Merge pull request #6 from songquanpeng/main

xxx

.env.example

@@ -0,0 +1,3 @@
+PORT=3000
+DEBUG=false
+HTTPS_PROXY=http://localhost:7890

.github/workflows/ci.yml

@@ -0,0 +1,47 @@
+name: CI
+
+# This setup assumes that you run the unit tests with code coverage in the same
+# workflow that will also print the coverage report as comment to the pull request. 
+# Therefore, you need to trigger this workflow when a pull request is (re)opened or
+# when new code is pushed to the branch of the pull request. In addition, you also
+# need to trigger this workflow when new code is pushed to the main branch because 
+# we need to upload the code coverage results as artifact for the main branch as
+# well since it will be the baseline code coverage.
+# 
+# We do not want to trigger the workflow for pushes to *any* branch because this
+# would trigger our jobs twice on pull requests (once from "push" event and once
+# from "pull_request->synchronize")
+on:
+  pull_request:
+    types: [opened, reopened, synchronize]
+  push:
+    branches:
+      - 'main'
+
+jobs:
+  unit_tests:
+    name: "Unit tests"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Setup Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: ^1.22
+
+      # When you execute your unit tests, make sure to use the "-coverprofile" flag to write a 
+      # coverage profile to a file. You will need the name of the file (e.g. "coverage.txt")
+      # in the next step as well as the next job.
+      - name: Test
+        run: go test -cover -coverprofile=coverage.txt ./...
+      - uses: codecov/codecov-action@v4
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+
+  commit_lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: wagoid/commitlint-github-action@v6

.gitignore

@@ -8,4 +8,5 @@ build
 logs
 data
 /web/node_modules
-cmd.md
+cmd.md
+.env

README.en.md

@@ -101,7 +101,7 @@ Nginx reference configuration:
 ```
 server{
    server_name openai.justsong.cn;  # Modify your domain name accordingly
-   
+
    location / {
           client_max_body_size  64m;
           proxy_http_version 1.1;
@@ -132,12 +132,12 @@ The initial account username is `root` and password is `123456`.
 1. Download the executable file from [GitHub Releases](https://github.com/songquanpeng/one-api/releases/latest) or compile from source:
    ```shell
    git clone https://github.com/songquanpeng/one-api.git
-   
+
    # Build the frontend
    cd one-api/web/default
    npm install
    npm run build
-   
+
    # Build the backend
    cd ../..
    go mod download
@@ -287,7 +287,9 @@ If the channel ID is not provided, load balancing will be used to distribute the
     + Double-check that your interface address and API Key are correct.
 
 ## Related Projects
-[FastGPT](https://github.com/labring/FastGPT): Knowledge question answering system based on the LLM
+* [FastGPT](https://github.com/labring/FastGPT): Knowledge question answering system based on the LLM
+* [VChart](https://github.com/VisActor/VChart):  More than just a cross-platform charting library, but also an expressive data storyteller.
+* [VMind](https://github.com/VisActor/VMind):  Not just automatic, but also fantastic. Open-source solution for intelligent visualization.
 
 ## Note
 This project is an open-source project. Please use it in compliance with OpenAI's [Terms of Use](https://openai.com/policies/terms-of-use) and **applicable laws and regulations**. It must not be used for illegal purposes.

README.md

@@ -53,7 +53,7 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型，开箱即用
 
 > [!NOTE]
 > 本项目为开源项目，使用者必须在遵循 OpenAI 的[使用条款](https://openai.com/policies/terms-of-use)以及**法律法规**的情况下使用，不得用于非法用途。
-> 
+>
 > 根据[《生成式人工智能服务管理暂行办法》](http://www.cac.gov.cn/2023-07/13/c_1690898327029107.htm)的要求，请勿对中国地区公众提供一切未经备案的生成式人工智能服务。
 
 > [!WARNING]
@@ -68,6 +68,7 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型，开箱即用
    + [x] [Anthropic Claude 系列模型](https://anthropic.com) (支持 AWS Claude)
    + [x] [Google PaLM2/Gemini 系列模型](https://developers.generativeai.google)
    + [x] [Mistral 系列模型](https://mistral.ai/)
+   + [x] [字节跳动豆包大模型](https://console.volcengine.com/ark/region:ark+cn-beijing/model)
    + [x] [百度文心一言系列模型](https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html)
    + [x] [阿里通义千问系列模型](https://help.aliyun.com/document_detail/2400395.html)
    + [x] [讯飞星火认知大模型](https://www.xfyun.cn/doc/spark/Web.html)
@@ -76,7 +77,6 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型，开箱即用
    + [x] [腾讯混元大模型](https://cloud.tencent.com/document/product/1729)
    + [x] [Moonshot AI](https://platform.moonshot.cn/)
    + [x] [百川大模型](https://platform.baichuan-ai.com)
-   + [ ] [字节云雀大模型](https://www.volcengine.com/product/ark) (WIP)
    + [x] [MINIMAX](https://api.minimax.chat/)
    + [x] [Groq](https://wow.groq.com/)
    + [x] [Ollama](https://github.com/ollama/ollama)
@@ -144,7 +144,7 @@ Nginx 的参考配置：
 ```
 server{
    server_name openai.justsong.cn;  # 请根据实际情况修改你的域名
-   
+
    location / {
           client_max_body_size  64m;
           proxy_http_version 1.1;
@@ -189,12 +189,12 @@ docker-compose ps
 1. 从 [GitHub Releases](https://github.com/songquanpeng/one-api/releases/latest) 下载可执行文件或者从源码编译：
    ```shell
    git clone https://github.com/songquanpeng/one-api.git
-   
+
    # 构建前端
    cd one-api/web/default
    npm install
    npm run build
-   
+
    # 构建后端
    cd ../..
    go mod download
@@ -321,7 +321,7 @@ Render 可以直接部署 docker 镜像，不需要 fork 仓库：https://dashbo
 例如对于 OpenAI 的官方库：
 ```bash
 OPENAI_API_KEY="sk-xxxxxx"
-OPENAI_API_BASE="https://<HOST>:<PORT>/v1" 
+OPENAI_API_BASE="https://<HOST>:<PORT>/v1"
 ```
 
 ```mermaid
@@ -340,6 +340,7 @@ graph LR
 不加的话将会使用负载均衡的方式使用多个渠道。
 
 ### 环境变量
+> One API 支持从 `.env` 文件中读取环境变量，请参照 `.env.example` 文件，使用时请将其重命名为 `.env`。
 1. `REDIS_CONN_STRING`：设置之后将使用 Redis 作为缓存使用。
    + 例子：`REDIS_CONN_STRING=redis://default:redispw@localhost:49153`
    + 如果数据库访问延迟很低，没有必要启用 Redis，启用后反而会出现数据滞后的问题。
@@ -384,14 +385,17 @@ graph LR
     + `TIKTOKEN_CACHE_DIR`：默认程序启动时会联网下载一些通用的词元的编码，如：`gpt-3.5-turbo`，在一些网络环境不稳定，或者离线情况，可能会导致启动有问题，可以配置此目录缓存数据，可迁移到离线环境。
     + `DATA_GYM_CACHE_DIR`：目前该配置作用与 `TIKTOKEN_CACHE_DIR` 一致，但是优先级没有它高。
 17. `RELAY_TIMEOUT`：中继超时设置，单位为秒，默认不设置超时时间。
-18. `SQLITE_BUSY_TIMEOUT`：SQLite 锁等待超时设置，单位为毫秒，默认 `3000`。
-19. `GEMINI_SAFETY_SETTING`：Gemini 的安全设置，默认 `BLOCK_NONE`。
-20. `GEMINI_VERSION`：One API 所使用的 Gemini 版本，默认为 `v1`。
-21. `THEME`：系统的主题设置，默认为 `default`，具体可选值参考[此处](./web/README.md)。
-22. `ENABLE_METRIC`：是否根据请求成功率禁用渠道，默认不开启，可选值为 `true` 和 `false`。
-23. `METRIC_QUEUE_SIZE`：请求成功率统计队列大小，默认为 `10`。
-24. `METRIC_SUCCESS_RATE_THRESHOLD`：请求成功率阈值，默认为 `0.8`。
-25. `INITIAL_ROOT_TOKEN`：如果设置了该值，则在系统首次启动时会自动创建一个值为该环境变量值的 root 用户令牌。
+18. `RELAY_PROXY`：设置后使用该代理来请求 API。
+19. `USER_CONTENT_REQUEST_TIMEOUT`：用户上传内容下载超时时间，单位为秒。
+20. `USER_CONTENT_REQUEST_PROXY`：设置后使用该代理来请求用户上传的内容，例如图片。
+21. `SQLITE_BUSY_TIMEOUT`：SQLite 锁等待超时设置，单位为毫秒，默认 `3000`。
+22. `GEMINI_SAFETY_SETTING`：Gemini 的安全设置，默认 `BLOCK_NONE`。
+23. `GEMINI_VERSION`：One API 所使用的 Gemini 版本，默认为 `v1`。
+24. `THEME`：系统的主题设置，默认为 `default`，具体可选值参考[此处](./web/README.md)。
+25. `ENABLE_METRIC`：是否根据请求成功率禁用渠道，默认不开启，可选值为 `true` 和 `false`。
+26. `METRIC_QUEUE_SIZE`：请求成功率统计队列大小，默认为 `10`。
+27. `METRIC_SUCCESS_RATE_THRESHOLD`：请求成功率阈值，默认为 `0.8`。
+28. `INITIAL_ROOT_TOKEN`：如果设置了该值，则在系统首次启动时会自动创建一个值为该环境变量值的 root 用户令牌。
 
 ### 命令行参数
 1. `--port <port_number>`: 指定服务器监听的端口号，默认为 `3000`。
@@ -444,6 +448,8 @@ https://openai.justsong.cn
 ## 相关项目
 * [FastGPT](https://github.com/labring/FastGPT): 基于 LLM 大语言模型的知识库问答系统
 * [ChatGPT Next Web](https://github.com/Yidadaa/ChatGPT-Next-Web):  一键拥有你自己的跨平台 ChatGPT 应用
+* [VChart](https://github.com/VisActor/VChart):  不只是开箱即用的多端图表库，更是生动灵活的数据故事讲述者。
+* [VMind](https://github.com/VisActor/VMind):  不仅自动，还很智能。开源智能可视化解决方案。
 
 ## 注意
 

common/client/init.go

@@ -0,0 +1,60 @@
+package client
+
+import (
+	"fmt"
+	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/logger"
+	"net/http"
+	"net/url"
+	"time"
+)
+
+var HTTPClient *http.Client
+var ImpatientHTTPClient *http.Client
+var UserContentRequestHTTPClient *http.Client
+
+func Init() {
+	if config.UserContentRequestProxy != "" {
+		logger.SysLog(fmt.Sprintf("using %s as proxy to fetch user content", config.UserContentRequestProxy))
+		proxyURL, err := url.Parse(config.UserContentRequestProxy)
+		if err != nil {
+			logger.FatalLog(fmt.Sprintf("USER_CONTENT_REQUEST_PROXY set but invalid: %s", config.UserContentRequestProxy))
+		}
+		transport := &http.Transport{
+			Proxy: http.ProxyURL(proxyURL),
+		}
+		UserContentRequestHTTPClient = &http.Client{
+			Transport: transport,
+			Timeout:   time.Second * time.Duration(config.UserContentRequestTimeout),
+		}
+	} else {
+		UserContentRequestHTTPClient = &http.Client{}
+	}
+	var transport http.RoundTripper
+	if config.RelayProxy != "" {
+		logger.SysLog(fmt.Sprintf("using %s as api relay proxy", config.RelayProxy))
+		proxyURL, err := url.Parse(config.RelayProxy)
+		if err != nil {
+			logger.FatalLog(fmt.Sprintf("USER_CONTENT_REQUEST_PROXY set but invalid: %s", config.UserContentRequestProxy))
+		}
+		transport = &http.Transport{
+			Proxy: http.ProxyURL(proxyURL),
+		}
+	}
+
+	if config.RelayTimeout == 0 {
+		HTTPClient = &http.Client{
+			Transport: transport,
+		}
+	} else {
+		HTTPClient = &http.Client{
+			Timeout:   time.Duration(config.RelayTimeout) * time.Second,
+			Transport: transport,
+		}
+	}
+
+	ImpatientHTTPClient = &http.Client{
+		Timeout:   5 * time.Second,
+		Transport: transport,
+	}
+}

common/config/config.go

@@ -117,10 +117,10 @@ var ValidThemes = map[string]bool{
 // All duration's unit is seconds
 // Shouldn't larger then RateLimitKeyExpirationDuration
 var (
-	GlobalApiRateLimitNum            = env.Int("GLOBAL_API_RATE_LIMIT", 180)
+	GlobalApiRateLimitNum            = env.Int("GLOBAL_API_RATE_LIMIT", 240)
 	GlobalApiRateLimitDuration int64 = 3 * 60
 
-	GlobalWebRateLimitNum            = env.Int("GLOBAL_WEB_RATE_LIMIT", 60)
+	GlobalWebRateLimitNum            = env.Int("GLOBAL_WEB_RATE_LIMIT", 120)
 	GlobalWebRateLimitDuration int64 = 3 * 60
 
 	UploadRateLimitNum            = 10
@@ -144,3 +144,10 @@ var MetricFailChanSize = env.Int("METRIC_FAIL_CHAN_SIZE", 128)
 var InitialRootToken = os.Getenv("INITIAL_ROOT_TOKEN")
 
 var GeminiVersion = env.String("GEMINI_VERSION", "v1")
+
+
+var OnlyOneLogFile = env.Bool("ONLY_ONE_LOG_FILE", false)
+
+var RelayProxy = env.String("RELAY_PROXY", "")
+var UserContentRequestProxy = env.String("USER_CONTENT_REQUEST_PROXY", "")
+var UserContentRequestTimeout = env.Int("USER_CONTENT_REQUEST_TIMEOUT", 30)

common/ctxkey/key.go

@@ -19,4 +19,5 @@ const (
 	TokenName         = "token_name"
 	BaseURL           = "base_url"
 	AvailableModels   = "available_models"
+	KeyRequestBody    = "key_request_body"
 )

common/gin.go

@@ -4,14 +4,13 @@ import (
 	"bytes"
 	"encoding/json"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common/ctxkey"
 	"io"
 	"strings"
 )
 
-const KeyRequestBody = "key_request_body"
-
 func GetRequestBody(c *gin.Context) ([]byte, error) {
-	requestBody, _ := c.Get(KeyRequestBody)
+	requestBody, _ := c.Get(ctxkey.KeyRequestBody)
 	if requestBody != nil {
 		return requestBody.([]byte), nil
 	}
@@ -20,7 +19,7 @@ func GetRequestBody(c *gin.Context) ([]byte, error) {
 		return nil, err
 	}
 	_ = c.Request.Body.Close()
-	c.Set(KeyRequestBody, requestBody)
+	c.Set(ctxkey.KeyRequestBody, requestBody)
 	return requestBody.([]byte), nil
 }
 

common/image/image.go

@@ -3,6 +3,7 @@ package image
 import (
 	"bytes"
 	"encoding/base64"
+	"github.com/songquanpeng/one-api/common/client"
 	"image"
 	_ "image/gif"
 	_ "image/jpeg"
@@ -19,7 +20,7 @@ import (
 var dataURLPattern = regexp.MustCompile(`data:image/([^;]+);base64,(.*)`)
 
 func IsImageUrl(url string) (bool, error) {
-	resp, err := http.Head(url)
+	resp, err := client.UserContentRequestHTTPClient.Head(url)
 	if err != nil {
 		return false, err
 	}
@@ -34,7 +35,7 @@ func GetImageSizeFromUrl(url string) (width int, height int, err error) {
 	if !isImage {
 		return
 	}
-	resp, err := http.Get(url)
+	resp, err := client.UserContentRequestHTTPClient.Get(url)
 	if err != nil {
 		return
 	}

common/image/image_test.go

@@ -2,6 +2,7 @@ package image_test
 
 import (
 	"encoding/base64"
+	"github.com/songquanpeng/one-api/common/client"
 	"image"
 	_ "image/gif"
 	_ "image/jpeg"
@@ -44,6 +45,11 @@ var (
 	}
 )
 
+func TestMain(m *testing.M) {
+	client.Init()
+	m.Run()
+}
+
 func TestDecode(t *testing.T) {
 	// Bytes read: varies sometimes
 	// jpeg: 1063892

common/init.go

@@ -24,7 +24,7 @@ func printHelp() {
 	fmt.Println("Usage: one-api [--port <port>] [--log-dir <log directory>] [--version] [--help]")
 }
 
-func init() {
+func Init() {
 	flag.Parse()
 
 	if *PrintVersion {

common/logger/logger.go

@@ -27,7 +27,12 @@ var setupLogOnce sync.Once
 func SetupLogger() {
 	setupLogOnce.Do(func() {
 		if LogDir != "" {
-			logPath := filepath.Join(LogDir, fmt.Sprintf("oneapi-%s.log", time.Now().Format("20060102")))
+			var logPath string
+			if config.OnlyOneLogFile {
+				logPath = filepath.Join(LogDir, "oneapi.log")
+			} else {
+				logPath = filepath.Join(LogDir, fmt.Sprintf("oneapi-%s.log", time.Now().Format("20060102")))
+			}
 			fd, err := os.OpenFile(logPath, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0644)
 			if err != nil {
 				log.Fatal("failed to open log file")
@@ -43,11 +48,19 @@ func SysLog(s string) {
 	_, _ = fmt.Fprintf(gin.DefaultWriter, "[SYS] %v | %s \n", t.Format("2006/01/02 - 15:04:05"), s)
 }
 
+func SysLogf(format string, a ...any) {
+	SysLog(fmt.Sprintf(format, a...))
+}
+
 func SysError(s string) {
 	t := time.Now()
 	_, _ = fmt.Fprintf(gin.DefaultErrorWriter, "[SYS] %v | %s \n", t.Format("2006/01/02 - 15:04:05"), s)
 }
 
+func SysErrorf(format string, a ...any) {
+	SysError(fmt.Sprintf(format, a...))
+}
+
 func Debug(ctx context.Context, msg string) {
 	if config.DebugEnabled {
 		logHelper(ctx, loggerDEBUG, msg)

common/render/render.go

@@ -0,0 +1,29 @@
+package render
+
+import (
+	"encoding/json"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"strings"
+)
+
+func StringData(c *gin.Context, str string) {
+	str = strings.TrimPrefix(str, "data: ")
+	str = strings.TrimSuffix(str, "\r")
+	c.Render(-1, common.CustomEvent{Data: "data: " + str})
+	c.Writer.Flush()
+}
+
+func ObjectData(c *gin.Context, object interface{}) error {
+	jsonData, err := json.Marshal(object)
+	if err != nil {
+		return fmt.Errorf("error marshalling object: %w", err)
+	}
+	StringData(c, string(jsonData))
+	return nil
+}
+
+func Done(c *gin.Context) {
+	StringData(c, "[DONE]")
+}

controller/channel-billing.go

@@ -4,12 +4,12 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"github.com/songquanpeng/one-api/common/client"
 	"github.com/songquanpeng/one-api/common/config"
 	"github.com/songquanpeng/one-api/common/logger"
 	"github.com/songquanpeng/one-api/model"
 	"github.com/songquanpeng/one-api/monitor"
 	"github.com/songquanpeng/one-api/relay/channeltype"
-	"github.com/songquanpeng/one-api/relay/client"
 	"io"
 	"net/http"
 	"strconv"

controller/relay.go

@@ -4,6 +4,9 @@ import (
 	"bytes"
 	"context"
 	"fmt"
+	"io"
+	"net/http"
+
 	"github.com/gin-gonic/gin"
 	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/config"
@@ -16,8 +19,6 @@ import (
 	"github.com/songquanpeng/one-api/relay/controller"
 	"github.com/songquanpeng/one-api/relay/model"
 	"github.com/songquanpeng/one-api/relay/relaymode"
-	"io"
-	"net/http"
 )
 
 // https://platform.openai.com/docs/api-reference/chat
@@ -47,6 +48,7 @@ func Relay(c *gin.Context) {
 		logger.Debugf(ctx, "request body: %s", string(requestBody))
 	}
 	channelId := c.GetInt(ctxkey.ChannelId)
+	userId := c.GetInt(ctxkey.Id)
 	bizErr := relayHelper(c, relayMode)
 	if bizErr == nil {
 		monitor.Emit(channelId, true)
@@ -56,7 +58,7 @@ func Relay(c *gin.Context) {
 	channelName := c.GetString(ctxkey.ChannelName)
 	group := c.GetString(ctxkey.Group)
 	originalModel := c.GetString(ctxkey.OriginalModel)
-	go processChannelRelayError(ctx, channelId, channelName, bizErr)
+	go processChannelRelayError(ctx, userId, channelId, channelName, bizErr)
 	requestId := c.GetString(helper.RequestIdKey)
 	retryTimes := config.RetryTimes
 	if !shouldRetry(c, bizErr.StatusCode) {
@@ -83,7 +85,7 @@ func Relay(c *gin.Context) {
 		channelId := c.GetInt(ctxkey.ChannelId)
 		lastFailedChannelId = channelId
 		channelName := c.GetString(ctxkey.ChannelName)
-		go processChannelRelayError(ctx, channelId, channelName, bizErr)
+		go processChannelRelayError(ctx, userId, channelId, channelName, bizErr)
 	}
 	if bizErr != nil {
 		if bizErr.StatusCode == http.StatusTooManyRequests {
@@ -115,8 +117,8 @@ func shouldRetry(c *gin.Context, statusCode int) bool {
 	return true
 }
 
-func processChannelRelayError(ctx context.Context, channelId int, channelName string, err *model.ErrorWithStatusCode) {
-	logger.Errorf(ctx, "relay error (channel #%d): %s", channelId, err.Message)
+func processChannelRelayError(ctx context.Context, userId int, channelId int, channelName string, err *model.ErrorWithStatusCode) {
+	logger.Errorf(ctx, "relay error (channel id %d, user id: %d): %s", channelId, userId, err.Message)
 	// https://platform.openai.com/docs/guides/error-codes/api-errors
 	if monitor.ShouldDisableChannel(&err.Error, err.StatusCode) {
 		monitor.DisableChannel(channelId, channelName, err.Message)

controller/user.go

@@ -173,6 +173,7 @@ func Register(c *gin.Context) {
 		})
 		return
 	}
+
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",

go.mod

@@ -4,42 +4,43 @@ module github.com/songquanpeng/one-api
 go 1.20
 
 require (
-	github.com/aws/aws-sdk-go-v2 v1.26.1
-	github.com/aws/aws-sdk-go-v2/credentials v1.17.11
-	github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.7.4
-	github.com/gin-contrib/cors v1.7.1
-	github.com/gin-contrib/gzip v1.0.0
-	github.com/gin-contrib/sessions v1.0.0
-	github.com/gin-contrib/static v1.1.1
-	github.com/gin-gonic/gin v1.9.1
-	github.com/go-playground/validator/v10 v10.19.0
+	github.com/aws/aws-sdk-go-v2 v1.27.0
+	github.com/aws/aws-sdk-go-v2/credentials v1.17.15
+	github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.8.3
+	github.com/gin-contrib/cors v1.7.2
+	github.com/gin-contrib/gzip v1.0.1
+	github.com/gin-contrib/sessions v1.0.1
+	github.com/gin-contrib/static v1.1.2
+	github.com/gin-gonic/gin v1.10.0
+	github.com/go-playground/validator/v10 v10.20.0
 	github.com/go-redis/redis/v8 v8.11.5
 	github.com/golang-jwt/jwt v3.2.2+incompatible
 	github.com/google/uuid v1.6.0
 	github.com/gorilla/websocket v1.5.1
 	github.com/jinzhu/copier v0.4.0
+	github.com/joho/godotenv v1.5.1
 	github.com/pkg/errors v0.9.1
-	github.com/pkoukk/tiktoken-go v0.1.6
+	github.com/pkoukk/tiktoken-go v0.1.7
 	github.com/smartystreets/goconvey v1.8.1
 	github.com/stretchr/testify v1.9.0
-	golang.org/x/crypto v0.22.0
-	golang.org/x/image v0.15.0
+	golang.org/x/crypto v0.23.0
+	golang.org/x/image v0.18.0
 	gorm.io/driver/mysql v1.5.6
 	gorm.io/driver/postgres v1.5.7
 	gorm.io/driver/sqlite v1.5.5
-	gorm.io/gorm v1.25.9
+	gorm.io/gorm v1.25.10
 )
 
 require (
 	filippo.io/edwards25519 v1.1.0 // indirect
 	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.2 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.5 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.5 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.7 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.7 // indirect
 	github.com/aws/smithy-go v1.20.2 // indirect
-	github.com/bytedance/sonic v1.11.5 // indirect
+	github.com/bytedance/sonic v1.11.6 // indirect
 	github.com/bytedance/sonic/loader v0.1.1 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
-	github.com/cloudwego/base64x v0.1.3 // indirect
+	github.com/cloudwego/base64x v0.1.4 // indirect
 	github.com/cloudwego/iasm v0.2.0 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
@@ -50,7 +51,7 @@ require (
 	github.com/go-playground/locales v0.14.1 // indirect
 	github.com/go-playground/universal-translator v0.18.1 // indirect
 	github.com/go-sql-driver/mysql v1.8.1 // indirect
-	github.com/goccy/go-json v0.10.2 // indirect
+	github.com/goccy/go-json v0.10.3 // indirect
 	github.com/gopherjs/gopherjs v1.17.2 // indirect
 	github.com/gorilla/context v1.1.2 // indirect
 	github.com/gorilla/securecookie v1.1.2 // indirect
@@ -70,16 +71,16 @@ require (
 	github.com/mattn/go-sqlite3 v2.0.3+incompatible // 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 v2.2.1 // indirect
+	github.com/pelletier/go-toml/v2 v2.2.2 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/smarty/assertions v1.15.0 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
 	github.com/ugorji/go/codec v1.2.12 // indirect
-	golang.org/x/arch v0.7.0 // indirect
-	golang.org/x/net v0.24.0 // indirect
+	golang.org/x/arch v0.8.0 // indirect
+	golang.org/x/net v0.25.0 // indirect
 	golang.org/x/sync v0.7.0 // indirect
-	golang.org/x/sys v0.19.0 // indirect
-	golang.org/x/text v0.14.0 // indirect
-	google.golang.org/protobuf v1.33.0 // indirect
+	golang.org/x/sys v0.20.0 // indirect
+	golang.org/x/text v0.16.0 // indirect
+	google.golang.org/protobuf v1.34.1 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

go.sum

@@ -1,28 +1,27 @@
 filippo.io/edwards25519 v1.1.0 h1:FNf4tywRC1HmFuKW5xopWpigGjJKiJSV0Cqo0cJWDaA=
 filippo.io/edwards25519 v1.1.0/go.mod h1:BxyFTGdWcka3PhytdK4V28tE5sGfRvvvRV7EaN4VDT4=
-github.com/aws/aws-sdk-go-v2 v1.26.1 h1:5554eUqIYVWpU0YmeeYZ0wU64H2VLBs8TlhRB2L+EkA=
-github.com/aws/aws-sdk-go-v2 v1.26.1/go.mod h1:ffIFB97e2yNsv4aTSGkqtHnppsIJzw7G7BReUZ3jCXM=
+github.com/aws/aws-sdk-go-v2 v1.27.0 h1:7bZWKoXhzI+mMR/HjdMx8ZCC5+6fY0lS5tr0bbgiLlo=
+github.com/aws/aws-sdk-go-v2 v1.27.0/go.mod h1:ffIFB97e2yNsv4aTSGkqtHnppsIJzw7G7BReUZ3jCXM=
 github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.2 h1:x6xsQXGSmW6frevwDA+vi/wqhp1ct18mVXYN08/93to=
 github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.2/go.mod h1:lPprDr1e6cJdyYeGXnRaJoP4Md+cDBvi2eOj00BlGmg=
-github.com/aws/aws-sdk-go-v2/credentials v1.17.11 h1:YuIB1dJNf1Re822rriUOTxopaHHvIq0l/pX3fwO+Tzs=
-github.com/aws/aws-sdk-go-v2/credentials v1.17.11/go.mod h1:AQtFPsDH9bI2O+71anW6EKL+NcD7LG3dpKGMV4SShgo=
-github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.5 h1:aw39xVGeRWlWx9EzGVnhOR4yOjQDHPQ6o6NmBlscyQg=
-github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.5/go.mod h1:FSaRudD0dXiMPK2UjknVwwTYyZMRsHv3TtkabsZih5I=
-github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.5 h1:PG1F3OD1szkuQPzDw3CIQsRIrtTlUC3lP84taWzHlq0=
-github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.5/go.mod h1:jU1li6RFryMz+so64PpKtudI+QzbKoIEivqdf6LNpOc=
-github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.7.4 h1:JgHnonzbnA3pbqj76wYsSZIZZQYBxkmMEjvL6GHy8XU=
-github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.7.4/go.mod h1:nZspkhg+9p8iApLFoyAqfyuMP0F38acy2Hm3r5r95Cg=
+github.com/aws/aws-sdk-go-v2/credentials v1.17.15 h1:YDexlvDRCA8ems2T5IP1xkMtOZ1uLJOCJdTr0igs5zo=
+github.com/aws/aws-sdk-go-v2/credentials v1.17.15/go.mod h1:vxHggqW6hFNaeNC0WyXS3VdyjcV0a4KMUY4dKJ96buU=
+github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.7 h1:lf/8VTF2cM+N4SLzaYJERKEWAXq8MOMpZfU6wEPWsPk=
+github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.7/go.mod h1:4SjkU7QiqK2M9oozyMzfZ/23LmUY+h3oFqhdeP5OMiI=
+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.7 h1:4OYVp0705xu8yjdyoWix0r9wPIRXnIzzOoUpQVHIJ/g=
+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.7/go.mod h1:vd7ESTEvI76T2Na050gODNmNU7+OyKrIKroYTu4ABiI=
+github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.8.3 h1:Fihjyd6DeNjcawBEGLH9dkIEUi6AdhucDKPE9nJ4QiY=
+github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.8.3/go.mod h1:opvUj3ismqSCxYc+m4WIjPL0ewZGtvp0ess7cKvBPOQ=
 github.com/aws/smithy-go v1.20.2 h1:tbp628ireGtzcHDDmLT/6ADHidqnwgF57XOXZe6tp4Q=
 github.com/aws/smithy-go v1.20.2/go.mod h1:krry+ya/rV9RDcV/Q16kpu6ypI4K2czasz0NC3qS14E=
-github.com/bytedance/sonic v1.11.5 h1:G00FYjjqll5iQ1PYXynbg/hyzqBqavH8Mo9/oTopd9k=
-github.com/bytedance/sonic v1.11.5/go.mod h1:X2PC2giUdj/Cv2lliWFLk6c/DUQok5rViJSemeB0wDw=
-github.com/bytedance/sonic/loader v0.1.0/go.mod h1:UmRT+IRTGKz/DAkzcEGzyVqQFJ7H9BqwBO3pm9H/+HY=
+github.com/bytedance/sonic v1.11.6 h1:oUp34TzMlL+OY1OUWxHqsdkgC/Zfc85zGqw9siXjrc0=
+github.com/bytedance/sonic v1.11.6/go.mod h1:LysEHSvpvDySVdC2f87zGWf6CIKJcAvqab1ZaiQtds4=
 github.com/bytedance/sonic/loader v0.1.1 h1:c+e5Pt1k/cy5wMveRDyk2X4B9hF4g7an8N3zCYjJFNM=
 github.com/bytedance/sonic/loader v0.1.1/go.mod h1:ncP89zfokxS5LZrJxl5z0UJcsk4M4yY2JpfqGeCtNLU=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
 github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
-github.com/cloudwego/base64x v0.1.3 h1:b5J/l8xolB7dyDTTmhJP2oTs5LdrjyrUFuNxdfq5hAg=
-github.com/cloudwego/base64x v0.1.3/go.mod h1:1+1K5BUHIQzyapgpF7LwvOGAEDicKtt1umPV+aN8pi8=
+github.com/cloudwego/base64x v0.1.4 h1:jwCgWpFanWmN8xoIUHa2rtzmkd5J2plF/dnLS6Xd/0Y=
+github.com/cloudwego/base64x v0.1.4/go.mod h1:0zlkT4Wn5C6NdauXdJRhSKRlJvmclQ1hhJgA0rcu/8w=
 github.com/cloudwego/iasm v0.2.0 h1:1KNIy1I1H9hNNFEEH3DVnI4UujN+1zjpuk6gwHLTssg=
 github.com/cloudwego/iasm v0.2.0/go.mod h1:8rXZaNYT2n95jn+zTI1sDr+IgcD2GVs0nlbbQPiEFhY=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
@@ -37,32 +36,32 @@ github.com/fsnotify/fsnotify v1.7.0 h1:8JEhPFa5W2WU7YfeZzPNqzMP6Lwt7L2715Ggo0nos
 github.com/fsnotify/fsnotify v1.7.0/go.mod h1:40Bi/Hjc2AVfZrqy+aj+yEI+/bRxZnMJyTJwOpGvigM=
 github.com/gabriel-vasile/mimetype v1.4.3 h1:in2uUcidCuFcDKtdcBxlR0rJ1+fsokWf+uqxgUFjbI0=
 github.com/gabriel-vasile/mimetype v1.4.3/go.mod h1:d8uq/6HKRL6CGdk+aubisF/M5GcPfT7nKyLpA0lbSSk=
-github.com/gin-contrib/cors v1.7.1 h1:s9SIppU/rk8enVvkzwiC2VK3UZ/0NNGsWfUKvV55rqs=
-github.com/gin-contrib/cors v1.7.1/go.mod h1:n/Zj7B4xyrgk/cX1WCX2dkzFfaNm/xJb6oIUk7WTtps=
-github.com/gin-contrib/gzip v1.0.0 h1:UKN586Po/92IDX6ie5CWLgMI81obiIp5nSP85T3wlTk=
-github.com/gin-contrib/gzip v1.0.0/go.mod h1:CtG7tQrPB3vIBo6Gat9FVUsis+1emjvQqd66ME5TdnE=
-github.com/gin-contrib/sessions v1.0.0 h1:r5GLta4Oy5xo9rAwMHx8B4wLpeRGHMdz9NafzJAdP8Y=
-github.com/gin-contrib/sessions v1.0.0/go.mod h1:DN0f4bvpqMQElDdi+gNGScrP2QEI04IErRyMFyorUOI=
+github.com/gin-contrib/cors v1.7.2 h1:oLDHxdg8W/XDoN/8zamqk/Drgt4oVZDvaV0YmvVICQw=
+github.com/gin-contrib/cors v1.7.2/go.mod h1:SUJVARKgQ40dmrzgXEVxj2m7Ig1v1qIboQkPDTQ9t2E=
+github.com/gin-contrib/gzip v1.0.1 h1:HQ8ENHODeLY7a4g1Au/46Z92bdGFl74OhxcZble9WJE=
+github.com/gin-contrib/gzip v1.0.1/go.mod h1:njt428fdUNRvjuJf16tZMYZ2Yl+WQB53X5wmhDwXvC4=
+github.com/gin-contrib/sessions v1.0.1 h1:3hsJyNs7v7N8OtelFmYXFrulAf6zSR7nW/putcPEHxI=
+github.com/gin-contrib/sessions v1.0.1/go.mod h1:ouxSFM24/OgIud5MJYQJLpy6AwxQ5EYO9yLhbtObGkM=
 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-contrib/static v1.1.1 h1:XEvBd4DDLG1HBlyPBQU1XO8NlTpw6mgdqcPteetYA5k=
-github.com/gin-contrib/static v1.1.1/go.mod h1:yRGmar7+JYvbMLRPIi4H5TVVSBwULfT9vetnVD0IO74=
-github.com/gin-gonic/gin v1.9.1 h1:4idEAncQnU5cB7BeOkPtxjfCSye0AAm1R0RVIqJ+Jmg=
-github.com/gin-gonic/gin v1.9.1/go.mod h1:hPrL7YrpYKXt5YId3A/Tnip5kqbEAP+KLuI3SUcPTeU=
+github.com/gin-contrib/static v1.1.2 h1:c3kT4bFkUJn2aoRU3s6XnMjJT8J6nNWJkR0NglqmlZ4=
+github.com/gin-contrib/static v1.1.2/go.mod h1:Fw90ozjHCmZBWbgrsqrDvO28YbhKEKzKp8GixhR4yLw=
+github.com/gin-gonic/gin v1.10.0 h1:nTuyha1TYqgedzytsKYqna+DfLos46nTv2ygFy86HFU=
+github.com/gin-gonic/gin v1.10.0/go.mod h1:4PMNQiOhvDRa013RKVbsiNwoyezlm2rm0uX/T7kzp5Y=
 github.com/go-playground/assert/v2 v2.2.0 h1:JvknZsQTYeFEAhQwI4qEt9cyV5ONwRHC+lYKSsYSR8s=
 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 v10.19.0 h1:ol+5Fu+cSq9JD7SoSqe04GMI92cbn0+wvQ3bZ8b/AU4=
-github.com/go-playground/validator/v10 v10.19.0/go.mod h1:dbuPbCMFw/DrkbEynArYaCwl3amGuJotoKCe95atGMM=
+github.com/go-playground/validator/v10 v10.20.0 h1:K9ISHbSaI0lyB2eWMPJo+kOS/FBExVwjEviJTixqxL8=
+github.com/go-playground/validator/v10 v10.20.0/go.mod h1:dbuPbCMFw/DrkbEynArYaCwl3amGuJotoKCe95atGMM=
 github.com/go-redis/redis/v8 v8.11.5 h1:AcZZR7igkdvfVmQTPnu9WE37LRrO/YrBH5zWyjDC0oI=
 github.com/go-redis/redis/v8 v8.11.5/go.mod h1:gREzHqY1hg6oD9ngVRbLStwAWKhA0FEgq8Jd4h5lpwo=
 github.com/go-sql-driver/mysql v1.7.0/go.mod h1:OXbVy3sEdcQ2Doequ6Z5BW6fXNQTmx+9S1MCJN5yJMI=
 github.com/go-sql-driver/mysql v1.8.1 h1:LedoTUt/eveggdHS9qUFC1EFSa8bU2+1pZjSRpvNJ1Y=
 github.com/go-sql-driver/mysql v1.8.1/go.mod h1:wEBSXgmK//2ZFJyE+qWnIsVGmvmEKlqwuVSjsCm7DZg=
-github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
-github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
+github.com/goccy/go-json v0.10.3 h1:KZ5WoDbxAIgm2HNbYckL0se1fHD6rz5j4ywS6ebzDqA=
+github.com/goccy/go-json v0.10.3/go.mod h1:oq7eo15ShAhp70Anwd5lgX2pLfOS3QCiwU/PULtXL6M=
 github.com/golang-jwt/jwt v3.2.2+incompatible h1:IfV12K8xAKAnZqdXVzCZ+TOjboZ2keLg81eXfW3O+oY=
 github.com/golang-jwt/jwt v3.2.2+incompatible/go.mod h1:8pz2t5EyA70fFQQSrl6XZXzqecmYZeUEB8OUGHkxJ+I=
 github.com/google/go-cmp v0.5.6 h1:BKbKCqvP6I+rmFHt06ZmyQtvB8xAkWdhFyr0ZUNZcxQ=
@@ -94,6 +93,8 @@ github.com/jinzhu/inflection v1.0.0 h1:K317FqzuhWc8YvSVlFMCCUb36O/S9MCKRDI7QkRKD
 github.com/jinzhu/inflection v1.0.0/go.mod h1:h+uFLlag+Qp1Va5pdKtLDYj+kHp5pxUVkryuEj+Srlc=
 github.com/jinzhu/now v1.1.5 h1:/o9tlHleP7gOFmsnYNz3RGnqzefHA47wQpKrrdTIwXQ=
 github.com/jinzhu/now v1.1.5/go.mod h1:d3SSVoowX0Lcu0IBviAWJpolVfI5UJVZZ7cO71lE/z8=
+github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0=
+github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4=
 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/jtolds/gls v4.20.0+incompatible h1:xdiiI2gbIgH/gLH7ADydsJ1uDOEzR8yvV7C0MuV77Wo=
@@ -119,12 +120,12 @@ github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjY
 github.com/nxadm/tail v1.4.8 h1:nPr65rt6Y5JFSKQO7qToXr7pePgD6Gwiw05lkbyAQTE=
 github.com/onsi/ginkgo v1.16.5 h1:8xi0RTUf59SOSfEtZMvwTvXYMzG4gV23XVHOZiXNtnE=
 github.com/onsi/gomega v1.18.1 h1:M1GfJqGRrBrrGGsbxzV5dqM2U2ApXefZCQpkukxYRLE=
-github.com/pelletier/go-toml/v2 v2.2.1 h1:9TA9+T8+8CUCO2+WYnDLCgrYi9+omqKXyjDtosvtEhg=
-github.com/pelletier/go-toml/v2 v2.2.1/go.mod h1:1t835xjRzz80PqgE6HHgN2JOsmgYu/h4qDAS4n929Rs=
+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/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
-github.com/pkoukk/tiktoken-go v0.1.6 h1:JF0TlJzhTbrI30wCvFuiw6FzP2+/bR+FIxUdgEAcUsw=
-github.com/pkoukk/tiktoken-go v0.1.6/go.mod h1:9NiV+i9mJKGj1rYOT+njbv+ZwA/zJxYdewGl6qVatpg=
+github.com/pkoukk/tiktoken-go v0.1.7 h1:qOBHXX4PHtvIvmOtyg1EeKlwFRiMKAcoMp4Q+bLQDmw=
+github.com/pkoukk/tiktoken-go v0.1.7/go.mod h1:9NiV+i9mJKGj1rYOT+njbv+ZwA/zJxYdewGl6qVatpg=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/rogpeppe/go-internal v1.8.0 h1:FCbCCtXNOY3UtUuHUYaghJg4y7Fd14rXifAYUAtL9R8=
@@ -149,25 +150,25 @@ github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2
 github.com/ugorji/go/codec v1.2.12 h1:9LC83zGrHhuUA9l16C9AHXAqEV/2wBQ4nkvumAE65EE=
 github.com/ugorji/go/codec v1.2.12/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
 golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
-golang.org/x/arch v0.7.0 h1:pskyeJh/3AmoQ8CPE95vxHLqp1G1GfGNXTmcl9NEKTc=
-golang.org/x/arch v0.7.0/go.mod h1:FEVrYAQjsQXMVJ1nsMoVVXPZg6p2JE2mx8psSWTDQys=
-golang.org/x/crypto v0.22.0 h1:g1v0xeRhjcugydODzvb3mEM9SQ0HGp9s/nh3COQ/C30=
-golang.org/x/crypto v0.22.0/go.mod h1:vr6Su+7cTlO45qkww3VDJlzDn0ctJvRgYbC2NvXHt+M=
-golang.org/x/image v0.15.0 h1:kOELfmgrmJlw4Cdb7g/QGuB3CvDrXbqEIww/pNtNBm8=
-golang.org/x/image v0.15.0/go.mod h1:HUYqC05R2ZcZ3ejNQsIHQDQiwWM4JBqmm6MKANTp4LE=
-golang.org/x/net v0.24.0 h1:1PcaxkF854Fu3+lvBIx5SYn9wRlBzzcnHZSiaFFAb0w=
-golang.org/x/net v0.24.0/go.mod h1:2Q7sJY5mzlzWjKtYUEXSlBWCdyaioyXzRB2RtU8KVE8=
+golang.org/x/arch v0.8.0 h1:3wRIsP3pM4yUptoR96otTUOXI367OS0+c9eeRi9doIc=
+golang.org/x/arch v0.8.0/go.mod h1:FEVrYAQjsQXMVJ1nsMoVVXPZg6p2JE2mx8psSWTDQys=
+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/image v0.18.0 h1:jGzIakQa/ZXI1I0Fxvaa9W7yP25TqT6cHIHn+6CqvSQ=
+golang.org/x/image v0.18.0/go.mod h1:4yyo5vMFQjVjUcVk4jEQcU9MGy/rulF5WvUILseCM2E=
+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/sync v0.7.0 h1:YsImfSBoP9QPYL0xyKJPq0gcaJdG3rInoqxTWbfQu9M=
 golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.19.0 h1:q5f1RH2jigJ1MoAWp2KTp3gm5zAGFUTarQZ5U386+4o=
-golang.org/x/sys v0.19.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
-golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
-golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+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 v0.16.0 h1:a94ExnEXNtEwYLGJSIUxnWoxoRz/ZcCsV63ROupILh4=
+golang.org/x/text v0.16.0/go.mod h1:GhwF1Be+LQoKShO3cGOHzqOgRrGaYc9AvblQOmPVHnI=
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1 h1:go1bK/D/BFZV2I8cIQd1NKEZ+0owSTG1fDTci4IqFcE=
-google.golang.org/protobuf v1.33.0 h1:uNO2rsAINq/JlFpSdYEKIZ0uKD/R9cpdv0T+yoGwGmI=
-google.golang.org/protobuf v1.33.0/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
+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/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 h1:uRGJdciOHaEIrze2W8Q3AKkepLTh2hOroT7a+7czfdQ=
@@ -182,7 +183,7 @@ gorm.io/driver/postgres v1.5.7/go.mod h1:3e019WlBaYI5o5LIdNV+LyxCMNtLOQETBXL2h4c
 gorm.io/driver/sqlite v1.5.5 h1:7MDMtUZhV065SilG62E0MquljeArQZNfJnjd9i9gx3E=
 gorm.io/driver/sqlite v1.5.5/go.mod h1:6NgQ7sQWAIFsPrJJl1lSNSu2TABh0ZZ/zm5fosATavE=
 gorm.io/gorm v1.25.7/go.mod h1:hbnx/Oo0ChWMn1BIhpy1oYozzpM15i4YPuHDmfYtwg8=
-gorm.io/gorm v1.25.9 h1:wct0gxZIELDk8+ZqF/MVnHLkA1rvYlBWUMv2EdsK1g8=
-gorm.io/gorm v1.25.9/go.mod h1:hbnx/Oo0ChWMn1BIhpy1oYozzpM15i4YPuHDmfYtwg8=
+gorm.io/gorm v1.25.10 h1:dQpO+33KalOA+aFYGlK+EfxcI5MbO7EP2yYygwh9h+s=
+gorm.io/gorm v1.25.10/go.mod h1:hbnx/Oo0ChWMn1BIhpy1oYozzpM15i4YPuHDmfYtwg8=
 nullprogram.com/x/optparse v1.0.0/go.mod h1:KdyPE+Igbe0jQUrVfMqDMeJQIJZEuyV7pjYmp6pbG50=
 rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=

main.go

@@ -6,7 +6,9 @@ import (
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-contrib/sessions/cookie"
 	"github.com/gin-gonic/gin"
+	_ "github.com/joho/godotenv/autoload"
 	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/client"
 	"github.com/songquanpeng/one-api/common/config"
 	"github.com/songquanpeng/one-api/common/logger"
 	"github.com/songquanpeng/one-api/controller"
@@ -22,29 +24,22 @@ import (
 var buildFS embed.FS
 
 func main() {
+	common.Init()
 	logger.SetupLogger()
-	logger.SysLog(fmt.Sprintf("One API %s started", common.Version))
-	if os.Getenv("GIN_MODE") != "debug" {
+	logger.SysLogf("One API %s started", common.Version)
+
+	if os.Getenv("GIN_MODE") != gin.DebugMode {
 		gin.SetMode(gin.ReleaseMode)
 	}
 	if config.DebugEnabled {
 		logger.SysLog("running in debug mode")
 	}
-	var err error
+
 	// Initialize SQL Database
-	model.DB, err = model.InitDB("SQL_DSN")
-	if err != nil {
-		logger.FatalLog("failed to initialize database: " + err.Error())
-	}
-	if os.Getenv("LOG_SQL_DSN") != "" {
-		logger.SysLog("using secondary database for table logs")
-		model.LOG_DB, err = model.InitDB("LOG_SQL_DSN")
-		if err != nil {
-			logger.FatalLog("failed to initialize secondary database: " + err.Error())
-		}
-	} else {
-		model.LOG_DB = model.DB
-	}
+	model.InitDB()
+	model.InitLogDB()
+
+	var err error
 	err = model.CreateRootAccountIfNeed()
 	if err != nil {
 		logger.FatalLog("database init error: " + err.Error())
@@ -94,6 +89,7 @@ func main() {
 		logger.SysLog("metric enabled, will disable channel if too much request failed")
 	}
 	openai.InitTokenEncoders()
+	client.Init()
 
 	// Initialize HTTP server
 	server := gin.New()
@@ -111,6 +107,7 @@ func main() {
 	if port == "" {
 		port = strconv.Itoa(*common.Port)
 	}
+	logger.SysLogf("server started on http://localhost:%s", port)
 	err = server.Run(":" + port)
 	if err != nil {
 		logger.FatalLog("failed to start HTTP server: " + err.Error())

middleware/distributor.go

@@ -67,26 +67,28 @@ func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, mode
 	c.Set(ctxkey.BaseURL, channel.GetBaseURL())
 	cfg, _ := channel.LoadConfig()
 	// this is for backward compatibility
-	switch channel.Type {
-	case channeltype.Azure:
-		if cfg.APIVersion == "" {
-			cfg.APIVersion = channel.Other
-		}
-	case channeltype.Xunfei:
-		if cfg.APIVersion == "" {
-			cfg.APIVersion = channel.Other
-		}
-	case channeltype.Gemini:
-		if cfg.APIVersion == "" {
-			cfg.APIVersion = channel.Other
-		}
-	case channeltype.AIProxyLibrary:
-		if cfg.LibraryID == "" {
-			cfg.LibraryID = channel.Other
-		}
-	case channeltype.Ali:
-		if cfg.Plugin == "" {
-			cfg.Plugin = channel.Other
+	if channel.Other != nil {
+		switch channel.Type {
+		case channeltype.Azure:
+			if cfg.APIVersion == "" {
+				cfg.APIVersion = *channel.Other
+			}
+		case channeltype.Xunfei:
+			if cfg.APIVersion == "" {
+				cfg.APIVersion = *channel.Other
+			}
+		case channeltype.Gemini:
+			if cfg.APIVersion == "" {
+				cfg.APIVersion = *channel.Other
+			}
+		case channeltype.AIProxyLibrary:
+			if cfg.LibraryID == "" {
+				cfg.LibraryID = *channel.Other
+			}
+		case channeltype.Ali:
+			if cfg.Plugin == "" {
+				cfg.Plugin = *channel.Other
+			}
 		}
 	}
 	c.Set(ctxkey.Config, cfg)

model/channel.go

@@ -27,7 +27,7 @@ type Channel struct {
 	TestTime           int64   `json:"test_time" gorm:"bigint"`
 	ResponseTime       int     `json:"response_time"` // in milliseconds
 	BaseURL            *string `json:"base_url" gorm:"column:base_url;default:''"`
-	Other              string  `json:"other"`   // DEPRECATED: please save config to field Config
+	Other              *string `json:"other"`   // DEPRECATED: please save config to field Config
 	Balance            float64 `json:"balance"` // in USD
 	BalanceUpdatedTime int64   `json:"balance_updated_time" gorm:"bigint"`
 	Models             string  `json:"models"`

model/main.go

@@ -1,6 +1,7 @@
 package model
 
 import (
+	"database/sql"
 	"fmt"
 	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/config"
@@ -60,90 +61,156 @@ func CreateRootAccountIfNeed() error {
 }
 
 func chooseDB(envName string) (*gorm.DB, error) {
-	if os.Getenv(envName) != "" {
-		dsn := os.Getenv(envName)
-		if strings.HasPrefix(dsn, "postgres://") {
-			// Use PostgreSQL
-			logger.SysLog("using PostgreSQL as database")
-			common.UsingPostgreSQL = true
-			return gorm.Open(postgres.New(postgres.Config{
-				DSN:                  dsn,
-				PreferSimpleProtocol: true, // disables implicit prepared statement usage
-			}), &gorm.Config{
-				PrepareStmt: true, // precompile SQL
-			})
-		}
+	dsn := os.Getenv(envName)
+
+	switch {
+	case strings.HasPrefix(dsn, "postgres://"):
+		// Use PostgreSQL
+		return openPostgreSQL(dsn)
+	case dsn != "":
 		// Use MySQL
-		logger.SysLog("using MySQL as database")
-		common.UsingMySQL = true
-		return gorm.Open(mysql.Open(dsn), &gorm.Config{
-			PrepareStmt: true, // precompile SQL
-		})
+		return openMySQL(dsn)
+	default:
+		// Use SQLite
+		return openSQLite()
 	}
-	// Use SQLite
-	logger.SysLog("SQL_DSN not set, using SQLite as database")
-	common.UsingSQLite = true
-	config := fmt.Sprintf("?_busy_timeout=%d", common.SQLiteBusyTimeout)
-	return gorm.Open(sqlite.Open(common.SQLitePath+config), &gorm.Config{
+}
+
+func openPostgreSQL(dsn string) (*gorm.DB, error) {
+	logger.SysLog("using PostgreSQL as database")
+	common.UsingPostgreSQL = true
+	return gorm.Open(postgres.New(postgres.Config{
+		DSN:                  dsn,
+		PreferSimpleProtocol: true, // disables implicit prepared statement usage
+	}), &gorm.Config{
 		PrepareStmt: true, // precompile SQL
 	})
 }
 
-func InitDB(envName string) (db *gorm.DB, err error) {
-	db, err = chooseDB(envName)
-	if err == nil {
-		if config.DebugSQLEnabled {
-			db = db.Debug()
-		}
-		sqlDB, err := db.DB()
-		if err != nil {
-			return nil, err
-		}
-		sqlDB.SetMaxIdleConns(env.Int("SQL_MAX_IDLE_CONNS", 100))
-		sqlDB.SetMaxOpenConns(env.Int("SQL_MAX_OPEN_CONNS", 1000))
-		sqlDB.SetConnMaxLifetime(time.Second * time.Duration(env.Int("SQL_MAX_LIFETIME", 60)))
+func openMySQL(dsn string) (*gorm.DB, error) {
+	logger.SysLog("using MySQL as database")
+	common.UsingMySQL = true
+	return gorm.Open(mysql.Open(dsn), &gorm.Config{
+		PrepareStmt: true, // precompile SQL
+	})
+}
 
-		if !config.IsMasterNode {
-			return db, err
-		}
-		if common.UsingMySQL {
-			_, _ = sqlDB.Exec("DROP INDEX idx_channels_key ON channels;") // TODO: delete this line when most users have upgraded
-		}
-		logger.SysLog("database migration started")
-		err = db.AutoMigrate(&Channel{})
-		if err != nil {
-			return nil, err
-		}
-		err = db.AutoMigrate(&Token{})
-		if err != nil {
-			return nil, err
-		}
-		err = db.AutoMigrate(&User{})
-		if err != nil {
-			return nil, err
-		}
-		err = db.AutoMigrate(&Option{})
-		if err != nil {
-			return nil, err
-		}
-		err = db.AutoMigrate(&Redemption{})
-		if err != nil {
-			return nil, err
-		}
-		err = db.AutoMigrate(&Ability{})
-		if err != nil {
-			return nil, err
-		}
-		err = db.AutoMigrate(&Log{})
-		if err != nil {
-			return nil, err
-		}
-		logger.SysLog("database migrated")
-		return db, err
-	} else {
-		logger.FatalLog(err)
+func openSQLite() (*gorm.DB, error) {
+	logger.SysLog("SQL_DSN not set, using SQLite as database")
+	common.UsingSQLite = true
+	dsn := fmt.Sprintf("%s?_busy_timeout=%d", common.SQLitePath, common.SQLiteBusyTimeout)
+	return gorm.Open(sqlite.Open(dsn), &gorm.Config{
+		PrepareStmt: true, // precompile SQL
+	})
+}
+
+func InitDB() {
+	var err error
+	DB, err = chooseDB("SQL_DSN")
+	if err != nil {
+		logger.FatalLog("failed to initialize database: " + err.Error())
+		return
 	}
-	return db, err
+
+	sqlDB := setDBConns(DB)
+
+	if !config.IsMasterNode {
+		return
+	}
+
+	if common.UsingMySQL {
+		_, _ = sqlDB.Exec("DROP INDEX idx_channels_key ON channels;") // TODO: delete this line when most users have upgraded
+	}
+
+	logger.SysLog("database migration started")
+	if err = migrateDB(); err != nil {
+		logger.FatalLog("failed to migrate database: " + err.Error())
+		return
+	}
+	logger.SysLog("database migrated")
+}
+
+func migrateDB() error {
+	var err error
+	if err = DB.AutoMigrate(&Channel{}); err != nil {
+		return err
+	}
+	if err = DB.AutoMigrate(&Token{}); err != nil {
+		return err
+	}
+	if err = DB.AutoMigrate(&User{}); err != nil {
+		return err
+	}
+	if err = DB.AutoMigrate(&Option{}); err != nil {
+		return err
+	}
+	if err = DB.AutoMigrate(&Redemption{}); err != nil {
+		return err
+	}
+	if err = DB.AutoMigrate(&Ability{}); err != nil {
+		return err
+	}
+	if err = DB.AutoMigrate(&Log{}); err != nil {
+		return err
+	}
+	if err = DB.AutoMigrate(&Channel{}); err != nil {
+		return err
+	}
+	return nil
+}
+
+func InitLogDB() {
+	if os.Getenv("LOG_SQL_DSN") == "" {
+		LOG_DB = DB
+		return
+	}
+
+	logger.SysLog("using secondary database for table logs")
+	var err error
+	LOG_DB, err = chooseDB("LOG_SQL_DSN")
+	if err != nil {
+		logger.FatalLog("failed to initialize secondary database: " + err.Error())
+		return
+	}
+
+	setDBConns(LOG_DB)
+
+	if !config.IsMasterNode {
+		return
+	}
+
+	logger.SysLog("secondary database migration started")
+	err = migrateLOGDB()
+	if err != nil {
+		logger.FatalLog("failed to migrate secondary database: " + err.Error())
+		return
+	}
+	logger.SysLog("secondary database migrated")
+}
+
+func migrateLOGDB() error {
+	var err error
+	if err = LOG_DB.AutoMigrate(&Log{}); err != nil {
+		return err
+	}
+	return nil
+}
+
+func setDBConns(db *gorm.DB) *sql.DB {
+	if config.DebugSQLEnabled {
+		db = db.Debug()
+	}
+
+	sqlDB, err := db.DB()
+	if err != nil {
+		logger.FatalLog("failed to connect database: " + err.Error())
+		return nil
+	}
+
+	sqlDB.SetMaxIdleConns(env.Int("SQL_MAX_IDLE_CONNS", 100))
+	sqlDB.SetMaxOpenConns(env.Int("SQL_MAX_OPEN_CONNS", 1000))
+	sqlDB.SetConnMaxLifetime(time.Second * time.Duration(env.Int("SQL_MAX_LIFETIME", 60)))
+	return sqlDB
 }
 
 func closeDB(db *gorm.DB) error {

model/user.go

@@ -6,6 +6,7 @@ import (
 	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/blacklist"
 	"github.com/songquanpeng/one-api/common/config"
+	"github.com/songquanpeng/one-api/common/helper"
 	"github.com/songquanpeng/one-api/common/logger"
 	"github.com/songquanpeng/one-api/common/random"
 	"gorm.io/gorm"
@@ -140,6 +141,22 @@ func (user *User) Insert(inviterId int) error {
 			RecordLog(inviterId, LogTypeSystem, fmt.Sprintf("邀请用户赠送 %s", common.LogQuota(config.QuotaForInviter)))
 		}
 	}
+	// create default token
+	cleanToken := Token{
+		UserId:         user.Id,
+		Name:           "default",
+		Key:            random.GenerateKey(),
+		CreatedTime:    helper.GetTimestamp(),
+		AccessedTime:   helper.GetTimestamp(),
+		ExpiredTime:    -1,
+		RemainQuota:    -1,
+		UnlimitedQuota: true,
+	}
+	result.Error = cleanToken.Insert()
+	if result.Error != nil {
+		// do not block
+		logger.SysError(fmt.Sprintf("create default token for user %d failed: %s", user.Id, result.Error.Error()))
+	}
 	return nil
 }
 

relay/adaptor/aiproxy/main.go

@@ -4,6 +4,12 @@ import (
 	"bufio"
 	"encoding/json"
 	"fmt"
+	"github.com/songquanpeng/one-api/common/render"
+	"io"
+	"net/http"
+	"strconv"
+	"strings"
+
 	"github.com/gin-gonic/gin"
 	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/helper"
@@ -12,10 +18,6 @@ import (
 	"github.com/songquanpeng/one-api/relay/adaptor/openai"
 	"github.com/songquanpeng/one-api/relay/constant"
 	"github.com/songquanpeng/one-api/relay/model"
-	"io"
-	"net/http"
-	"strconv"
-	"strings"
 )
 
 // https://docs.aiproxy.io/dev/library#使用已经定制好的知识库进行对话问答
@@ -89,6 +91,7 @@ func streamResponseAIProxyLibrary2OpenAI(response *LibraryStreamResponse) *opena
 
 func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *model.Usage) {
 	var usage model.Usage
+	var documents []LibraryDocument
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
 		if atEOF && len(data) == 0 {
@@ -102,60 +105,48 @@ func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusC
 		}
 		return 0, nil, nil
 	})
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			if len(data) < 5 { // ignore blank line or wrong format
-				continue
-			}
-			if data[:5] != "data:" {
-				continue
-			}
-			data = data[5:]
-			dataChan <- data
-		}
-		stopChan <- true
-	}()
+
 	common.SetEventStreamHeaders(c)
-	var documents []LibraryDocument
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			var AIProxyLibraryResponse LibraryStreamResponse
-			err := json.Unmarshal([]byte(data), &AIProxyLibraryResponse)
-			if err != nil {
-				logger.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
-			if len(AIProxyLibraryResponse.Documents) != 0 {
-				documents = AIProxyLibraryResponse.Documents
-			}
-			response := streamResponseAIProxyLibrary2OpenAI(&AIProxyLibraryResponse)
-			jsonResponse, err := json.Marshal(response)
-			if err != nil {
-				logger.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
-			return true
-		case <-stopChan:
-			response := documentsAIProxyLibrary(documents)
-			jsonResponse, err := json.Marshal(response)
-			if err != nil {
-				logger.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		if len(data) < 5 || data[:5] != "data:" {
+			continue
 		}
-	})
-	err := resp.Body.Close()
+		data = data[5:]
+
+		var AIProxyLibraryResponse LibraryStreamResponse
+		err := json.Unmarshal([]byte(data), &AIProxyLibraryResponse)
+		if err != nil {
+			logger.SysError("error unmarshalling stream response: " + err.Error())
+			continue
+		}
+		if len(AIProxyLibraryResponse.Documents) != 0 {
+			documents = AIProxyLibraryResponse.Documents
+		}
+		response := streamResponseAIProxyLibrary2OpenAI(&AIProxyLibraryResponse)
+		err = render.ObjectData(c, response)
+		if err != nil {
+			logger.SysError(err.Error())
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		logger.SysError("error reading stream: " + err.Error())
+	}
+
+	response := documentsAIProxyLibrary(documents)
+	err := render.ObjectData(c, response)
+	if err != nil {
+		logger.SysError(err.Error())
+	}
+	render.Done(c)
+
+	err = resp.Body.Close()
 	if err != nil {
 		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
+
 	return nil, &usage
 }
 

relay/adaptor/ali/main.go

@@ -3,15 +3,17 @@ package ali
 import (
 	"bufio"
 	"encoding/json"
+	"github.com/songquanpeng/one-api/common/render"
+	"io"
+	"net/http"
+	"strings"
+
 	"github.com/gin-gonic/gin"
 	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/helper"
 	"github.com/songquanpeng/one-api/common/logger"
 	"github.com/songquanpeng/one-api/relay/adaptor/openai"
 	"github.com/songquanpeng/one-api/relay/model"
-	"io"
-	"net/http"
-	"strings"
 )
 
 // https://help.aliyun.com/document_detail/613695.html?spm=a2c4g.2399480.0.0.1adb778fAdzP9w#341800c0f8w0r
@@ -181,56 +183,43 @@ func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusC
 		}
 		return 0, nil, nil
 	})
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			if len(data) < 5 { // ignore blank line or wrong format
-				continue
-			}
-			if data[:5] != "data:" {
-				continue
-			}
-			data = data[5:]
-			dataChan <- data
-		}
-		stopChan <- true
-	}()
+
 	common.SetEventStreamHeaders(c)
-	//lastResponseText := ""
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			var aliResponse ChatResponse
-			err := json.Unmarshal([]byte(data), &aliResponse)
-			if err != nil {
-				logger.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
-			if aliResponse.Usage.OutputTokens != 0 {
-				usage.PromptTokens = aliResponse.Usage.InputTokens
-				usage.CompletionTokens = aliResponse.Usage.OutputTokens
-				usage.TotalTokens = aliResponse.Usage.InputTokens + aliResponse.Usage.OutputTokens
-			}
-			response := streamResponseAli2OpenAI(&aliResponse)
-			if response == nil {
-				return true
-			}
-			//response.Choices[0].Delta.Content = strings.TrimPrefix(response.Choices[0].Delta.Content, lastResponseText)
-			//lastResponseText = aliResponse.Output.Text
-			jsonResponse, err := json.Marshal(response)
-			if err != nil {
-				logger.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		if len(data) < 5 || data[:5] != "data:" {
+			continue
 		}
-	})
+		data = data[5:]
+
+		var aliResponse ChatResponse
+		err := json.Unmarshal([]byte(data), &aliResponse)
+		if err != nil {
+			logger.SysError("error unmarshalling stream response: " + err.Error())
+			continue
+		}
+		if aliResponse.Usage.OutputTokens != 0 {
+			usage.PromptTokens = aliResponse.Usage.InputTokens
+			usage.CompletionTokens = aliResponse.Usage.OutputTokens
+			usage.TotalTokens = aliResponse.Usage.InputTokens + aliResponse.Usage.OutputTokens
+		}
+		response := streamResponseAli2OpenAI(&aliResponse)
+		if response == nil {
+			continue
+		}
+		err = render.ObjectData(c, response)
+		if err != nil {
+			logger.SysError(err.Error())
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		logger.SysError("error reading stream: " + err.Error())
+	}
+
+	render.Done(c)
+
 	err := resp.Body.Close()
 	if err != nil {
 		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil

relay/adaptor/anthropic/constants.go

@@ -5,4 +5,5 @@ var ModelList = []string{
 	"claude-3-haiku-20240307",
 	"claude-3-sonnet-20240229",
 	"claude-3-opus-20240229",
+	"claude-3-5-sonnet-20240620",
 }

relay/adaptor/anthropic/main.go

@@ -4,6 +4,7 @@ import (
 	"bufio"
 	"encoding/json"
 	"fmt"
+	"github.com/songquanpeng/one-api/common/render"
 	"io"
 	"net/http"
 	"strings"
@@ -28,12 +29,30 @@ func stopReasonClaude2OpenAI(reason *string) string {
 		return "stop"
 	case "max_tokens":
 		return "length"
+	case "tool_use":
+		return "tool_calls"
 	default:
 		return *reason
 	}
 }
 
 func ConvertRequest(textRequest model.GeneralOpenAIRequest) *Request {
+	claudeTools := make([]Tool, 0, len(textRequest.Tools))
+
+	for _, tool := range textRequest.Tools {
+		if params, ok := tool.Function.Parameters.(map[string]any); ok {
+			claudeTools = append(claudeTools, Tool{
+				Name:        tool.Function.Name,
+				Description: tool.Function.Description,
+				InputSchema: InputSchema{
+					Type:       params["type"].(string),
+					Properties: params["properties"],
+					Required:   params["required"],
+				},
+			})
+		}
+	}
+
 	claudeRequest := Request{
 		Model:       textRequest.Model,
 		MaxTokens:   textRequest.MaxTokens,
@@ -41,6 +60,24 @@ func ConvertRequest(textRequest model.GeneralOpenAIRequest) *Request {
 		TopP:        textRequest.TopP,
 		TopK:        textRequest.TopK,
 		Stream:      textRequest.Stream,
+		Tools:       claudeTools,
+	}
+	if len(claudeTools) > 0 {
+		claudeToolChoice := struct {
+			Type string `json:"type"`
+			Name string `json:"name,omitempty"`
+		}{Type: "auto"} // default value https://docs.anthropic.com/en/docs/build-with-claude/tool-use#controlling-claudes-output
+		if choice, ok := textRequest.ToolChoice.(map[string]any); ok {
+			if function, ok := choice["function"].(map[string]any); ok {
+				claudeToolChoice.Type = "tool"
+				claudeToolChoice.Name = function["name"].(string)
+			}
+		} else if toolChoiceType, ok := textRequest.ToolChoice.(string); ok {
+			if toolChoiceType == "any" {
+				claudeToolChoice.Type = toolChoiceType
+			}
+		}
+		claudeRequest.ToolChoice = claudeToolChoice
 	}
 	if claudeRequest.MaxTokens == 0 {
 		claudeRequest.MaxTokens = 4096
@@ -63,7 +100,24 @@ func ConvertRequest(textRequest model.GeneralOpenAIRequest) *Request {
 		if message.IsStringContent() {
 			content.Type = "text"
 			content.Text = message.StringContent()
+			if message.Role == "tool" {
+				claudeMessage.Role = "user"
+				content.Type = "tool_result"
+				content.Content = content.Text
+				content.Text = ""
+				content.ToolUseId = message.ToolCallId
+			}
 			claudeMessage.Content = append(claudeMessage.Content, content)
+			for i := range message.ToolCalls {
+				inputParam := make(map[string]any)
+				_ = json.Unmarshal([]byte(message.ToolCalls[i].Function.Arguments.(string)), &inputParam)
+				claudeMessage.Content = append(claudeMessage.Content, Content{
+					Type:  "tool_use",
+					Id:    message.ToolCalls[i].Id,
+					Name:  message.ToolCalls[i].Function.Name,
+					Input: inputParam,
+				})
+			}
 			claudeRequest.Messages = append(claudeRequest.Messages, claudeMessage)
 			continue
 		}
@@ -96,16 +150,35 @@ func StreamResponseClaude2OpenAI(claudeResponse *StreamResponse) (*openai.ChatCo
 	var response *Response
 	var responseText string
 	var stopReason string
+	tools := make([]model.Tool, 0)
+
 	switch claudeResponse.Type {
 	case "message_start":
 		return nil, claudeResponse.Message
 	case "content_block_start":
 		if claudeResponse.ContentBlock != nil {
 			responseText = claudeResponse.ContentBlock.Text
+			if claudeResponse.ContentBlock.Type == "tool_use" {
+				tools = append(tools, model.Tool{
+					Id:   claudeResponse.ContentBlock.Id,
+					Type: "function",
+					Function: model.Function{
+						Name:      claudeResponse.ContentBlock.Name,
+						Arguments: "",
+					},
+				})
+			}
 		}
 	case "content_block_delta":
 		if claudeResponse.Delta != nil {
 			responseText = claudeResponse.Delta.Text
+			if claudeResponse.Delta.Type == "input_json_delta" {
+				tools = append(tools, model.Tool{
+					Function: model.Function{
+						Arguments: claudeResponse.Delta.PartialJson,
+					},
+				})
+			}
 		}
 	case "message_delta":
 		if claudeResponse.Usage != nil {
@@ -119,6 +192,10 @@ func StreamResponseClaude2OpenAI(claudeResponse *StreamResponse) (*openai.ChatCo
 	}
 	var choice openai.ChatCompletionsStreamResponseChoice
 	choice.Delta.Content = responseText
+	if len(tools) > 0 {
+		choice.Delta.Content = nil // compatible with other OpenAI derivative applications, like LobeOpenAICompatibleFactory ...
+		choice.Delta.ToolCalls = tools
+	}
 	choice.Delta.Role = "assistant"
 	finishReason := stopReasonClaude2OpenAI(&stopReason)
 	if finishReason != "null" {
@@ -135,12 +212,27 @@ func ResponseClaude2OpenAI(claudeResponse *Response) *openai.TextResponse {
 	if len(claudeResponse.Content) > 0 {
 		responseText = claudeResponse.Content[0].Text
 	}
+	tools := make([]model.Tool, 0)
+	for _, v := range claudeResponse.Content {
+		if v.Type == "tool_use" {
+			args, _ := json.Marshal(v.Input)
+			tools = append(tools, model.Tool{
+				Id:   v.Id,
+				Type: "function", // compatible with other OpenAI derivative applications
+				Function: model.Function{
+					Name:      v.Name,
+					Arguments: string(args),
+				},
+			})
+		}
+	}
 	choice := openai.TextResponseChoice{
 		Index: 0,
 		Message: model.Message{
-			Role:    "assistant",
-			Content: responseText,
-			Name:    nil,
+			Role:      "assistant",
+			Content:   responseText,
+			Name:      nil,
+			ToolCalls: tools,
 		},
 		FinishReason: stopReasonClaude2OpenAI(claudeResponse.StopReason),
 	}
@@ -169,64 +261,77 @@ func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusC
 		}
 		return 0, nil, nil
 	})
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			if len(data) < 6 {
-				continue
-			}
-			if !strings.HasPrefix(data, "data:") {
-				continue
-			}
-			data = strings.TrimPrefix(data, "data:")
-			dataChan <- data
-		}
-		stopChan <- true
-	}()
+
 	common.SetEventStreamHeaders(c)
+
 	var usage model.Usage
 	var modelName string
 	var id string
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			// some implementations may add \r at the end of data
-			data = strings.TrimSpace(data)
-			var claudeResponse StreamResponse
-			err := json.Unmarshal([]byte(data), &claudeResponse)
-			if err != nil {
-				logger.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
-			response, meta := StreamResponseClaude2OpenAI(&claudeResponse)
-			if meta != nil {
-				usage.PromptTokens += meta.Usage.InputTokens
-				usage.CompletionTokens += meta.Usage.OutputTokens
+	var lastToolCallChoice openai.ChatCompletionsStreamResponseChoice
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		if len(data) < 6 || !strings.HasPrefix(data, "data:") {
+			continue
+		}
+		data = strings.TrimPrefix(data, "data:")
+		data = strings.TrimSpace(data)
+
+		var claudeResponse StreamResponse
+		err := json.Unmarshal([]byte(data), &claudeResponse)
+		if err != nil {
+			logger.SysError("error unmarshalling stream response: " + err.Error())
+			continue
+		}
+
+		response, meta := StreamResponseClaude2OpenAI(&claudeResponse)
+		if meta != nil {
+			usage.PromptTokens += meta.Usage.InputTokens
+			usage.CompletionTokens += meta.Usage.OutputTokens
+			if len(meta.Id) > 0 { // only message_start has an id, otherwise it's a finish_reason event.
 				modelName = meta.Model
 				id = fmt.Sprintf("chatcmpl-%s", meta.Id)
-				return true
+				continue
+			} else { // finish_reason case
+				if len(lastToolCallChoice.Delta.ToolCalls) > 0 {
+					lastArgs := &lastToolCallChoice.Delta.ToolCalls[len(lastToolCallChoice.Delta.ToolCalls)-1].Function
+					if len(lastArgs.Arguments.(string)) == 0 { // compatible with OpenAI sending an empty object `{}` when no arguments.
+						lastArgs.Arguments = "{}"
+						response.Choices[len(response.Choices)-1].Delta.Content = nil
+						response.Choices[len(response.Choices)-1].Delta.ToolCalls = lastToolCallChoice.Delta.ToolCalls
+					}
+				}
 			}
-			if response == nil {
-				return true
-			}
-			response.Id = id
-			response.Model = modelName
-			response.Created = createdTime
-			jsonStr, err := json.Marshal(response)
-			if err != nil {
-				logger.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonStr)})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
 		}
-	})
-	_ = resp.Body.Close()
+		if response == nil {
+			continue
+		}
+
+		response.Id = id
+		response.Model = modelName
+		response.Created = createdTime
+
+		for _, choice := range response.Choices {
+			if len(choice.Delta.ToolCalls) > 0 {
+				lastToolCallChoice = choice
+			}
+		}
+		err = render.ObjectData(c, response)
+		if err != nil {
+			logger.SysError(err.Error())
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		logger.SysError("error reading stream: " + err.Error())
+	}
+
+	render.Done(c)
+
+	err := resp.Body.Close()
+	if err != nil {
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
 	return nil, &usage
 }
 

relay/adaptor/anthropic/model.go

@@ -16,6 +16,12 @@ type Content struct {
 	Type   string       `json:"type"`
 	Text   string       `json:"text,omitempty"`
 	Source *ImageSource `json:"source,omitempty"`
+	// tool_calls
+	Id        string `json:"id,omitempty"`
+	Name      string `json:"name,omitempty"`
+	Input     any    `json:"input,omitempty"`
+	Content   string `json:"content,omitempty"`
+	ToolUseId string `json:"tool_use_id,omitempty"`
 }
 
 type Message struct {
@@ -23,6 +29,18 @@ type Message struct {
 	Content []Content `json:"content"`
 }
 
+type Tool struct {
+	Name        string      `json:"name"`
+	Description string      `json:"description,omitempty"`
+	InputSchema InputSchema `json:"input_schema"`
+}
+
+type InputSchema struct {
+	Type       string `json:"type"`
+	Properties any    `json:"properties,omitempty"`
+	Required   any    `json:"required,omitempty"`
+}
+
 type Request struct {
 	Model         string    `json:"model"`
 	Messages      []Message `json:"messages"`
@@ -33,6 +51,8 @@ type Request struct {
 	Temperature   float64   `json:"temperature,omitempty"`
 	TopP          float64   `json:"top_p,omitempty"`
 	TopK          int       `json:"top_k,omitempty"`
+	Tools         []Tool    `json:"tools,omitempty"`
+	ToolChoice    any       `json:"tool_choice,omitempty"`
 	//Metadata    `json:"metadata,omitempty"`
 }
 
@@ -61,6 +81,7 @@ type Response struct {
 type Delta struct {
 	Type         string  `json:"type"`
 	Text         string  `json:"text"`
+	PartialJson  string  `json:"partial_json,omitempty"`
 	StopReason   *string `json:"stop_reason"`
 	StopSequence *string `json:"stop_sequence"`
 }

relay/adaptor/aws/main.go

@@ -6,6 +6,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"github.com/songquanpeng/one-api/common/ctxkey"
+	"github.com/songquanpeng/one-api/relay/adaptor/openai"
 	"io"
 	"net/http"
 
@@ -33,12 +34,13 @@ func wrapErr(err error) *relaymodel.ErrorWithStatusCode {
 
 // https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html
 var awsModelIDMap = map[string]string{
-	"claude-instant-1.2":       "anthropic.claude-instant-v1",
-	"claude-2.0":               "anthropic.claude-v2",
-	"claude-2.1":               "anthropic.claude-v2:1",
-	"claude-3-sonnet-20240229": "anthropic.claude-3-sonnet-20240229-v1:0",
-	"claude-3-opus-20240229":   "anthropic.claude-3-opus-20240229-v1:0",
-	"claude-3-haiku-20240307":  "anthropic.claude-3-haiku-20240307-v1:0",
+	"claude-instant-1.2":         "anthropic.claude-instant-v1",
+	"claude-2.0":                 "anthropic.claude-v2",
+	"claude-2.1":                 "anthropic.claude-v2:1",
+	"claude-3-sonnet-20240229":   "anthropic.claude-3-sonnet-20240229-v1:0",
+	"claude-3-5-sonnet-20240620": "anthropic.claude-3-5-sonnet-20240620-v1:0",
+	"claude-3-opus-20240229":     "anthropic.claude-3-opus-20240229-v1:0",
+	"claude-3-haiku-20240307":    "anthropic.claude-3-haiku-20240307-v1:0",
 }
 
 func awsModelID(requestModel string) (string, error) {
@@ -142,6 +144,8 @@ func StreamHandler(c *gin.Context, awsCli *bedrockruntime.Client) (*relaymodel.E
 	c.Writer.Header().Set("Content-Type", "text/event-stream")
 	var usage relaymodel.Usage
 	var id string
+	var lastToolCallChoice openai.ChatCompletionsStreamResponseChoice
+
 	c.Stream(func(w io.Writer) bool {
 		event, ok := <-stream.Events()
 		if !ok {
@@ -162,8 +166,19 @@ func StreamHandler(c *gin.Context, awsCli *bedrockruntime.Client) (*relaymodel.E
 			if meta != nil {
 				usage.PromptTokens += meta.Usage.InputTokens
 				usage.CompletionTokens += meta.Usage.OutputTokens
-				id = fmt.Sprintf("chatcmpl-%s", meta.Id)
-				return true
+				if len(meta.Id) > 0 { // only message_start has an id, otherwise it's a finish_reason event.
+					id = fmt.Sprintf("chatcmpl-%s", meta.Id)
+					return true
+				} else { // finish_reason case
+					if len(lastToolCallChoice.Delta.ToolCalls) > 0 {
+						lastArgs := &lastToolCallChoice.Delta.ToolCalls[len(lastToolCallChoice.Delta.ToolCalls)-1].Function
+						if len(lastArgs.Arguments.(string)) == 0 { // compatible with OpenAI sending an empty object `{}` when no arguments.
+							lastArgs.Arguments = "{}"
+							response.Choices[len(response.Choices)-1].Delta.Content = nil
+							response.Choices[len(response.Choices)-1].Delta.ToolCalls = lastToolCallChoice.Delta.ToolCalls
+						}
+					}
+				}
 			}
 			if response == nil {
 				return true
@@ -171,6 +186,12 @@ func StreamHandler(c *gin.Context, awsCli *bedrockruntime.Client) (*relaymodel.E
 			response.Id = id
 			response.Model = c.GetString(ctxkey.OriginalModel)
 			response.Created = createdTime
+
+			for _, choice := range response.Choices {
+				if len(choice.Delta.ToolCalls) > 0 {
+					lastToolCallChoice = choice
+				}
+			}
 			jsonStr, err := json.Marshal(response)
 			if err != nil {
 				logger.SysError("error marshalling stream response: " + err.Error())

relay/adaptor/aws/model.go

@@ -9,9 +9,12 @@ type Request struct {
 	// AnthropicVersion should be "bedrock-2023-05-31"
 	AnthropicVersion string              `json:"anthropic_version"`
 	Messages         []anthropic.Message `json:"messages"`
+	System           string              `json:"system,omitempty"`
 	MaxTokens        int                 `json:"max_tokens,omitempty"`
 	Temperature      float64             `json:"temperature,omitempty"`
 	TopP             float64             `json:"top_p,omitempty"`
 	TopK             int                 `json:"top_k,omitempty"`
 	StopSequences    []string            `json:"stop_sequences,omitempty"`
+	Tools            []anthropic.Tool    `json:"tools,omitempty"`
+	ToolChoice       any                 `json:"tool_choice,omitempty"`
 }

relay/adaptor/baidu/main.go

@@ -5,18 +5,20 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
-	"github.com/songquanpeng/one-api/common"
-	"github.com/songquanpeng/one-api/common/logger"
-	"github.com/songquanpeng/one-api/relay/adaptor/openai"
-	"github.com/songquanpeng/one-api/relay/client"
-	"github.com/songquanpeng/one-api/relay/constant"
-	"github.com/songquanpeng/one-api/relay/model"
+	"github.com/songquanpeng/one-api/common/render"
 	"io"
 	"net/http"
 	"strings"
 	"sync"
 	"time"
+
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/client"
+	"github.com/songquanpeng/one-api/common/logger"
+	"github.com/songquanpeng/one-api/relay/adaptor/openai"
+	"github.com/songquanpeng/one-api/relay/constant"
+	"github.com/songquanpeng/one-api/relay/model"
 )
 
 // https://cloud.baidu.com/doc/WENXINWORKSHOP/s/flfmc9do2
@@ -137,59 +139,41 @@ func embeddingResponseBaidu2OpenAI(response *EmbeddingResponse) *openai.Embeddin
 func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *model.Usage) {
 	var usage model.Usage
 	scanner := bufio.NewScanner(resp.Body)
-	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		if atEOF && len(data) == 0 {
-			return 0, nil, nil
-		}
-		if i := strings.Index(string(data), "\n"); i >= 0 {
-			return i + 1, data[0:i], nil
-		}
-		if atEOF {
-			return len(data), data, nil
-		}
-		return 0, nil, nil
-	})
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			if len(data) < 6 { // ignore blank line or wrong format
-				continue
-			}
-			data = data[6:]
-			dataChan <- data
-		}
-		stopChan <- true
-	}()
+	scanner.Split(bufio.ScanLines)
+
 	common.SetEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			var baiduResponse ChatStreamResponse
-			err := json.Unmarshal([]byte(data), &baiduResponse)
-			if err != nil {
-				logger.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
-			if baiduResponse.Usage.TotalTokens != 0 {
-				usage.TotalTokens = baiduResponse.Usage.TotalTokens
-				usage.PromptTokens = baiduResponse.Usage.PromptTokens
-				usage.CompletionTokens = baiduResponse.Usage.TotalTokens - baiduResponse.Usage.PromptTokens
-			}
-			response := streamResponseBaidu2OpenAI(&baiduResponse)
-			jsonResponse, err := json.Marshal(response)
-			if err != nil {
-				logger.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		if len(data) < 6 {
+			continue
 		}
-	})
+		data = data[6:]
+
+		var baiduResponse ChatStreamResponse
+		err := json.Unmarshal([]byte(data), &baiduResponse)
+		if err != nil {
+			logger.SysError("error unmarshalling stream response: " + err.Error())
+			continue
+		}
+		if baiduResponse.Usage.TotalTokens != 0 {
+			usage.TotalTokens = baiduResponse.Usage.TotalTokens
+			usage.PromptTokens = baiduResponse.Usage.PromptTokens
+			usage.CompletionTokens = baiduResponse.Usage.TotalTokens - baiduResponse.Usage.PromptTokens
+		}
+		response := streamResponseBaidu2OpenAI(&baiduResponse)
+		err = render.ObjectData(c, response)
+		if err != nil {
+			logger.SysError(err.Error())
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		logger.SysError("error reading stream: " + err.Error())
+	}
+
+	render.Done(c)
+
 	err := resp.Body.Close()
 	if err != nil {
 		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil

relay/adaptor/cloudflare/main.go

@@ -2,8 +2,8 @@ package cloudflare
 
 import (
 	"bufio"
-	"bytes"
 	"encoding/json"
+	"github.com/songquanpeng/one-api/common/render"
 	"io"
 	"net/http"
 	"strings"
@@ -17,10 +17,15 @@ import (
 )
 
 func ConvertRequest(textRequest model.GeneralOpenAIRequest) *Request {
-	lastMessage := textRequest.Messages[len(textRequest.Messages)-1]
+	var promptBuilder strings.Builder
+	for _, message := range textRequest.Messages {
+		promptBuilder.WriteString(message.StringContent())
+		promptBuilder.WriteString("\n") // 添加换行符来分隔每个消息
+	}
+
 	return &Request{
 		MaxTokens:   textRequest.MaxTokens,
-		Prompt:      lastMessage.StringContent(),
+		Prompt:      promptBuilder.String(),
 		Stream:      textRequest.Stream,
 		Temperature: textRequest.Temperature,
 	}
@@ -57,67 +62,54 @@ func StreamResponseCloudflare2OpenAI(cloudflareResponse *StreamResponse) *openai
 
 func StreamHandler(c *gin.Context, resp *http.Response, promptTokens int, modelName string) (*model.ErrorWithStatusCode, *model.Usage) {
 	scanner := bufio.NewScanner(resp.Body)
-	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		if atEOF && len(data) == 0 {
-			return 0, nil, nil
-		}
-		if i := bytes.IndexByte(data, '\n'); i >= 0 {
-			return i + 1, data[0:i], nil
-		}
-		if atEOF {
-			return len(data), data, nil
-		}
-		return 0, nil, nil
-	})
+	scanner.Split(bufio.ScanLines)
 
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			if len(data) < len("data: ") {
-				continue
-			}
-			data = strings.TrimPrefix(data, "data: ")
-			dataChan <- data
-		}
-		stopChan <- true
-	}()
 	common.SetEventStreamHeaders(c)
 	id := helper.GetResponseID(c)
 	responseModel := c.GetString("original_model")
 	var responseText string
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			// some implementations may add \r at the end of data
-			data = strings.TrimSuffix(data, "\r")
-			var cloudflareResponse StreamResponse
-			err := json.Unmarshal([]byte(data), &cloudflareResponse)
-			if err != nil {
-				logger.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
-			response := StreamResponseCloudflare2OpenAI(&cloudflareResponse)
-			if response == nil {
-				return true
-			}
-			responseText += cloudflareResponse.Response
-			response.Id = id
-			response.Model = responseModel
-			jsonStr, err := json.Marshal(response)
-			if err != nil {
-				logger.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonStr)})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		if len(data) < len("data: ") {
+			continue
 		}
-	})
-	_ = resp.Body.Close()
+		data = strings.TrimPrefix(data, "data: ")
+		data = strings.TrimSuffix(data, "\r")
+
+		var cloudflareResponse StreamResponse
+		err := json.Unmarshal([]byte(data), &cloudflareResponse)
+		if err != nil {
+			logger.SysError("error unmarshalling stream response: " + err.Error())
+			continue
+		}
+
+		response := StreamResponseCloudflare2OpenAI(&cloudflareResponse)
+		if response == nil {
+			continue
+		}
+
+		responseText += cloudflareResponse.Response
+		response.Id = id
+		response.Model = responseModel
+
+		err = render.ObjectData(c, response)
+		if err != nil {
+			logger.SysError(err.Error())
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		logger.SysError("error reading stream: " + err.Error())
+	}
+
+	render.Done(c)
+
+	err := resp.Body.Close()
+	if err != nil {
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+
 	usage := openai.ResponseText2Usage(responseText, responseModel, promptTokens)
 	return nil, usage
 }

relay/adaptor/cohere/main.go

@@ -2,9 +2,9 @@ package cohere
 
 import (
 	"bufio"
-	"bytes"
 	"encoding/json"
 	"fmt"
+	"github.com/songquanpeng/one-api/common/render"
 	"io"
 	"net/http"
 	"strings"
@@ -134,66 +134,53 @@ func ResponseCohere2OpenAI(cohereResponse *Response) *openai.TextResponse {
 func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *model.Usage) {
 	createdTime := helper.GetTimestamp()
 	scanner := bufio.NewScanner(resp.Body)
-	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		if atEOF && len(data) == 0 {
-			return 0, nil, nil
-		}
-		if i := bytes.IndexByte(data, '\n'); i >= 0 {
-			return i + 1, data[0:i], nil
-		}
-		if atEOF {
-			return len(data), data, nil
-		}
-		return 0, nil, nil
-	})
+	scanner.Split(bufio.ScanLines)
 
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			dataChan <- data
-		}
-		stopChan <- true
-	}()
 	common.SetEventStreamHeaders(c)
 	var usage model.Usage
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			// some implementations may add \r at the end of data
-			data = strings.TrimSuffix(data, "\r")
-			var cohereResponse StreamResponse
-			err := json.Unmarshal([]byte(data), &cohereResponse)
-			if err != nil {
-				logger.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
-			response, meta := StreamResponseCohere2OpenAI(&cohereResponse)
-			if meta != nil {
-				usage.PromptTokens += meta.Meta.Tokens.InputTokens
-				usage.CompletionTokens += meta.Meta.Tokens.OutputTokens
-				return true
-			}
-			if response == nil {
-				return true
-			}
-			response.Id = fmt.Sprintf("chatcmpl-%d", createdTime)
-			response.Model = c.GetString("original_model")
-			response.Created = createdTime
-			jsonStr, err := json.Marshal(response)
-			if err != nil {
-				logger.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonStr)})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		data = strings.TrimSuffix(data, "\r")
+
+		var cohereResponse StreamResponse
+		err := json.Unmarshal([]byte(data), &cohereResponse)
+		if err != nil {
+			logger.SysError("error unmarshalling stream response: " + err.Error())
+			continue
 		}
-	})
-	_ = resp.Body.Close()
+
+		response, meta := StreamResponseCohere2OpenAI(&cohereResponse)
+		if meta != nil {
+			usage.PromptTokens += meta.Meta.Tokens.InputTokens
+			usage.CompletionTokens += meta.Meta.Tokens.OutputTokens
+			continue
+		}
+		if response == nil {
+			continue
+		}
+
+		response.Id = fmt.Sprintf("chatcmpl-%d", createdTime)
+		response.Model = c.GetString("original_model")
+		response.Created = createdTime
+
+		err = render.ObjectData(c, response)
+		if err != nil {
+			logger.SysError(err.Error())
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		logger.SysError("error reading stream: " + err.Error())
+	}
+
+	render.Done(c)
+
+	err := resp.Body.Close()
+	if err != nil {
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+
 	return nil, &usage
 }
 

relay/adaptor/common.go

@@ -4,7 +4,7 @@ import (
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
-	"github.com/songquanpeng/one-api/relay/client"
+	"github.com/songquanpeng/one-api/common/client"
 	"github.com/songquanpeng/one-api/relay/meta"
 	"io"
 	"net/http"

relay/adaptor/coze/main.go

@@ -4,6 +4,11 @@ import (
 	"bufio"
 	"encoding/json"
 	"fmt"
+	"github.com/songquanpeng/one-api/common/render"
+	"io"
+	"net/http"
+	"strings"
+
 	"github.com/gin-gonic/gin"
 	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/conv"
@@ -12,9 +17,6 @@ import (
 	"github.com/songquanpeng/one-api/relay/adaptor/coze/constant/messagetype"
 	"github.com/songquanpeng/one-api/relay/adaptor/openai"
 	"github.com/songquanpeng/one-api/relay/model"
-	"io"
-	"net/http"
-	"strings"
 )
 
 // https://www.coze.com/open
@@ -109,69 +111,54 @@ func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusC
 	var responseText string
 	createdTime := helper.GetTimestamp()
 	scanner := bufio.NewScanner(resp.Body)
-	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		if atEOF && len(data) == 0 {
-			return 0, nil, nil
-		}
-		if i := strings.Index(string(data), "\n"); i >= 0 {
-			return i + 1, data[0:i], nil
-		}
-		if atEOF {
-			return len(data), data, nil
-		}
-		return 0, nil, nil
-	})
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			if len(data) < 5 {
-				continue
-			}
-			if !strings.HasPrefix(data, "data:") {
-				continue
-			}
-			data = strings.TrimPrefix(data, "data:")
-			dataChan <- data
-		}
-		stopChan <- true
-	}()
+	scanner.Split(bufio.ScanLines)
+
 	common.SetEventStreamHeaders(c)
 	var modelName string
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			// some implementations may add \r at the end of data
-			data = strings.TrimSuffix(data, "\r")
-			var cozeResponse StreamResponse
-			err := json.Unmarshal([]byte(data), &cozeResponse)
-			if err != nil {
-				logger.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
-			response, _ := StreamResponseCoze2OpenAI(&cozeResponse)
-			if response == nil {
-				return true
-			}
-			for _, choice := range response.Choices {
-				responseText += conv.AsString(choice.Delta.Content)
-			}
-			response.Model = modelName
-			response.Created = createdTime
-			jsonStr, err := json.Marshal(response)
-			if err != nil {
-				logger.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonStr)})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		if len(data) < 5 || !strings.HasPrefix(data, "data:") {
+			continue
 		}
-	})
-	_ = resp.Body.Close()
+		data = strings.TrimPrefix(data, "data:")
+		data = strings.TrimSuffix(data, "\r")
+
+		var cozeResponse StreamResponse
+		err := json.Unmarshal([]byte(data), &cozeResponse)
+		if err != nil {
+			logger.SysError("error unmarshalling stream response: " + err.Error())
+			continue
+		}
+
+		response, _ := StreamResponseCoze2OpenAI(&cozeResponse)
+		if response == nil {
+			continue
+		}
+
+		for _, choice := range response.Choices {
+			responseText += conv.AsString(choice.Delta.Content)
+		}
+		response.Model = modelName
+		response.Created = createdTime
+
+		err = render.ObjectData(c, response)
+		if err != nil {
+			logger.SysError(err.Error())
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		logger.SysError("error reading stream: " + err.Error())
+	}
+
+	render.Done(c)
+
+	err := resp.Body.Close()
+	if err != nil {
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+
 	return nil, &responseText
 }
 

relay/adaptor/doubao/constants.go

@@ -0,0 +1,13 @@
+package doubao
+
+// https://console.volcengine.com/ark/region:ark+cn-beijing/model
+
+var ModelList = []string{
+	"Doubao-pro-128k",
+	"Doubao-pro-32k",
+	"Doubao-pro-4k",
+	"Doubao-lite-128k",
+	"Doubao-lite-32k",
+	"Doubao-lite-4k",
+	"Doubao-embedding",
+}

relay/adaptor/doubao/main.go

@@ -0,0 +1,14 @@
+package doubao
+
+import (
+	"fmt"
+	"github.com/songquanpeng/one-api/relay/meta"
+	"github.com/songquanpeng/one-api/relay/relaymode"
+)
+
+func GetRequestURL(meta *meta.Meta) (string, error) {
+	if meta.Mode == relaymode.ChatCompletions {
+		return fmt.Sprintf("%s/api/v3/chat/completions", meta.BaseURL), nil
+	}
+	return "", fmt.Errorf("unsupported relay mode %d for doubao", meta.Mode)
+}

relay/adaptor/gemini/adaptor.go

@@ -13,6 +13,7 @@ import (
 	"github.com/songquanpeng/one-api/relay/adaptor/openai"
 	"github.com/songquanpeng/one-api/relay/meta"
 	"github.com/songquanpeng/one-api/relay/model"
+	"github.com/songquanpeng/one-api/relay/relaymode"
 )
 
 type Adaptor struct {
@@ -24,7 +25,14 @@ func (a *Adaptor) Init(meta *meta.Meta) {
 
 func (a *Adaptor) GetRequestURL(meta *meta.Meta) (string, error) {
 	version := helper.AssignOrDefault(meta.Config.APIVersion, config.GeminiVersion)
-	action := "generateContent"
+	action := ""
+	switch meta.Mode {
+	case relaymode.Embeddings:
+		action = "batchEmbedContents"
+	default:
+		action = "generateContent"
+	}
+
 	if meta.IsStream {
 		action = "streamGenerateContent?alt=sse"
 	}
@@ -41,7 +49,14 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.G
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
-	return ConvertRequest(*request), nil
+	switch relayMode {
+	case relaymode.Embeddings:
+		geminiEmbeddingRequest := ConvertEmbeddingRequest(*request)
+		return geminiEmbeddingRequest, nil
+	default:
+		geminiRequest := ConvertRequest(*request)
+		return geminiRequest, nil
+	}
 }
 
 func (a *Adaptor) ConvertImageRequest(request *model.ImageRequest) (any, error) {
@@ -61,7 +76,12 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *meta.Met
 		err, responseText = StreamHandler(c, resp)
 		usage = openai.ResponseText2Usage(responseText, meta.ActualModelName, meta.PromptTokens)
 	} else {
-		err, usage = Handler(c, resp, meta.PromptTokens, meta.ActualModelName)
+		switch meta.Mode {
+		case relaymode.Embeddings:
+			err, usage = EmbeddingHandler(c, resp)
+		default:
+			err, usage = Handler(c, resp, meta.PromptTokens, meta.ActualModelName)
+		}
 	}
 	return
 }

relay/adaptor/gemini/constants.go

@@ -4,5 +4,5 @@ package gemini
 
 var ModelList = []string{
 	"gemini-pro", "gemini-1.0-pro-001", "gemini-1.5-pro",
-	"gemini-pro-vision", "gemini-1.0-pro-vision-001",
+	"gemini-pro-vision", "gemini-1.0-pro-vision-001", "embedding-001", "text-embedding-004",
 }

relay/adaptor/gemini/main.go

@@ -4,6 +4,7 @@ import (
 	"bufio"
 	"encoding/json"
 	"fmt"
+	"github.com/songquanpeng/one-api/common/render"
 	"io"
 	"net/http"
 	"strings"
@@ -134,6 +135,29 @@ func ConvertRequest(textRequest model.GeneralOpenAIRequest) *ChatRequest {
 	return &geminiRequest
 }
 
+func ConvertEmbeddingRequest(request model.GeneralOpenAIRequest) *BatchEmbeddingRequest {
+	inputs := request.ParseInput()
+	requests := make([]EmbeddingRequest, len(inputs))
+	model := fmt.Sprintf("models/%s", request.Model)
+
+	for i, input := range inputs {
+		requests[i] = EmbeddingRequest{
+			Model: model,
+			Content: ChatContent{
+				Parts: []Part{
+					{
+						Text: input,
+					},
+				},
+			},
+		}
+	}
+
+	return &BatchEmbeddingRequest{
+		Requests: requests,
+	}
+}
+
 type ChatResponse struct {
 	Candidates     []ChatCandidate    `json:"candidates"`
 	PromptFeedback ChatPromptFeedback `json:"promptFeedback"`
@@ -222,75 +246,80 @@ func responseGeminiChat2OpenAI(response *ChatResponse) *openai.TextResponse {
 func streamResponseGeminiChat2OpenAI(geminiResponse *ChatResponse) *openai.ChatCompletionsStreamResponse {
 	var choice openai.ChatCompletionsStreamResponseChoice
 	choice.Delta.Content = geminiResponse.GetResponseText()
-	choice.FinishReason = &constant.StopFinishReason
+	//choice.FinishReason = &constant.StopFinishReason
 	var response openai.ChatCompletionsStreamResponse
+	response.Id = fmt.Sprintf("chatcmpl-%s", random.GetUUID())
+	response.Created = helper.GetTimestamp()
 	response.Object = "chat.completion.chunk"
 	response.Model = "gemini"
 	response.Choices = []openai.ChatCompletionsStreamResponseChoice{choice}
 	return &response
 }
 
+func embeddingResponseGemini2OpenAI(response *EmbeddingResponse) *openai.EmbeddingResponse {
+	openAIEmbeddingResponse := openai.EmbeddingResponse{
+		Object: "list",
+		Data:   make([]openai.EmbeddingResponseItem, 0, len(response.Embeddings)),
+		Model:  "gemini-embedding",
+		Usage:  model.Usage{TotalTokens: 0},
+	}
+	for _, item := range response.Embeddings {
+		openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, openai.EmbeddingResponseItem{
+			Object:    `embedding`,
+			Index:     0,
+			Embedding: item.Values,
+		})
+	}
+	return &openAIEmbeddingResponse
+}
+
 func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, string) {
 	responseText := ""
 	scanner := bufio.NewScanner(resp.Body)
-	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		if atEOF && len(data) == 0 {
-			return 0, nil, nil
-		}
-		if i := strings.Index(string(data), "\n"); i >= 0 {
-			return i + 1, data[0:i], nil
-		}
-		if atEOF {
-			return len(data), data, nil
-		}
-		return 0, nil, nil
-	})
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			data = strings.TrimSpace(data)
-			if !strings.HasPrefix(data, "data: ") {
-				continue
-			}
-			data = strings.TrimPrefix(data, "data: ")
-			data = strings.TrimSuffix(data, "\"")
-			dataChan <- data
-		}
-		stopChan <- true
-	}()
+	scanner.Split(bufio.ScanLines)
+
 	common.SetEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			var geminiResponse ChatResponse
-			err := json.Unmarshal([]byte(data), &geminiResponse)
-			if err != nil {
-				logger.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
-			response := streamResponseGeminiChat2OpenAI(&geminiResponse)
-			if response == nil {
-				return true
-			}
-			responseText += response.Choices[0].Delta.StringContent()
-			jsonResponse, err := json.Marshal(response)
-			if err != nil {
-				logger.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		data = strings.TrimSpace(data)
+		if !strings.HasPrefix(data, "data: ") {
+			continue
 		}
-	})
+		data = strings.TrimPrefix(data, "data: ")
+		data = strings.TrimSuffix(data, "\"")
+
+		var geminiResponse ChatResponse
+		err := json.Unmarshal([]byte(data), &geminiResponse)
+		if err != nil {
+			logger.SysError("error unmarshalling stream response: " + err.Error())
+			continue
+		}
+
+		response := streamResponseGeminiChat2OpenAI(&geminiResponse)
+		if response == nil {
+			continue
+		}
+
+		responseText += response.Choices[0].Delta.StringContent()
+
+		err = render.ObjectData(c, response)
+		if err != nil {
+			logger.SysError(err.Error())
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		logger.SysError("error reading stream: " + err.Error())
+	}
+
+	render.Done(c)
+
 	err := resp.Body.Close()
 	if err != nil {
 		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
 	}
+
 	return nil, responseText
 }
 
@@ -337,3 +366,39 @@ func Handler(c *gin.Context, resp *http.Response, promptTokens int, modelName st
 	_, err = c.Writer.Write(jsonResponse)
 	return nil, &usage
 }
+
+func EmbeddingHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *model.Usage) {
+	var geminiEmbeddingResponse EmbeddingResponse
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return openai.ErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = json.Unmarshal(responseBody, &geminiEmbeddingResponse)
+	if err != nil {
+		return openai.ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	if geminiEmbeddingResponse.Error != nil {
+		return &model.ErrorWithStatusCode{
+			Error: model.Error{
+				Message: geminiEmbeddingResponse.Error.Message,
+				Type:    "gemini_error",
+				Param:   "",
+				Code:    geminiEmbeddingResponse.Error.Code,
+			},
+			StatusCode: resp.StatusCode,
+		}, nil
+	}
+	fullTextResponse := embeddingResponseGemini2OpenAI(&geminiEmbeddingResponse)
+	jsonResponse, err := json.Marshal(fullTextResponse)
+	if err != nil {
+		return openai.ErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	return nil, &fullTextResponse.Usage
+}

relay/adaptor/gemini/model.go

@@ -7,6 +7,33 @@ type ChatRequest struct {
 	Tools            []ChatTools          `json:"tools,omitempty"`
 }
 
+type EmbeddingRequest struct {
+	Model                string      `json:"model"`
+	Content              ChatContent `json:"content"`
+	TaskType             string      `json:"taskType,omitempty"`
+	Title                string      `json:"title,omitempty"`
+	OutputDimensionality int         `json:"outputDimensionality,omitempty"`
+}
+
+type BatchEmbeddingRequest struct {
+	Requests []EmbeddingRequest `json:"requests"`
+}
+
+type EmbeddingData struct {
+	Values []float64 `json:"values"`
+}
+
+type EmbeddingResponse struct {
+	Embeddings []EmbeddingData `json:"embeddings"`
+	Error      *Error          `json:"error,omitempty"`
+}
+
+type Error struct {
+	Code    int    `json:"code,omitempty"`
+	Message string `json:"message,omitempty"`
+	Status  string `json:"status,omitempty"`
+}
+
 type InlineData struct {
 	MimeType string `json:"mimeType"`
 	Data     string `json:"data"`

relay/adaptor/ollama/main.go

@@ -5,12 +5,14 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
-	"github.com/songquanpeng/one-api/common/helper"
-	"github.com/songquanpeng/one-api/common/random"
+	"github.com/songquanpeng/one-api/common/render"
 	"io"
 	"net/http"
 	"strings"
 
+	"github.com/songquanpeng/one-api/common/helper"
+	"github.com/songquanpeng/one-api/common/random"
+
 	"github.com/gin-gonic/gin"
 	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/image"
@@ -105,54 +107,51 @@ func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusC
 			return 0, nil, nil
 		}
 		if i := strings.Index(string(data), "}\n"); i >= 0 {
-			return i + 2, data[0:i], nil
+			return i + 2, data[0 : i+1], nil
 		}
 		if atEOF {
 			return len(data), data, nil
 		}
 		return 0, nil, nil
 	})
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
-	go func() {
-		for scanner.Scan() {
-			data := strings.TrimPrefix(scanner.Text(), "}")
-			dataChan <- data + "}"
-		}
-		stopChan <- true
-	}()
+
 	common.SetEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			var ollamaResponse ChatResponse
-			err := json.Unmarshal([]byte(data), &ollamaResponse)
-			if err != nil {
-				logger.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
-			if ollamaResponse.EvalCount != 0 {
-				usage.PromptTokens = ollamaResponse.PromptEvalCount
-				usage.CompletionTokens = ollamaResponse.EvalCount
-				usage.TotalTokens = ollamaResponse.PromptEvalCount + ollamaResponse.EvalCount
-			}
-			response := streamResponseOllama2OpenAI(&ollamaResponse)
-			jsonResponse, err := json.Marshal(response)
-			if err != nil {
-				logger.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
+
+	for scanner.Scan() {
+		data := strings.TrimPrefix(scanner.Text(), "}")
+		data = data + "}"
+
+		var ollamaResponse ChatResponse
+		err := json.Unmarshal([]byte(data), &ollamaResponse)
+		if err != nil {
+			logger.SysError("error unmarshalling stream response: " + err.Error())
+			continue
 		}
-	})
+
+		if ollamaResponse.EvalCount != 0 {
+			usage.PromptTokens = ollamaResponse.PromptEvalCount
+			usage.CompletionTokens = ollamaResponse.EvalCount
+			usage.TotalTokens = ollamaResponse.PromptEvalCount + ollamaResponse.EvalCount
+		}
+
+		response := streamResponseOllama2OpenAI(&ollamaResponse)
+		err = render.ObjectData(c, response)
+		if err != nil {
+			logger.SysError(err.Error())
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		logger.SysError("error reading stream: " + err.Error())
+	}
+
+	render.Done(c)
+
 	err := resp.Body.Close()
 	if err != nil {
 		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
+
 	return nil, &usage
 }
 

relay/adaptor/openai/adaptor.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 	"github.com/gin-gonic/gin"
 	"github.com/songquanpeng/one-api/relay/adaptor"
+	"github.com/songquanpeng/one-api/relay/adaptor/doubao"
 	"github.com/songquanpeng/one-api/relay/adaptor/minimax"
 	"github.com/songquanpeng/one-api/relay/channeltype"
 	"github.com/songquanpeng/one-api/relay/meta"
@@ -45,6 +46,8 @@ func (a *Adaptor) GetRequestURL(meta *meta.Meta) (string, error) {
 		return GetFullRequestURL(meta.BaseURL, requestURL, meta.ChannelType), nil
 	case channeltype.Minimax:
 		return minimax.GetRequestURL(meta)
+	case channeltype.Doubao:
+		return doubao.GetRequestURL(meta)
 	default:
 		return GetFullRequestURL(meta.BaseURL, meta.RequestURLPath, meta.ChannelType), nil
 	}

relay/adaptor/openai/compatible.go

@@ -4,6 +4,7 @@ import (
 	"github.com/songquanpeng/one-api/relay/adaptor/ai360"
 	"github.com/songquanpeng/one-api/relay/adaptor/baichuan"
 	"github.com/songquanpeng/one-api/relay/adaptor/deepseek"
+	"github.com/songquanpeng/one-api/relay/adaptor/doubao"
 	"github.com/songquanpeng/one-api/relay/adaptor/groq"
 	"github.com/songquanpeng/one-api/relay/adaptor/lingyiwanwu"
 	"github.com/songquanpeng/one-api/relay/adaptor/minimax"
@@ -20,6 +21,7 @@ var CompatibleChannels = []int{
 	channeltype.Moonshot,
 	channeltype.Baichuan,
 	channeltype.Minimax,
+	channeltype.Doubao,
 	channeltype.Mistral,
 	channeltype.Groq,
 	channeltype.LingYiWanWu,
@@ -52,6 +54,8 @@ func GetCompatibleChannelMeta(channelType int) (string, []string) {
 		return "deepseek", deepseek.ModelList
 	case channeltype.TogetherAI:
 		return "together.ai", togetherai.ModelList
+	case channeltype.Doubao:
+		return "doubao", doubao.ModelList
 	default:
 		return "openai", ModelList
 	}

relay/adaptor/openai/constants.go

@@ -7,6 +7,7 @@ var ModelList = []string{
 	"gpt-4", "gpt-4-0314", "gpt-4-0613", "gpt-4-1106-preview", "gpt-4-0125-preview",
 	"gpt-4-32k", "gpt-4-32k-0314", "gpt-4-32k-0613",
 	"gpt-4-turbo-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
+	"gpt-4o", "gpt-4o-2024-05-13",
 	"gpt-4-vision-preview",
 	"text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large",
 	"text-curie-001", "text-babbage-001", "text-ada-001", "text-davinci-002", "text-davinci-003",

relay/adaptor/openai/main.go

@@ -4,15 +4,17 @@ import (
 	"bufio"
 	"bytes"
 	"encoding/json"
+	"github.com/songquanpeng/one-api/common/render"
+	"io"
+	"net/http"
+	"strings"
+
 	"github.com/gin-gonic/gin"
 	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/conv"
 	"github.com/songquanpeng/one-api/common/logger"
 	"github.com/songquanpeng/one-api/relay/model"
 	"github.com/songquanpeng/one-api/relay/relaymode"
-	"io"
-	"net/http"
-	"strings"
 )
 
 const (
@@ -24,88 +26,68 @@ const (
 func StreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*model.ErrorWithStatusCode, string, *model.Usage) {
 	responseText := ""
 	scanner := bufio.NewScanner(resp.Body)
-	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		if atEOF && len(data) == 0 {
-			return 0, nil, nil
-		}
-		if i := strings.Index(string(data), "\n"); i >= 0 {
-			return i + 1, data[0:i], nil
-		}
-		if atEOF {
-			return len(data), data, nil
-		}
-		return 0, nil, nil
-	})
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
+	scanner.Split(bufio.ScanLines)
 	var usage *model.Usage
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			if len(data) < dataPrefixLength { // ignore blank line or wrong format
-				continue
-			}
-			if data[:dataPrefixLength] != dataPrefix && data[:dataPrefixLength] != done {
-				continue
-			}
-			if strings.HasPrefix(data[dataPrefixLength:], done) {
-				dataChan <- data
-				continue
-			}
-			switch relayMode {
-			case relaymode.ChatCompletions:
-				var streamResponse ChatCompletionsStreamResponse
-				err := json.Unmarshal([]byte(data[dataPrefixLength:]), &streamResponse)
-				if err != nil {
-					logger.SysError("error unmarshalling stream response: " + err.Error())
-					dataChan <- data // if error happened, pass the data to client
-					continue         // just ignore the error
-				}
-				if len(streamResponse.Choices) == 0 {
-					// but for empty choice, we should not pass it to client, this is for azure
-					continue // just ignore empty choice
-				}
-				dataChan <- data
-				for _, choice := range streamResponse.Choices {
-					responseText += conv.AsString(choice.Delta.Content)
-				}
-				if streamResponse.Usage != nil {
-					usage = streamResponse.Usage
-				}
-			case relaymode.Completions:
-				dataChan <- data
-				var streamResponse CompletionsStreamResponse
-				err := json.Unmarshal([]byte(data[dataPrefixLength:]), &streamResponse)
-				if err != nil {
-					logger.SysError("error unmarshalling stream response: " + err.Error())
-					continue
-				}
-				for _, choice := range streamResponse.Choices {
-					responseText += choice.Text
-				}
-			}
-		}
-		stopChan <- true
-	}()
+
 	common.SetEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			if strings.HasPrefix(data, "data: [DONE]") {
-				data = data[:12]
-			}
-			// some implementations may add \r at the end of data
-			data = strings.TrimSuffix(data, "\r")
-			c.Render(-1, common.CustomEvent{Data: data})
-			return true
-		case <-stopChan:
-			return false
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		if len(data) < dataPrefixLength { // ignore blank line or wrong format
+			continue
 		}
-	})
+		if data[:dataPrefixLength] != dataPrefix && data[:dataPrefixLength] != done {
+			continue
+		}
+		if strings.HasPrefix(data[dataPrefixLength:], done) {
+			render.StringData(c, data)
+			continue
+		}
+		switch relayMode {
+		case relaymode.ChatCompletions:
+			var streamResponse ChatCompletionsStreamResponse
+			err := json.Unmarshal([]byte(data[dataPrefixLength:]), &streamResponse)
+			if err != nil {
+				logger.SysError("error unmarshalling stream response: " + err.Error())
+				render.StringData(c, data) // if error happened, pass the data to client
+				continue                   // just ignore the error
+			}
+			if len(streamResponse.Choices) == 0 {
+				// but for empty choice, we should not pass it to client, this is for azure
+				continue // just ignore empty choice
+			}
+			render.StringData(c, data)
+			for _, choice := range streamResponse.Choices {
+				responseText += conv.AsString(choice.Delta.Content)
+			}
+			if streamResponse.Usage != nil {
+				usage = streamResponse.Usage
+			}
+		case relaymode.Completions:
+			render.StringData(c, data)
+			var streamResponse CompletionsStreamResponse
+			err := json.Unmarshal([]byte(data[dataPrefixLength:]), &streamResponse)
+			if err != nil {
+				logger.SysError("error unmarshalling stream response: " + err.Error())
+				continue
+			}
+			for _, choice := range streamResponse.Choices {
+				responseText += choice.Text
+			}
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		logger.SysError("error reading stream: " + err.Error())
+	}
+
+	render.Done(c)
+
 	err := resp.Body.Close()
 	if err != nil {
 		return ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), "", nil
 	}
+
 	return nil, responseText, usage
 }
 
@@ -149,7 +131,7 @@ func Handler(c *gin.Context, resp *http.Response, promptTokens int, modelName st
 		return ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 
-	if textResponse.Usage.TotalTokens == 0 {
+	if textResponse.Usage.TotalTokens == 0 || (textResponse.Usage.PromptTokens == 0 && textResponse.Usage.CompletionTokens == 0) {
 		completionTokens := 0
 		for _, choice := range textResponse.Choices {
 			completionTokens += CountTokenText(choice.Message.StringContent(), modelName)

relay/adaptor/openai/token.go

@@ -24,6 +24,10 @@ func InitTokenEncoders() {
 		logger.FatalLog(fmt.Sprintf("failed to get gpt-3.5-turbo token encoder: %s", err.Error()))
 	}
 	defaultTokenEncoder = gpt35TokenEncoder
+	gpt4oTokenEncoder, err := tiktoken.EncodingForModel("gpt-4o")
+	if err != nil {
+		logger.FatalLog(fmt.Sprintf("failed to get gpt-4o token encoder: %s", err.Error()))
+	}
 	gpt4TokenEncoder, err := tiktoken.EncodingForModel("gpt-4")
 	if err != nil {
 		logger.FatalLog(fmt.Sprintf("failed to get gpt-4 token encoder: %s", err.Error()))
@@ -31,6 +35,8 @@ func InitTokenEncoders() {
 	for model := range billingratio.ModelRatio {
 		if strings.HasPrefix(model, "gpt-3.5") {
 			tokenEncoderMap[model] = gpt35TokenEncoder
+		} else if strings.HasPrefix(model, "gpt-4o") {
+			tokenEncoderMap[model] = gpt4oTokenEncoder
 		} else if strings.HasPrefix(model, "gpt-4") {
 			tokenEncoderMap[model] = gpt4TokenEncoder
 		} else {

relay/adaptor/palm/palm.go

@@ -3,6 +3,10 @@ package palm
 import (
 	"encoding/json"
 	"fmt"
+	"github.com/songquanpeng/one-api/common/render"
+	"io"
+	"net/http"
+
 	"github.com/gin-gonic/gin"
 	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/helper"
@@ -11,8 +15,6 @@ import (
 	"github.com/songquanpeng/one-api/relay/adaptor/openai"
 	"github.com/songquanpeng/one-api/relay/constant"
 	"github.com/songquanpeng/one-api/relay/model"
-	"io"
-	"net/http"
 )
 
 // https://developers.generativeai.google/api/rest/generativelanguage/models/generateMessage#request-body
@@ -77,58 +79,51 @@ func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusC
 	responseText := ""
 	responseId := fmt.Sprintf("chatcmpl-%s", random.GetUUID())
 	createdTime := helper.GetTimestamp()
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
-	go func() {
-		responseBody, err := io.ReadAll(resp.Body)
-		if err != nil {
-			logger.SysError("error reading stream response: " + err.Error())
-			stopChan <- true
-			return
-		}
-		err = resp.Body.Close()
-		if err != nil {
-			logger.SysError("error closing stream response: " + err.Error())
-			stopChan <- true
-			return
-		}
-		var palmResponse ChatResponse
-		err = json.Unmarshal(responseBody, &palmResponse)
-		if err != nil {
-			logger.SysError("error unmarshalling stream response: " + err.Error())
-			stopChan <- true
-			return
-		}
-		fullTextResponse := streamResponsePaLM2OpenAI(&palmResponse)
-		fullTextResponse.Id = responseId
-		fullTextResponse.Created = createdTime
-		if len(palmResponse.Candidates) > 0 {
-			responseText = palmResponse.Candidates[0].Content
-		}
-		jsonResponse, err := json.Marshal(fullTextResponse)
-		if err != nil {
-			logger.SysError("error marshalling stream response: " + err.Error())
-			stopChan <- true
-			return
-		}
-		dataChan <- string(jsonResponse)
-		stopChan <- true
-	}()
+
 	common.SetEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			c.Render(-1, common.CustomEvent{Data: "data: " + data})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
+
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		logger.SysError("error reading stream response: " + err.Error())
+		err := resp.Body.Close()
+		if err != nil {
+			return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
 		}
-	})
-	err := resp.Body.Close()
+		return openai.ErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), ""
+	}
+
+	err = resp.Body.Close()
 	if err != nil {
 		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
 	}
+
+	var palmResponse ChatResponse
+	err = json.Unmarshal(responseBody, &palmResponse)
+	if err != nil {
+		logger.SysError("error unmarshalling stream response: " + err.Error())
+		return openai.ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), ""
+	}
+
+	fullTextResponse := streamResponsePaLM2OpenAI(&palmResponse)
+	fullTextResponse.Id = responseId
+	fullTextResponse.Created = createdTime
+	if len(palmResponse.Candidates) > 0 {
+		responseText = palmResponse.Candidates[0].Content
+	}
+
+	jsonResponse, err := json.Marshal(fullTextResponse)
+	if err != nil {
+		logger.SysError("error marshalling stream response: " + err.Error())
+		return openai.ErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), ""
+	}
+
+	err = render.ObjectData(c, string(jsonResponse))
+	if err != nil {
+		logger.SysError(err.Error())
+	}
+
+	render.Done(c)
+
 	return nil, responseText
 }
 

relay/adaptor/tencent/adaptor.go

@@ -2,35 +2,43 @@ package tencent
 
 import (
 	"errors"
-	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common/helper"
 	"github.com/songquanpeng/one-api/relay/adaptor"
 	"github.com/songquanpeng/one-api/relay/adaptor/openai"
 	"github.com/songquanpeng/one-api/relay/meta"
 	"github.com/songquanpeng/one-api/relay/model"
 	"io"
 	"net/http"
+	"strconv"
 	"strings"
 )
 
 // https://cloud.tencent.com/document/api/1729/101837
 
 type Adaptor struct {
-	Sign string
+	Sign      string
+	Action    string
+	Version   string
+	Timestamp int64
 }
 
 func (a *Adaptor) Init(meta *meta.Meta) {
-
+	a.Action = "ChatCompletions"
+	a.Version = "2023-09-01"
+	a.Timestamp = helper.GetTimestamp()
 }
 
 func (a *Adaptor) GetRequestURL(meta *meta.Meta) (string, error) {
-	return fmt.Sprintf("%s/hyllm/v1/chat/completions", meta.BaseURL), nil
+	return meta.BaseURL + "/", nil
 }
 
 func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, meta *meta.Meta) error {
 	adaptor.SetupCommonRequestHeader(c, req, meta)
 	req.Header.Set("Authorization", a.Sign)
-	req.Header.Set("X-TC-Action", meta.ActualModelName)
+	req.Header.Set("X-TC-Action", a.Action)
+	req.Header.Set("X-TC-Version", a.Version)
+	req.Header.Set("X-TC-Timestamp", strconv.FormatInt(a.Timestamp, 10))
 	return nil
 }
 
@@ -40,15 +48,13 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.G
 	}
 	apiKey := c.Request.Header.Get("Authorization")
 	apiKey = strings.TrimPrefix(apiKey, "Bearer ")
-	appId, secretId, secretKey, err := ParseConfig(apiKey)
+	_, secretId, secretKey, err := ParseConfig(apiKey)
 	if err != nil {
 		return nil, err
 	}
 	tencentRequest := ConvertRequest(*request)
-	tencentRequest.AppId = appId
-	tencentRequest.SecretId = secretId
 	// we have to calculate the sign here
-	a.Sign = GetSign(*tencentRequest, secretKey)
+	a.Sign = GetSign(*tencentRequest, a, secretId, secretKey)
 	return tencentRequest, nil
 }
 

relay/adaptor/tencent/constants.go

@@ -1,7 +1,8 @@
 package tencent
 
 var ModelList = []string{
-	"ChatPro",
-	"ChatStd",
-	"hunyuan",
+	"hunyuan-lite",
+	"hunyuan-standard",
+	"hunyuan-standard-256K",
+	"hunyuan-pro",
 }

relay/adaptor/tencent/main.go

@@ -3,11 +3,18 @@ package tencent
 import (
 	"bufio"
 	"crypto/hmac"
-	"crypto/sha1"
-	"encoding/base64"
+	"crypto/sha256"
+	"encoding/hex"
 	"encoding/json"
 	"errors"
 	"fmt"
+	"github.com/songquanpeng/one-api/common/render"
+	"io"
+	"net/http"
+	"strconv"
+	"strings"
+	"time"
+
 	"github.com/gin-gonic/gin"
 	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/conv"
@@ -17,36 +24,23 @@ import (
 	"github.com/songquanpeng/one-api/relay/adaptor/openai"
 	"github.com/songquanpeng/one-api/relay/constant"
 	"github.com/songquanpeng/one-api/relay/model"
-	"io"
-	"net/http"
-	"sort"
-	"strconv"
-	"strings"
 )
 
-// https://cloud.tencent.com/document/product/1729/97732
-
 func ConvertRequest(request model.GeneralOpenAIRequest) *ChatRequest {
-	messages := make([]Message, 0, len(request.Messages))
+	messages := make([]*Message, 0, len(request.Messages))
 	for i := 0; i < len(request.Messages); i++ {
 		message := request.Messages[i]
-		messages = append(messages, Message{
+		messages = append(messages, &Message{
 			Content: message.StringContent(),
 			Role:    message.Role,
 		})
 	}
-	stream := 0
-	if request.Stream {
-		stream = 1
-	}
 	return &ChatRequest{
-		Timestamp:   helper.GetTimestamp(),
-		Expired:     helper.GetTimestamp() + 24*60*60,
-		QueryID:     random.GetUUID(),
-		Temperature: request.Temperature,
-		TopP:        request.TopP,
-		Stream:      stream,
+		Model:       &request.Model,
+		Stream:      &request.Stream,
 		Messages:    messages,
+		TopP:        &request.TopP,
+		Temperature: &request.Temperature,
 	}
 }
 
@@ -54,7 +48,11 @@ func responseTencent2OpenAI(response *ChatResponse) *openai.TextResponse {
 	fullTextResponse := openai.TextResponse{
 		Object:  "chat.completion",
 		Created: helper.GetTimestamp(),
-		Usage:   response.Usage,
+		Usage: model.Usage{
+			PromptTokens:     response.Usage.PromptTokens,
+			CompletionTokens: response.Usage.CompletionTokens,
+			TotalTokens:      response.Usage.TotalTokens,
+		},
 	}
 	if len(response.Choices) > 0 {
 		choice := openai.TextResponseChoice{
@@ -91,69 +89,52 @@ func streamResponseTencent2OpenAI(TencentResponse *ChatResponse) *openai.ChatCom
 func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, string) {
 	var responseText string
 	scanner := bufio.NewScanner(resp.Body)
-	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		if atEOF && len(data) == 0 {
-			return 0, nil, nil
-		}
-		if i := strings.Index(string(data), "\n"); i >= 0 {
-			return i + 1, data[0:i], nil
-		}
-		if atEOF {
-			return len(data), data, nil
-		}
-		return 0, nil, nil
-	})
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			if len(data) < 5 { // ignore blank line or wrong format
-				continue
-			}
-			if data[:5] != "data:" {
-				continue
-			}
-			data = data[5:]
-			dataChan <- data
-		}
-		stopChan <- true
-	}()
+	scanner.Split(bufio.ScanLines)
+
 	common.SetEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			var TencentResponse ChatResponse
-			err := json.Unmarshal([]byte(data), &TencentResponse)
-			if err != nil {
-				logger.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
-			response := streamResponseTencent2OpenAI(&TencentResponse)
-			if len(response.Choices) != 0 {
-				responseText += conv.AsString(response.Choices[0].Delta.Content)
-			}
-			jsonResponse, err := json.Marshal(response)
-			if err != nil {
-				logger.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		if len(data) < 5 || !strings.HasPrefix(data, "data:") {
+			continue
 		}
-	})
+		data = strings.TrimPrefix(data, "data:")
+
+		var tencentResponse ChatResponse
+		err := json.Unmarshal([]byte(data), &tencentResponse)
+		if err != nil {
+			logger.SysError("error unmarshalling stream response: " + err.Error())
+			continue
+		}
+
+		response := streamResponseTencent2OpenAI(&tencentResponse)
+		if len(response.Choices) != 0 {
+			responseText += conv.AsString(response.Choices[0].Delta.Content)
+		}
+
+		err = render.ObjectData(c, response)
+		if err != nil {
+			logger.SysError(err.Error())
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		logger.SysError("error reading stream: " + err.Error())
+	}
+
+	render.Done(c)
+
 	err := resp.Body.Close()
 	if err != nil {
 		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
 	}
+
 	return nil, responseText
 }
 
 func Handler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *model.Usage) {
 	var TencentResponse ChatResponse
+	var responseP ChatResponseP
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
 		return openai.ErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
@@ -162,10 +143,11 @@ func Handler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *
 	if err != nil {
 		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
-	err = json.Unmarshal(responseBody, &TencentResponse)
+	err = json.Unmarshal(responseBody, &responseP)
 	if err != nil {
 		return openai.ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
+	TencentResponse = responseP.Response
 	if TencentResponse.Error.Code != 0 {
 		return &model.ErrorWithStatusCode{
 			Error: model.Error{
@@ -202,29 +184,62 @@ func ParseConfig(config string) (appId int64, secretId string, secretKey string,
 	return
 }
 
-func GetSign(req ChatRequest, secretKey string) string {
-	params := make([]string, 0)
-	params = append(params, "app_id="+strconv.FormatInt(req.AppId, 10))
-	params = append(params, "secret_id="+req.SecretId)
-	params = append(params, "timestamp="+strconv.FormatInt(req.Timestamp, 10))
-	params = append(params, "query_id="+req.QueryID)
-	params = append(params, "temperature="+strconv.FormatFloat(req.Temperature, 'f', -1, 64))
-	params = append(params, "top_p="+strconv.FormatFloat(req.TopP, 'f', -1, 64))
-	params = append(params, "stream="+strconv.Itoa(req.Stream))
-	params = append(params, "expired="+strconv.FormatInt(req.Expired, 10))
-
-	var messageStr string
-	for _, msg := range req.Messages {
-		messageStr += fmt.Sprintf(`{"role":"%s","content":"%s"},`, msg.Role, msg.Content)
-	}
-	messageStr = strings.TrimSuffix(messageStr, ",")
-	params = append(params, "messages=["+messageStr+"]")
-
-	sort.Strings(params)
-	url := "hunyuan.cloud.tencent.com/hyllm/v1/chat/completions?" + strings.Join(params, "&")
-	mac := hmac.New(sha1.New, []byte(secretKey))
-	signURL := url
-	mac.Write([]byte(signURL))
-	sign := mac.Sum([]byte(nil))
-	return base64.StdEncoding.EncodeToString(sign)
+func sha256hex(s string) string {
+	b := sha256.Sum256([]byte(s))
+	return hex.EncodeToString(b[:])
+}
+
+func hmacSha256(s, key string) string {
+	hashed := hmac.New(sha256.New, []byte(key))
+	hashed.Write([]byte(s))
+	return string(hashed.Sum(nil))
+}
+
+func GetSign(req ChatRequest, adaptor *Adaptor, secId, secKey string) string {
+	// build canonical request string
+	host := "hunyuan.tencentcloudapi.com"
+	httpRequestMethod := "POST"
+	canonicalURI := "/"
+	canonicalQueryString := ""
+	canonicalHeaders := fmt.Sprintf("content-type:%s\nhost:%s\nx-tc-action:%s\n",
+		"application/json", host, strings.ToLower(adaptor.Action))
+	signedHeaders := "content-type;host;x-tc-action"
+	payload, _ := json.Marshal(req)
+	hashedRequestPayload := sha256hex(string(payload))
+	canonicalRequest := fmt.Sprintf("%s\n%s\n%s\n%s\n%s\n%s",
+		httpRequestMethod,
+		canonicalURI,
+		canonicalQueryString,
+		canonicalHeaders,
+		signedHeaders,
+		hashedRequestPayload)
+	// build string to sign
+	algorithm := "TC3-HMAC-SHA256"
+	requestTimestamp := strconv.FormatInt(adaptor.Timestamp, 10)
+	timestamp, _ := strconv.ParseInt(requestTimestamp, 10, 64)
+	t := time.Unix(timestamp, 0).UTC()
+	// must be the format 2006-01-02, ref to package time for more info
+	date := t.Format("2006-01-02")
+	credentialScope := fmt.Sprintf("%s/%s/tc3_request", date, "hunyuan")
+	hashedCanonicalRequest := sha256hex(canonicalRequest)
+	string2sign := fmt.Sprintf("%s\n%s\n%s\n%s",
+		algorithm,
+		requestTimestamp,
+		credentialScope,
+		hashedCanonicalRequest)
+
+	// sign string
+	secretDate := hmacSha256(date, "TC3"+secKey)
+	secretService := hmacSha256("hunyuan", secretDate)
+	secretKey := hmacSha256("tc3_request", secretService)
+	signature := hex.EncodeToString([]byte(hmacSha256(string2sign, secretKey)))
+
+	// build authorization
+	authorization := fmt.Sprintf("%s Credential=%s/%s, SignedHeaders=%s, Signature=%s",
+		algorithm,
+		secId,
+		credentialScope,
+		signedHeaders,
+		signature)
+	return authorization
 }

relay/adaptor/tencent/model.go

@@ -1,63 +1,75 @@
 package tencent
 
-import (
-	"github.com/songquanpeng/one-api/relay/model"
-)
-
 type Message struct {
-	Role    string `json:"role"`
-	Content string `json:"content"`
+	Role    string `json:"Role"`
+	Content string `json:"Content"`
 }
 
 type ChatRequest struct {
-	AppId    int64  `json:"app_id"`    // 腾讯云账号的 APPID
-	SecretId string `json:"secret_id"` // 官网 SecretId
-	// Timestamp当前 UNIX 时间戳，单位为秒，可记录发起 API 请求的时间。
-	// 例如1529223702，如果与当前时间相差过大，会引起签名过期错误
-	Timestamp int64 `json:"timestamp"`
-	// Expired 签名的有效期，是一个符合 UNIX Epoch 时间戳规范的数值，
-	// 单位为秒；Expired 必须大于 Timestamp 且 Expired-Timestamp 小于90天
-	Expired int64  `json:"expired"`
-	QueryID string `json:"query_id"` //请求 Id，用于问题排查
-	// Temperature 较高的数值会使输出更加随机，而较低的数值会使其更加集中和确定
-	// 默认 1.0，取值区间为[0.0,2.0]，非必要不建议使用,不合理的取值会影响效果
-	// 建议该参数和 top_p 只设置1个，不要同时更改 top_p
-	Temperature float64 `json:"temperature"`
-	// TopP 影响输出文本的多样性，取值越大，生成文本的多样性越强
-	// 默认1.0，取值区间为[0.0, 1.0]，非必要不建议使用, 不合理的取值会影响效果
-	// 建议该参数和 temperature 只设置1个，不要同时更改
-	TopP float64 `json:"top_p"`
-	// Stream 0：同步，1：流式 （默认，协议：SSE)
-	// 同步请求超时：60s，如果内容较长建议使用流式
-	Stream int `json:"stream"`
-	// Messages 会话内容, 长度最多为40, 按对话时间从旧到新在数组中排列
-	// 输入 content 总数最大支持 3000 token。
-	Messages []Message `json:"messages"`
+	// 模型名称，可选值包括 hunyuan-lite、hunyuan-standard、hunyuan-standard-256K、hunyuan-pro。
+	// 各模型介绍请阅读 [产品概述](https://cloud.tencent.com/document/product/1729/104753) 中的说明。
+	//
+	// 注意：
+	// 不同的模型计费不同，请根据 [购买指南](https://cloud.tencent.com/document/product/1729/97731) 按需调用。
+	Model *string `json:"Model"`
+	// 聊天上下文信息。
+	// 说明：
+	// 1. 长度最多为 40，按对话时间从旧到新在数组中排列。
+	// 2. Message.Role 可选值：system、user、assistant。
+	// 其中，system 角色可选，如存在则必须位于列表的最开始。user 和 assistant 需交替出现（一问一答），以 user 提问开始和结束，且 Content 不能为空。Role 的顺序示例：[system（可选） user assistant user assistant user ...]。
+	// 3. Messages 中 Content 总长度不能超过模型输入长度上限（可参考 [产品概述](https://cloud.tencent.com/document/product/1729/104753) 文档），超过则会截断最前面的内容，只保留尾部内容。
+	Messages []*Message `json:"Messages"`
+	// 流式调用开关。
+	// 说明：
+	// 1. 未传值时默认为非流式调用（false）。
+	// 2. 流式调用时以 SSE 协议增量返回结果（返回值取 Choices[n].Delta 中的值，需要拼接增量数据才能获得完整结果）。
+	// 3. 非流式调用时：
+	// 调用方式与普通 HTTP 请求无异。
+	// 接口响应耗时较长，**如需更低时延建议设置为 true**。
+	// 只返回一次最终结果（返回值取 Choices[n].Message 中的值）。
+	//
+	// 注意：
+	// 通过 SDK 调用时，流式和非流式调用需用**不同的方式**获取返回值，具体参考 SDK 中的注释或示例（在各语言 SDK 代码仓库的 examples/hunyuan/v20230901/ 目录中）。
+	Stream *bool `json:"Stream"`
+	// 说明：
+	// 1. 影响输出文本的多样性，取值越大，生成文本的多样性越强。
+	// 2. 取值区间为 [0.0, 1.0]，未传值时使用各模型推荐值。
+	// 3. 非必要不建议使用，不合理的取值会影响效果。
+	TopP *float64 `json:"TopP"`
+	// 说明：
+	// 1. 较高的数值会使输出更加随机，而较低的数值会使其更加集中和确定。
+	// 2. 取值区间为 [0.0, 2.0]，未传值时使用各模型推荐值。
+	// 3. 非必要不建议使用，不合理的取值会影响效果。
+	Temperature *float64 `json:"Temperature"`
 }
 
 type Error struct {
-	Code    int    `json:"code"`
-	Message string `json:"message"`
+	Code    int    `json:"Code"`
+	Message string `json:"Message"`
 }
 
 type Usage struct {
-	InputTokens  int `json:"input_tokens"`
-	OutputTokens int `json:"output_tokens"`
-	TotalTokens  int `json:"total_tokens"`
+	PromptTokens     int `json:"PromptTokens"`
+	CompletionTokens int `json:"CompletionTokens"`
+	TotalTokens      int `json:"TotalTokens"`
 }
 
 type ResponseChoices struct {
-	FinishReason string  `json:"finish_reason,omitempty"` // 流式结束标志位，为 stop 则表示尾包
-	Messages     Message `json:"messages,omitempty"`      // 内容，同步模式返回内容，流模式为 null 输出 content 内容总数最多支持 1024token。
-	Delta        Message `json:"delta,omitempty"`         // 内容，流模式返回内容，同步模式为 null 输出 content 内容总数最多支持 1024token。
+	FinishReason string  `json:"FinishReason,omitempty"` // 流式结束标志位，为 stop 则表示尾包
+	Messages     Message `json:"Message,omitempty"`      // 内容，同步模式返回内容，流模式为 null 输出 content 内容总数最多支持 1024token。
+	Delta        Message `json:"Delta,omitempty"`        // 内容，流模式返回内容，同步模式为 null 输出 content 内容总数最多支持 1024token。
 }
 
 type ChatResponse struct {
-	Choices []ResponseChoices `json:"choices,omitempty"` // 结果
-	Created string            `json:"created,omitempty"` // unix 时间戳的字符串
-	Id      string            `json:"id,omitempty"`      // 会话 id
-	Usage   model.Usage       `json:"usage,omitempty"`   // token 数量
-	Error   Error             `json:"error,omitempty"`   // 错误信息 注意：此字段可能返回 null，表示取不到有效值
-	Note    string            `json:"note,omitempty"`    // 注释
-	ReqID   string            `json:"req_id,omitempty"`  // 唯一请求 Id，每次请求都会返回。用于反馈接口入参
+	Choices []ResponseChoices `json:"Choices,omitempty"` // 结果
+	Created int64             `json:"Created,omitempty"` // unix 时间戳的字符串
+	Id      string            `json:"Id,omitempty"`      // 会话 id
+	Usage   Usage             `json:"Usage,omitempty"`   // token 数量
+	Error   Error             `json:"Error,omitempty"`   // 错误信息 注意：此字段可能返回 null，表示取不到有效值
+	Note    string            `json:"Note,omitempty"`    // 注释
+	ReqID   string            `json:"Req_id,omitempty"`  // 唯一请求 Id，每次请求都会返回。用于反馈接口入参
+}
+
+type ChatResponseP struct {
+	Response ChatResponse `json:"Response,omitempty"`
 }

relay/adaptor/xunfei/adaptor.go

@@ -27,14 +27,6 @@ func (a *Adaptor) GetRequestURL(meta *meta.Meta) (string, error) {
 
 func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, meta *meta.Meta) error {
 	adaptor.SetupCommonRequestHeader(c, req, meta)
-	version := parseAPIVersionByModelName(meta.ActualModelName)
-	if version == "" {
-		version = a.meta.Config.APIVersion
-	}
-	if version == "" {
-		version = "v1.1"
-	}
-	a.meta.Config.APIVersion = version
 	// check DoResponse for auth part
 	return nil
 }
@@ -69,6 +61,14 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *meta.Met
 	if a.request == nil {
 		return nil, openai.ErrorWrapper(errors.New("request is nil"), "request_is_nil", http.StatusBadRequest)
 	}
+	version := parseAPIVersionByModelName(meta.ActualModelName)
+	if version == "" {
+		version = a.meta.Config.APIVersion
+	}
+	if version == "" {
+		version = "v1.1"
+	}
+	a.meta.Config.APIVersion = version
 	if meta.IsStream {
 		err, usage = StreamHandler(c, meta, *a.request, splits[0], splits[1], splits[2])
 	} else {

relay/adaptor/xunfei/constants.go

@@ -6,4 +6,5 @@ var ModelList = []string{
 	"SparkDesk-v2.1",
 	"SparkDesk-v3.1",
 	"SparkDesk-v3.5",
+	"SparkDesk-v4.0",
 }

relay/adaptor/xunfei/main.go

@@ -5,7 +5,14 @@ import (
 	"crypto/sha256"
 	"encoding/base64"
 	"encoding/json"
+	"errors"
 	"fmt"
+	"io"
+	"net/http"
+	"net/url"
+	"strings"
+	"time"
+
 	"github.com/gin-gonic/gin"
 	"github.com/gorilla/websocket"
 	"github.com/songquanpeng/one-api/common"
@@ -16,11 +23,6 @@ import (
 	"github.com/songquanpeng/one-api/relay/constant"
 	"github.com/songquanpeng/one-api/relay/meta"
 	"github.com/songquanpeng/one-api/relay/model"
-	"io"
-	"net/http"
-	"net/url"
-	"strings"
-	"time"
 )
 
 // https://console.xfyun.cn/services/cbm
@@ -28,11 +30,7 @@ import (
 
 func requestOpenAI2Xunfei(request model.GeneralOpenAIRequest, xunfeiAppId string, domain string) *ChatRequest {
 	messages := make([]Message, 0, len(request.Messages))
-	var lastToolCalls []model.Tool
 	for _, message := range request.Messages {
-		if message.ToolCalls != nil {
-			lastToolCalls = message.ToolCalls
-		}
 		messages = append(messages, Message{
 			Role:    message.Role,
 			Content: message.StringContent(),
@@ -45,9 +43,14 @@ func requestOpenAI2Xunfei(request model.GeneralOpenAIRequest, xunfeiAppId string
 	xunfeiRequest.Parameter.Chat.TopK = request.N
 	xunfeiRequest.Parameter.Chat.MaxTokens = request.MaxTokens
 	xunfeiRequest.Payload.Message.Text = messages
-	if len(lastToolCalls) != 0 {
-		for _, toolCall := range lastToolCalls {
-			xunfeiRequest.Payload.Functions.Text = append(xunfeiRequest.Payload.Functions.Text, toolCall.Function)
+
+	if strings.HasPrefix(domain, "generalv3") || domain == "4.0Ultra" {
+		functions := make([]model.Function, len(request.Tools))
+		for i, tool := range request.Tools {
+			functions[i] = tool.Function
+		}
+		xunfeiRequest.Payload.Functions = &Functions{
+			Text: functions,
 		}
 	}
 
@@ -203,7 +206,7 @@ func Handler(c *gin.Context, meta *meta.Meta, textRequest model.GeneralOpenAIReq
 		}
 	}
 	if len(xunfeiResponse.Payload.Choices.Text) == 0 {
-		return openai.ErrorWrapper(err, "xunfei_empty_response_detected", http.StatusInternalServerError), nil
+		return openai.ErrorWrapper(errors.New("xunfei empty response detected"), "xunfei_empty_response_detected", http.StatusInternalServerError), nil
 	}
 	xunfeiResponse.Payload.Choices.Text[0].Content = content
 
@@ -287,6 +290,8 @@ func apiVersion2domain(apiVersion string) string {
 		return "generalv3"
 	case "v3.5":
 		return "generalv3.5"
+	case "v4.0":
+		return "4.0Ultra"
 	}
 	return "general" + apiVersion
 }

relay/adaptor/xunfei/model.go

@@ -9,6 +9,10 @@ type Message struct {
 	Content string `json:"content"`
 }
 
+type Functions struct {
+	Text []model.Function `json:"text,omitempty"`
+}
+
 type ChatRequest struct {
 	Header struct {
 		AppId string `json:"app_id"`
@@ -26,9 +30,7 @@ type ChatRequest struct {
 		Message struct {
 			Text []Message `json:"text"`
 		} `json:"message"`
-		Functions struct {
-			Text []model.Function `json:"text,omitempty"`
-		} `json:"functions,omitempty"`
+		Functions *Functions `json:"functions,omitempty"`
 	} `json:"payload"`
 }
 

relay/adaptor/zhipu/main.go

@@ -3,6 +3,13 @@ package zhipu
 import (
 	"bufio"
 	"encoding/json"
+	"github.com/songquanpeng/one-api/common/render"
+	"io"
+	"net/http"
+	"strings"
+	"sync"
+	"time"
+
 	"github.com/gin-gonic/gin"
 	"github.com/golang-jwt/jwt"
 	"github.com/songquanpeng/one-api/common"
@@ -11,11 +18,6 @@ import (
 	"github.com/songquanpeng/one-api/relay/adaptor/openai"
 	"github.com/songquanpeng/one-api/relay/constant"
 	"github.com/songquanpeng/one-api/relay/model"
-	"io"
-	"net/http"
-	"strings"
-	"sync"
-	"time"
 )
 
 // https://open.bigmodel.cn/doc/api#chatglm_std
@@ -155,66 +157,55 @@ func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusC
 		}
 		return 0, nil, nil
 	})
-	dataChan := make(chan string)
-	metaChan := make(chan string)
-	stopChan := make(chan bool)
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			lines := strings.Split(data, "\n")
-			for i, line := range lines {
-				if len(line) < 5 {
+
+	common.SetEventStreamHeaders(c)
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		lines := strings.Split(data, "\n")
+		for i, line := range lines {
+			if len(line) < 5 {
+				continue
+			}
+			if strings.HasPrefix(line, "data:") {
+				dataSegment := line[5:]
+				if i != len(lines)-1 {
+					dataSegment += "\n"
+				}
+				response := streamResponseZhipu2OpenAI(dataSegment)
+				err := render.ObjectData(c, response)
+				if err != nil {
+					logger.SysError("error marshalling stream response: " + err.Error())
+				}
+			} else if strings.HasPrefix(line, "meta:") {
+				metaSegment := line[5:]
+				var zhipuResponse StreamMetaResponse
+				err := json.Unmarshal([]byte(metaSegment), &zhipuResponse)
+				if err != nil {
+					logger.SysError("error unmarshalling stream response: " + err.Error())
 					continue
 				}
-				if line[:5] == "data:" {
-					dataChan <- line[5:]
-					if i != len(lines)-1 {
-						dataChan <- "\n"
-					}
-				} else if line[:5] == "meta:" {
-					metaChan <- line[5:]
+				response, zhipuUsage := streamMetaResponseZhipu2OpenAI(&zhipuResponse)
+				err = render.ObjectData(c, response)
+				if err != nil {
+					logger.SysError("error marshalling stream response: " + err.Error())
 				}
+				usage = zhipuUsage
 			}
 		}
-		stopChan <- true
-	}()
-	common.SetEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			response := streamResponseZhipu2OpenAI(data)
-			jsonResponse, err := json.Marshal(response)
-			if err != nil {
-				logger.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
-			return true
-		case data := <-metaChan:
-			var zhipuResponse StreamMetaResponse
-			err := json.Unmarshal([]byte(data), &zhipuResponse)
-			if err != nil {
-				logger.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
-			response, zhipuUsage := streamMetaResponseZhipu2OpenAI(&zhipuResponse)
-			jsonResponse, err := json.Marshal(response)
-			if err != nil {
-				logger.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			usage = zhipuUsage
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
-		}
-	})
+	}
+
+	if err := scanner.Err(); err != nil {
+		logger.SysError("error reading stream: " + err.Error())
+	}
+
+	render.Done(c)
+
 	err := resp.Body.Close()
 	if err != nil {
 		return openai.ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
+
 	return nil, usage
 }
 

relay/adaptor_test.go

@@ -0,0 +1,16 @@
+package relay
+
+import (
+	. "github.com/smartystreets/goconvey/convey"
+	"github.com/songquanpeng/one-api/relay/apitype"
+	"testing"
+)
+
+func TestGetAdaptor(t *testing.T) {
+	Convey("get adaptor", t, func() {
+		for i := 0; i < apitype.Dummy; i++ {
+			a := GetAdaptor(i)
+			So(a, ShouldNotBeNil)
+		}
+	})
+}

relay/billing/ratio/image.go

@@ -49,3 +49,8 @@ var ImagePromptLengthLimitations = map[string]int{
 	"wanx-v1":                   4000,
 	"cogview-3":                 833,
 }
+
+var ImageOriginModelName = map[string]string{
+	"ali-stable-diffusion-xl":   "stable-diffusion-xl",
+	"ali-stable-diffusion-v1.5": "stable-diffusion-v1.5",
+}

relay/billing/ratio/model.go

@@ -32,6 +32,8 @@ var ModelRatio = map[string]float64{
 	"gpt-4-turbo-preview":     5,    // $0.01 / 1K tokens
 	"gpt-4-turbo":             5,    // $0.01 / 1K tokens
 	"gpt-4-turbo-2024-04-09":  5,    // $0.01 / 1K tokens
+	"gpt-4o":                  2.5,  // $0.005 / 1K tokens
+	"gpt-4o-2024-05-13":       2.5,  // $0.005 / 1K tokens
 	"gpt-4-vision-preview":    5,    // $0.01 / 1K tokens
 	"gpt-3.5-turbo":           0.25, // $0.0005 / 1K tokens
 	"gpt-3.5-turbo-0301":      0.75,
@@ -68,12 +70,13 @@ var ModelRatio = map[string]float64{
 	"dall-e-2":                0.02 * USD, // $0.016 - $0.020 / image
 	"dall-e-3":                0.04 * USD, // $0.040 - $0.120 / image
 	// https://www.anthropic.com/api#pricing
-	"claude-instant-1.2":       0.8 / 1000 * USD,
-	"claude-2.0":               8.0 / 1000 * USD,
-	"claude-2.1":               8.0 / 1000 * USD,
-	"claude-3-haiku-20240307":  0.25 / 1000 * USD,
-	"claude-3-sonnet-20240229": 3.0 / 1000 * USD,
-	"claude-3-opus-20240229":   15.0 / 1000 * USD,
+	"claude-instant-1.2":         0.8 / 1000 * USD,
+	"claude-2.0":                 8.0 / 1000 * USD,
+	"claude-2.1":                 8.0 / 1000 * USD,
+	"claude-3-haiku-20240307":    0.25 / 1000 * USD,
+	"claude-3-sonnet-20240229":   3.0 / 1000 * USD,
+	"claude-3-5-sonnet-20240620": 3.0 / 1000 * USD,
+	"claude-3-opus-20240229":     15.0 / 1000 * USD,
 	// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7
 	"ERNIE-4.0-8K":       0.120 * RMB,
 	"ERNIE-3.5-8K":       0.012 * RMB,
@@ -122,6 +125,7 @@ var ModelRatio = map[string]float64{
 	"SparkDesk-v2.1":            1.2858, // ￥0.018 / 1k tokens
 	"SparkDesk-v3.1":            1.2858, // ￥0.018 / 1k tokens
 	"SparkDesk-v3.5":            1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v4.0":            1.2858, // ￥0.018 / 1k tokens
 	"360GPT_S2_V9":              0.8572, // ¥0.012 / 1k tokens
 	"embedding-bert-512-v1":     0.0715, // ¥0.001 / 1k tokens
 	"embedding_s1_v1":           0.0715, // ¥0.001 / 1k tokens
@@ -171,7 +175,7 @@ var ModelRatio = map[string]float64{
 	"command-light":         0.5,
 	"command-light-nightly": 0.5,
 	"command-r":             0.5 / 1000 * USD,
-	"command-r-plus	":       3.0 / 1000 * USD,
+	"command-r-plus":        3.0 / 1000 * USD,
 	// https://platform.deepseek.com/api-docs/pricing/
 	"deepseek-chat":  1.0 / 1000 * RMB,
 	"deepseek-coder": 1.0 / 1000 * RMB,
@@ -280,7 +284,9 @@ func GetCompletionRatio(name string) float64 {
 		return 4.0 / 3.0
 	}
 	if strings.HasPrefix(name, "gpt-4") {
-		if strings.HasPrefix(name, "gpt-4-turbo") || strings.HasSuffix(name, "preview") {
+		if strings.HasPrefix(name, "gpt-4-turbo") ||
+			strings.HasPrefix(name, "gpt-4o") ||
+			strings.HasSuffix(name, "preview") {
 			return 3
 		}
 		return 2

relay/channeltype/define.go

@@ -41,6 +41,6 @@ const (
 	Cloudflare
 	DeepL
 	TogetherAI
-
+	Doubao
 	Dummy
 )

relay/channeltype/url.go

@@ -24,7 +24,7 @@ var ChannelBaseURLs = []string{
 	"https://openrouter.ai/api",                 // 20
 	"https://api.aiproxy.io",                    // 21
 	"https://fastgpt.run/api/openapi",           // 22
-	"https://hunyuan.cloud.tencent.com",         // 23
+	"https://hunyuan.tencentcloudapi.com",       // 23
 	"https://generativelanguage.googleapis.com", // 24
 	"https://api.moonshot.cn",                   // 25
 	"https://api.baichuan-ai.com",               // 26
@@ -41,6 +41,7 @@ var ChannelBaseURLs = []string{
 	"https://api.cloudflare.com",                // 37
 	"https://api-free.deepl.com",                // 38
 	"https://api.together.xyz",                  // 39
+	"https://ark.cn-beijing.volces.com",         // 40
 }
 
 func init() {

relay/channeltype/url_test.go

@@ -0,0 +1,12 @@
+package channeltype
+
+import (
+	. "github.com/smartystreets/goconvey/convey"
+	"testing"
+)
+
+func TestChannelBaseURLs(t *testing.T) {
+	Convey("channel base urls", t, func() {
+		So(len(ChannelBaseURLs), ShouldEqual, Dummy)
+	})
+}

relay/client/init.go

@@ -1,24 +0,0 @@
-package client
-
-import (
-	"github.com/songquanpeng/one-api/common/config"
-	"net/http"
-	"time"
-)
-
-var HTTPClient *http.Client
-var ImpatientHTTPClient *http.Client
-
-func init() {
-	if config.RelayTimeout == 0 {
-		HTTPClient = &http.Client{}
-	} else {
-		HTTPClient = &http.Client{
-			Timeout: time.Duration(config.RelayTimeout) * time.Second,
-		}
-	}
-
-	ImpatientHTTPClient = &http.Client{
-		Timeout: 5 * time.Second,
-	}
-}

relay/controller/audio.go

@@ -9,6 +9,7 @@ import (
 	"fmt"
 	"github.com/gin-gonic/gin"
 	"github.com/songquanpeng/one-api/common"
+	"github.com/songquanpeng/one-api/common/client"
 	"github.com/songquanpeng/one-api/common/config"
 	"github.com/songquanpeng/one-api/common/ctxkey"
 	"github.com/songquanpeng/one-api/common/logger"
@@ -17,7 +18,6 @@ import (
 	"github.com/songquanpeng/one-api/relay/billing"
 	billingratio "github.com/songquanpeng/one-api/relay/billing/ratio"
 	"github.com/songquanpeng/one-api/relay/channeltype"
-	"github.com/songquanpeng/one-api/relay/client"
 	"github.com/songquanpeng/one-api/relay/meta"
 	relaymodel "github.com/songquanpeng/one-api/relay/model"
 	"github.com/songquanpeng/one-api/relay/relaymode"

relay/controller/helper.go

@@ -40,78 +40,6 @@ func getAndValidateTextRequest(c *gin.Context, relayMode int) (*relaymodel.Gener
 	return textRequest, nil
 }
 
-func getImageRequest(c *gin.Context, relayMode int) (*relaymodel.ImageRequest, error) {
-	imageRequest := &relaymodel.ImageRequest{}
-	err := common.UnmarshalBodyReusable(c, imageRequest)
-	if err != nil {
-		return nil, err
-	}
-	if imageRequest.N == 0 {
-		imageRequest.N = 1
-	}
-	if imageRequest.Size == "" {
-		imageRequest.Size = "1024x1024"
-	}
-	if imageRequest.Model == "" {
-		imageRequest.Model = "dall-e-2"
-	}
-	return imageRequest, nil
-}
-
-func isValidImageSize(model string, size string) bool {
-	if model == "cogview-3" {
-		return true
-	}
-	_, ok := billingratio.ImageSizeRatios[model][size]
-	return ok
-}
-
-func getImageSizeRatio(model string, size string) float64 {
-	ratio, ok := billingratio.ImageSizeRatios[model][size]
-	if !ok {
-		return 1
-	}
-	return ratio
-}
-
-func validateImageRequest(imageRequest *relaymodel.ImageRequest, meta *meta.Meta) *relaymodel.ErrorWithStatusCode {
-	// model validation
-	hasValidSize := isValidImageSize(imageRequest.Model, imageRequest.Size)
-	if !hasValidSize {
-		return openai.ErrorWrapper(errors.New("size not supported for this image model"), "size_not_supported", http.StatusBadRequest)
-	}
-	// check prompt length
-	if imageRequest.Prompt == "" {
-		return openai.ErrorWrapper(errors.New("prompt is required"), "prompt_missing", http.StatusBadRequest)
-	}
-	if len(imageRequest.Prompt) > billingratio.ImagePromptLengthLimitations[imageRequest.Model] {
-		return openai.ErrorWrapper(errors.New("prompt is too long"), "prompt_too_long", http.StatusBadRequest)
-	}
-	// Number of generated images validation
-	if !isWithinRange(imageRequest.Model, imageRequest.N) {
-		// channel not azure
-		if meta.ChannelType != channeltype.Azure {
-			return openai.ErrorWrapper(errors.New("invalid value of n"), "n_not_within_range", http.StatusBadRequest)
-		}
-	}
-	return nil
-}
-
-func getImageCostRatio(imageRequest *relaymodel.ImageRequest) (float64, error) {
-	if imageRequest == nil {
-		return 0, errors.New("imageRequest is nil")
-	}
-	imageCostRatio := getImageSizeRatio(imageRequest.Model, imageRequest.Size)
-	if imageRequest.Quality == "hd" && imageRequest.Model == "dall-e-3" {
-		if imageRequest.Size == "1024x1024" {
-			imageCostRatio *= 2
-		} else {
-			imageCostRatio *= 1.5
-		}
-	}
-	return imageCostRatio, nil
-}
-
 func getPromptTokens(textRequest *relaymodel.GeneralOpenAIRequest, relayMode int) int {
 	switch relayMode {
 	case relaymode.ChatCompletions:

relay/controller/image.go

@@ -7,6 +7,7 @@ import (
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/ctxkey"
 	"github.com/songquanpeng/one-api/common/logger"
 	"github.com/songquanpeng/one-api/model"
@@ -20,13 +21,84 @@ import (
 	"net/http"
 )
 
-func isWithinRange(element string, value int) bool {
-	if _, ok := billingratio.ImageGenerationAmounts[element]; !ok {
-		return false
+func getImageRequest(c *gin.Context, relayMode int) (*relaymodel.ImageRequest, error) {
+	imageRequest := &relaymodel.ImageRequest{}
+	err := common.UnmarshalBodyReusable(c, imageRequest)
+	if err != nil {
+		return nil, err
 	}
-	min := billingratio.ImageGenerationAmounts[element][0]
-	max := billingratio.ImageGenerationAmounts[element][1]
-	return value >= min && value <= max
+	if imageRequest.N == 0 {
+		imageRequest.N = 1
+	}
+	if imageRequest.Size == "" {
+		imageRequest.Size = "1024x1024"
+	}
+	if imageRequest.Model == "" {
+		imageRequest.Model = "dall-e-2"
+	}
+	return imageRequest, nil
+}
+
+func isValidImageSize(model string, size string) bool {
+	if model == "cogview-3" || billingratio.ImageSizeRatios[model] == nil {
+		return true
+	}
+	_, ok := billingratio.ImageSizeRatios[model][size]
+	return ok
+}
+
+func isValidImagePromptLength(model string, promptLength int) bool {
+	maxPromptLength, ok := billingratio.ImagePromptLengthLimitations[model]
+	return !ok || promptLength <= maxPromptLength
+}
+
+func isWithinRange(element string, value int) bool {
+	amounts, ok := billingratio.ImageGenerationAmounts[element]
+	return !ok || (value >= amounts[0] && value <= amounts[1])
+}
+
+func getImageSizeRatio(model string, size string) float64 {
+	if ratio, ok := billingratio.ImageSizeRatios[model][size]; ok {
+		return ratio
+	}
+	return 1
+}
+
+func validateImageRequest(imageRequest *relaymodel.ImageRequest, meta *meta.Meta) *relaymodel.ErrorWithStatusCode {
+	// check prompt length
+	if imageRequest.Prompt == "" {
+		return openai.ErrorWrapper(errors.New("prompt is required"), "prompt_missing", http.StatusBadRequest)
+	}
+
+	// model validation
+	if !isValidImageSize(imageRequest.Model, imageRequest.Size) {
+		return openai.ErrorWrapper(errors.New("size not supported for this image model"), "size_not_supported", http.StatusBadRequest)
+	}
+
+	if !isValidImagePromptLength(imageRequest.Model, len(imageRequest.Prompt)) {
+		return openai.ErrorWrapper(errors.New("prompt is too long"), "prompt_too_long", http.StatusBadRequest)
+	}
+
+	// Number of generated images validation
+	if !isWithinRange(imageRequest.Model, imageRequest.N) {
+		return openai.ErrorWrapper(errors.New("invalid value of n"), "n_not_within_range", http.StatusBadRequest)
+	}
+	return nil
+}
+
+func getImageCostRatio(imageRequest *relaymodel.ImageRequest) (float64, error) {
+	if imageRequest == nil {
+		return 0, errors.New("imageRequest is nil")
+	}
+	imageCostRatio := getImageSizeRatio(imageRequest.Model, imageRequest.Size)
+	if imageRequest.Quality == "hd" && imageRequest.Model == "dall-e-3" {
+		if imageRequest.Size == "1024x1024" {
+			imageCostRatio *= 2
+		} else {
+			imageCostRatio *= 1.5
+		}
+	}
+	return imageCostRatio, nil
 }
 
 func RelayImageHelper(c *gin.Context, relayMode int) *relaymodel.ErrorWithStatusCode {
@@ -55,6 +127,11 @@ func RelayImageHelper(c *gin.Context, relayMode int) *relaymodel.ErrorWithStatus
 		return openai.ErrorWrapper(err, "get_image_cost_ratio_failed", http.StatusInternalServerError)
 	}
 
+	imageModel := imageRequest.Model
+	// Convert the original image model
+	imageRequest.Model, _ = getMappedModelName(imageRequest.Model, billingratio.ImageOriginModelName)
+	c.Set("response_format", imageRequest.ResponseFormat)
+
 	var requestBody io.Reader
 	if isModelMapped || meta.ChannelType == channeltype.Azure { // make Azure channel request body
 		jsonStr, err := json.Marshal(imageRequest)
@@ -89,7 +166,7 @@ func RelayImageHelper(c *gin.Context, relayMode int) *relaymodel.ErrorWithStatus
 		requestBody = bytes.NewBuffer(jsonStr)
 	}
 
-	modelRatio := billingratio.GetModelRatio(imageRequest.Model)
+	modelRatio := billingratio.GetModelRatio(imageModel)
 	groupRatio := billingratio.GetGroupRatio(meta.Group)
 	ratio := modelRatio * groupRatio
 	userQuota, err := model.CacheGetUserQuota(ctx, meta.UserId)

relay/model/message.go

@@ -1,10 +1,11 @@
 package model
 
 type Message struct {
-	Role      string  `json:"role,omitempty"`
-	Content   any     `json:"content,omitempty"`
-	Name      *string `json:"name,omitempty"`
-	ToolCalls []Tool  `json:"tool_calls,omitempty"`
+	Role       string  `json:"role,omitempty"`
+	Content    any     `json:"content,omitempty"`
+	Name       *string `json:"name,omitempty"`
+	ToolCalls  []Tool  `json:"tool_calls,omitempty"`
+	ToolCallId string  `json:"tool_call_id,omitempty"`
 }
 
 func (m Message) IsStringContent() bool {

relay/model/tool.go

@@ -2,13 +2,13 @@ package model
 
 type Tool struct {
 	Id       string   `json:"id,omitempty"`
-	Type     string   `json:"type"`
+	Type     string   `json:"type,omitempty"` // when splicing claude tools stream messages, it is empty
 	Function Function `json:"function"`
 }
 
 type Function struct {
 	Description string `json:"description,omitempty"`
-	Name        string `json:"name"`
+	Name        string `json:"name,omitempty"`       // when splicing claude tools stream messages, it is empty
 	Parameters  any    `json:"parameters,omitempty"` // request
 	Arguments   any    `json:"arguments,omitempty"`  // response
 }

web/air/public/index.html

@@ -1,5 +1,5 @@
 <!DOCTYPE html>
-<html lang="en">
+<html lang="zh-CN">
 <head>
   <meta charset="utf-8" />
   <link rel="icon" href="logo.png" />

web/air/src/pages/Channel/EditChannel.js

@@ -63,7 +63,7 @@ const EditChannel = (props) => {
             let localModels = [];
             switch (value) {
                 case 14:
-                    localModels = ["claude-instant-1.2", "claude-2", "claude-2.0", "claude-2.1", "claude-3-opus-20240229", "claude-3-sonnet-20240229", "claude-3-haiku-20240307"];
+                    localModels = ["claude-instant-1.2", "claude-2", "claude-2.0", "claude-2.1", "claude-3-opus-20240229", "claude-3-sonnet-20240229", "claude-3-haiku-20240307", "claude-3-5-sonnet-20240620"];
                     break;
                 case 11:
                     localModels = ['PaLM-2'];
@@ -78,7 +78,7 @@ const EditChannel = (props) => {
                     localModels = ['chatglm_pro', 'chatglm_std', 'chatglm_lite'];
                     break;
                 case 18:
-                    localModels = ['SparkDesk', 'SparkDesk-v1.1', 'SparkDesk-v2.1', 'SparkDesk-v3.1', 'SparkDesk-v3.5'];
+                    localModels = ['SparkDesk', 'SparkDesk-v1.1', 'SparkDesk-v2.1', 'SparkDesk-v3.1', 'SparkDesk-v3.5', 'SparkDesk-v4.0'];
                     break;
                 case 19:
                     localModels = ['360GPT_S2_V9', 'embedding-bert-512-v1', 'embedding_s1_v1', 'semantic_similarity_s1_v1'];

web/berry/package.json

@@ -15,7 +15,7 @@
     "@mui/utils": "^5.8.6",
     "@mui/x-date-pickers": "^6.18.5",
     "@tabler/icons-react": "^2.44.0",
-    "apexcharts": "^3.35.3",
+    "apexcharts": "3.35.3",
     "axios": "^0.27.2",
     "dayjs": "^1.11.10",
     "formik": "^2.2.9",
@@ -26,7 +26,7 @@
     "notistack": "^3.0.1",
     "prop-types": "^15.8.1",
     "react": "^18.2.0",
-    "react-apexcharts": "^1.4.0",
+    "react-apexcharts": "1.4.0",
     "react-device-detect": "^2.2.2",
     "react-dom": "^18.2.0",
     "react-perfect-scrollbar": "^1.5.8",

web/berry/public/index.html

@@ -1,5 +1,5 @@
 <!DOCTYPE html>
-<html lang="en">
+<html lang="zh-CN">
   <head>
     <title>One API</title>
     <link rel="icon" href="/favicon.ico" />

web/berry/src/constants/ChannelConstants.js

@@ -11,12 +11,18 @@ export const CHANNEL_OPTIONS = {
     value: 14,
     color: 'primary'
   },
-  // 33: {
-  //   key: 33,
-  //   text: 'AWS Claude',
-  //   value: 33,
-  //   color: 'primary'
-  // },
+  33: {
+    key: 33,
+    text: 'AWS Claude',
+    value: 33,
+    color: 'primary'
+  },
+  37: {
+    key: 37,
+    text: 'Cloudflare',
+    value: 37,
+    color: 'success'
+  },
   3: {
     key: 3,
     text: 'Azure OpenAI',
@@ -41,6 +47,12 @@ export const CHANNEL_OPTIONS = {
     value: 28,
     color: 'warning'
   },
+  40: {
+    key: 40,
+    text: '字节跳动豆包',
+    value: 40,
+    color: 'primary'
+  },
   15: {
     key: 15,
     text: '百度文心千帆',
@@ -119,12 +131,12 @@ export const CHANNEL_OPTIONS = {
     value: 32,
     color: 'primary'
   },
-  // 34: {
-  //   key: 34,
-  //   text: 'Coze',
-  //   value: 34,
-  //   color: 'primary'
-  // },
+  34: {
+    key: 34,
+    text: 'Coze',
+    value: 34,
+    color: 'primary'
+  },
   35: {
     key: 35,
     text: 'Cohere',

web/berry/src/constants/SnackbarConstants.js

@@ -1,24 +1,56 @@
+import { closeSnackbar } from 'notistack';
+import { IconX } from '@tabler/icons-react';
+import { IconButton } from '@mui/material';
+const action = (snackbarId) => (
+  <>
+    <IconButton
+      onClick={() => {
+        closeSnackbar(snackbarId);
+      }}
+    >
+      <IconX stroke={1.5} size="1.25rem" />
+    </IconButton>
+  </>
+);
+
 export const snackbarConstants = {
   Common: {
     ERROR: {
       variant: 'error',
-      autoHideDuration: 5000
+      autoHideDuration: 5000,
+      preventDuplicate: true,
+      action
     },
     WARNING: {
       variant: 'warning',
-      autoHideDuration: 10000
+      autoHideDuration: 10000,
+      preventDuplicate: true,
+      action
     },
     SUCCESS: {
       variant: 'success',
-      autoHideDuration: 1500
+      autoHideDuration: 1500,
+      preventDuplicate: true,
+      action
     },
     INFO: {
       variant: 'info',
-      autoHideDuration: 3000
+      autoHideDuration: 3000,
+      preventDuplicate: true,
+      action
     },
     NOTICE: {
       variant: 'info',
-      autoHideDuration: 7000
+      autoHideDuration: 20000,
+      preventDuplicate: true,
+      action
+    },
+    COPY: {
+      variant: 'copy',
+      persist: true,
+      preventDuplicate: true,
+      allowDownload: true,
+      action
     }
   },
   Mobile: {

web/berry/src/utils/common.js

@@ -193,3 +193,40 @@ export function removeTrailingSlash(url) {
     return url;
   }
 }
+
+let channelModels = undefined;
+export async function loadChannelModels() {
+  const res = await API.get('/api/models');
+  const { success, data } = res.data;
+  if (!success) {
+    return;
+  }
+  channelModels = data;
+  localStorage.setItem('channel_models', JSON.stringify(data));
+}
+
+export function getChannelModels(type) {
+  if (channelModels !== undefined && type in channelModels) {
+    return channelModels[type];
+  }
+  let models = localStorage.getItem('channel_models');
+  if (!models) {
+    return [];
+  }
+  channelModels = JSON.parse(models);
+  if (type in channelModels) {
+    return channelModels[type];
+  }
+  return [];
+}
+
+export function copy(text, name = '') {
+  try {
+    navigator.clipboard.writeText(text);
+  } catch (error) {
+    text = `复制${name}失败，请手动复制：<br /><br />${text}`;
+    enqueueSnackbar(<SnackbarHTMLContent htmlContent={text} />, getSnackbarOptions('COPY'));
+    return;
+  }
+  showSuccess(`复制${name}成功！`);
+}

web/berry/src/views/Authentication/AuthForms/ResetPasswordForm.js

@@ -1,22 +1,22 @@
-import { useState, useEffect } from "react";
-import { useSearchParams } from "react-router-dom";
+import { useState, useEffect } from 'react';
+import { useSearchParams } from 'react-router-dom';
 
 // material-ui
-import { Button, Stack, Typography, Alert } from "@mui/material";
+import { Button, Stack, Typography, Alert } from '@mui/material';
 
 // assets
-import { showError, showInfo } from "utils/common";
-import { API } from "utils/api";
+import { showError, copy } from 'utils/common';
+import { API } from 'utils/api';
 
 // ===========================|| FIREBASE - REGISTER ||=========================== //
 
 const ResetPasswordForm = () => {
   const [searchParams] = useSearchParams();
   const [inputs, setInputs] = useState({
-    email: "",
-    token: "",
+    email: '',
+    token: ''
   });
-  const [newPassword, setNewPassword] = useState("");
+  const [newPassword, setNewPassword] = useState('');
 
   const submit = async () => {
     const res = await API.post(`/api/user/reset`, inputs);
@@ -24,31 +24,25 @@ const ResetPasswordForm = () => {
     if (success) {
       let password = res.data.data;
       setNewPassword(password);
-      navigator.clipboard.writeText(password);
-      showInfo(`新密码已复制到剪贴板：${password}`);
+      copy(password, '新密码');
     } else {
       showError(message);
     }
   };
 
   useEffect(() => {
-    let email = searchParams.get("email");
-    let token = searchParams.get("token");
+    let email = searchParams.get('email');
+    let token = searchParams.get('token');
     setInputs({
       token,
-      email,
+      email
     });
   }, []);
 
   return (
-    <Stack
-      spacing={3}
-      padding={"24px"}
-      justifyContent={"center"}
-      alignItems={"center"}
-    >
+    <Stack spacing={3} padding={'24px'} justifyContent={'center'} alignItems={'center'}>
       {!inputs.email || !inputs.token ? (
-        <Typography variant="h3" sx={{ textDecoration: "none" }}>
+        <Typography variant="h3" sx={{ textDecoration: 'none' }}>
           无效的链接
         </Typography>
       ) : newPassword ? (
@@ -57,14 +51,7 @@ const ResetPasswordForm = () => {
           请登录后及时修改密码
         </Alert>
       ) : (
-        <Button
-          fullWidth
-          onClick={submit}
-          size="large"
-          type="submit"
-          variant="contained"
-          color="primary"
-        >
+        <Button fullWidth onClick={submit} size="large" type="submit" variant="contained" color="primary">
           点击重置密码
         </Button>
       )}

web/berry/src/views/Channel/component/EditModal.js

@@ -1,9 +1,9 @@
-import PropTypes from "prop-types";
-import { useState, useEffect } from "react";
-import { CHANNEL_OPTIONS } from "constants/ChannelConstants";
-import { useTheme } from "@mui/material/styles";
-import { API } from "utils/api";
-import { showError, showSuccess } from "utils/common";
+import PropTypes from 'prop-types';
+import { useState, useEffect } from 'react';
+import { CHANNEL_OPTIONS } from 'constants/ChannelConstants';
+import { useTheme } from '@mui/material/styles';
+import { API } from 'utils/api';
+import { showError, showSuccess, getChannelModels } from 'utils/common';
 import {
   Dialog,
   DialogTitle,
@@ -22,15 +22,15 @@ import {
   Autocomplete,
   FormHelperText,
   Switch,
-  Checkbox,
-} from "@mui/material";
+  Checkbox
+} from '@mui/material';
 
-import { Formik } from "formik";
-import * as Yup from "yup";
-import { defaultConfig, typeConfig } from "../type/Config"; //typeConfig
-import { createFilterOptions } from "@mui/material/Autocomplete";
-import CheckBoxOutlineBlankIcon from "@mui/icons-material/CheckBoxOutlineBlank";
-import CheckBoxIcon from "@mui/icons-material/CheckBox";
+import { Formik } from 'formik';
+import * as Yup from 'yup';
+import { defaultConfig, typeConfig } from '../type/Config'; //typeConfig
+import { createFilterOptions } from '@mui/material/Autocomplete';
+import CheckBoxOutlineBlankIcon from '@mui/icons-material/CheckBoxOutlineBlank';
+import CheckBoxIcon from '@mui/icons-material/CheckBox';
 
 const icon = <CheckBoxOutlineBlankIcon fontSize="small" />;
 const checkedIcon = <CheckBoxIcon fontSize="small" />;
@@ -38,38 +38,34 @@ const checkedIcon = <CheckBoxIcon fontSize="small" />;
 const filter = createFilterOptions();
 const validationSchema = Yup.object().shape({
   is_edit: Yup.boolean(),
-  name: Yup.string().required("名称 不能为空"),
-  type: Yup.number().required("渠道 不能为空"),
-  key: Yup.string().when("is_edit", {
-    is: false,
-    then: Yup.string().required("密钥 不能为空"),
+  name: Yup.string().required('名称 不能为空'),
+  type: Yup.number().required('渠道 不能为空'),
+  key: Yup.string().when(['is_edit', 'type'], {
+    is: (is_edit, type) => !is_edit && type !== 33,
+    then: Yup.string().required('密钥 不能为空')
   }),
   other: Yup.string(),
-  models: Yup.array().min(1, "模型 不能为空"),
-  groups: Yup.array().min(1, "用户组 不能为空"),
-  base_url: Yup.string().when("type", {
+  models: Yup.array().min(1, '模型 不能为空'),
+  groups: Yup.array().min(1, '用户组 不能为空'),
+  base_url: Yup.string().when('type', {
     is: (value) => [3, 8].includes(value),
-    then: Yup.string().required("渠道API地址 不能为空"), // base_url 是必需的
-    otherwise: Yup.string(), // 在其他情况下，base_url 可以是任意字符串
+    then: Yup.string().required('渠道API地址 不能为空'), // base_url 是必需的
+    otherwise: Yup.string() // 在其他情况下，base_url 可以是任意字符串
   }),
-  model_mapping: Yup.string().test(
-    "is-json",
-    "必须是有效的JSON字符串",
-    function (value) {
-      try {
-        if (value === "" || value === null || value === undefined) {
-          return true;
-        }
-        const parsedValue = JSON.parse(value);
-        if (typeof parsedValue === "object") {
-          return true;
-        }
-      } catch (e) {
-        return false;
+  model_mapping: Yup.string().test('is-json', '必须是有效的JSON字符串', function (value) {
+    try {
+      if (value === '' || value === null || value === undefined) {
+        return true;
       }
+      const parsedValue = JSON.parse(value);
+      if (typeof parsedValue === 'object') {
+        return true;
+      }
+    } catch (e) {
       return false;
     }
-  ),
+    return false;
+  })
 });
 
 const EditModal = ({ open, channelId, onCancel, onOk }) => {
@@ -81,12 +77,13 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
   const [groupOptions, setGroupOptions] = useState([]);
   const [modelOptions, setModelOptions] = useState([]);
   const [batchAdd, setBatchAdd] = useState(false);
+  const [basicModels, setBasicModels] = useState([]);
 
   const initChannel = (typeValue) => {
     if (typeConfig[typeValue]?.inputLabel) {
       setInputLabel({
         ...defaultConfig.inputLabel,
-        ...typeConfig[typeValue].inputLabel,
+        ...typeConfig[typeValue].inputLabel
       });
     } else {
       setInputLabel(defaultConfig.inputLabel);
@@ -95,7 +92,7 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
     if (typeConfig[typeValue]?.prompt) {
       setInputPrompt({
         ...defaultConfig.prompt,
-        ...typeConfig[typeValue].prompt,
+        ...typeConfig[typeValue].prompt
       });
     } else {
       setInputPrompt(defaultConfig.prompt);
@@ -104,40 +101,14 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
     return typeConfig[typeValue]?.input;
   };
   const handleTypeChange = (setFieldValue, typeValue, values) => {
-    const newInput = initChannel(typeValue);
-
-    if (newInput) {
-      Object.keys(newInput).forEach((key) => {
-        if (
-          (!Array.isArray(values[key]) &&
-            values[key] !== null &&
-            values[key] !== undefined &&
-            values[key] !== "") ||
-          (Array.isArray(values[key]) && values[key].length > 0)
-        ) {
-          return;
-        }
-
-        if (key === "models") {
-          setFieldValue(key, initialModel(newInput[key]));
-          return;
-        }
-        setFieldValue(key, newInput[key]);
-      });
+    initChannel(typeValue);
+    let localModels = getChannelModels(typeValue);
+    setBasicModels(localModels);
+    if (localModels.length > 0 && Array.isArray(values['models']) && values['models'].length == 0) {
+      setFieldValue('models', initialModel(localModels));
     }
-  };
 
-  const basicModels = (channelType) => {
-    let modelGroup =
-      typeConfig[channelType]?.modelGroup || defaultConfig.modelGroup;
-    // 循环 modelOptions，找到 modelGroup 对应的模型
-    let modelList = [];
-    modelOptions.forEach((model) => {
-      if (model.group === modelGroup) {
-        modelList.push(model);
-      }
-    });
-    return modelList;
+    setFieldValue('config', {});
   };
 
   const fetchGroups = async () => {
@@ -155,7 +126,7 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
       const { data } = res.data;
       data.forEach((item) => {
         if (!item.owned_by) {
-          item.owned_by = "未知";
+          item.owned_by = '未知';
         }
       });
       // 先对data排序
@@ -171,7 +142,7 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
         data.map((model) => {
           return {
             id: model.id,
-            group: model.owned_by,
+            group: model.owned_by
           };
         })
       );
@@ -182,33 +153,41 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
 
   const submit = async (values, { setErrors, setStatus, setSubmitting }) => {
     setSubmitting(true);
-    if (values.base_url && values.base_url.endsWith("/")) {
+    if (values.base_url && values.base_url.endsWith('/')) {
       values.base_url = values.base_url.slice(0, values.base_url.length - 1);
     }
-    if (values.type === 3 && values.other === "") {
-      values.other = "2023-09-01-preview";
+    if (values.type === 3 && values.other === '') {
+      values.other = '2023-09-01-preview';
     }
-    if (values.type === 18 && values.other === "") {
-      values.other = "v2.1";
+    if (values.type === 18 && values.other === '') {
+      values.other = 'v2.1';
     }
+    if (values.key === '') {
+      if (values.config.ak && values.config.sk && values.config.region) {
+        values.key = `${values.config.ak}|${values.config.sk}|${values.config.region}`;
+      }
+    }
+
     let res;
-    const modelsStr = values.models.map((model) => model.id).join(",");
-    values.group = values.groups.join(",");
+    const modelsStr = values.models.map((model) => model.id).join(',');
+    const configStr = JSON.stringify(values.config);
+    values.group = values.groups.join(',');
     if (channelId) {
       res = await API.put(`/api/channel/`, {
         ...values,
         id: parseInt(channelId),
         models: modelsStr,
+        config: configStr
       });
     } else {
-      res = await API.post(`/api/channel/`, { ...values, models: modelsStr });
+      res = await API.post(`/api/channel/`, { ...values, models: modelsStr, config: configStr });
     }
     const { success, message } = res.data;
     if (success) {
       if (channelId) {
-        showSuccess("渠道更新成功！");
+        showSuccess('渠道更新成功！');
       } else {
-        showSuccess("渠道创建成功！");
+        showSuccess('渠道创建成功！');
       }
       setSubmitting(false);
       setStatus({ success: true });
@@ -226,15 +205,15 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
     }
 
     // 如果 channelModel 是一个字符串
-    if (typeof channelModel === "string") {
-      channelModel = channelModel.split(",");
+    if (typeof channelModel === 'string') {
+      channelModel = channelModel.split(',');
     }
     let modelList = channelModel.map((model) => {
       const modelOption = modelOptions.find((option) => option.id === model);
       if (modelOption) {
         return modelOption;
       }
-      return { id: model, group: "自定义：点击或回车输入" };
+      return { id: model, group: '自定义：点击或回车输入' };
     });
     return modelList;
   }
@@ -243,24 +222,24 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
     let res = await API.get(`/api/channel/${channelId}`);
     const { success, message, data } = res.data;
     if (success) {
-      if (data.models === "") {
+      if (data.models === '') {
         data.models = [];
       } else {
         data.models = initialModel(data.models);
       }
-      if (data.group === "") {
+      if (data.group === '') {
         data.groups = [];
       } else {
-        data.groups = data.group.split(",");
+        data.groups = data.group.split(',');
       }
-      if (data.model_mapping !== "") {
-        data.model_mapping = JSON.stringify(
-          JSON.parse(data.model_mapping),
-          null,
-          2
-        );
+      if (data.model_mapping !== '') {
+        data.model_mapping = JSON.stringify(JSON.parse(data.model_mapping), null, 2);
       }
-      data.base_url = data.base_url ?? "";
+      if (data.config !== '') {
+        data.config = JSON.parse(data.config);
+      }
+
+      data.base_url = data.base_url ?? '';
       data.is_edit = true;
       initChannel(data.type);
       setInitialInput(data);
@@ -286,45 +265,25 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
   }, [channelId]);
 
   return (
-    <Dialog open={open} onClose={onCancel} fullWidth maxWidth={"md"}>
+    <Dialog open={open} onClose={onCancel} fullWidth maxWidth={'md'}>
       <DialogTitle
         sx={{
-          margin: "0px",
+          margin: '0px',
           fontWeight: 700,
-          lineHeight: "1.55556",
-          padding: "24px",
-          fontSize: "1.125rem",
+          lineHeight: '1.55556',
+          padding: '24px',
+          fontSize: '1.125rem'
         }}
       >
-        {channelId ? "编辑渠道" : "新建渠道"}
+        {channelId ? '编辑渠道' : '新建渠道'}
       </DialogTitle>
       <Divider />
       <DialogContent>
-        <Formik
-          initialValues={initialInput}
-          enableReinitialize
-          validationSchema={validationSchema}
-          onSubmit={submit}
-        >
-          {({
-            errors,
-            handleBlur,
-            handleChange,
-            handleSubmit,
-            isSubmitting,
-            touched,
-            values,
-            setFieldValue,
-          }) => (
+        <Formik initialValues={initialInput} enableReinitialize validationSchema={validationSchema} onSubmit={submit}>
+          {({ errors, handleBlur, handleChange, handleSubmit, isSubmitting, touched, values, setFieldValue }) => (
             <form noValidate onSubmit={handleSubmit}>
-              <FormControl
-                fullWidth
-                error={Boolean(touched.type && errors.type)}
-                sx={{ ...theme.typography.otherInput }}
-              >
-                <InputLabel htmlFor="channel-type-label">
-                  {inputLabel.type}
-                </InputLabel>
+              <FormControl fullWidth error={Boolean(touched.type && errors.type)} sx={{ ...theme.typography.otherInput }}>
+                <InputLabel htmlFor="channel-type-label">{inputLabel.type}</InputLabel>
                 <Select
                   id="channel-type-label"
                   label={inputLabel.type}
@@ -338,9 +297,9 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
                   MenuProps={{
                     PaperProps: {
                       style: {
-                        maxHeight: 200,
-                      },
-                    },
+                        maxHeight: 200
+                      }
+                    }
                   }}
                 >
                   {Object.values(CHANNEL_OPTIONS)
@@ -360,21 +319,12 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
                     {errors.type}
                   </FormHelperText>
                 ) : (
-                  <FormHelperText id="helper-tex-channel-type-label">
-                    {" "}
-                    {inputPrompt.type}{" "}
-                  </FormHelperText>
+                  <FormHelperText id="helper-tex-channel-type-label"> {inputPrompt.type} </FormHelperText>
                 )}
               </FormControl>
 
-              <FormControl
-                fullWidth
-                error={Boolean(touched.name && errors.name)}
-                sx={{ ...theme.typography.otherInput }}
-              >
-                <InputLabel htmlFor="channel-name-label">
-                  {inputLabel.name}
-                </InputLabel>
+              <FormControl fullWidth error={Boolean(touched.name && errors.name)} sx={{ ...theme.typography.otherInput }}>
+                <InputLabel htmlFor="channel-name-label">{inputLabel.name}</InputLabel>
                 <OutlinedInput
                   id="channel-name-label"
                   label={inputLabel.name}
@@ -383,7 +333,7 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
                   name="name"
                   onBlur={handleBlur}
                   onChange={handleChange}
-                  inputProps={{ autoComplete: "name" }}
+                  inputProps={{ autoComplete: 'name' }}
                   aria-describedby="helper-text-channel-name-label"
                 />
                 {touched.name && errors.name ? (
@@ -391,21 +341,12 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
                     {errors.name}
                   </FormHelperText>
                 ) : (
-                  <FormHelperText id="helper-tex-channel-name-label">
-                    {" "}
-                    {inputPrompt.name}{" "}
-                  </FormHelperText>
+                  <FormHelperText id="helper-tex-channel-name-label"> {inputPrompt.name} </FormHelperText>
                 )}
               </FormControl>
 
-              <FormControl
-                fullWidth
-                error={Boolean(touched.base_url && errors.base_url)}
-                sx={{ ...theme.typography.otherInput }}
-              >
-                <InputLabel htmlFor="channel-base_url-label">
-                  {inputLabel.base_url}
-                </InputLabel>
+              <FormControl fullWidth error={Boolean(touched.base_url && errors.base_url)} sx={{ ...theme.typography.otherInput }}>
+                <InputLabel htmlFor="channel-base_url-label">{inputLabel.base_url}</InputLabel>
                 <OutlinedInput
                   id="channel-base_url-label"
                   label={inputLabel.base_url}
@@ -422,22 +363,13 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
                     {errors.base_url}
                   </FormHelperText>
                 ) : (
-                  <FormHelperText id="helper-tex-channel-base_url-label">
-                    {" "}
-                    {inputPrompt.base_url}{" "}
-                  </FormHelperText>
+                  <FormHelperText id="helper-tex-channel-base_url-label"> {inputPrompt.base_url} </FormHelperText>
                 )}
               </FormControl>
 
               {inputPrompt.other && (
-                <FormControl
-                  fullWidth
-                  error={Boolean(touched.other && errors.other)}
-                  sx={{ ...theme.typography.otherInput }}
-                >
-                  <InputLabel htmlFor="channel-other-label">
-                    {inputLabel.other}
-                  </InputLabel>
+                <FormControl fullWidth error={Boolean(touched.other && errors.other)} sx={{ ...theme.typography.otherInput }}>
+                  <InputLabel htmlFor="channel-other-label">{inputLabel.other}</InputLabel>
                   <OutlinedInput
                     id="channel-other-label"
                     label={inputLabel.other}
@@ -454,10 +386,7 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
                       {errors.other}
                     </FormHelperText>
                   ) : (
-                    <FormHelperText id="helper-tex-channel-other-label">
-                      {" "}
-                      {inputPrompt.other}{" "}
-                    </FormHelperText>
+                    <FormHelperText id="helper-tex-channel-other-label"> {inputPrompt.other} </FormHelperText>
                   )}
                 </FormControl>
               )}
@@ -471,22 +400,15 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
                   onChange={(e, value) => {
                     const event = {
                       target: {
-                        name: "groups",
-                        value: value,
-                      },
+                        name: 'groups',
+                        value: value
+                      }
                     };
                     handleChange(event);
                   }}
                   onBlur={handleBlur}
                   filterSelectedOptions
-                  renderInput={(params) => (
-                    <TextField
-                      {...params}
-                      name="groups"
-                      error={Boolean(errors.groups)}
-                      label={inputLabel.groups}
-                    />
-                  )}
+                  renderInput={(params) => <TextField {...params} name="groups" error={Boolean(errors.groups)} label={inputLabel.groups} />}
                   aria-describedby="helper-text-channel-groups-label"
                 />
                 {errors.groups ? (
@@ -494,10 +416,7 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
                     {errors.groups}
                   </FormHelperText>
                 ) : (
-                  <FormHelperText id="helper-tex-channel-groups-label">
-                    {" "}
-                    {inputPrompt.groups}{" "}
-                  </FormHelperText>
+                  <FormHelperText id="helper-tex-channel-groups-label"> {inputPrompt.groups} </FormHelperText>
                 )}
               </FormControl>
 
@@ -511,30 +430,19 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
                   onChange={(e, value) => {
                     const event = {
                       target: {
-                        name: "models",
-                        value: value.map((item) =>
-                          typeof item === "string"
-                            ? { id: item, group: "自定义：点击或回车输入" }
-                            : item
-                        ),
-                      },
+                        name: 'models',
+                        value: value.map((item) => (typeof item === 'string' ? { id: item, group: '自定义：点击或回车输入' } : item))
+                      }
                     };
                     handleChange(event);
                   }}
                   onBlur={handleBlur}
                   // filterSelectedOptions
                   disableCloseOnSelect
-                  renderInput={(params) => (
-                    <TextField
-                      {...params}
-                      name="models"
-                      error={Boolean(errors.models)}
-                      label={inputLabel.models}
-                    />
-                  )}
+                  renderInput={(params) => <TextField {...params} name="models" error={Boolean(errors.models)} label={inputLabel.models} />}
                   groupBy={(option) => option.group}
                   getOptionLabel={(option) => {
-                    if (typeof option === "string") {
+                    if (typeof option === 'string') {
                       return option;
                     }
                     if (option.inputValue) {
@@ -545,25 +453,18 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
                   filterOptions={(options, params) => {
                     const filtered = filter(options, params);
                     const { inputValue } = params;
-                    const isExisting = options.some(
-                      (option) => inputValue === option.id
-                    );
-                    if (inputValue !== "" && !isExisting) {
+                    const isExisting = options.some((option) => inputValue === option.id);
+                    if (inputValue !== '' && !isExisting) {
                       filtered.push({
                         id: inputValue,
-                        group: "自定义：点击或回车输入",
+                        group: '自定义：点击或回车输入'
                       });
                     }
                     return filtered;
                   }}
                   renderOption={(props, option, { selected }) => (
                     <li {...props}>
-                      <Checkbox
-                        icon={icon}
-                        checkedIcon={checkedIcon}
-                        style={{ marginRight: 8 }}
-                        checked={selected}
-                      />
+                      <Checkbox icon={icon} checkedIcon={checkedIcon} style={{ marginRight: 8 }} checked={selected} />
                       {option.id}
                     </li>
                   )}
@@ -573,103 +474,104 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
                     {errors.models}
                   </FormHelperText>
                 ) : (
-                  <FormHelperText id="helper-tex-channel-models-label">
-                    {" "}
-                    {inputPrompt.models}{" "}
-                  </FormHelperText>
+                  <FormHelperText id="helper-tex-channel-models-label"> {inputPrompt.models} </FormHelperText>
                 )}
               </FormControl>
               <Container
                 sx={{
-                  textAlign: "right",
+                  textAlign: 'right'
                 }}
               >
-                <ButtonGroup
-                  variant="outlined"
-                  aria-label="small outlined primary button group"
-                >
+                <ButtonGroup variant="outlined" aria-label="small outlined primary button group">
                   <Button
                     onClick={() => {
-                      setFieldValue("models", basicModels(values.type));
+                      setFieldValue('models', initialModel(basicModels));
                     }}
                   >
-                    填入渠道支持模型
+                    填入相关模型
                   </Button>
                   <Button
                     onClick={() => {
-                      setFieldValue("models", modelOptions);
+                      setFieldValue('models', modelOptions);
                     }}
                   >
                     填入所有模型
                   </Button>
                 </ButtonGroup>
               </Container>
-              <FormControl
-                fullWidth
-                error={Boolean(touched.key && errors.key)}
-                sx={{ ...theme.typography.otherInput }}
-              >
-                {!batchAdd ? (
-                  <>
-                    <InputLabel htmlFor="channel-key-label">
-                      {inputLabel.key}
-                    </InputLabel>
-                    <OutlinedInput
-                      id="channel-key-label"
-                      label={inputLabel.key}
-                      type="text"
-                      value={values.key}
-                      name="key"
-                      onBlur={handleBlur}
-                      onChange={handleChange}
-                      inputProps={{}}
-                      aria-describedby="helper-text-channel-key-label"
-                    />
-                  </>
-                ) : (
-                  <TextField
-                    multiline
-                    id="channel-key-label"
-                    label={inputLabel.key}
-                    value={values.key}
-                    name="key"
-                    onBlur={handleBlur}
-                    onChange={handleChange}
-                    aria-describedby="helper-text-channel-key-label"
-                    minRows={5}
-                    placeholder={inputPrompt.key + "，一行一个密钥"}
-                  />
-                )}
+              {inputLabel.key && (
+                <>
+                  <FormControl fullWidth error={Boolean(touched.key && errors.key)} sx={{ ...theme.typography.otherInput }}>
+                    {!batchAdd ? (
+                      <>
+                        <InputLabel htmlFor="channel-key-label">{inputLabel.key}</InputLabel>
+                        <OutlinedInput
+                          id="channel-key-label"
+                          label={inputLabel.key}
+                          type="text"
+                          value={values.key}
+                          name="key"
+                          onBlur={handleBlur}
+                          onChange={handleChange}
+                          inputProps={{}}
+                          aria-describedby="helper-text-channel-key-label"
+                        />
+                      </>
+                    ) : (
+                      <TextField
+                        multiline
+                        id="channel-key-label"
+                        label={inputLabel.key}
+                        value={values.key}
+                        name="key"
+                        onBlur={handleBlur}
+                        onChange={handleChange}
+                        aria-describedby="helper-text-channel-key-label"
+                        minRows={5}
+                        placeholder={inputPrompt.key + '，一行一个密钥'}
+                      />
+                    )}
 
-                {touched.key && errors.key ? (
-                  <FormHelperText error id="helper-tex-channel-key-label">
-                    {errors.key}
-                  </FormHelperText>
-                ) : (
-                  <FormHelperText id="helper-tex-channel-key-label">
-                    {" "}
-                    {inputPrompt.key}{" "}
-                  </FormHelperText>
-                )}
-              </FormControl>
-              {channelId === 0 && (
-                <Container
-                  sx={{
-                    textAlign: "right",
-                  }}
-                >
-                  <Switch
-                    checked={batchAdd}
-                    onChange={(e) => setBatchAdd(e.target.checked)}
-                  />
-                  批量添加
-                </Container>
+                    {touched.key && errors.key ? (
+                      <FormHelperText error id="helper-tex-channel-key-label">
+                        {errors.key}
+                      </FormHelperText>
+                    ) : (
+                      <FormHelperText id="helper-tex-channel-key-label"> {inputPrompt.key} </FormHelperText>
+                    )}
+                  </FormControl>
+                  {channelId === 0 && (
+                    <Container
+                      sx={{
+                        textAlign: 'right'
+                      }}
+                    >
+                      <Switch checked={batchAdd} onChange={(e) => setBatchAdd(e.target.checked)} />
+                      批量添加
+                    </Container>
+                  )}
+                </>
               )}
-              <FormControl
-                fullWidth
-                error={Boolean(touched.model_mapping && errors.model_mapping)}
-                sx={{ ...theme.typography.otherInput }}
-              >
+
+              {inputLabel.config &&
+                Object.keys(inputLabel.config).map((configName) => {
+                  return (
+                    <FormControl key={'config.' + configName} fullWidth sx={{ ...theme.typography.otherInput }}>
+                      <TextField
+                        multiline
+                        key={'config.' + configName}
+                        name={'config.' + configName}
+                        value={values.config?.[configName] || ''}
+                        label={configName}
+                        placeholder={inputPrompt.config[configName]}
+                        onChange={handleChange}
+                      />
+                      <FormHelperText id={`helper-tex-config.${configName}-label`}> {inputPrompt.config[configName]} </FormHelperText>
+                    </FormControl>
+                  );
+                })}
+
+              <FormControl fullWidth error={Boolean(touched.model_mapping && errors.model_mapping)} sx={{ ...theme.typography.otherInput }}>
                 {/* <InputLabel htmlFor="channel-model_mapping-label">{inputLabel.model_mapping}</InputLabel> */}
                 <TextField
                   multiline
@@ -684,28 +586,16 @@ const EditModal = ({ open, channelId, onCancel, onOk }) => {
                   placeholder={inputPrompt.model_mapping}
                 />
                 {touched.model_mapping && errors.model_mapping ? (
-                  <FormHelperText
-                    error
-                    id="helper-tex-channel-model_mapping-label"
-                  >
+                  <FormHelperText error id="helper-tex-channel-model_mapping-label">
                     {errors.model_mapping}
                   </FormHelperText>
                 ) : (
-                  <FormHelperText id="helper-tex-channel-model_mapping-label">
-                    {" "}
-                    {inputPrompt.model_mapping}{" "}
-                  </FormHelperText>
+                  <FormHelperText id="helper-tex-channel-model_mapping-label"> {inputPrompt.model_mapping} </FormHelperText>
                 )}
               </FormControl>
               <DialogActions>
                 <Button onClick={onCancel}>取消</Button>
-                <Button
-                  disableElevation
-                  disabled={isSubmitting}
-                  type="submit"
-                  variant="contained"
-                  color="primary"
-                >
+                <Button disableElevation disabled={isSubmitting} type="submit" variant="contained" color="primary">
                   提交
                 </Button>
               </DialogActions>
@@ -723,5 +613,5 @@ EditModal.propTypes = {
   open: PropTypes.bool,
   channelId: PropTypes.number,
   onCancel: PropTypes.func,
-  onOk: PropTypes.func,
+  onOk: PropTypes.func
 };

web/berry/src/views/Channel/component/NameLabel.js

@@ -1,20 +1,20 @@
-import PropTypes from "prop-types";
-import { Tooltip, Stack, Container } from "@mui/material";
-import Label from "ui-component/Label";
-import { styled } from "@mui/material/styles";
-import { showSuccess } from "utils/common";
+import PropTypes from 'prop-types';
+import { Tooltip, Stack, Container } from '@mui/material';
+import Label from 'ui-component/Label';
+import { styled } from '@mui/material/styles';
+import { showSuccess, copy } from 'utils/common';
 
 const TooltipContainer = styled(Container)({
-  maxHeight: "250px",
-  overflow: "auto",
-  "&::-webkit-scrollbar": {
-    width: "0px", // Set the width to 0 to hide the scrollbar
-  },
+  maxHeight: '250px',
+  overflow: 'auto',
+  '&::-webkit-scrollbar': {
+    width: '0px' // Set the width to 0 to hide the scrollbar
+  }
 });
 
 const NameLabel = ({ name, models }) => {
   let modelMap = [];
-  modelMap = models.split(",");
+  modelMap = models.split(',');
   modelMap.sort();
 
   return (
@@ -28,8 +28,7 @@ const NameLabel = ({ name, models }) => {
                   variant="ghost"
                   key={index}
                   onClick={() => {
-                    navigator.clipboard.writeText(item);
-                    showSuccess("复制模型名称成功！");
+                    copy(item, '模型名称');
                   }}
                 >
                   {item}
@@ -48,7 +47,7 @@ const NameLabel = ({ name, models }) => {
 
 NameLabel.propTypes = {
   name: PropTypes.string,
-  models: PropTypes.string,
+  models: PropTypes.string
 };
 
 export default NameLabel;

web/berry/src/views/Channel/index.js

@@ -1,5 +1,5 @@
 import { useState, useEffect } from 'react';
-import { showError, showSuccess, showInfo } from 'utils/common';
+import { showError, showSuccess, showInfo, loadChannelModels } from 'utils/common';
 
 import { useTheme } from '@mui/material/styles';
 import Table from '@mui/material/Table';
@@ -8,7 +8,6 @@ import TableContainer from '@mui/material/TableContainer';
 import PerfectScrollbar from 'react-perfect-scrollbar';
 import TablePagination from '@mui/material/TablePagination';
 import LinearProgress from '@mui/material/LinearProgress';
-import Alert from '@mui/material/Alert';
 import ButtonGroup from '@mui/material/ButtonGroup';
 import Toolbar from '@mui/material/Toolbar';
 import useMediaQuery from '@mui/material/useMediaQuery';
@@ -189,6 +188,7 @@ export default function ChannelPage() {
       .catch((reason) => {
         showError(reason);
       });
+    loadChannelModels().then();
   }, []);
 
   return (
@@ -200,7 +200,7 @@ export default function ChannelPage() {
         </Button>
       </Stack>
       <Card>
-        <Box component="form" onSubmit={searchChannels} noValidate sx={{marginTop: 2}}>
+        <Box component="form" onSubmit={searchChannels} noValidate sx={{ marginTop: 2 }}>
           <TableToolBar filterName={searchKeyword} handleFilterName={handleSearchKeyword} placeholder={'搜索渠道的 ID，名称和密钥 ...'} />
         </Box>
         <Toolbar
@@ -214,7 +214,7 @@ export default function ChannelPage() {
         >
           <Container>
             {matchUpMd ? (
-              <ButtonGroup variant="outlined" aria-label="outlined small primary button group" sx={{marginBottom: 2}}>
+              <ButtonGroup variant="outlined" aria-label="outlined small primary button group" sx={{ marginBottom: 2 }}>
                 <Button onClick={handleRefresh} startIcon={<IconRefresh width={'18px'} />}>
                   刷新
                 </Button>

web/berry/src/views/Channel/type/Config.js

@@ -1,177 +1,209 @@
 const defaultConfig = {
   input: {
-    name: "",
+    name: '',
     type: 1,
-    key: "",
-    base_url: "",
-    other: "",
-    model_mapping: "",
+    key: '',
+    base_url: '',
+    other: '',
+    model_mapping: '',
     models: [],
-    groups: ["default"],
+    groups: ['default'],
+    config: {}
   },
   inputLabel: {
-    name: "渠道名称",
-    type: "渠道类型",
-    base_url: "渠道API地址",
-    key: "密钥",
-    other: "其他参数",
-    models: "模型",
-    model_mapping: "模型映射关系",
-    groups: "用户组",
+    name: '渠道名称',
+    type: '渠道类型',
+    base_url: '渠道API地址',
+    key: '密钥',
+    other: '其他参数',
+    models: '模型',
+    model_mapping: '模型映射关系',
+    groups: '用户组',
+    config: null
   },
   prompt: {
-    type: "请选择渠道类型",
-    name: "请为渠道命名",
-    base_url: "可空，请输入中转API地址，例如通过cloudflare中转",
-    key: "请输入渠道对应的鉴权密钥",
-    other: "",
-    models: "请选择该渠道所支持的模型",
+    type: '请选择渠道类型',
+    name: '请为渠道命名',
+    base_url: '可空，请输入中转API地址，例如通过cloudflare中转',
+    key: '请输入渠道对应的鉴权密钥',
+    other: '',
+    models: '请选择该渠道所支持的模型',
     model_mapping:
       '请输入要修改的模型映射关系，格式为：api请求模型ID:实际转发给渠道的模型ID，使用JSON数组表示，例如：{"gpt-3.5": "gpt-35"}',
-    groups: "请选择该渠道所支持的用户组",
+    groups: '请选择该渠道所支持的用户组',
+    config: null
   },
-  modelGroup: "openai",
+  modelGroup: 'openai'
 };
 
 const typeConfig = {
   3: {
     inputLabel: {
-      base_url: "AZURE_OPENAI_ENDPOINT",
-      other: "默认 API 版本",
+      base_url: 'AZURE_OPENAI_ENDPOINT',
+      other: '默认 API 版本'
     },
     prompt: {
-      base_url: "请填写AZURE_OPENAI_ENDPOINT",
-      other: "请输入默认API版本，例如：2024-03-01-preview",
-    },
+      base_url: '请填写AZURE_OPENAI_ENDPOINT',
+      other: '请输入默认API版本，例如：2024-03-01-preview'
+    }
   },
   11: {
     input: {
-      models: ["PaLM-2"],
+      models: ['PaLM-2']
     },
-    modelGroup: "google palm",
+    modelGroup: 'google palm'
   },
   14: {
     input: {
-      models: ["claude-instant-1", "claude-2", "claude-2.0", "claude-2.1"],
+      models: ['claude-instant-1', 'claude-2', 'claude-2.0', 'claude-2.1']
     },
-    modelGroup: "anthropic",
+    modelGroup: 'anthropic'
   },
   15: {
     input: {
-      models: ["ERNIE-Bot", "ERNIE-Bot-turbo", "ERNIE-Bot-4", "Embedding-V1"],
+      models: ['ERNIE-Bot', 'ERNIE-Bot-turbo', 'ERNIE-Bot-4', 'Embedding-V1']
     },
     prompt: {
-      key: "按照如下格式输入：APIKey|SecretKey",
+      key: '按照如下格式输入：APIKey|SecretKey'
     },
-    modelGroup: "baidu",
+    modelGroup: 'baidu'
   },
   16: {
     input: {
-      models: ["glm-4", "glm-4v", "glm-3-turbo", "chatglm_turbo", "chatglm_pro", "chatglm_std", "chatglm_lite"],
+      models: ['glm-4', 'glm-4v', 'glm-3-turbo', 'chatglm_turbo', 'chatglm_pro', 'chatglm_std', 'chatglm_lite']
     },
-    modelGroup: "zhipu",
+    modelGroup: 'zhipu'
   },
   17: {
     inputLabel: {
-      other: "插件参数",
+      other: '插件参数'
     },
     input: {
-      models: [
-        "qwen-turbo",
-        "qwen-plus",
-        "qwen-max",
-        "qwen-max-longcontext",
-        "text-embedding-v1",
-      ],
+      models: ['qwen-turbo', 'qwen-plus', 'qwen-max', 'qwen-max-longcontext', 'text-embedding-v1']
     },
     prompt: {
-      other: "请输入插件参数，即 X-DashScope-Plugin 请求头的取值",
+      other: '请输入插件参数，即 X-DashScope-Plugin 请求头的取值'
     },
-    modelGroup: "ali",
+    modelGroup: 'ali'
   },
   18: {
     inputLabel: {
-      other: "版本号",
+      other: '版本号'
     },
     input: {
-      models: [
-          "SparkDesk",
-        'SparkDesk-v1.1',
-        'SparkDesk-v2.1',
-        'SparkDesk-v3.1',
-        'SparkDesk-v3.5'
-      ],
+      models: ['SparkDesk', 'SparkDesk-v1.1', 'SparkDesk-v2.1', 'SparkDesk-v3.1', 'SparkDesk-v3.5', 'SparkDesk-v4.0']
     },
     prompt: {
-      key: "按照如下格式输入：APPID|APISecret|APIKey",
-      other: "请输入版本号，例如：v3.1",
+      key: '按照如下格式输入：APPID|APISecret|APIKey',
+      other: '请输入版本号，例如：v3.1'
     },
-    modelGroup: "xunfei",
+    modelGroup: 'xunfei'
   },
   19: {
     input: {
-      models: [
-        "360GPT_S2_V9",
-        "embedding-bert-512-v1",
-        "embedding_s1_v1",
-        "semantic_similarity_s1_v1",
-      ],
+      models: ['360GPT_S2_V9', 'embedding-bert-512-v1', 'embedding_s1_v1', 'semantic_similarity_s1_v1']
     },
-    modelGroup: "360",
+    modelGroup: '360'
   },
   22: {
     prompt: {
-      key: "按照如下格式输入：APIKey-AppId，例如：fastgpt-0sp2gtvfdgyi4k30jwlgwf1i-64f335d84283f05518e9e041",
-    },
+      key: '按照如下格式输入：APIKey-AppId，例如：fastgpt-0sp2gtvfdgyi4k30jwlgwf1i-64f335d84283f05518e9e041'
+    }
   },
   23: {
     input: {
-      models: ["hunyuan"],
+      models: ['hunyuan']
     },
     prompt: {
-      key: "按照如下格式输入：AppId|SecretId|SecretKey",
+      key: '按照如下格式输入：AppId|SecretId|SecretKey'
     },
-    modelGroup: "tencent",
+    modelGroup: 'tencent'
   },
   24: {
     inputLabel: {
-      other: "版本号",
+      other: '版本号'
     },
     input: {
-      models: ["gemini-pro"],
+      models: ['gemini-pro']
     },
     prompt: {
-      other: "请输入版本号，例如：v1",
+      other: '请输入版本号，例如：v1'
     },
-    modelGroup: "google gemini",
+    modelGroup: 'google gemini'
   },
   25: {
     input: {
-      models: ['moonshot-v1-8k', 'moonshot-v1-32k', 'moonshot-v1-128k'],
+      models: ['moonshot-v1-8k', 'moonshot-v1-32k', 'moonshot-v1-128k']
     },
-    modelGroup: "moonshot",
+    modelGroup: 'moonshot'
   },
   26: {
     input: {
-      models: ['Baichuan2-Turbo', 'Baichuan2-Turbo-192k', 'Baichuan-Text-Embedding'],
+      models: ['Baichuan2-Turbo', 'Baichuan2-Turbo-192k', 'Baichuan-Text-Embedding']
     },
-    modelGroup: "baichuan",
+    modelGroup: 'baichuan'
   },
   27: {
     input: {
-      models: ['abab5.5s-chat', 'abab5.5-chat', 'abab6-chat'],
+      models: ['abab5.5s-chat', 'abab5.5-chat', 'abab6-chat']
     },
-    modelGroup: "minimax",
+    modelGroup: 'minimax'
   },
   29: {
-    modelGroup: "groq",
+    modelGroup: 'groq'
   },
   30: {
-    modelGroup: "ollama",
+    modelGroup: 'ollama'
   },
   31: {
-    modelGroup: "lingyiwanwu",
+    modelGroup: 'lingyiwanwu'
   },
+  33: {
+    inputLabel: {
+      key: '',
+      config: {
+        region: 'Region',
+        ak: 'Access Key',
+        sk: 'Secret Key'
+      }
+    },
+    prompt: {
+      key: '',
+      config: {
+        region: 'region，e.g. us-west-2',
+        ak: 'AWS IAM Access Key',
+        sk: 'AWS IAM Secret Key'
+      }
+    },
+    modelGroup: 'anthropic'
+  },
+  37: {
+    inputLabel: {
+      config: {
+        user_id: 'Account ID'
+      }
+    },
+    prompt: {
+      config: {
+        user_id: '请输入 Account ID，例如：d8d7c61dbc334c32d3ced580e4bf42b4'
+      }
+    },
+    modelGroup: 'Cloudflare'
+  },
+  34: {
+    inputLabel: {
+      config: {
+        user_id: 'User ID'
+      }
+    },
+    prompt: {
+      models: '对于 Coze 而言，模型名称即 Bot ID，你可以添加一个前缀 `bot-`，例如：`bot-123456`',
+      config: {
+        user_id: '生成该密钥的用户 ID'
+      }
+    },
+    modelGroup: 'Coze'
+  }
 };
 
 export { defaultConfig, typeConfig };

web/berry/src/views/Profile/index.js

@@ -21,7 +21,7 @@ import { IconBrandWechat, IconBrandGithub, IconMail } from '@tabler/icons-react'
 import Label from 'ui-component/Label';
 import { API } from 'utils/api';
 import { showError, showSuccess } from 'utils/common';
-import { onGitHubOAuthClicked, onLarkOAuthClicked } from 'utils/common';
+import { onGitHubOAuthClicked, onLarkOAuthClicked, copy } from 'utils/common';
 import * as Yup from 'yup';
 import WechatModal from 'views/Authentication/AuthForms/WechatModal';
 import { useSelector } from 'react-redux';
@@ -90,8 +90,7 @@ export default function Profile() {
     const { success, message, data } = res.data;
     if (success) {
       setInputs((inputs) => ({ ...inputs, access_token: data }));
-      navigator.clipboard.writeText(data);
-      showSuccess(`令牌已重置并已复制到剪贴板`);
+      copy(data, '访问令牌');
     } else {
       showError(message);
     }

web/berry/src/views/Redemption/component/TableRow.js

@@ -18,7 +18,7 @@ import {
 
 import Label from 'ui-component/Label';
 import TableSwitch from 'ui-component/Switch';
-import { timestamp2string, renderQuota, showSuccess } from 'utils/common';
+import { timestamp2string, renderQuota, copy } from 'utils/common';
 
 import { IconDotsVertical, IconEdit, IconTrash } from '@tabler/icons-react';
 
@@ -83,8 +83,7 @@ export default function RedemptionTableRow({ item, manageRedemption, handleOpenM
               variant="contained"
               color="primary"
               onClick={() => {
-                navigator.clipboard.writeText(item.key);
-                showSuccess('已复制到剪贴板！');
+                copy(item.key, '兑换码');
               }}
             >
               复制

web/berry/src/views/Token/component/TableRow.js

@@ -20,7 +20,7 @@ import {
 } from '@mui/material';
 
 import TableSwitch from 'ui-component/Switch';
-import { renderQuota, showSuccess, timestamp2string } from 'utils/common';
+import { renderQuota, timestamp2string, copy } from 'utils/common';
 
 import { IconDotsVertical, IconEdit, IconTrash, IconCaretDownFilled } from '@tabler/icons-react';
 
@@ -141,8 +141,7 @@ export default function TokensTableRow({ item, manageToken, handleOpenModal, set
     if (type === 'link') {
       window.open(text);
     } else {
-      navigator.clipboard.writeText(text);
-      showSuccess('已复制到剪贴板！');
+      copy(text);
     }
     handleCloseMenu();
   };
@@ -192,7 +191,7 @@ export default function TokensTableRow({ item, manageToken, handleOpenModal, set
               id={`switch-${item.id}`}
               checked={statusSwitch === 1}
               onChange={handleStatus}
-            // disabled={statusSwitch !== 1 && statusSwitch !== 2}
+              // disabled={statusSwitch !== 1 && statusSwitch !== 2}
             />
           </Tooltip>
         </TableCell>
@@ -211,8 +210,7 @@ export default function TokensTableRow({ item, manageToken, handleOpenModal, set
               <Button
                 color="primary"
                 onClick={() => {
-                  navigator.clipboard.writeText(`sk-${item.key}`);
-                  showSuccess('已复制到剪贴板！');
+                  copy(`sk-${item.key}`);
                 }}
               >
                 复制
@@ -222,7 +220,9 @@ export default function TokensTableRow({ item, manageToken, handleOpenModal, set
               </Button>
             </ButtonGroup>
             <ButtonGroup size="small" aria-label="split button">
-              <Button color="primary" onClick={(e) => handleCopy(COPY_OPTIONS[0], 'link')}>聊天</Button>
+              <Button color="primary" onClick={(e) => handleCopy(COPY_OPTIONS[0], 'link')}>
+                聊天
+              </Button>
               <Button size="small" onClick={(e) => handleOpenMenu(e, 'link')}>
                 <IconCaretDownFilled size={'16px'} />
               </Button>

web/berry/src/views/Topup/component/InviteCard.js

@@ -4,7 +4,7 @@ import SubCard from 'ui-component/cards/SubCard';
 import inviteImage from 'assets/images/invite/cwok_casual_19.webp';
 import { useState } from 'react';
 import { API } from 'utils/api';
-import { showError, showSuccess } from 'utils/common';
+import { showError, copy } from 'utils/common';
 
 const InviteCard = () => {
   const theme = useTheme();
@@ -12,8 +12,7 @@ const InviteCard = () => {
 
   const handleInviteUrl = async () => {
     if (inviteUl) {
-      navigator.clipboard.writeText(inviteUl);
-      showSuccess(`邀请链接已复制到剪切板`);
+      copy(inviteUl, '邀请链接');
       return;
     }
     const res = await API.get('/api/user/aff');
@@ -21,8 +20,7 @@ const InviteCard = () => {
     if (success) {
       let link = `${window.location.origin}/register?aff=${data}`;
       setInviteUrl(link);
-      navigator.clipboard.writeText(link);
-      showSuccess(`邀请链接已复制到剪切板`);
+      copy(link, '邀请链接');
     } else {
       showError(message);
     }

web/default/public/index.html

@@ -1,5 +1,5 @@
 <!DOCTYPE html>
-<html lang="en">
+<html lang="zh-CN">
   <head>
     <meta charset="utf-8" />
     <link rel="icon" href="logo.png" />

web/default/src/constants/channel.constants.js

@@ -6,6 +6,7 @@ export const CHANNEL_OPTIONS = [
     {key: 11, text: 'Google PaLM2', value: 11, color: 'orange'},
     {key: 24, text: 'Google Gemini', value: 24, color: 'orange'},
     {key: 28, text: 'Mistral AI', value: 28, color: 'orange'},
+    {key: 40, text: '字节跳动豆包', value: 40, color: 'blue'},
     {key: 15, text: '百度文心千帆', value: 15, color: 'blue'},
     {key: 17, text: '阿里通义千问', value: 17, color: 'orange'},
     {key: 18, text: '讯飞星火认知', value: 18, color: 'blue'},

web/default/src/pages/Channel/EditChannel.js

@@ -181,9 +181,6 @@ const EditChannel = () => {
     if (localInputs.type === 3 && localInputs.other === '') {
       localInputs.other = '2024-03-01-preview';
     }
-    if (localInputs.type === 18 && localInputs.other === '') {
-      localInputs.other = 'v2.1';
-    }
     let res;
     localInputs.models = localInputs.models.join(',');
     localInputs.group = localInputs.groups.join(',');
@@ -362,6 +359,13 @@ const EditChannel = () => {
               </Message>
             )
           }
+          {
+            inputs.type === 40 && (
+              <Message>
+                对于豆包而言，需要手动去 <a target="_blank" href="https://console.volcengine.com/ark/region:ark+cn-beijing/endpoint">模型推理页面</a> 创建推理接入点，以接入点名称作为模型名称，例如：`ep-20240608051426-tkxvl`。
+              </Message>
+            )
+          }
           <Form.Field>
             <Form.Dropdown
               label='模型'