perf: lazy initialization for token encoders (close #566)

Co-authored-by: igophper <admin@jialilgu.cn>

README.md

@@ -59,6 +59,9 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型，开箱即用
 > **Warning**
 > 使用 Docker 拉取的最新镜像可能是 `alpha` 版本，如果追求稳定性请手动指定版本。
 
+> **Warning**
+> 使用 root 用户初次登录系统后，务必修改默认密码 `123456`！
+
 ## 功能
 1. 支持多种大模型：
    + [x] [OpenAI ChatGPT 系列模型](https://platform.openai.com/docs/guides/gpt/chat-completions-api)（支持 [Azure OpenAI API](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference)）
@@ -269,6 +272,12 @@ docker run --name chatgpt-web -d -p 3002:3002 -e OPENAI_API_BASE_URL=https://ope
 
 注意，具体的 API Base 的格式取决于你所使用的客户端。
 
+例如对于 OpenAI 的官方库：
+```bash
+OPENAI_API_KEY="sk-xxxxxx"
+OPENAI_API_BASE="https://<HOST>:<PORT>/v1" 
+```
+
 ```mermaid
 graph LR
     A(用户)
@@ -303,22 +312,24 @@ graph LR
      + `SQL_CONN_MAX_LIFETIME`：连接的最大生命周期，默认为 `60`，单位分钟。
 4. `FRONTEND_BASE_URL`：设置之后将重定向页面请求到指定的地址，仅限从服务器设置。
    + 例子：`FRONTEND_BASE_URL=https://openai.justsong.cn`
-5. `SYNC_FREQUENCY`：设置之后将定期与数据库同步配置，单位为秒，未设置则不进行同步。
+5. `MEMORY_CACHE_ENABLED`：启用内存缓存，会导致用户额度的更新存在一定的延迟，可选值为 `true` 和 `false`，未设置则默认为 `false`。
+   + 例子：`MEMORY_CACHE_ENABLED=true`
+6. `SYNC_FREQUENCY`：在启用缓存的情况下与数据库同步配置的频率，单位为秒，默认为 `600` 秒。
    + 例子：`SYNC_FREQUENCY=60`
-6. `NODE_TYPE`：设置之后将指定节点类型，可选值为 `master` 和 `slave`，未设置则默认为 `master`。
+7. `NODE_TYPE`：设置之后将指定节点类型，可选值为 `master` 和 `slave`，未设置则默认为 `master`。
    + 例子：`NODE_TYPE=slave`
-7. `CHANNEL_UPDATE_FREQUENCY`：设置之后将定期更新渠道余额，单位为分钟，未设置则不进行更新。
+8. `CHANNEL_UPDATE_FREQUENCY`：设置之后将定期更新渠道余额，单位为分钟，未设置则不进行更新。
    + 例子：`CHANNEL_UPDATE_FREQUENCY=1440`
-8. `CHANNEL_TEST_FREQUENCY`：设置之后将定期检查渠道，单位为分钟，未设置则不进行检查。
+9. `CHANNEL_TEST_FREQUENCY`：设置之后将定期检查渠道，单位为分钟，未设置则不进行检查。
    + 例子：`CHANNEL_TEST_FREQUENCY=1440`
-9. `POLLING_INTERVAL`：批量更新渠道余额以及测试可用性时的请求间隔，单位为秒，默认无间隔。
-   + 例子：`POLLING_INTERVAL=5`
-10. `BATCH_UPDATE_ENABLED`：启用数据库批量更新聚合，会导致用户额度的更新存在一定的延迟可选值为 `true` 和 `false`，未设置则默认为 `false`。
+10. `POLLING_INTERVAL`：批量更新渠道余额以及测试可用性时的请求间隔，单位为秒，默认无间隔。
+    + 例子：`POLLING_INTERVAL=5`
+11. `BATCH_UPDATE_ENABLED`：启用数据库批量更新聚合，会导致用户额度的更新存在一定的延迟可选值为 `true` 和 `false`，未设置则默认为 `false`。
     + 例子：`BATCH_UPDATE_ENABLED=true`
     + 如果你遇到了数据库连接数过多的问题，可以尝试启用该选项。
-11. `BATCH_UPDATE_INTERVAL=5`：批量更新聚合的时间间隔，单位为秒，默认为 `5`。
+12. `BATCH_UPDATE_INTERVAL=5`：批量更新聚合的时间间隔，单位为秒，默认为 `5`。
     + 例子：`BATCH_UPDATE_INTERVAL=5`
-12. 请求频率限制：
+13. 请求频率限制：
     + `GLOBAL_API_RATE_LIMIT`：全局 API 速率限制（除中继请求外），单 ip 三分钟内的最大请求数，默认为 `180`。
     + `GLOBAL_WEB_RATE_LIMIT`：全局 Web 速率限制，单 ip 三分钟内的最大请求数，默认为 `60`。
 

common/constants.go

@@ -56,6 +56,7 @@ var EmailDomainWhitelist = []string{
 }
 
 var DebugEnabled = os.Getenv("DEBUG") == "true"
+var MemoryCacheEnabled = os.Getenv("MEMORY_CACHE_ENABLED") == "true"
 
 var LogConsumeEnabled = true
 
@@ -92,7 +93,7 @@ var IsMasterNode = os.Getenv("NODE_TYPE") != "slave"
 var requestInterval, _ = strconv.Atoi(os.Getenv("POLLING_INTERVAL"))
 var RequestInterval = time.Duration(requestInterval) * time.Second
 
-var SyncFrequency = 10 * 60 // unit is second, will be overwritten by SYNC_FREQUENCY
+var SyncFrequency = GetOrDefault("SYNC_FREQUENCY", 10*60) // unit is second
 
 var BatchUpdateEnabled = false
 var BatchUpdateInterval = GetOrDefault("BATCH_UPDATE_INTERVAL", 5)

common/model-ratio.go

@@ -24,6 +24,7 @@ var ModelRatio = map[string]float64{
 	"gpt-3.5-turbo-0613":        0.75,
 	"gpt-3.5-turbo-16k":         1.5, // $0.003 / 1K tokens
 	"gpt-3.5-turbo-16k-0613":    1.5,
+	"gpt-3.5-turbo-instruct":    0.75, // $0.0015 / 1K tokens
 	"text-ada-001":              0.2,
 	"text-babbage-001":          0.25,
 	"text-curie-001":            1,
@@ -50,8 +51,8 @@ var ModelRatio = map[string]float64{
 	"chatglm_pro":               0.7143, // ￥0.01 / 1k tokens
 	"chatglm_std":               0.3572, // ￥0.005 / 1k tokens
 	"chatglm_lite":              0.1429, // ￥0.002 / 1k tokens
-	"qwen-v1":                   0.8572, // ￥0.012 / 1k tokens
-	"qwen-plus-v1":              1,      // ￥0.014 / 1k tokens
+	"qwen-turbo":                0.8572, // ￥0.012 / 1k tokens
+	"qwen-plus":                 10,     // ￥0.14 / 1k tokens
 	"text-embedding-v1":         0.05,   // ￥0.0007 / 1k tokens
 	"SparkDesk":                 1.2858, // ￥0.018 / 1k tokens
 	"360GPT_S2_V9":              0.8572, // ¥0.012 / 1k tokens

controller/channel-billing.go

@@ -111,7 +111,7 @@ func GetResponseBody(method, url string, channel *model.Channel, headers http.He
 }
 
 func updateChannelCloseAIBalance(channel *model.Channel) (float64, error) {
-	url := fmt.Sprintf("%s/dashboard/billing/credit_grants", channel.BaseURL)
+	url := fmt.Sprintf("%s/dashboard/billing/credit_grants", channel.GetBaseURL())
 	body, err := GetResponseBody("GET", url, channel, GetAuthHeader(channel.Key))
 
 	if err != nil {
@@ -201,18 +201,18 @@ func updateChannelAIGC2DBalance(channel *model.Channel) (float64, error) {
 
 func updateChannelBalance(channel *model.Channel) (float64, error) {
 	baseURL := common.ChannelBaseURLs[channel.Type]
-	if channel.BaseURL == "" {
-		channel.BaseURL = baseURL
+	if channel.GetBaseURL() == "" {
+		channel.BaseURL = &baseURL
 	}
 	switch channel.Type {
 	case common.ChannelTypeOpenAI:
-		if channel.BaseURL != "" {
-			baseURL = channel.BaseURL
+		if channel.GetBaseURL() != "" {
+			baseURL = channel.GetBaseURL()
 		}
 	case common.ChannelTypeAzure:
 		return 0, errors.New("尚未实现")
 	case common.ChannelTypeCustom:
-		baseURL = channel.BaseURL
+		baseURL = channel.GetBaseURL()
 	case common.ChannelTypeCloseAI:
 		return updateChannelCloseAIBalance(channel)
 	case common.ChannelTypeOpenAISB:

controller/channel-test.go

@@ -42,10 +42,10 @@ func testChannel(channel *model.Channel, request ChatRequest) (err error, openai
 	}
 	requestURL := common.ChannelBaseURLs[channel.Type]
 	if channel.Type == common.ChannelTypeAzure {
-		requestURL = fmt.Sprintf("%s/openai/deployments/%s/chat/completions?api-version=2023-03-15-preview", channel.BaseURL, request.Model)
+		requestURL = fmt.Sprintf("%s/openai/deployments/%s/chat/completions?api-version=2023-03-15-preview", channel.GetBaseURL(), request.Model)
 	} else {
-		if channel.BaseURL != "" {
-			requestURL = channel.BaseURL
+		if channel.GetBaseURL() != "" {
+			requestURL = channel.GetBaseURL()
 		}
 		requestURL += "/v1/chat/completions"
 	}

controller/log.go

@@ -2,6 +2,7 @@ package controller
 
 import (
 	"github.com/gin-gonic/gin"
+	"net/http"
 	"one-api/common"
 	"one-api/model"
 	"strconv"
@@ -18,19 +19,21 @@ func GetAllLogs(c *gin.Context) {
 	username := c.Query("username")
 	tokenName := c.Query("token_name")
 	modelName := c.Query("model_name")
-	logs, err := model.GetAllLogs(logType, startTimestamp, endTimestamp, modelName, username, tokenName, p*common.ItemsPerPage, common.ItemsPerPage)
+	channel, _ := strconv.Atoi(c.Query("channel"))
+	logs, err := model.GetAllLogs(logType, startTimestamp, endTimestamp, modelName, username, tokenName, p*common.ItemsPerPage, common.ItemsPerPage, channel)
 	if err != nil {
-		c.JSON(200, gin.H{
+		c.JSON(http.StatusOK, gin.H{
 			"success": false,
 			"message": err.Error(),
 		})
 		return
 	}
-	c.JSON(200, gin.H{
+	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
 		"data":    logs,
 	})
+	return
 }
 
 func GetUserLogs(c *gin.Context) {
@@ -46,34 +49,36 @@ func GetUserLogs(c *gin.Context) {
 	modelName := c.Query("model_name")
 	logs, err := model.GetUserLogs(userId, logType, startTimestamp, endTimestamp, modelName, tokenName, p*common.ItemsPerPage, common.ItemsPerPage)
 	if err != nil {
-		c.JSON(200, gin.H{
+		c.JSON(http.StatusOK, gin.H{
 			"success": false,
 			"message": err.Error(),
 		})
 		return
 	}
-	c.JSON(200, gin.H{
+	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
 		"data":    logs,
 	})
+	return
 }
 
 func SearchAllLogs(c *gin.Context) {
 	keyword := c.Query("keyword")
 	logs, err := model.SearchAllLogs(keyword)
 	if err != nil {
-		c.JSON(200, gin.H{
+		c.JSON(http.StatusOK, gin.H{
 			"success": false,
 			"message": err.Error(),
 		})
 		return
 	}
-	c.JSON(200, gin.H{
+	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
 		"data":    logs,
 	})
+	return
 }
 
 func SearchUserLogs(c *gin.Context) {
@@ -81,17 +86,18 @@ func SearchUserLogs(c *gin.Context) {
 	userId := c.GetInt("id")
 	logs, err := model.SearchUserLogs(userId, keyword)
 	if err != nil {
-		c.JSON(200, gin.H{
+		c.JSON(http.StatusOK, gin.H{
 			"success": false,
 			"message": err.Error(),
 		})
 		return
 	}
-	c.JSON(200, gin.H{
+	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
 		"data":    logs,
 	})
+	return
 }
 
 func GetLogsStat(c *gin.Context) {
@@ -101,9 +107,10 @@ func GetLogsStat(c *gin.Context) {
 	tokenName := c.Query("token_name")
 	username := c.Query("username")
 	modelName := c.Query("model_name")
-	quotaNum := model.SumUsedQuota(logType, startTimestamp, endTimestamp, modelName, username, tokenName)
+	channel, _ := strconv.Atoi(c.Query("channel"))
+	quotaNum := model.SumUsedQuota(logType, startTimestamp, endTimestamp, modelName, username, tokenName, channel)
 	//tokenNum := model.SumUsedToken(logType, startTimestamp, endTimestamp, modelName, username, "")
-	c.JSON(200, gin.H{
+	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
 		"data": gin.H{
@@ -111,6 +118,7 @@ func GetLogsStat(c *gin.Context) {
 			//"token": tokenNum,
 		},
 	})
+	return
 }
 
 func GetLogsSelfStat(c *gin.Context) {
@@ -120,9 +128,10 @@ func GetLogsSelfStat(c *gin.Context) {
 	endTimestamp, _ := strconv.ParseInt(c.Query("end_timestamp"), 10, 64)
 	tokenName := c.Query("token_name")
 	modelName := c.Query("model_name")
-	quotaNum := model.SumUsedQuota(logType, startTimestamp, endTimestamp, modelName, username, tokenName)
+	channel, _ := strconv.Atoi(c.Query("channel"))
+	quotaNum := model.SumUsedQuota(logType, startTimestamp, endTimestamp, modelName, username, tokenName, channel)
 	//tokenNum := model.SumUsedToken(logType, startTimestamp, endTimestamp, modelName, username, tokenName)
-	c.JSON(200, gin.H{
+	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
 		"data": gin.H{
@@ -130,4 +139,30 @@ func GetLogsSelfStat(c *gin.Context) {
 			//"token": tokenNum,
 		},
 	})
+	return
+}
+
+func DeleteHistoryLogs(c *gin.Context) {
+	targetTimestamp, _ := strconv.ParseInt(c.Query("target_timestamp"), 10, 64)
+	if targetTimestamp == 0 {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "target timestamp is required",
+		})
+		return
+	}
+	count, err := model.DeleteOldLog(targetTimestamp)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data":    count,
+	})
+	return
 }

controller/model.go

@@ -117,6 +117,15 @@ func init() {
 			Root:       "gpt-3.5-turbo-16k-0613",
 			Parent:     nil,
 		},
+		{
+			Id:         "gpt-3.5-turbo-instruct",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "openai",
+			Permission: permission,
+			Root:       "gpt-3.5-turbo-instruct",
+			Parent:     nil,
+		},
 		{
 			Id:         "gpt-4",
 			Object:     "model",
@@ -343,21 +352,21 @@ func init() {
 			Parent:     nil,
 		},
 		{
-			Id:         "qwen-v1",
+			Id:         "qwen-turbo",
 			Object:     "model",
 			Created:    1677649963,
 			OwnedBy:    "ali",
 			Permission: permission,
-			Root:       "qwen-v1",
+			Root:       "qwen-turbo",
 			Parent:     nil,
 		},
 		{
-			Id:         "qwen-plus-v1",
+			Id:         "qwen-plus",
 			Object:     "model",
 			Created:    1677649963,
 			OwnedBy:    "ali",
 			Permission: permission,
-			Root:       "qwen-plus-v1",
+			Root:       "qwen-plus",
 			Parent:     nil,
 		},
 		{

controller/relay-audio.go

@@ -18,6 +18,7 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 
 	tokenId := c.GetInt("token_id")
 	channelType := c.GetInt("channel")
+	channelId := c.GetInt("channel_id")
 	userId := c.GetInt("id")
 	group := c.GetString("group")
 
@@ -107,7 +108,7 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 			if quota != 0 {
 				tokenName := c.GetString("token_name")
 				logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
-				model.RecordConsumeLog(ctx, userId, 0, 0, audioModel, tokenName, quota, logContent)
+				model.RecordConsumeLog(ctx, userId, channelId, 0, 0, audioModel, tokenName, quota, logContent)
 				model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
 				channelId := c.GetInt("channel_id")
 				model.UpdateChannelUsedQuota(channelId, quota)

controller/relay-image.go

@@ -19,6 +19,7 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 
 	tokenId := c.GetInt("token_id")
 	channelType := c.GetInt("channel")
+	channelId := c.GetInt("channel_id")
 	userId := c.GetInt("id")
 	consumeQuota := c.GetBool("consume_quota")
 	group := c.GetString("group")
@@ -138,7 +139,7 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 			if quota != 0 {
 				tokenName := c.GetString("token_name")
 				logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
-				model.RecordConsumeLog(ctx, userId, 0, 0, imageModel, tokenName, quota, logContent)
+				model.RecordConsumeLog(ctx, userId, channelId, 0, 0, imageModel, tokenName, quota, logContent)
 				model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
 				channelId := c.GetInt("channel_id")
 				model.UpdateChannelUsedQuota(channelId, quota)

controller/relay-text.go

@@ -38,6 +38,7 @@ func init() {
 
 func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 	channelType := c.GetInt("channel")
+	channelId := c.GetInt("channel_id")
 	tokenId := c.GetInt("token_id")
 	userId := c.GetInt("id")
 	consumeQuota := c.GetBool("consume_quota")
@@ -364,7 +365,6 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 
 	var textResponse TextResponse
 	tokenName := c.GetString("token_name")
-	channelId := c.GetInt("channel_id")
 
 	defer func(ctx context.Context) {
 		// c.Writer.Flush()
@@ -397,7 +397,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 				}
 				if quota != 0 {
 					logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
-					model.RecordConsumeLog(ctx, userId, promptTokens, completionTokens, textRequest.Model, tokenName, quota, logContent)
+					model.RecordConsumeLog(ctx, userId, channelId, promptTokens, completionTokens, textRequest.Model, tokenName, quota, logContent)
 					model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
 					model.UpdateChannelUsedQuota(channelId, quota)
 				}
@@ -541,24 +541,26 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			return nil
 		}
 	case APITypeXunfei:
-		if isStream {
-			auth := c.Request.Header.Get("Authorization")
-			auth = strings.TrimPrefix(auth, "Bearer ")
-			splits := strings.Split(auth, "|")
-			if len(splits) != 3 {
-				return errorWrapper(errors.New("invalid auth"), "invalid_auth", http.StatusBadRequest)
-			}
-			err, usage := xunfeiStreamHandler(c, textRequest, splits[0], splits[1], splits[2])
-			if err != nil {
-				return err
-			}
-			if usage != nil {
-				textResponse.Usage = *usage
-			}
-			return nil
-		} else {
-			return errorWrapper(errors.New("xunfei api does not support non-stream mode"), "invalid_api_type", http.StatusBadRequest)
+		auth := c.Request.Header.Get("Authorization")
+		auth = strings.TrimPrefix(auth, "Bearer ")
+		splits := strings.Split(auth, "|")
+		if len(splits) != 3 {
+			return errorWrapper(errors.New("invalid auth"), "invalid_auth", http.StatusBadRequest)
 		}
+		var err *OpenAIErrorWithStatusCode
+		var usage *Usage
+		if isStream {
+			err, usage = xunfeiStreamHandler(c, textRequest, splits[0], splits[1], splits[2])
+		} else {
+			err, usage = xunfeiHandler(c, textRequest, splits[0], splits[1], splits[2])
+		}
+		if err != nil {
+			return err
+		}
+		if usage != nil {
+			textResponse.Usage = *usage
+		}
+		return nil
 	case APITypeAIProxyLibrary:
 		if isStream {
 			err, usage := aiProxyLibraryStreamHandler(c, resp)

controller/relay-utils.go

@@ -9,44 +9,53 @@ import (
 	"net/http"
 	"one-api/common"
 	"strconv"
+	"strings"
 )
 
 var stopFinishReason = "stop"
 
+// tokenEncoderMap won't grow after initialization
 var tokenEncoderMap = map[string]*tiktoken.Tiktoken{}
+var defaultTokenEncoder *tiktoken.Tiktoken
 
 func InitTokenEncoders() {
 	common.SysLog("initializing token encoders")
-	fallbackTokenEncoder, err := tiktoken.EncodingForModel("gpt-3.5-turbo")
+	gpt35TokenEncoder, err := tiktoken.EncodingForModel("gpt-3.5-turbo")
 	if err != nil {
-		common.FatalLog(fmt.Sprintf("failed to get fallback token encoder: %s", err.Error()))
+		common.FatalLog(fmt.Sprintf("failed to get gpt-3.5-turbo token encoder: %s", err.Error()))
+	}
+	defaultTokenEncoder = gpt35TokenEncoder
+	gpt4TokenEncoder, err := tiktoken.EncodingForModel("gpt-4")
+	if err != nil {
+		common.FatalLog(fmt.Sprintf("failed to get gpt-4 token encoder: %s", err.Error()))
 	}
 	for model, _ := range common.ModelRatio {
-		tokenEncoder, err := tiktoken.EncodingForModel(model)
-		if err != nil {
-			common.SysError(fmt.Sprintf("using fallback encoder for model %s", model))
-			tokenEncoderMap[model] = fallbackTokenEncoder
-			continue
+		if strings.HasPrefix(model, "gpt-3.5") {
+			tokenEncoderMap[model] = gpt35TokenEncoder
+		} else if strings.HasPrefix(model, "gpt-4") {
+			tokenEncoderMap[model] = gpt4TokenEncoder
+		} else {
+			tokenEncoderMap[model] = nil
 		}
-		tokenEncoderMap[model] = tokenEncoder
 	}
 	common.SysLog("token encoders initialized")
 }
 
 func getTokenEncoder(model string) *tiktoken.Tiktoken {
-	if tokenEncoder, ok := tokenEncoderMap[model]; ok {
+	tokenEncoder, ok := tokenEncoderMap[model]
+	if ok && tokenEncoder != nil {
 		return tokenEncoder
 	}
-	tokenEncoder, err := tiktoken.EncodingForModel(model)
-	if err != nil {
-		common.SysError(fmt.Sprintf("failed to get token encoder for model %s: %s, using encoder for gpt-3.5-turbo", model, err.Error()))
-		tokenEncoder, err = tiktoken.EncodingForModel("gpt-3.5-turbo")
+	if ok {
+		tokenEncoder, err := tiktoken.EncodingForModel(model)
 		if err != nil {
-			common.FatalLog(fmt.Sprintf("failed to get token encoder for model gpt-3.5-turbo: %s", err.Error()))
+			common.SysError(fmt.Sprintf("failed to get token encoder for model %s: %s, using encoder for gpt-3.5-turbo", model, err.Error()))
+			tokenEncoder = defaultTokenEncoder
 		}
+		tokenEncoderMap[model] = tokenEncoder
+		return tokenEncoder
 	}
-	tokenEncoderMap[model] = tokenEncoder
-	return tokenEncoder
+	return defaultTokenEncoder
 }
 
 func getTokenNum(tokenEncoder *tiktoken.Tiktoken, text string) int {

controller/relay-xunfei.go

@@ -118,6 +118,7 @@ func responseXunfei2OpenAI(response *XunfeiChatResponse) *OpenAITextResponse {
 			Role:    "assistant",
 			Content: response.Payload.Choices.Text[0].Content,
 		},
+		FinishReason: stopFinishReason,
 	}
 	fullTextResponse := OpenAITextResponse{
 		Object:  "chat.completion",
@@ -177,33 +178,82 @@ func buildXunfeiAuthUrl(hostUrl string, apiKey, apiSecret string) string {
 }
 
 func xunfeiStreamHandler(c *gin.Context, textRequest GeneralOpenAIRequest, appId string, apiSecret string, apiKey string) (*OpenAIErrorWithStatusCode, *Usage) {
+	domain, authUrl := getXunfeiAuthUrl(c, apiKey, apiSecret)
+	dataChan, stopChan, err := xunfeiMakeRequest(textRequest, domain, authUrl, appId)
+	if err != nil {
+		return errorWrapper(err, "make xunfei request err", http.StatusInternalServerError), nil
+	}
+	setEventStreamHeaders(c)
 	var usage Usage
-	query := c.Request.URL.Query()
-	apiVersion := query.Get("api-version")
-	if apiVersion == "" {
-		apiVersion = c.GetString("api_version")
+	c.Stream(func(w io.Writer) bool {
+		select {
+		case xunfeiResponse := <-dataChan:
+			usage.PromptTokens += xunfeiResponse.Payload.Usage.Text.PromptTokens
+			usage.CompletionTokens += xunfeiResponse.Payload.Usage.Text.CompletionTokens
+			usage.TotalTokens += xunfeiResponse.Payload.Usage.Text.TotalTokens
+			response := streamResponseXunfei2OpenAI(&xunfeiResponse)
+			jsonResponse, err := json.Marshal(response)
+			if err != nil {
+				common.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
+		}
+	})
+	return nil, &usage
+}
+
+func xunfeiHandler(c *gin.Context, textRequest GeneralOpenAIRequest, appId string, apiSecret string, apiKey string) (*OpenAIErrorWithStatusCode, *Usage) {
+	domain, authUrl := getXunfeiAuthUrl(c, apiKey, apiSecret)
+	dataChan, stopChan, err := xunfeiMakeRequest(textRequest, domain, authUrl, appId)
+	if err != nil {
+		return errorWrapper(err, "make xunfei request err", http.StatusInternalServerError), nil
 	}
-	if apiVersion == "" {
-		apiVersion = "v1.1"
-		common.SysLog("api_version not found, use default: " + apiVersion)
+	var usage Usage
+	var content string
+	var xunfeiResponse XunfeiChatResponse
+	stop := false
+	for !stop {
+		select {
+		case xunfeiResponse = <-dataChan:
+			content += xunfeiResponse.Payload.Choices.Text[0].Content
+			usage.PromptTokens += xunfeiResponse.Payload.Usage.Text.PromptTokens
+			usage.CompletionTokens += xunfeiResponse.Payload.Usage.Text.CompletionTokens
+			usage.TotalTokens += xunfeiResponse.Payload.Usage.Text.TotalTokens
+		case stop = <-stopChan:
+		}
 	}
-	domain := "general"
-	if apiVersion == "v2.1" {
-		domain = "generalv2"
+
+	xunfeiResponse.Payload.Choices.Text[0].Content = content
+
+	response := responseXunfei2OpenAI(&xunfeiResponse)
+	jsonResponse, err := json.Marshal(response)
+	if err != nil {
+		return errorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
 	}
-	hostUrl := fmt.Sprintf("wss://spark-api.xf-yun.com/%s/chat", apiVersion)
+	c.Writer.Header().Set("Content-Type", "application/json")
+	_, _ = c.Writer.Write(jsonResponse)
+	return nil, &usage
+}
+
+func xunfeiMakeRequest(textRequest GeneralOpenAIRequest, domain, authUrl, appId string) (chan XunfeiChatResponse, chan bool, error) {
 	d := websocket.Dialer{
 		HandshakeTimeout: 5 * time.Second,
 	}
-	conn, resp, err := d.Dial(buildXunfeiAuthUrl(hostUrl, apiKey, apiSecret), nil)
+	conn, resp, err := d.Dial(authUrl, nil)
 	if err != nil || resp.StatusCode != 101 {
-		return errorWrapper(err, "dial_failed", http.StatusInternalServerError), nil
+		return nil, nil, err
 	}
 	data := requestOpenAI2Xunfei(textRequest, appId, domain)
 	err = conn.WriteJSON(data)
 	if err != nil {
-		return errorWrapper(err, "write_json_failed", http.StatusInternalServerError), nil
+		return nil, nil, err
 	}
+
 	dataChan := make(chan XunfeiChatResponse)
 	stopChan := make(chan bool)
 	go func() {
@@ -230,61 +280,24 @@ func xunfeiStreamHandler(c *gin.Context, textRequest GeneralOpenAIRequest, appId
 		}
 		stopChan <- true
 	}()
-	setEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case xunfeiResponse := <-dataChan:
-			usage.PromptTokens += xunfeiResponse.Payload.Usage.Text.PromptTokens
-			usage.CompletionTokens += xunfeiResponse.Payload.Usage.Text.CompletionTokens
-			usage.TotalTokens += xunfeiResponse.Payload.Usage.Text.TotalTokens
-			response := streamResponseXunfei2OpenAI(&xunfeiResponse)
-			jsonResponse, err := json.Marshal(response)
-			if err != nil {
-				common.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
-		}
-	})
-	return nil, &usage
+
+	return dataChan, stopChan, nil
 }
 
-func xunfeiHandler(c *gin.Context, resp *http.Response) (*OpenAIErrorWithStatusCode, *Usage) {
-	var xunfeiResponse XunfeiChatResponse
-	responseBody, err := io.ReadAll(resp.Body)
-	if err != nil {
-		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+func getXunfeiAuthUrl(c *gin.Context, apiKey string, apiSecret string) (string, string) {
+	query := c.Request.URL.Query()
+	apiVersion := query.Get("api-version")
+	if apiVersion == "" {
+		apiVersion = c.GetString("api_version")
 	}
-	err = resp.Body.Close()
-	if err != nil {
-		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	if apiVersion == "" {
+		apiVersion = "v1.1"
+		common.SysLog("api_version not found, use default: " + apiVersion)
 	}
-	err = json.Unmarshal(responseBody, &xunfeiResponse)
-	if err != nil {
-		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	domain := "general"
+	if apiVersion == "v2.1" {
+		domain = "generalv2"
 	}
-	if xunfeiResponse.Header.Code != 0 {
-		return &OpenAIErrorWithStatusCode{
-			OpenAIError: OpenAIError{
-				Message: xunfeiResponse.Header.Message,
-				Type:    "xunfei_error",
-				Param:   "",
-				Code:    xunfeiResponse.Header.Code,
-			},
-			StatusCode: resp.StatusCode,
-		}, nil
-	}
-	fullTextResponse := responseXunfei2OpenAI(&xunfeiResponse)
-	jsonResponse, err := json.Marshal(fullTextResponse)
-	if err != nil {
-		return 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
+	authUrl := buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/%s/chat", apiVersion), apiKey, apiSecret)
+	return domain, authUrl
 }

main.go

@@ -2,6 +2,7 @@ package main
 
 import (
 	"embed"
+	"fmt"
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-contrib/sessions/cookie"
 	"github.com/gin-gonic/gin"
@@ -50,18 +51,17 @@ func main() {
 	// Initialize options
 	model.InitOptionMap()
 	if common.RedisEnabled {
+		// for compatibility with old versions
+		common.MemoryCacheEnabled = true
+	}
+	if common.MemoryCacheEnabled {
+		common.SysLog("memory cache enabled")
+		common.SysError(fmt.Sprintf("sync frequency: %d seconds", common.SyncFrequency))
 		model.InitChannelCache()
 	}
-	if os.Getenv("SYNC_FREQUENCY") != "" {
-		frequency, err := strconv.Atoi(os.Getenv("SYNC_FREQUENCY"))
-		if err != nil {
-			common.FatalLog("failed to parse SYNC_FREQUENCY: " + err.Error())
-		}
-		common.SyncFrequency = frequency
-		go model.SyncOptions(frequency)
-		if common.RedisEnabled {
-			go model.SyncChannelCache(frequency)
-		}
+	if common.MemoryCacheEnabled {
+		go model.SyncOptions(common.SyncFrequency)
+		go model.SyncChannelCache(common.SyncFrequency)
 	}
 	if os.Getenv("CHANNEL_UPDATE_FREQUENCY") != "" {
 		frequency, err := strconv.Atoi(os.Getenv("CHANNEL_UPDATE_FREQUENCY"))

middleware/auth.go

@@ -94,7 +94,7 @@ func TokenAuth() func(c *gin.Context) {
 			abortWithMessage(c, http.StatusUnauthorized, err.Error())
 			return
 		}
-		userEnabled, err := model.IsUserEnabled(token.UserId)
+		userEnabled, err := model.CacheIsUserEnabled(token.UserId)
 		if err != nil {
 			abortWithMessage(c, http.StatusInternalServerError, err.Error())
 			return

middleware/distributor.go

@@ -82,9 +82,9 @@ func Distribute() func(c *gin.Context) {
 		c.Set("channel", channel.Type)
 		c.Set("channel_id", channel.Id)
 		c.Set("channel_name", channel.Name)
-		c.Set("model_mapping", channel.ModelMapping)
+		c.Set("model_mapping", channel.GetModelMapping())
 		c.Request.Header.Set("Authorization", fmt.Sprintf("Bearer %s", channel.Key))
-		c.Set("base_url", channel.BaseURL)
+		c.Set("base_url", channel.GetBaseURL())
 		switch channel.Type {
 		case common.ChannelTypeAzure:
 			c.Set("api_version", channel.Other)

model/ability.go

@@ -10,15 +10,18 @@ type Ability struct {
 	Model     string `json:"model" gorm:"primaryKey;autoIncrement:false"`
 	ChannelId int    `json:"channel_id" gorm:"primaryKey;autoIncrement:false;index"`
 	Enabled   bool   `json:"enabled"`
+	Priority  *int64 `json:"priority" gorm:"bigint;default:0;index"`
 }
 
 func GetRandomSatisfiedChannel(group string, model string) (*Channel, error) {
 	ability := Ability{}
 	var err error = nil
+	maxPrioritySubQuery := DB.Model(&Ability{}).Select("MAX(priority)").Where("`group` = ? and model = ? and enabled = 1", group, model)
+	channelQuery := DB.Where("`group` = ? and model = ? and enabled = 1 and priority = (?)", group, model, maxPrioritySubQuery)
 	if common.UsingSQLite {
-		err = DB.Where("`group` = ? and model = ? and enabled = 1", group, model).Order("RANDOM()").Limit(1).First(&ability).Error
+		err = channelQuery.Order("RANDOM()").First(&ability).Error
 	} else {
-		err = DB.Where("`group` = ? and model = ? and enabled = 1", group, model).Order("RAND()").Limit(1).First(&ability).Error
+		err = channelQuery.Order("RAND()").First(&ability).Error
 	}
 	if err != nil {
 		return nil, err
@@ -40,6 +43,7 @@ func (channel *Channel) AddAbilities() error {
 				Model:     model,
 				ChannelId: channel.Id,
 				Enabled:   channel.Status == common.ChannelStatusEnabled,
+				Priority:  channel.Priority,
 			}
 			abilities = append(abilities, ability)
 		}

model/cache.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"math/rand"
 	"one-api/common"
+	"sort"
 	"strconv"
 	"strings"
 	"sync"
@@ -159,6 +160,17 @@ func InitChannelCache() {
 			}
 		}
 	}
+
+	// sort by priority
+	for group, model2channels := range newGroup2model2channels {
+		for model, channels := range model2channels {
+			sort.Slice(channels, func(i, j int) bool {
+				return channels[i].GetPriority() > channels[j].GetPriority()
+			})
+			newGroup2model2channels[group][model] = channels
+		}
+	}
+
 	channelSyncLock.Lock()
 	group2model2channels = newGroup2model2channels
 	channelSyncLock.Unlock()
@@ -174,7 +186,7 @@ func SyncChannelCache(frequency int) {
 }
 
 func CacheGetRandomSatisfiedChannel(group string, model string) (*Channel, error) {
-	if !common.RedisEnabled {
+	if !common.MemoryCacheEnabled {
 		return GetRandomSatisfiedChannel(group, model)
 	}
 	channelSyncLock.RLock()
@@ -183,6 +195,17 @@ func CacheGetRandomSatisfiedChannel(group string, model string) (*Channel, error
 	if len(channels) == 0 {
 		return nil, errors.New("channel not found")
 	}
-	idx := rand.Intn(len(channels))
+	endIdx := len(channels)
+	// choose by priority
+	firstChannel := channels[0]
+	if firstChannel.GetPriority() > 0 {
+		for i := range channels {
+			if channels[i].GetPriority() != firstChannel.GetPriority() {
+				endIdx = i
+				break
+			}
+		}
+	}
+	idx := rand.Intn(endIdx)
 	return channels[idx], nil
 }

model/channel.go

@@ -15,14 +15,15 @@ type Channel struct {
 	CreatedTime        int64   `json:"created_time" gorm:"bigint"`
 	TestTime           int64   `json:"test_time" gorm:"bigint"`
 	ResponseTime       int     `json:"response_time"` // in milliseconds
-	BaseURL            string  `json:"base_url" gorm:"column:base_url"`
+	BaseURL            *string `json:"base_url" gorm:"column:base_url;default:''"`
 	Other              string  `json:"other"`
 	Balance            float64 `json:"balance"` // in USD
 	BalanceUpdatedTime int64   `json:"balance_updated_time" gorm:"bigint"`
 	Models             string  `json:"models"`
 	Group              string  `json:"group" gorm:"type:varchar(32);default:'default'"`
 	UsedQuota          int64   `json:"used_quota" gorm:"bigint;default:0"`
-	ModelMapping       string  `json:"model_mapping" gorm:"type:varchar(1024);default:''"`
+	ModelMapping       *string `json:"model_mapping" gorm:"type:varchar(1024);default:''"`
+	Priority           *int64  `json:"priority" gorm:"bigint;default:0"`
 }
 
 func GetAllChannels(startIdx int, num int, selectAll bool) ([]*Channel, error) {
@@ -78,6 +79,27 @@ func BatchInsertChannels(channels []Channel) error {
 	return nil
 }
 
+func (channel *Channel) GetPriority() int64 {
+	if channel.Priority == nil {
+		return 0
+	}
+	return *channel.Priority
+}
+
+func (channel *Channel) GetBaseURL() string {
+	if channel.BaseURL == nil {
+		return ""
+	}
+	return *channel.BaseURL
+}
+
+func (channel *Channel) GetModelMapping() string {
+	if channel.ModelMapping == nil {
+		return ""
+	}
+	return *channel.ModelMapping
+}
+
 func (channel *Channel) Insert() error {
 	var err error
 	err = DB.Create(channel).Error

model/log.go

@@ -19,6 +19,7 @@ type Log struct {
 	Quota            int    `json:"quota" gorm:"default:0"`
 	PromptTokens     int    `json:"prompt_tokens" gorm:"default:0"`
 	CompletionTokens int    `json:"completion_tokens" gorm:"default:0"`
+	Channel          int    `json:"channel" gorm:"default:0"`
 }
 
 const (
@@ -46,8 +47,9 @@ func RecordLog(userId int, logType int, content string) {
 	}
 }
 
-func RecordConsumeLog(ctx context.Context, userId int, promptTokens int, completionTokens int, modelName string, tokenName string, quota int, content string) {
-	common.LogInfo(ctx, fmt.Sprintf("record consume log: userId=%d, promptTokens=%d, completionTokens=%d, modelName=%s, tokenName=%s, quota=%d, content=%s", userId, promptTokens, completionTokens, modelName, tokenName, quota, content))
+
+func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptTokens int, completionTokens int, modelName string, tokenName string, quota int, content string) {
+	common.LogInfo(ctx, fmt.Sprintf("record consume log: userId=%d, channelId=%d, promptTokens=%d, completionTokens=%d, modelName=%s, tokenName=%s, quota=%d, content=%s", userId, channelId, promptTokens, completionTokens, modelName, tokenName, quota, content))
 	if !common.LogConsumeEnabled {
 		return
 	}
@@ -62,6 +64,7 @@ func RecordConsumeLog(ctx context.Context, userId int, promptTokens int, complet
 		TokenName:        tokenName,
 		ModelName:        modelName,
 		Quota:            quota,
+		Channel:          channelId,
 	}
 	err := DB.Create(log).Error
 	if err != nil {
@@ -69,7 +72,7 @@ func RecordConsumeLog(ctx context.Context, userId int, promptTokens int, complet
 	}
 }
 
-func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string, startIdx int, num int) (logs []*Log, err error) {
+func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string, startIdx int, num int, channel int) (logs []*Log, err error) {
 	var tx *gorm.DB
 	if logType == LogTypeUnknown {
 		tx = DB
@@ -91,6 +94,9 @@ func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName
 	if endTimestamp != 0 {
 		tx = tx.Where("created_at <= ?", endTimestamp)
 	}
+	if channel != 0 {
+		tx = tx.Where("channel = ?", channel)
+	}
 	err = tx.Order("id desc").Limit(num).Offset(startIdx).Find(&logs).Error
 	return logs, err
 }
@@ -128,8 +134,8 @@ func SearchUserLogs(userId int, keyword string) (logs []*Log, err error) {
 	return logs, err
 }
 
-func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string) (quota int) {
-	tx := DB.Table("logs").Select("sum(quota)")
+func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string, channel int) (quota int) {
+	tx := DB.Table("logs").Select("ifnull(sum(quota),0)")
 	if username != "" {
 		tx = tx.Where("username = ?", username)
 	}
@@ -145,12 +151,15 @@ func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelNa
 	if modelName != "" {
 		tx = tx.Where("model_name = ?", modelName)
 	}
+	if channel != 0 {
+		tx = tx.Where("channel = ?", channel)
+	}
 	tx.Where("type = ?", LogTypeConsume).Scan(&quota)
 	return quota
 }
 
 func SumUsedToken(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string) (token int) {
-	tx := DB.Table("logs").Select("sum(prompt_tokens) + sum(completion_tokens)")
+	tx := DB.Table("logs").Select("ifnull(sum(prompt_tokens),0) + ifnull(sum(completion_tokens),0)")
 	if username != "" {
 		tx = tx.Where("username = ?", username)
 	}
@@ -169,3 +178,8 @@ func SumUsedToken(logType int, startTimestamp int64, endTimestamp int64, modelNa
 	tx.Where("type = ?", LogTypeConsume).Scan(&token)
 	return token
 }
+
+func DeleteOldLog(targetTimestamp int64) (int64, error) {
+	result := DB.Where("created_at < ?", targetTimestamp).Delete(&Log{})
+	return result.RowsAffected, result.Error
+}

router/api-router.go

@@ -98,6 +98,7 @@ func SetApiRouter(router *gin.Engine) {
 		}
 		logRoute := apiRouter.Group("/log")
 		logRoute.GET("/", middleware.AdminAuth(), controller.GetAllLogs)
+		logRoute.DELETE("/", middleware.AdminAuth(), controller.DeleteHistoryLogs)
 		logRoute.GET("/stat", middleware.AdminAuth(), controller.GetLogsStat)
 		logRoute.GET("/self/stat", middleware.UserAuth(), controller.GetLogsSelfStat)
 		logRoute.GET("/search", middleware.AdminAuth(), controller.SearchAllLogs)

web/src/components/ChannelsTable.js

@@ -1,5 +1,5 @@
 import React, { useEffect, useState } from 'react';
-import { Button, Form, Label, Pagination, Popup, Table } from 'semantic-ui-react';
+import {Button, Form, Input, Label, Pagination, Popup, Table} from 'semantic-ui-react';
 import { Link } from 'react-router-dom';
 import { API, showError, showInfo, showNotice, showSuccess, timestamp2string } from '../helpers';
 
@@ -24,7 +24,7 @@ function renderType(type) {
     }
     type2label[0] = { value: 0, text: '未知类型', color: 'grey' };
   }
-  return <Label basic color={type2label[type].color}>{type2label[type].text}</Label>;
+  return <Label basic color={type2label[type]?.color}>{type2label[type]?.text}</Label>;
 }
 
 function renderBalance(type, balance) {
@@ -96,7 +96,7 @@ const ChannelsTable = () => {
       });
   }, []);
 
-  const manageChannel = async (id, action, idx) => {
+  const manageChannel = async (id, action, idx, priority) => {
     let data = { id };
     let res;
     switch (action) {
@@ -111,6 +111,13 @@ const ChannelsTable = () => {
         data.status = 2;
         res = await API.put('/api/channel/', data);
         break;
+      case 'priority':
+        if (priority === '') {
+          return;
+        }
+        data.priority = parseInt(priority);
+        res = await API.put('/api/channel/', data);
+        break;
     }
     const { success, message } = res.data;
     if (success) {
@@ -335,6 +342,14 @@ const ChannelsTable = () => {
             >
               余额
             </Table.HeaderCell>
+            <Table.HeaderCell
+                style={{ cursor: 'pointer' }}
+                onClick={() => {
+                  sortChannel('priority');
+                }}
+            >
+              优先级
+            </Table.HeaderCell>
             <Table.HeaderCell>操作</Table.HeaderCell>
           </Table.Row>
         </Table.Header>
@@ -373,6 +388,22 @@ const ChannelsTable = () => {
                       basic
                     />
                   </Table.Cell>
+                  <Table.Cell>
+                    <Popup
+                        trigger={<Input type="number"  defaultValue={channel.priority} onBlur={(event) => {
+                          manageChannel(
+                              channel.id,
+                              'priority',
+                              idx,
+                              event.target.value,
+                          );
+                        }}>
+                          <input style={{maxWidth:'60px'}} />
+                        </Input>}
+                        content='渠道选择优先级，越高越优先'
+                        basic
+                    />
+                  </Table.Cell>
                   <Table.Cell>
                     <div>
                       <Button
@@ -441,7 +472,7 @@ const ChannelsTable = () => {
 
         <Table.Footer>
           <Table.Row>
-            <Table.HeaderCell colSpan='8'>
+            <Table.HeaderCell colSpan='9'>
               <Button size='small' as={Link} to='/channel/add' loading={loading}>
                 添加新的渠道
               </Button>

web/src/components/LogsTable.js

@@ -56,9 +56,10 @@ const LogsTable = () => {
     token_name: '',
     model_name: '',
     start_timestamp: timestamp2string(0),
-    end_timestamp: timestamp2string(now.getTime() / 1000 + 3600)
+    end_timestamp: timestamp2string(now.getTime() / 1000 + 3600),
+    channel: ''
   });
-  const { username, token_name, model_name, start_timestamp, end_timestamp } = inputs;
+  const { username, token_name, model_name, start_timestamp, end_timestamp, channel } = inputs;
 
   const [stat, setStat] = useState({
     quota: 0,
@@ -84,7 +85,7 @@ const LogsTable = () => {
   const getLogStat = async () => {
     let localStartTimestamp = Date.parse(start_timestamp) / 1000;
     let localEndTimestamp = Date.parse(end_timestamp) / 1000;
-    let res = await API.get(`/api/log/stat?type=${logType}&username=${username}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`);
+    let res = await API.get(`/api/log/stat?type=${logType}&username=${username}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}&channel=${channel}`);
     const { success, message, data } = res.data;
     if (success) {
       setStat(data);
@@ -109,7 +110,7 @@ const LogsTable = () => {
     let localStartTimestamp = Date.parse(start_timestamp) / 1000;
     let localEndTimestamp = Date.parse(end_timestamp) / 1000;
     if (isAdminUser) {
-      url = `/api/log/?p=${startIdx}&type=${logType}&username=${username}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`;
+      url = `/api/log/?p=${startIdx}&type=${logType}&username=${username}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}&channel=${channel}`;
     } else {
       url = `/api/log/self/?p=${startIdx}&type=${logType}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`;
     }
@@ -205,16 +206,9 @@ const LogsTable = () => {
         </Header>
         <Form>
           <Form.Group>
-            {
-              isAdminUser && (
-                <Form.Input fluid label={'用户名称'} width={2} value={username}
-                            placeholder={'可选值'} name='username'
-                            onChange={handleInputChange} />
-              )
-            }
-            <Form.Input fluid label={'令牌名称'} width={isAdminUser ? 2 : 3} value={token_name}
+            <Form.Input fluid label={'令牌名称'} width={3} value={token_name}
                         placeholder={'可选值'} name='token_name' onChange={handleInputChange} />
-            <Form.Input fluid label='模型名称' width={isAdminUser ? 2 : 3} value={model_name} placeholder='可选值'
+            <Form.Input fluid label='模型名称' width={3} value={model_name} placeholder='可选值'
                         name='model_name'
                         onChange={handleInputChange} />
             <Form.Input fluid label='起始时间' width={4} value={start_timestamp} type='datetime-local'
@@ -225,6 +219,19 @@ const LogsTable = () => {
                         onChange={handleInputChange} />
             <Form.Button fluid label='操作' width={2} onClick={refresh}>查询</Form.Button>
           </Form.Group>
+          {
+            isAdminUser && <>
+              <Form.Group>
+                <Form.Input fluid label={'渠道 ID'} width={3} value={channel}
+                            placeholder='可选值' name='channel'
+                            onChange={handleInputChange} />
+                <Form.Input fluid label={'用户名称'} width={3} value={username}
+                            placeholder={'可选值'} name='username'
+                            onChange={handleInputChange} />
+
+              </Form.Group>
+            </>
+          }
         </Form>
         <Table basic compact size='small'>
           <Table.Header>
@@ -238,6 +245,17 @@ const LogsTable = () => {
               >
                 时间
               </Table.HeaderCell>
+              {
+                isAdminUser && <Table.HeaderCell
+                  style={{ cursor: 'pointer' }}
+                  onClick={() => {
+                    sortLog('channel');
+                  }}
+                  width={1}
+                >
+                  渠道
+                </Table.HeaderCell>
+              }
               {
                 isAdminUser && <Table.HeaderCell
                   style={{ cursor: 'pointer' }}
@@ -299,16 +317,16 @@ const LogsTable = () => {
                 onClick={() => {
                   sortLog('quota');
                 }}
-                width={2}
+                width={1}
               >
-                消耗额度
+                额度
               </Table.HeaderCell>
               <Table.HeaderCell
                 style={{ cursor: 'pointer' }}
                 onClick={() => {
                   sortLog('content');
                 }}
-                width={isAdminUser ? 4 : 5}
+                width={isAdminUser ? 4 : 6}
               >
                 详情
               </Table.HeaderCell>
@@ -326,6 +344,11 @@ const LogsTable = () => {
                 return (
                   <Table.Row key={log.id}>
                     <Table.Cell>{renderTimestamp(log.created_at)}</Table.Cell>
+                    {
+                      isAdminUser && (
+                        <Table.Cell>{log.channel ? <Label basic>{log.channel}</Label> : ''}</Table.Cell>
+                      )
+                    }
                     {
                       isAdminUser && (
                         <Table.Cell>{log.username ? <Label>{log.username}</Label> : ''}</Table.Cell>
@@ -345,7 +368,7 @@ const LogsTable = () => {
 
           <Table.Footer>
             <Table.Row>
-              <Table.HeaderCell colSpan={'9'}>
+              <Table.HeaderCell colSpan={'10'}>
                 <Select
                   placeholder='选择明细分类'
                   options={LOG_OPTIONS}

web/src/components/OperationSetting.js

@@ -1,8 +1,9 @@
 import React, { useEffect, useState } from 'react';
 import { Divider, Form, Grid, Header } from 'semantic-ui-react';
-import { API, showError, verifyJSON } from '../helpers';
+import { API, showError, showSuccess, timestamp2string, verifyJSON } from '../helpers';
 
 const OperationSetting = () => {
+  let now = new Date();
   let [inputs, setInputs] = useState({
     QuotaForNewUser: 0,
     QuotaForInviter: 0,
@@ -20,10 +21,11 @@ const OperationSetting = () => {
     DisplayInCurrencyEnabled: '',
     DisplayTokenStatEnabled: '',
     ApproximateTokenEnabled: '',
-    RetryTimes: 0,
+    RetryTimes: 0
   });
   const [originInputs, setOriginInputs] = useState({});
   let [loading, setLoading] = useState(false);
+  let [historyTimestamp, setHistoryTimestamp] = useState(timestamp2string(now.getTime() / 1000 - 30 * 24 * 3600)); // a month ago
 
   const getOptions = async () => {
     const res = await API.get('/api/option/');
@@ -130,6 +132,17 @@ const OperationSetting = () => {
     }
   };
 
+  const deleteHistoryLogs = async () => {
+    console.log(inputs);
+    const res = await API.delete(`/api/log/?target_timestamp=${Date.parse(historyTimestamp) / 1000}`);
+    const { success, message, data } = res.data;
+    if (success) {
+      showSuccess(`${data} 条日志已清理！`);
+      return;
+    }
+    showError('日志清理失败：' + message);
+  };
+
   return (
     <Grid columns={1}>
       <Grid.Column>
@@ -179,12 +192,6 @@ const OperationSetting = () => {
             />
           </Form.Group>
           <Form.Group inline>
-            <Form.Checkbox
-              checked={inputs.LogConsumeEnabled === 'true'}
-              label='启用额度消费日志记录'
-              name='LogConsumeEnabled'
-              onChange={handleInputChange}
-            />
             <Form.Checkbox
               checked={inputs.DisplayInCurrencyEnabled === 'true'}
               label='以货币形式显示额度'
@@ -208,6 +215,28 @@ const OperationSetting = () => {
             submitConfig('general').then();
           }}>保存通用设置</Form.Button>
           <Divider />
+          <Header as='h3'>
+            日志设置
+          </Header>
+          <Form.Group inline>
+            <Form.Checkbox
+              checked={inputs.LogConsumeEnabled === 'true'}
+              label='启用额度消费日志记录'
+              name='LogConsumeEnabled'
+              onChange={handleInputChange}
+            />
+          </Form.Group>
+          <Form.Group widths={4}>
+            <Form.Input label='目标时间' value={historyTimestamp} type='datetime-local'
+                        name='history_timestamp'
+                        onChange={(e, { name, value }) => {
+                          setHistoryTimestamp(value);
+                        }} />
+          </Form.Group>
+          <Form.Button onClick={() => {
+            deleteHistoryLogs().then();
+          }}>清理历史日志</Form.Button>
+          <Divider />
           <Header as='h3'>
             监控设置
           </Header>

web/src/components/TokensTable.js

@@ -96,7 +96,7 @@ const TokensTable = () => {
     let nextUrl;
   
     if (nextLink) {
-      nextUrl = nextLink + `/#/?settings={"key":"sk-${key}"}`;
+      nextUrl = nextLink + `/#/?settings={"key":"sk-${key}","url":"${serverAddress}"}`;
     } else {
       nextUrl = `https://chat.oneapi.pro/#/?settings={"key":"sk-${key}","url":"${serverAddress}"}`;
     }

web/src/pages/Channel/EditChannel.js

@@ -67,7 +67,7 @@ const EditChannel = () => {
           localModels = ['ERNIE-Bot', 'ERNIE-Bot-turbo', 'Embedding-V1'];
           break;
         case 17:
-          localModels = ['qwen-v1', 'qwen-plus-v1', 'text-embedding-v1'];
+          localModels = ['qwen-turbo', 'qwen-plus', 'text-embedding-v1'];
           break;
         case 16:
           localModels = ['chatglm_pro', 'chatglm_std', 'chatglm_lite'];
@@ -174,7 +174,7 @@ const EditChannel = () => {
       return;
     }
     let localInputs = inputs;
-    if (localInputs.base_url.endsWith('/')) {
+    if (localInputs.base_url && localInputs.base_url.endsWith('/')) {
       localInputs.base_url = localInputs.base_url.slice(0, localInputs.base_url.length - 1);
     }
     if (localInputs.type === 3 && localInputs.other === '') {
@@ -183,9 +183,6 @@ const EditChannel = () => {
     if (localInputs.type === 18 && localInputs.other === '') {
       localInputs.other = 'v2.1';
     }
-    if (localInputs.model_mapping === '') {
-      localInputs.model_mapping = '{}';
-    }
     let res;
     localInputs.models = localInputs.models.join(',');
     localInputs.group = localInputs.groups.join(',');