chore: update quota calc logic (close #599) (#627)

* fix: change quota calc code (close #599)

Use float64 during calc and do math.Ceil after calc. This will result in the quota being used slightly more than the official standard, but it will be guaranteed that it will not be less.

* chore: remove blank line

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>

README.md

@@ -352,6 +352,10 @@ graph LR
 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`。
+14. 编码器缓存设置：
+    + `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。
+15. `RELAY_TIMEOUT`：中继超时设置，单位为秒，默认不设置超时时间。
 
 ### 命令行参数
 1. `--port <port_number>`: 指定服务器监听的端口号，默认为 `3000`。

common/constants.go

@@ -21,12 +21,9 @@ var QuotaPerUnit = 500 * 1000.0 // $0.002 / 1K tokens
 var DisplayInCurrencyEnabled = true
 var DisplayTokenStatEnabled = true
 
-var UsingSQLite = false
-
 // Any options with "Secret", "Token" in its key won't be return by GetOptions
 
 var SessionSecret = uuid.New().String()
-var SQLitePath = "one-api.db"
 
 var OptionMap map[string]string
 var OptionMapRWMutex sync.RWMutex
@@ -98,6 +95,8 @@ var SyncFrequency = GetOrDefault("SYNC_FREQUENCY", 10*60) // unit is second
 var BatchUpdateEnabled = false
 var BatchUpdateInterval = GetOrDefault("BATCH_UPDATE_INTERVAL", 5)
 
+var RelayTimeout = GetOrDefault("RELAY_TIMEOUT", 0) // unit is second
+
 const (
 	RequestIdKey = "X-Oneapi-Request-Id"
 )

common/database.go

@@ -0,0 +1,6 @@
+package common
+
+var UsingSQLite = false
+var UsingPostgreSQL = false
+
+var SQLitePath = "one-api.db"

common/model-ratio.go

@@ -46,8 +46,10 @@ var ModelRatio = map[string]float64{
 	"claude-2":                  5.51,   // $11.02 / 1M tokens
 	"ERNIE-Bot":                 0.8572, // ￥0.012 / 1k tokens
 	"ERNIE-Bot-turbo":           0.5715, // ￥0.008 / 1k tokens
+	"ERNIE-Bot-4":               8.572,  // ￥0.12 / 1k tokens
 	"Embedding-V1":              0.1429, // ￥0.002 / 1k tokens
 	"PaLM-2":                    1,
+	"chatglm_turbo":             0.3572, // ￥0.005 / 1k tokens
 	"chatglm_pro":               0.7143, // ￥0.01 / 1k tokens
 	"chatglm_std":               0.3572, // ￥0.005 / 1k tokens
 	"chatglm_lite":              0.1429, // ￥0.002 / 1k tokens

common/utils.go

@@ -199,3 +199,11 @@ func GetOrDefault(env string, defaultValue int) int {
 func MessageWithRequestId(message string, id string) string {
 	return fmt.Sprintf("%s (request id: %s)", message, id)
 }
+
+func String2Int(str string) int {
+	num, err := strconv.Atoi(str)
+	if err != nil {
+		return 0
+	}
+	return num
+}

controller/channel-test.go

@@ -10,6 +10,7 @@ import (
 	"one-api/common"
 	"one-api/model"
 	"strconv"
+	"strings"
 	"sync"
 	"time"
 )
@@ -49,6 +50,8 @@ func testChannel(channel *model.Channel, request ChatRequest) (err error, openai
 		}
 		requestURL += "/v1/chat/completions"
 	}
+	// for Cloudflare AI gateway: https://github.com/songquanpeng/one-api/pull/639
+	requestURL = strings.Replace(requestURL, "/v1/v1", "/v1", 1)
 
 	jsonData, err := json.Marshal(request)
 	if err != nil {

controller/model.go

@@ -274,7 +274,7 @@ func init() {
 			Id:         "claude-instant-1",
 			Object:     "model",
 			Created:    1677649963,
-			OwnedBy:    "anturopic",
+			OwnedBy:    "anthropic",
 			Permission: permission,
 			Root:       "claude-instant-1",
 			Parent:     nil,
@@ -283,7 +283,7 @@ func init() {
 			Id:         "claude-2",
 			Object:     "model",
 			Created:    1677649963,
-			OwnedBy:    "anturopic",
+			OwnedBy:    "anthropic",
 			Permission: permission,
 			Root:       "claude-2",
 			Parent:     nil,
@@ -306,6 +306,15 @@ func init() {
 			Root:       "ERNIE-Bot-turbo",
 			Parent:     nil,
 		},
+		{
+			Id:         "ERNIE-Bot-4",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "baidu",
+			Permission: permission,
+			Root:       "ERNIE-Bot-4",
+			Parent:     nil,
+		},
 		{
 			Id:         "Embedding-V1",
 			Object:     "model",
@@ -324,6 +333,15 @@ func init() {
 			Root:       "PaLM-2",
 			Parent:     nil,
 		},
+		{
+			Id:         "chatglm_turbo",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "zhipu",
+			Permission: permission,
+			Root:       "chatglm_turbo",
+			Parent:     nil,
+		},
 		{
 			Id:         "chatglm_pro",
 			Object:     "model",

controller/relay-audio.go

@@ -6,12 +6,11 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
-
-	"github.com/gin-gonic/gin"
 )
 
 func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
@@ -66,12 +65,11 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 
 	baseURL := common.ChannelBaseURLs[channelType]
 	requestURL := c.Request.URL.String()
-
 	if c.GetString("base_url") != "" {
 		baseURL = c.GetString("base_url")
 	}
 
-	fullRequestURL := fmt.Sprintf("%s%s", baseURL, requestURL)
+	fullRequestURL := getFullRequestURL(baseURL, requestURL, channelType)
 	requestBody := c.Request.Body
 
 	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)

controller/relay-image.go

@@ -6,12 +6,11 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
-
-	"github.com/gin-gonic/gin"
 )
 
 func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
@@ -61,16 +60,12 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 			isModelMapped = true
 		}
 	}
-
 	baseURL := common.ChannelBaseURLs[channelType]
 	requestURL := c.Request.URL.String()
-
 	if c.GetString("base_url") != "" {
 		baseURL = c.GetString("base_url")
 	}
-
-	fullRequestURL := fmt.Sprintf("%s%s", baseURL, requestURL)
-
+	fullRequestURL := getFullRequestURL(baseURL, requestURL, channelType)
 	var requestBody io.Reader
 	if isModelMapped {
 		jsonStr, err := json.Marshal(imageRequest)

controller/relay-text.go

@@ -6,13 +6,15 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
+	"math"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
 	"strings"
 	"time"
+
+	"github.com/gin-gonic/gin"
 )
 
 const (
@@ -31,7 +33,14 @@ var httpClient *http.Client
 var impatientHTTPClient *http.Client
 
 func init() {
-	httpClient = &http.Client{}
+	if common.RelayTimeout == 0 {
+		httpClient = &http.Client{}
+	} else {
+		httpClient = &http.Client{
+			Timeout: time.Duration(common.RelayTimeout) * time.Second,
+		}
+	}
+
 	impatientHTTPClient = &http.Client{
 		Timeout: 5 * time.Second,
 	}
@@ -118,12 +127,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 	if c.GetString("base_url") != "" {
 		baseURL = c.GetString("base_url")
 	}
-	fullRequestURL := fmt.Sprintf("%s%s", baseURL, requestURL)
-	if channelType == common.ChannelTypeOpenAI {
-		if strings.HasPrefix(baseURL, "https://gateway.ai.cloudflare.com") {
-			fullRequestURL = fmt.Sprintf("%s%s", baseURL, strings.TrimPrefix(requestURL, "/v1"))
-		}
-	}
+	fullRequestURL := getFullRequestURL(baseURL, requestURL, channelType)
 	switch apiType {
 	case APITypeOpenAI:
 		if channelType == common.ChannelTypeAzure {
@@ -156,6 +160,8 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions"
 		case "ERNIE-Bot-turbo":
 			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant"
+		case "ERNIE-Bot-4":
+			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions_pro"
 		case "BLOOMZ-7B":
 			fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/bloomz_7b1"
 		case "Embedding-V1":
@@ -366,6 +372,9 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 		}
 		req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
 		req.Header.Set("Accept", c.Request.Header.Get("Accept"))
+		if isStream && c.Request.Header.Get("Accept") == "" {
+			req.Header.Set("Accept", "text/event-stream")
+		}
 		//req.Header.Set("Connection", c.Request.Header.Get("Connection"))
 		resp, err = httpClient.Do(req)
 		if err != nil {
@@ -406,9 +415,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 				completionRatio := common.GetCompletionRatio(textRequest.Model)
 				promptTokens = textResponse.Usage.PromptTokens
 				completionTokens = textResponse.Usage.CompletionTokens
-
-				quota = promptTokens + int(float64(completionTokens)*completionRatio)
-				quota = int(float64(quota) * ratio)
+				quota = int(math.Ceil((float64(promptTokens) + float64(completionTokens)*completionRatio) * ratio))
 				if ratio != 0 && quota <= 0 {
 					quota = 1
 				}

controller/relay-utils.go

@@ -176,3 +176,13 @@ func relayErrorHandler(resp *http.Response) (openAIErrorWithStatusCode *OpenAIEr
 	openAIErrorWithStatusCode.OpenAIError = textResponse.Error
 	return
 }
+
+func getFullRequestURL(baseURL string, requestURL string, channelType int) string {
+	fullRequestURL := fmt.Sprintf("%s%s", baseURL, requestURL)
+	if channelType == common.ChannelTypeOpenAI {
+		if strings.HasPrefix(baseURL, "https://gateway.ai.cloudflare.com") {
+			fullRequestURL = fmt.Sprintf("%s%s", baseURL, strings.TrimPrefix(requestURL, "/v1"))
+		}
+	}
+	return fullRequestURL
+}

controller/relay-xunfei.go

@@ -298,8 +298,8 @@ func getXunfeiAuthUrl(c *gin.Context, apiKey string, apiSecret string) (string,
 		common.SysLog("api_version not found, use default: " + apiVersion)
 	}
 	domain := "general"
-	if apiVersion == "v2.1" {
-		domain = "generalv2"
+	if apiVersion != "v1.1" {
+		domain += strings.Split(apiVersion, ".")[0]
 	}
 	authUrl := buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/%s/chat", apiVersion), apiKey, apiSecret)
 	return domain, authUrl

docker-compose.yml

@@ -23,7 +23,7 @@ services:
     depends_on:
       - redis
     healthcheck:
-      test: [ "CMD-SHELL", "curl -s http://localhost:3000/api/status | grep -o '\"success\":\\s*true' | awk '{print $2}' | grep 'true'" ]
+      test: [ "CMD-SHELL", "wget -q -O - http://localhost:3000/api/status | grep -o '\"success\":\\s*true' | awk -F: '{print $2}'" ]
       interval: 30s
       timeout: 10s
       retries: 3

model/ability.go

@@ -15,10 +15,17 @@ type Ability struct {
 
 func GetRandomSatisfiedChannel(group string, model string) (*Channel, error) {
 	ability := Ability{}
+	groupCol := "`group`"
+	trueVal := "1"
+	if common.UsingPostgreSQL {
+		groupCol = `"group"`
+		trueVal = "true"
+	}
+
 	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 {
+	maxPrioritySubQuery := DB.Model(&Ability{}).Select("MAX(priority)").Where(groupCol+" = ? and model = ? and enabled = "+trueVal, group, model)
+	channelQuery := DB.Where(groupCol+" = ? and model = ? and enabled = "+trueVal+" and priority = (?)", group, model, maxPrioritySubQuery)
+	if common.UsingSQLite || common.UsingPostgreSQL {
 		err = channelQuery.Order("RANDOM()").First(&ability).Error
 	} else {
 		err = channelQuery.Order("RAND()").First(&ability).Error

model/cache.go

@@ -21,14 +21,18 @@ var (
 )
 
 func CacheGetTokenByKey(key string) (*Token, error) {
+	keyCol := "`key`"
+	if common.UsingPostgreSQL {
+		keyCol = `"key"`
+	}
 	var token Token
 	if !common.RedisEnabled {
-		err := DB.Where("`key` = ?", key).First(&token).Error
+		err := DB.Where(keyCol+" = ?", key).First(&token).Error
 		return &token, err
 	}
 	tokenObjectString, err := common.RedisGet(fmt.Sprintf("token:%s", key))
 	if err != nil {
-		err := DB.Where("`key` = ?", key).First(&token).Error
+		err := DB.Where(keyCol+" = ?", key).First(&token).Error
 		if err != nil {
 			return nil, err
 		}

model/channel.go

@@ -38,7 +38,11 @@ func GetAllChannels(startIdx int, num int, selectAll bool) ([]*Channel, error) {
 }
 
 func SearchChannels(keyword string) (channels []*Channel, err error) {
-	err = DB.Omit("key").Where("id = ? or name LIKE ? or `key` = ?", keyword, keyword+"%", keyword).Find(&channels).Error
+	keyCol := "`key`"
+	if common.UsingPostgreSQL {
+		keyCol = `"key"`
+	}
+	err = DB.Omit("key").Where("id = ? or name LIKE ? or "+keyCol+" = ?", common.String2Int(keyword), keyword+"%", keyword).Find(&channels).Error
 	return channels, err
 }
 
@@ -53,17 +57,6 @@ func GetChannelById(id int, selectAll bool) (*Channel, error) {
 	return &channel, err
 }
 
-func GetRandomChannel() (*Channel, error) {
-	channel := Channel{}
-	var err error = nil
-	if common.UsingSQLite {
-		err = DB.Where("status = ? and `group` = ?", common.ChannelStatusEnabled, "default").Order("RANDOM()").Limit(1).First(&channel).Error
-	} else {
-		err = DB.Where("status = ? and `group` = ?", common.ChannelStatusEnabled, "default").Order("RAND()").Limit(1).First(&channel).Error
-	}
-	return &channel, err
-}
-
 func BatchInsertChannels(channels []Channel) error {
 	var err error
 	err = DB.Create(&channels).Error

model/main.go

@@ -42,6 +42,7 @@ func chooseDB() (*gorm.DB, error) {
 		if strings.HasPrefix(dsn, "postgres://") {
 			// Use PostgreSQL
 			common.SysLog("using PostgreSQL as database")
+			common.UsingPostgreSQL = true
 			return gorm.Open(postgres.New(postgres.Config{
 				DSN:                  dsn,
 				PreferSimpleProtocol: true, // disables implicit prepared statement usage

model/redemption.go

@@ -50,8 +50,13 @@ func Redeem(key string, userId int) (quota int, err error) {
 	}
 	redemption := &Redemption{}
 
+	keyCol := "`key`"
+	if common.UsingPostgreSQL {
+		keyCol = `"key"`
+	}
+
 	err = DB.Transaction(func(tx *gorm.DB) error {
-		err := tx.Set("gorm:query_option", "FOR UPDATE").Where("`key` = ?", key).First(redemption).Error
+		err := tx.Set("gorm:query_option", "FOR UPDATE").Where(keyCol+" = ?", key).First(redemption).Error
 		if err != nil {
 			return errors.New("无效的兑换码")
 		}

model/user.go

@@ -266,7 +266,12 @@ func GetUserEmail(id int) (email string, err error) {
 }
 
 func GetUserGroup(id int) (group string, err error) {
-	err = DB.Model(&User{}).Where("id = ?", id).Select("`group`").Find(&group).Error
+	groupCol := "`group`"
+	if common.UsingPostgreSQL {
+		groupCol = `"group"`
+	}
+
+	err = DB.Model(&User{}).Where("id = ?", id).Select(groupCol).Find(&group).Error
 	return group, err
 }
 

web/src/pages/Channel/EditChannel.js

@@ -66,13 +66,13 @@ const EditChannel = () => {
           localModels = ['PaLM-2'];
           break;
         case 15:
-          localModels = ['ERNIE-Bot', 'ERNIE-Bot-turbo', 'Embedding-V1'];
+          localModels = ['ERNIE-Bot', 'ERNIE-Bot-turbo', 'ERNIE-Bot-4', 'Embedding-V1'];
           break;
         case 17:
           localModels = ['qwen-turbo', 'qwen-plus', 'text-embedding-v1'];
           break;
         case 16:
-          localModels = ['chatglm_pro', 'chatglm_std', 'chatglm_lite'];
+          localModels = ['chatglm_turbo', 'chatglm_pro', 'chatglm_std', 'chatglm_lite'];
           break;
         case 18:
           localModels = ['SparkDesk'];