEKbFPqYX2/J+iBAM6HpqSLTASQIKqDmF7Mt0=
+github.com/spf13/afero v1.11.0 h1:WJQKhtpdm3v2IzqG8VMqrr6Rf3UYpEF239Jy9wNepM8=
+github.com/spf13/afero v1.11.0/go.mod h1:GH9Y3pIexgf1MTIWtNGyogA5MwRIDXGUr+hbWNoBjkY=
+github.com/spf13/cast v1.6.0 h1:GEiTHELF+vaR5dhz3VqZfFSzZjYbgeKDpBxQVS4GYJ0=
+github.com/spf13/cast v1.6.0/go.mod h1:ancEpBxwJDODSW/UG4rDrAqiKolqNNh2DX3mk86cAdo=
+github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
+github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
+github.com/spf13/viper v1.19.0 h1:RWq5SEjt8o25SROyN3z2OrDB9l7RPd3lwTWU8EcEdcI=
+github.com/spf13/viper v1.19.0/go.mod h1:GQUN9bilAbhU/jgc1bKs99f/suXKeUMct8Adx5+Ntkg=
+github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
+github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
+github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
+github.com/stretchr/objx v0.5.2/go.mod h1:FRsXN1f5AsAjCGJKqEizvkpNtU+EGNCLh3NxZ/8L+MA=
+github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
+github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
+github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
+github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
+github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
+github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
+github.com/subosito/gotenv v1.6.0 h1:9NlTDc1FTs4qu0DDq7AEtTPNw6SVm7uBMsUCUjABIf8=
+github.com/subosito/gotenv v1.6.0/go.mod h1:Dk4QP5c2W3ibzajGcXpNraDfq2IrhjMIvMSWPKKo0FU=
+github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS4MhqMhdFk5YI=
+github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08=
+github.com/ugorji/go/codec v1.2.9 h1:rmenucSohSTiyL09Y+l2OCk+FrMxGMzho2+tjr5ticU=
+github.com/ugorji/go/codec v1.2.9/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
+go.uber.org/atomic v1.9.0 h1:ECmE8Bn/WFTYwEW/bpKD3M8VtR/zQVbavAoalC1PYyE=
+go.uber.org/atomic v1.9.0/go.mod h1:fEN4uk6kAWBTFdckzkM89CLk9XfWZrxpCo0nPH17wJc=
+go.uber.org/multierr v1.9.0 h1:7fIwc/ZtS0q++VgcfqFDxSBZVv/Xo49/SYnDFupUwlI=
+go.uber.org/multierr v1.9.0/go.mod h1:X2jQV1h+kxSjClGpnseKVIxpmcjrj7MNnI0bnlfKTVQ=
+golang.org/x/arch v0.0.0-20210923205945-b76863e36670 h1:18EFjUmQOcUvxNYSkA6jO9VAiXCnxFY6NyDX0bHDmkU=
+golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
+golang.org/x/crypto v0.23.0 h1:dIJU/v2J8Mdglj/8rJ6UUOM3Zc9zLZxVZwwxMooUSAI=
+golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=
+golang.org/x/exp v0.0.0-20230905200255-921286631fa9 h1:GoHiUyI/Tp2nVkLI2mCxVkOjsbSXD66ic0XW0js0R9g=
+golang.org/x/exp v0.0.0-20230905200255-921286631fa9/go.mod h1:S2oDrQGGwySpoQPVqRShND87VCbxmc6bL1Yd2oYrm6k=
+golang.org/x/net v0.25.0 h1:d/OCCoBEUq33pjydKrGQhw7IlUPI2Oylr+8qLx49kac=
+golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
+golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.20.0 h1:Od9JTbYCk261bKm4M/mw7AklTlFYIa0bIp9BgSm1S8Y=
+golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/text v0.15.0 h1:h1V/4gjBv8v9cjcR6+AR5+/cIYK5N/WAgiv4xlsEtAk=
+golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/time v0.5.0 h1:o7cqy6amK/52YcAKIPlM3a+Fpj35zvRj2TP+e1xFSfk=
+golang.org/x/time v0.5.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20240528184218-531527333157 h1:Zy9XzmMEflZ/MAaA7vNcoebnRAld7FsPW1EeBB7V0m8=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20240528184218-531527333157/go.mod h1:EfXuqaE1J41VCDicxHzUDm+8rk+7ZdXzHV0IhO/I6s0=
+google.golang.org/grpc v1.65.0 h1:bs/cUb4lp1G5iImFFd3u5ixQzweKizoZJAwBNLR42lc=
+google.golang.org/grpc v1.65.0/go.mod h1:WgYC2ypjlB0EiQi6wdKixMqukr6lBc0Vo+oOgjrM5ZQ=
+google.golang.org/protobuf v1.34.1 h1:9ddQBjfCyZPOHPUiPxpYESBLc+T8P3E+Vo4IbKZgFWg=
+google.golang.org/protobuf v1.34.1/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
+gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
+gopkg.in/ini.v1 v1.67.0 h1:Dgnx+6+nfE+IfzjUEISNeydPJh9AXNNsWbGP9KzCsOA=
+gopkg.in/ini.v1 v1.67.0/go.mod h1:pNLf8WUiyNEtQjuu5G5vTm06TEv9tsIgeAvK8hOrP4k=
+gopkg.in/natefinch/lumberjack.v2 v2.2.1 h1:bBRl1b0OH9s/DuPhuXpNl+VtCaJXFZ5/uEFST95x9zc=
+gopkg.in/natefinch/lumberjack.v2 v2.2.1/go.mod h1:YD8tP3GAjkrDg1eZH7EGmyESg/lsYskCTPBJVb9jqSc=
+gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+k8s.io/klog/v2 v2.60.1 h1:VW25q3bZx9uE3vvdL6M8ezOX79vA2Aq1nEWLqNQclHc=
+k8s.io/klog/v2 v2.60.1/go.mod h1:y1WjHnz7Dj687irZUWR/WLkLc5N1YHtjLdmgWjndZn0=
+rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=

ai-chat-backend/pkg/config/config.go

@@ -0,0 +1,185 @@
+package config
+
+import (
+	"bufio"
+	"github.com/spf13/viper"
+	"log"
+	"os"
+	"path/filepath"
+	"strconv"
+	"strings"
+)
+
+type Config struct {
+	Http struct {
+		IP   string
+		Port int
+	}
+	BasicAuthUser     string `mapstructure:"basic_auth_user"`
+	BasicAuthPassword string `mapstructure:"basic_auth_password"`
+	FrontendPath      string `mapstructure:"frontend_path"`
+	Log struct {
+		Level   string
+		LogPath string `mapstructure:"logPath"`
+	} `mapstructure:"log"`
+	Chat struct {
+		Model             string  `mapstructure:"model"`
+		MaxTokens         int     `mapstructure:"max_tokens"`
+		Temperature       float32 `mapstructure:"temperature"`
+		TopP              float32 `mapstructure:"top_p"`
+		PresencePenalty   float32 `mapstructure:"presence_penalty"`
+		FrequencyPenalty  float32 `mapstructure:"frequency_penalty"`
+		BotDesc           string  `mapstructure:"bot_desc"`
+		MinResponseTokens int     `mapstructure:"min_response_tokens"`
+		ContextTTL        int     `mapstructure:"context_ttl"`
+		ContextLen        int     `mapstructure:"context_len"`
+	}
+	DependOn struct {
+		AiChatService struct {
+			Address     string
+			AccessToken string
+		} `mapstructure:"ai-chat-service"`
+	}
+}
+
+var conf *Config
+
+func InitConfig(filePath string, typ ...string) {
+	loadProjectDotEnv(filePath)
+	v := viper.New()
+	v.SetConfigFile(filePath)
+	if len(typ) > 0 {
+		v.SetConfigType(typ[0])
+	}
+	err := v.ReadInConfig()
+	if err != nil {
+		log.Fatal(err)
+	}
+	conf = &Config{}
+	err = v.Unmarshal(conf)
+	if err != nil {
+		log.Fatal(err)
+	}
+	normalizeConfig(conf)
+	overrideConfigFromEnv(conf)
+
+}
+
+func GetConfig() *Config {
+	return conf
+}
+
+func normalizeConfig(conf *Config) {
+	if conf.Http.IP == "" {
+		conf.Http.IP = "0.0.0.0"
+	}
+	if conf.Http.Port == 0 {
+		conf.Http.Port = 7080
+	}
+	if conf.FrontendPath == "" {
+		conf.FrontendPath = "www"
+	}
+	if conf.Chat.Model == "" {
+		conf.Chat.Model = "kimi-k2.5"
+	}
+	if conf.Chat.MaxTokens == 0 {
+		conf.Chat.MaxTokens = 4096
+	}
+	if conf.Chat.Temperature == 0 {
+		conf.Chat.Temperature = 1.0
+	}
+	if conf.Chat.TopP == 0 {
+		conf.Chat.TopP = 1.0
+	}
+	if conf.Chat.MinResponseTokens == 0 {
+		conf.Chat.MinResponseTokens = 600
+	}
+	if conf.DependOn.AiChatService.Address == "" {
+		conf.DependOn.AiChatService.Address = "localhost:50055"
+	}
+}
+
+func overrideConfigFromEnv(conf *Config) {
+	overrideString(&conf.Http.IP, os.Getenv("SERVER_HOST"))
+	overrideInt(&conf.Http.Port, os.Getenv("SERVER_PORT"))
+	overrideString(&conf.BasicAuthUser, os.Getenv("BASIC_AUTH_USER"))
+	overrideString(&conf.BasicAuthPassword, os.Getenv("BASIC_AUTH_PASSWORD"))
+	overrideString(&conf.FrontendPath, os.Getenv("FRONTEND_PATH"))
+	overrideString(&conf.Chat.Model, os.Getenv("OPENAI_MODEL"))
+	overrideInt(&conf.Chat.MaxTokens, os.Getenv("OPENAI_MAX_TOKENS"))
+	overrideScaledFloat32(&conf.Chat.Temperature, os.Getenv("OPENAI_TEMPERATURE"))
+	overrideScaledFloat32(&conf.Chat.PresencePenalty, os.Getenv("OPENAI_PRESENCE_PENALTY"))
+	overrideScaledFloat32(&conf.Chat.FrequencyPenalty, os.Getenv("OPENAI_FREQUENCY_PENALTY"))
+	overrideInt(&conf.Chat.MinResponseTokens, os.Getenv("CHAT_MIN_RESPONSE_TOKENS"))
+	overrideString(&conf.DependOn.AiChatService.Address, firstNonEmpty(
+		os.Getenv("AI_CHAT_SERVICE_ADDRESS"),
+		os.Getenv("AI_CHAT_SERVICE_ADDR"),
+	))
+	overrideString(&conf.DependOn.AiChatService.AccessToken, os.Getenv("AI_CHAT_SERVICE_ACCESS_TOKEN"))
+}
+
+func loadProjectDotEnv(configFilePath string) {
+	projectRoot := filepath.Dir(filepath.Dir(configFilePath))
+	envPath := filepath.Join(projectRoot, ".env")
+	file, err := os.Open(envPath)
+	if err != nil {
+		return
+	}
+	defer file.Close()
+
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		line := strings.TrimSpace(scanner.Text())
+		if line == "" || strings.HasPrefix(line, "#") {
+			continue
+		}
+		key, value, ok := strings.Cut(line, "=")
+		if !ok {
+			continue
+		}
+		key = strings.TrimSpace(key)
+		value = strings.TrimSpace(value)
+		if key == "" {
+			continue
+		}
+		if _, exists := os.LookupEnv(key); exists {
+			continue
+		}
+		_ = os.Setenv(key, value)
+	}
+}
+
+func firstNonEmpty(values ...string) string {
+	for _, value := range values {
+		if strings.TrimSpace(value) != "" {
+			return value
+		}
+	}
+	return ""
+}
+
+func overrideString(target *string, value string) {
+	if strings.TrimSpace(value) != "" {
+		*target = strings.TrimSpace(value)
+	}
+}
+
+func overrideInt(target *int, value string) {
+	value = strings.TrimSpace(value)
+	if value == "" {
+		return
+	}
+	if parsed, err := strconv.Atoi(value); err == nil {
+		*target = parsed
+	}
+}
+
+func overrideScaledFloat32(target *float32, value string) {
+	value = strings.TrimSpace(value)
+	if value == "" {
+		return
+	}
+	if parsed, err := strconv.ParseFloat(value, 32); err == nil {
+		*target = float32(parsed / 100.0)
+	}
+}

ai-chat-backend/pkg/controllers/chat.go

@@ -0,0 +1,192 @@
+package controllers
+
+import (
+	"ai-chat-backend/pkg/config"
+	"ai-chat-backend/pkg/log"
+	"ai-chat-backend/services"
+	ai_chat_service "ai-chat-backend/services/ai-chat-service"
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"strings"
+	"time"
+
+	ai_chat_service_proto "ai-chat-backend/services/ai-chat-service/proto"
+	"github.com/gin-gonic/gin"
+	"github.com/google/uuid"
+	openai "github.com/sashabaranov/go-openai"
+	"k8s.io/klog/v2"
+)
+
+type ChatService struct {
+	config *config.Config
+	log    log.ILogger
+}
+
+type ChatCompletionParams struct {
+	Model                 string        `json:"model"`
+	MaxTokens             int           `json:"max_tokens,omitempty"`
+	Temperature           float32       `json:"temperature,omitempty"`
+	PresencePenalty       float32       `json:"presence_penalty,omitempty"`
+	FrequencyPenalty      float32       `json:"frequency_penalty,omitempty"`
+	ChatSessionTTL        time.Duration `json:"chat_session_ttl"`
+	ChatMinResponseTokens int           `json:"chat_min_response_tokens"`
+}
+
+type ChatMessageRequest struct {
+	Prompt  string                    `json:"prompt"`
+	Options ChatMessageRequestOptions `json:"options"`
+}
+
+type ChatMessageRequestOptions struct {
+	Name            string `json:"name"`
+	ParentMessageId string `json:"parentMessageId"`
+}
+
+type ChatMessage struct {
+	ID              string                                              `json:"id"`
+	Text            string                                              `json:"text"`
+	Role            string                                              `json:"role"`
+	Name            string                                              `json:"name"`
+	Delta           string                                              `json:"delta"`
+	Detail          *ai_chat_service_proto.ChatCompletionStreamResponse `json:"detail"`
+	TokenCount      int                                                 `json:"tokenCount"`
+	ParentMessageId string                                              `json:"parentMessageId"`
+}
+
+func NewChatService(config *config.Config, log log.ILogger) (*ChatService, error) {
+	return &ChatService{
+		config: config,
+		log:    log,
+	}, nil
+}
+
+func (chat *ChatService) ChatProcess(ctx *gin.Context) {
+	payload := ChatMessageRequest{}
+	if err := ctx.BindJSON(&payload); err != nil {
+		klog.Error(err)
+		ctx.JSON(200, gin.H{
+			"status":  "Fail",
+			"message": fmt.Sprintf("%v", err),
+			"data":    nil,
+		})
+		return
+	}
+
+	messageID := uuid.New().String()
+
+	result := ChatMessage{
+		ID:              uuid.New().String(),
+		Role:            openai.ChatMessageRoleAssistant,
+		Text:            "",
+		ParentMessageId: messageID,
+	}
+
+	aiChatServicePool := ai_chat_service.GetAiChatServiceClientPool()
+	conn := aiChatServicePool.Get()
+	defer aiChatServicePool.Put(conn)
+	ctx1 := services.AppendBearerTokenToContext(context.Background(), chat.config.DependOn.AiChatService.AccessToken)
+	in := &ai_chat_service_proto.ChatCompletionRequest{
+		Id:            messageID,
+		Message:       payload.Prompt,
+		Pid:           payload.Options.ParentMessageId,
+		EnableContext: false,
+		ChatParam: &ai_chat_service_proto.ChatParam{
+			Model:             chat.config.Chat.Model,
+			MaxTokens:         int32(chat.config.Chat.MaxTokens),
+			Temperature:       chat.config.Chat.Temperature,
+			TopP:              chat.topP(),
+			PresencePenalty:   chat.config.Chat.PresencePenalty,
+			FrequencyPenalty:  chat.config.Chat.FrequencyPenalty,
+			BotDesc:           chat.config.Chat.BotDesc,
+			ContextTTL:        int32(chat.config.Chat.ContextTTL),
+			ContextLen:        int32(chat.config.Chat.ContextLen),
+			MinResponseTokens: int32(chat.config.Chat.MinResponseTokens),
+		},
+	}
+	if in.Pid != "" {
+		in.EnableContext = true
+	}
+
+	aiChatServiceClient := ai_chat_service_proto.NewChatClient(conn)
+	stream, err := aiChatServiceClient.ChatCompletionStream(ctx1, in)
+	if err != nil {
+		chat.log.Error(err)
+		ctx.JSON(200, gin.H{
+			"status":  "Fail",
+			"message": fmt.Sprintf("%v", err),
+			"data":    nil,
+		})
+		return
+	}
+	defer stream.CloseSend()
+
+	firstChunk := true
+	ctx.Header("Content-type", "application/octet-stream")
+	for {
+		rsp, err := stream.Recv()
+		if errors.Is(err, io.EOF) {
+			return
+		}
+
+		if err != nil {
+			klog.Error(err)
+			ctx.JSON(200, gin.H{
+				"status":  "Fail",
+				"message": fmt.Sprintf("OpenAI Event Error %v", err),
+				"data":    nil,
+			})
+			return
+		}
+
+		if rsp.Id != "" {
+			result.ID = rsp.Id
+		}
+
+		if len(rsp.Choices) > 0 {
+			content := rsp.Choices[0].Delta.Content
+			result.Delta = content
+			if len(content) > 0 {
+				result.Text += content
+			}
+			result.Detail = rsp
+		}
+
+		bts, err := json.Marshal(result)
+		if err != nil {
+			klog.Error(err)
+			ctx.JSON(200, gin.H{
+				"status":  "Fail",
+				"message": fmt.Sprintf("OpenAI Event Marshal Error %v", err),
+				"data":    nil,
+			})
+			return
+		}
+
+		if !firstChunk {
+			ctx.Writer.Write([]byte("\n"))
+		} else {
+			firstChunk = false
+		}
+
+		if _, err := ctx.Writer.Write(bts); err != nil {
+			klog.Error(err)
+			return
+		}
+
+		ctx.Writer.Flush()
+	}
+}
+
+func (chat *ChatService) topP() float32 {
+	model := strings.ToLower(chat.config.Chat.Model)
+	if strings.HasPrefix(model, "kimi-") || strings.HasPrefix(model, "moonshot-") {
+		return 0.95
+	}
+	if chat.config.Chat.TopP > 0 {
+		return chat.config.Chat.TopP
+	}
+	return 1
+}

ai-chat-backend/pkg/log/README.md

@@ -0,0 +1,3 @@
+# 日志框架
+1. 可通过包调用日志打印，也可以通过对象调用日志打印
+2. 可以自动切分日志文件

ai-chat-backend/pkg/log/hook.go

@@ -0,0 +1,19 @@
+package log
+
+import "github.com/sirupsen/logrus"
+import nativeLog "log"
+
+type errorHook struct {
+}
+
+func (*errorHook) Levels() []logrus.Level {
+	return []logrus.Level{
+		logrus.PanicLevel,
+		logrus.FatalLevel,
+		logrus.ErrorLevel,
+	}
+}
+func (*errorHook) Fire(entry *logrus.Entry) error {
+	nativeLog.Println(entry.Message, entry.Data)
+	return nil
+}

ai-chat-backend/pkg/log/log.go

@@ -0,0 +1,233 @@
+package log
+
+import (
+	"errors"
+	"fmt"
+	"github.com/sirupsen/logrus"
+	"io"
+	"runtime"
+)
+
+type ILogger interface {
+	SetLevel(lvl string)
+	SetOutput(writer io.Writer)
+	SetPrintCaller(bool)
+	SetCaller(caller func() (file string, line int, funcName string, err error))
+	Trace(args ...interface{})
+	Debug(args ...interface{})
+	Info(args ...interface{})
+	Warning(args ...interface{})
+	Error(args ...interface{})
+	Fatal(args ...interface{})
+	Panic(args ...interface{})
+	TraceF(format string, args ...interface{})
+	DebugF(format string, args ...interface{})
+	InfoF(format string, args ...interface{})
+	WarningF(format string, args ...interface{})
+	ErrorF(format string, args ...interface{})
+	FatalF(format string, args ...interface{})
+	PanicF(format string, args ...interface{})
+	WithFields(fields map[string]interface{}) ILogger
+}
+type Logger struct {
+	entry *logrus.Entry
+	// panic,fatal,error,warn,warning,info,debug,trace
+	level       string
+	printCaller bool
+	caller      func() (file string, line int, funcName string, err error)
+}
+
+// 设置日志打印级别
+func (l *Logger) SetLevel(lvl string) {
+	if lvl == "" {
+		return
+	}
+	level, err := logrus.ParseLevel(lvl)
+	if err == nil {
+		l.level = lvl
+		l.entry.Logger.Level = level
+	}
+}
+
+// 设置日志输出位置
+func (l *Logger) SetOutput(writer io.Writer) {
+	l.entry.Logger.SetOutput(writer)
+}
+
+// 设置是否打印调用信息
+func (l *Logger) SetPrintCaller(printCaller bool) {
+	l.printCaller = printCaller
+}
+func (l *Logger) SetCaller(caller func() (file string, line int, funcName string, err error)) {
+	l.caller = caller
+}
+
+// 获取caller信息
+func (l *Logger) getCallerInfo(level logrus.Level) map[string]interface{} {
+	mp := make(map[string]interface{})
+	if l.printCaller == true || level != logrus.InfoLevel {
+		file, line, funcName, err := l.caller()
+		if err == nil {
+			mp["file"] = fmt.Sprintf("%s:%d", file, line)
+			mp["func"] = funcName
+		}
+	}
+	return mp
+}
+
+func (l *Logger) log(level logrus.Level, args ...interface{}) {
+	l.entry.WithFields(l.getCallerInfo(level)).Log(level, args...)
+}
+func (l *Logger) logf(level logrus.Level, format string, args ...interface{}) {
+	l.entry.WithFields(l.getCallerInfo(level)).Logf(level, format, args...)
+}
+func (l *Logger) Trace(args ...interface{}) {
+	l.log(logrus.TraceLevel, args...)
+}
+func (l *Logger) Debug(args ...interface{}) {
+	l.log(logrus.DebugLevel, args...)
+}
+func (l *Logger) Info(args ...interface{}) {
+	l.log(logrus.InfoLevel, args...)
+}
+func (l *Logger) Warning(args ...interface{}) {
+	l.log(logrus.WarnLevel, args...)
+}
+func (l *Logger) Error(args ...interface{}) {
+	l.log(logrus.ErrorLevel, args...)
+}
+func (l *Logger) Fatal(args ...interface{}) {
+	l.log(logrus.FatalLevel, args...)
+}
+func (l *Logger) Panic(args ...interface{}) {
+	l.log(logrus.PanicLevel, args...)
+}
+func (l *Logger) TraceF(format string, args ...interface{}) {
+	l.logf(logrus.TraceLevel, format, args...)
+}
+func (l *Logger) DebugF(format string, args ...interface{}) {
+	l.logf(logrus.DebugLevel, format, args...)
+}
+func (l *Logger) InfoF(format string, args ...interface{}) {
+	l.logf(logrus.InfoLevel, format, args...)
+}
+func (l *Logger) WarningF(format string, args ...interface{}) {
+	l.logf(logrus.WarnLevel, format, args...)
+}
+func (l *Logger) ErrorF(format string, args ...interface{}) {
+	l.logf(logrus.ErrorLevel, format, args...)
+}
+func (l *Logger) FatalF(format string, args ...interface{}) {
+	l.logf(logrus.FatalLevel, format, args...)
+}
+func (l *Logger) PanicF(format string, args ...interface{}) {
+	l.logf(logrus.PanicLevel, format, args...)
+}
+func (l *Logger) WithFields(fields map[string]interface{}) ILogger {
+	entry := l.entry.WithFields(fields)
+	return &Logger{entry: entry, level: l.level, printCaller: l.printCaller, caller: l.caller}
+}
+
+var log *Logger
+
+func NewLogger() ILogger {
+	return newLogger()
+}
+func newLogger() *Logger {
+	log := logrus.New()
+	log.SetLevel(logrus.InfoLevel)
+	log.AddHook(&errorHook{})
+	logger := &Logger{
+		entry:  logrus.NewEntry(log),
+		caller: defaultCaller,
+	}
+	return logger
+}
+
+func init() {
+	log = newLogger()
+}
+
+// 设置日志打印级别
+func SetLevel(lvl string) {
+	if lvl == "" {
+		return
+	}
+	level, err := logrus.ParseLevel(lvl)
+	if err == nil {
+		log.level = lvl
+		log.entry.Logger.Level = level
+	}
+}
+
+// 设置日志的输出位置
+func SetOutput(writer io.Writer) {
+	log.entry.Logger.SetOutput(writer)
+}
+
+// 设置是否打印调用信息
+func SetPrintCaller(printCaller bool) {
+	log.printCaller = printCaller
+}
+
+func SetCaller(caller func() (file string, line int, funcName string, err error)) {
+	log.caller = caller
+}
+
+func defaultCaller() (file string, line int, funcName string, err error) {
+	pc, f, l, ok := runtime.Caller(4)
+	if !ok {
+		err = errors.New("caller failure")
+		return
+	}
+	funcName = runtime.FuncForPC(pc).Name()
+	file, line = f, l
+	return
+}
+
+func Trace(args ...interface{}) {
+	log.log(logrus.TraceLevel, args...)
+}
+func Debug(args ...interface{}) {
+	log.log(logrus.DebugLevel, args...)
+}
+func Info(args ...interface{}) {
+	log.log(logrus.InfoLevel, args...)
+}
+func Warning(args ...interface{}) {
+	log.log(logrus.WarnLevel, args...)
+}
+func Error(args ...interface{}) {
+	log.log(logrus.ErrorLevel, args...)
+}
+func Fatal(args ...interface{}) {
+	log.log(logrus.FatalLevel, args...)
+}
+func Panic(args ...interface{}) {
+	log.log(logrus.PanicLevel, args...)
+}
+func TraceF(format string, args ...interface{}) {
+	log.logf(logrus.TraceLevel, format, args...)
+}
+func DebugF(format string, args ...interface{}) {
+	log.logf(logrus.DebugLevel, format, args...)
+}
+func InfoF(format string, args ...interface{}) {
+	log.logf(logrus.InfoLevel, format, args...)
+}
+func WarningF(format string, args ...interface{}) {
+	log.logf(logrus.WarnLevel, format, args...)
+}
+func ErrorF(format string, args ...interface{}) {
+	log.logf(logrus.ErrorLevel, format, args...)
+}
+func FatalF(format string, args ...interface{}) {
+	log.logf(logrus.FatalLevel, format, args...)
+}
+func PanicF(format string, args ...interface{}) {
+	log.logf(logrus.PanicLevel, format, args...)
+}
+func WithFields(fields map[string]interface{}) *Logger {
+	entry := log.entry.WithFields(fields)
+	return &Logger{entry: entry, level: log.level, printCaller: log.printCaller, caller: log.caller}
+}

ai-chat-backend/pkg/log/rotate_writer.go

@@ -0,0 +1,58 @@
+package log
+
+import (
+	"gopkg.in/natefinch/lumberjack.v2"
+	"io"
+	"sync"
+)
+
+type fileRotateWriter struct {
+	data map[string]io.Writer
+	sync.RWMutex
+}
+
+func (frw *fileRotateWriter) getWriter(logPath string) io.Writer {
+	frw.RLock()
+	defer frw.RUnlock()
+	w, ok := frw.data[logPath]
+	if !ok {
+		return nil
+	}
+	return w
+}
+func (frw *fileRotateWriter) setWriter(logPath string, w io.Writer) io.Writer {
+	frw.Lock()
+	defer frw.Unlock()
+	frw.data[logPath] = w
+	return w
+}
+
+var _fileRotateWriter *fileRotateWriter
+
+func init() {
+	_fileRotateWriter = &fileRotateWriter{
+		data: map[string]io.Writer{},
+	}
+}
+
+func GetRotateWriter(logPath string) io.Writer {
+	if logPath == "" {
+		panic("日志文件路径不能为空")
+	}
+	writer := _fileRotateWriter.getWriter(logPath)
+	if writer != nil {
+		return writer
+	}
+	writer = &lumberjack.Logger{
+		//文件名
+		Filename: logPath,
+		//单个文件大小单位MB
+		MaxSize: 1,
+		//最多保留文件数
+		MaxBackups: 15,
+		//最长保留时间（天）
+		MaxAge:    7,
+		LocalTime: true,
+	}
+	return _fileRotateWriter.setWriter(logPath, writer)
+}

ai-chat-backend/pkg/middlewares/cors.go

@@ -0,0 +1,24 @@
+package middlewares
+
+import (
+	"github.com/gin-gonic/gin"
+	"net/http"
+)
+
+func Cors() gin.HandlerFunc {
+	return func(c *gin.Context) {
+		method := c.Request.Method
+		origin := c.Request.Header.Get("Origin")
+		if origin != "" {
+			c.Header("Access-Control-Allow-Origin", "*") // 可将将 * 替换为指定的域名
+			c.Header("Access-Control-Allow-Methods", "POST, GET, OPTIONS, PUT, DELETE, UPDATE")
+			c.Header("Access-Control-Allow-Headers", "Origin, X-Requested-With, Content-Type, Accept, Authorization")
+			c.Header("Access-Control-Expose-Headers", "Content-Length, Access-Control-Allow-Origin, Access-Control-Allow-Headers, Cache-Control, Content-Language, Content-Type")
+			c.Header("Access-Control-Allow-Credentials", "true")
+		}
+		if method == "OPTIONS" {
+			c.AbortWithStatus(http.StatusNoContent)
+		}
+		c.Next()
+	}
+}

ai-chat-backend/pkg/middlewares/rate_limit.go

@@ -0,0 +1,23 @@
+package middlewares
+
+import (
+	"github.com/gin-gonic/gin"
+	"golang.org/x/time/rate"
+)
+
+func RateLimitMiddleware(r rate.Limit, b int) gin.HandlerFunc {
+	limiter := rate.NewLimiter(r, b)
+	return func(c *gin.Context) {
+		if !limiter.Allow() {
+			// 请求被限制，返回错误信息
+			c.JSON(429, gin.H{
+				"status":  "Fail",
+				"message": "Too many requests, please try again later",
+				"data":    nil,
+			})
+			c.Abort()
+			return
+		}
+		c.Next()
+	}
+}

ai-chat-backend/pkg/tokenizer/tokenizer.go

@@ -0,0 +1,43 @@
+package tokenizer
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"net/http"
+
+	"github.com/sashabaranov/go-openai"
+)
+
+type tokenInfo struct {
+	Code  int    `json:"code"`
+	Count int    `json:"num_tokens"`
+	Msg   string `json:"msg"`
+}
+
+func GetTokenCount(message openai.ChatCompletionMessage, model string) (int, error) {
+	url := fmt.Sprintf("http://192.168.239.161:3002/tokenizer/%s", model)
+	info := tokenInfo{}
+	if err := postJSON(url, &message, &info); err != nil {
+		return 0, err
+	}
+	if info.Code != 200 {
+		return 0, fmt.Errorf("%v", info.Msg)
+	}
+	return info.Count, nil
+}
+
+func postJSON(url string, requestData *openai.ChatCompletionMessage, responseData *tokenInfo) error {
+	requestBody, err := json.Marshal(requestData)
+	if err != nil {
+		return err
+	}
+
+	resp, err := http.Post(url, "application/json", bytes.NewBuffer(requestBody))
+	if err != nil {
+		return err
+	}
+	defer resp.Body.Close()
+
+	return json.NewDecoder(resp.Body).Decode(responseData)
+}

ai-chat-backend/pkg/utils/utils.go

@@ -0,0 +1,65 @@
+package utils
+
+import (
+	"io/ioutil"
+	"os"
+	"path/filepath"
+	"strings"
+
+	"k8s.io/klog/v2"
+)
+
+func ReplaceInFile(filePath string, targetStr string, replaceStr string) error {
+	// 读取文件内容
+	content, err := ioutil.ReadFile(filePath)
+	if err != nil {
+		return err
+	}
+	// 判断是否需要替换
+	if !strings.Contains(string(content), targetStr) {
+		return nil
+	}
+
+	// 替换字符串并写回文件，保持原有 filemode
+	info, err := os.Stat(filePath)
+	if err != nil {
+		return err
+	}
+	newContent := strings.ReplaceAll(string(content), targetStr, replaceStr)
+	err = ioutil.WriteFile(filePath, []byte(newContent), info.Mode())
+	if err != nil {
+		return err
+	}
+	klog.Infof("Replaced in file: %s\n", filePath)
+	return nil
+}
+
+func ReplaceFiles(rootDir string, replacePairs map[string]string) error {
+	err := filepath.Walk(rootDir, func(path string, info os.FileInfo, err error) error {
+		if err != nil {
+			return err
+		}
+		// 如果当前路径是目录，则继续遍历
+		if info.IsDir() {
+			return nil
+		}
+		// 处理文件
+		for targetStr, replaceStr := range replacePairs {
+			err = ReplaceInFile(path, targetStr, replaceStr)
+			if err != nil {
+				return err
+			}
+		}
+		return nil
+	})
+	if err != nil {
+		return err
+	}
+	return nil
+}
+
+func Reverse[S ~[]E, E any](s S) {
+	for i, j := 0, len(s)-1; i < j; i, j = i+1, j-1 {
+		s[i], s[j] = s[j], s[i]
+	}
+}

ai-chat-backend/requirements.txt

@@ -0,0 +1,2 @@
+nuxt>=0.2.0
+tiktoken>=0.3.3

ai-chat-backend/services/ai-chat-service/ai-chat-service.go

@@ -0,0 +1,23 @@
+package ai_chat_service
+
+import (
+	"ai-chat-backend/pkg/config"
+	grpc_client "ai-chat-backend/services/grpc-client"
+	"sync"
+)
+
+var pool grpc_client.ClientPool
+var once sync.Once
+
+type client struct {
+	grpc_client.DefaultClient
+}
+
+func GetAiChatServiceClientPool() grpc_client.ClientPool {
+	once.Do(func() {
+		cnf := config.GetConfig()
+		c := &client{}
+		pool = c.GetPool(cnf.DependOn.AiChatService.Address)
+	})
+	return pool
+}

ai-chat-backend/services/ai-chat-service/proto/chat.proto

@@ -0,0 +1,72 @@
+syntax = "proto3";
+option go_package = "ai-chat-service/proto";
+package ai_chat_service.zvoice.com;
+
+message ChatCompletionRequest {
+  string message = 1[json_name = "message"];
+  string id = 2[json_name = "id"];
+  string pid = 3[json_name = "p_id"];
+  bool enableContext = 4[json_name = "enable_context"];
+  ChatParam chatParam = 5[json_name = "chat_param"];
+}
+
+message ChatParam {
+  string model = 1[json_name = "model"];
+  int32  maxTokens = 2[json_name = "max_tokens"];
+  float temperature = 3[json_name = "temperature"];
+  float topP = 4[json_name = "top_p"];
+  float presencePenalty = 5[json_name = "presence_penalty"];
+  float frequencyPenalty = 6[json_name = "frequency_penalty"];
+  string botDesc =7[json_name = "bot_desc"];
+  int32 minResponseTokens = 8[json_name = "min_response_tokens"];
+  int32 contextTTL = 9[json_name = "context_ttl"];
+  int32 contextLen = 10[json_name = "context_len"];
+}
+
+// 服务响应消息，非流式响应
+message ChatCompletionResponse {
+  string id = 1 [json_name = "id"];
+  string object = 2 [json_name = "object"];
+  int64 created = 3 [json_name = "created"];
+  string model = 4 [json_name = "model"];
+  repeated  ChatCompletionChoice choices = 5 [json_name = "choices"];
+  Usage usage = 6[json_name = "usage"];
+}
+message ChatCompletionChoice {
+  int32 index = 1[json_name = "index"];
+  ChatCompletionMessage message = 2 [json_name = "message"];
+  string finishReason = 3[json_name = "finish_reason"];
+}
+message ChatCompletionMessage {
+  string role=1[json_name = "role"];
+  string content=2[json_name = "content"];
+  string name=3[json_name = "name"];
+}
+message Usage {
+  int32 promptTokens = 1 [json_name = "prompt_tokens"];
+  int32 completionTokens =2 [json_name = "completion_tokens"];
+  int32 totalTokens      = 3 [json_name = "total_tokens"];
+}
+
+// 服务响应消息，流式响应
+message  ChatCompletionStreamResponse {
+  string id = 1 [json_name = "id"];
+  string object = 2 [json_name = "object"];
+  int64 created = 3 [json_name = "created"];
+  string model = 4 [json_name = "model"];
+  repeated  ChatCompletionStreamChoice choices = 5 [json_name = "choices"];
+}
+message ChatCompletionStreamChoice {
+  int32 index = 1[json_name = "index"];
+  ChatCompletionStreamChoiceDelta delta =2 [json_name = "delta"];
+  string finishReason = 3[json_name="finish_reason"];
+}
+message ChatCompletionStreamChoiceDelta {
+  string content = 1 [json_name = "content"];
+  string role = 2 [json_name = "role"];
+}
+
+service Chat {
+  rpc ChatCompletion(ChatCompletionRequest) returns (ChatCompletionResponse);
+  rpc ChatCompletionStream(ChatCompletionRequest) returns (stream ChatCompletionStreamResponse);
+}

ai-chat-backend/services/ai-chat-service/proto/chat_grpc.pb.go

@@ -0,0 +1,169 @@
+// Code generated by protoc-gen-go-grpc. DO NOT EDIT.
+// versions:
+// - protoc-gen-go-grpc v1.2.0
+// - protoc             v4.22.0
+// source: proto/chat.proto
+
+package proto
+
+import (
+	context "context"
+	grpc "google.golang.org/grpc"
+	codes "google.golang.org/grpc/codes"
+	status "google.golang.org/grpc/status"
+)
+
+// This is a compile-time assertion to ensure that this generated file
+// is compatible with the grpc package it is being compiled against.
+// Requires gRPC-Go v1.32.0 or later.
+const _ = grpc.SupportPackageIsVersion7
+
+// ChatClient is the client API for Chat service.
+//
+// For semantics around ctx use and closing/ending streaming RPCs, please refer to https://pkg.go.dev/google.golang.org/grpc/?tab=doc#ClientConn.NewStream.
+type ChatClient interface {
+	ChatCompletion(ctx context.Context, in *ChatCompletionRequest, opts ...grpc.CallOption) (*ChatCompletionResponse, error)
+	ChatCompletionStream(ctx context.Context, in *ChatCompletionRequest, opts ...grpc.CallOption) (Chat_ChatCompletionStreamClient, error)
+}
+
+type chatClient struct {
+	cc grpc.ClientConnInterface
+}
+
+func NewChatClient(cc grpc.ClientConnInterface) ChatClient {
+	return &chatClient{cc}
+}
+
+func (c *chatClient) ChatCompletion(ctx context.Context, in *ChatCompletionRequest, opts ...grpc.CallOption) (*ChatCompletionResponse, error) {
+	out := new(ChatCompletionResponse)
+	err := c.cc.Invoke(ctx, "/ai_chat_service.zvoice.com.Chat/ChatCompletion", in, out, opts...)
+	if err != nil {
+		return nil, err
+	}
+	return out, nil
+}
+
+func (c *chatClient) ChatCompletionStream(ctx context.Context, in *ChatCompletionRequest, opts ...grpc.CallOption) (Chat_ChatCompletionStreamClient, error) {
+	stream, err := c.cc.NewStream(ctx, &Chat_ServiceDesc.Streams[0], "/ai_chat_service.zvoice.com.Chat/ChatCompletionStream", opts...)
+	if err != nil {
+		return nil, err
+	}
+	x := &chatChatCompletionStreamClient{stream}
+	if err := x.ClientStream.SendMsg(in); err != nil {
+		return nil, err
+	}
+	if err := x.ClientStream.CloseSend(); err != nil {
+		return nil, err
+	}
+	return x, nil
+}
+
+type Chat_ChatCompletionStreamClient interface {
+	Recv() (*ChatCompletionStreamResponse, error)
+	grpc.ClientStream
+}
+
+type chatChatCompletionStreamClient struct {
+	grpc.ClientStream
+}
+
+func (x *chatChatCompletionStreamClient) Recv() (*ChatCompletionStreamResponse, error) {
+	m := new(ChatCompletionStreamResponse)
+	if err := x.ClientStream.RecvMsg(m); err != nil {
+		return nil, err
+	}
+	return m, nil
+}
+
+// ChatServer is the server API for Chat service.
+// All implementations must embed UnimplementedChatServer
+// for forward compatibility
+type ChatServer interface {
+	ChatCompletion(context.Context, *ChatCompletionRequest) (*ChatCompletionResponse, error)
+	ChatCompletionStream(*ChatCompletionRequest, Chat_ChatCompletionStreamServer) error
+	mustEmbedUnimplementedChatServer()
+}
+
+// UnimplementedChatServer must be embedded to have forward compatible implementations.
+type UnimplementedChatServer struct {
+}
+
+func (UnimplementedChatServer) ChatCompletion(context.Context, *ChatCompletionRequest) (*ChatCompletionResponse, error) {
+	return nil, status.Errorf(codes.Unimplemented, "method ChatCompletion not implemented")
+}
+func (UnimplementedChatServer) ChatCompletionStream(*ChatCompletionRequest, Chat_ChatCompletionStreamServer) error {
+	return status.Errorf(codes.Unimplemented, "method ChatCompletionStream not implemented")
+}
+func (UnimplementedChatServer) mustEmbedUnimplementedChatServer() {}
+
+// UnsafeChatServer may be embedded to opt out of forward compatibility for this service.
+// Use of this interface is not recommended, as added methods to ChatServer will
+// result in compilation errors.
+type UnsafeChatServer interface {
+	mustEmbedUnimplementedChatServer()
+}
+
+func RegisterChatServer(s grpc.ServiceRegistrar, srv ChatServer) {
+	s.RegisterService(&Chat_ServiceDesc, srv)
+}
+
+func _Chat_ChatCompletion_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
+	in := new(ChatCompletionRequest)
+	if err := dec(in); err != nil {
+		return nil, err
+	}
+	if interceptor == nil {
+		return srv.(ChatServer).ChatCompletion(ctx, in)
+	}
+	info := &grpc.UnaryServerInfo{
+		Server:     srv,
+		FullMethod: "/ai_chat_service.zvoice.com.Chat/ChatCompletion",
+	}
+	handler := func(ctx context.Context, req interface{}) (interface{}, error) {
+		return srv.(ChatServer).ChatCompletion(ctx, req.(*ChatCompletionRequest))
+	}
+	return interceptor(ctx, in, info, handler)
+}
+
+func _Chat_ChatCompletionStream_Handler(srv interface{}, stream grpc.ServerStream) error {
+	m := new(ChatCompletionRequest)
+	if err := stream.RecvMsg(m); err != nil {
+		return err
+	}
+	return srv.(ChatServer).ChatCompletionStream(m, &chatChatCompletionStreamServer{stream})
+}
+
+type Chat_ChatCompletionStreamServer interface {
+	Send(*ChatCompletionStreamResponse) error
+	grpc.ServerStream
+}
+
+type chatChatCompletionStreamServer struct {
+	grpc.ServerStream
+}
+
+func (x *chatChatCompletionStreamServer) Send(m *ChatCompletionStreamResponse) error {
+	return x.ServerStream.SendMsg(m)
+}
+
+// Chat_ServiceDesc is the grpc.ServiceDesc for Chat service.
+// It's only intended for direct use with grpc.RegisterService,
+// and not to be introspected or modified (even as a copy)
+var Chat_ServiceDesc = grpc.ServiceDesc{
+	ServiceName: "ai_chat_service.zvoice.com.Chat",
+	HandlerType: (*ChatServer)(nil),
+	Methods: []grpc.MethodDesc{
+		{
+			MethodName: "ChatCompletion",
+			Handler:    _Chat_ChatCompletion_Handler,
+		},
+	},
+	Streams: []grpc.StreamDesc{
+		{
+			StreamName:    "ChatCompletionStream",
+			Handler:       _Chat_ChatCompletionStream_Handler,
+			ServerStreams: true,
+		},
+	},
+	Metadata: "proto/chat.proto",
+}

ai-chat-backend/services/grpc-client/default.go

@@ -0,0 +1,28 @@
+package grpc_client
+
+import (
+	"ai-chat-backend/pkg/log"
+	"google.golang.org/grpc"
+	"google.golang.org/grpc/credentials/insecure"
+)
+
+type ServiceClient interface {
+	GetPool(addr string) ClientPool
+}
+type DefaultClient struct {
+}
+
+func (c *DefaultClient) GetPool(addr string) ClientPool {
+	pool, err := NewPool(addr, c.getOptions()...)
+	if err != nil {
+		log.Error(err)
+		return nil
+	}
+	return pool
+}
+
+func (c *DefaultClient) getOptions() []grpc.DialOption {
+	opts := make([]grpc.DialOption, 0)
+	opts = append(opts, grpc.WithTransportCredentials(insecure.NewCredentials()))
+	return opts
+}

ai-chat-backend/services/grpc-client/grpc_client_pool.go

@@ -0,0 +1,48 @@
+package grpc_client
+
+import (
+	"ai-chat-backend/pkg/log"
+	"google.golang.org/grpc"
+	"google.golang.org/grpc/connectivity"
+	"sync"
+)
+
+type ClientPool interface {
+	Get() *grpc.ClientConn
+	Put(*grpc.ClientConn)
+}
+
+type clientPool struct {
+	pool sync.Pool
+}
+
+func NewPool(target string, opts ...grpc.DialOption) (ClientPool, error) {
+	return &clientPool{
+		pool: sync.Pool{
+			New: func() any {
+				conn, err := grpc.NewClient(target, opts...)
+				if err != nil {
+					log.Error(err)
+					return nil
+				}
+				return conn
+			},
+		},
+	}, nil
+}
+
+func (c *clientPool) Get() *grpc.ClientConn {
+	conn := c.pool.Get().(*grpc.ClientConn)
+	if conn.GetState() == connectivity.Shutdown || conn.GetState() == connectivity.TransientFailure {
+		conn.Close()
+		conn = c.pool.New().(*grpc.ClientConn)
+	}
+	return conn
+}
+func (c *clientPool) Put(conn *grpc.ClientConn) {
+	if conn.GetState() == connectivity.Shutdown || conn.GetState() == connectivity.TransientFailure {
+		conn.Close()
+		return
+	}
+	c.pool.Put(conn)
+}

ai-chat-backend/services/services.go

@@ -0,0 +1,11 @@
+package services
+
+import (
+	"context"
+	"google.golang.org/grpc/metadata"
+)
+
+func AppendBearerTokenToContext(ctx context.Context, accessToken string) context.Context {
+	md := metadata.Pairs("Authorization", "Bearer "+accessToken)
+	return metadata.NewOutgoingContext(ctx, md)
+}

ai-chat-backend/tests/test.txt

@@ -0,0 +1 @@
+{avatar:"https://raw.githubusercontent.com/Chanzhaoyu/chatgpt-web/main/src/assets/avatar.jpg",name:"ChatGPT",description:'知之为知之'}

ai-chat-backend/tokenizer.py

@@ -0,0 +1,57 @@
+from nuxt import route, logger, Request
+from nuxt.repositorys.validation import fields, use_args
+import traceback
+import tiktoken
+
+encoding_cache = {}
+
+support_models = set(["gpt-3.5-turbo",
+                      "gpt-3.5-turbo-16k",
+                      "gpt-4",
+                      "gpt-4-32k"])
+
+
+@route("/tokenizer/<str:model_name>", methods=["POST"])
+@use_args({
+    "role": fields.Str(required=True),
+    "content": fields.Str(required=True),
+    "name": fields.Str(required=False)
+}, location="json")
+def get_num_tokens(req: Request, message: dict, model_name: str):
+    try:
+        return {
+            "code": 200,
+            "num_tokens": num_tokens_from_messages([message], model=model_name)
+        }
+    except Exception as e:
+        logger.error(traceback.format_exc())
+        return {
+            "code": 500,
+            "msg": "{}".format(e)
+        }
+
+
+def num_tokens_from_messages(messages, model="gpt-3.5-turbo"):
+    """Returns the number of tokens used by a list of messages."""
+    encoding = None
+    if model in encoding_cache:
+        encoding = encoding_cache.get(model)
+    else:
+        try:
+            encoding = tiktoken.encoding_for_model(model)
+        except KeyError:
+            encoding = tiktoken.get_encoding("cl100k_base")
+        encoding_cache[model] = encoding
+    if model in support_models:  # note: future models may deviate from this
+        num_tokens = 0
+        for message in messages:
+            num_tokens += 4  # every message follows <im_start>{role/name}\n{content}<im_end>\n
+            for key, value in message.items():
+                num_tokens += len(encoding.encode(value))
+                if key == "name":  # if there's a name, the role is omitted
+                    num_tokens += -1  # role is always required and always 1 token
+        num_tokens += 3  # every reply is primed with <im_start>assistant
+        return num_tokens
+    else:
+        raise NotImplementedError(f"""num_tokens_from_messages() is not presently implemented for model {model}.
+See https://github.com/openai/openai-python/blob/main/chatml.md for information on how messages are converted to tokens.""")

ai-chat-backend/www/assets/index-94a36651.css

@@ -0,0 +1 @@
+.markdown-body{background-color:transparent;font-size:14px}.markdown-body p{white-space:pre-wrap}.markdown-body ol{list-style-type:decimal}.markdown-body ul{list-style-type:disc}.markdown-body pre code,.markdown-body pre tt{line-height:1.65}.markdown-body .highlight pre,.markdown-body pre{background-color:#fff}.markdown-body code.hljs{padding:0}.markdown-body .code-block-wrapper{position:relative;padding-top:24px}.markdown-body .code-block-header{position:absolute;top:5px;right:0;width:100%;padding:0 1rem;display:flex;justify-content:flex-end;align-items:center;color:#b3b3b3}.markdown-body .code-block-header__copy{cursor:pointer;margin-left:.5rem;-webkit-user-select:none;-moz-user-select:none;user-select:none}.markdown-body .code-block-header__copy:hover{color:#65a665}html.dark .message-reply .whitespace-pre-wrap{white-space:pre-wrap;color:var(--n-text-color)}html.dark .highlight pre,html.dark pre{background-color:#282c34}

ai-chat-backend/www/assets/index-97a17bdd.js

@@ -0,0 +1 @@
+import{n as s,b7 as a,bh as o,ba as r,bb as c,b9 as n,bB as i,bC as l,b6 as d,aM as u,bA as p}from"./index-79a31bf6.js";const x="/assets/404-451d813e.svg",_={class:"flex h-full"},m={class:"px-4 m-auto space-y-4 text-center max-[400px]"},f=i('<h1 class="text-4xl text-slate-800 dark:text-neutral-200"> Sorry, page not found! </h1><p class="text-base text-slate-500 dark:text-neutral-400"> Sorry, we couldn’t find the page you’re looking for. Perhaps you’ve mistyped the URL? Be sure to check your spelling. </p><div class="flex items-center justify-center text-center"><div class="w-[300px]"><img src="'+x+'" alt="404"></div></div>',3),g=s({__name:"index",setup(h){const e=l();function t(){e.push("/")}return(b,y)=>(d(),a("div",_,[o("div",m,[f,r(n(p),{type:"primary",onClick:t},{default:c(()=>[u(" Go to Home ")]),_:1})])]))}});export{g as default};