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

@@ -355,6 +355,7 @@ graph LR
 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

@@ -95,6 +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/model-ratio.go

@@ -49,6 +49,7 @@ var ModelRatio = map[string]float64{
 	"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

controller/channel-test.go

@@ -5,14 +5,14 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"github.com/gin-gonic/gin"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
 	"strconv"
+	"strings"
 	"sync"
 	"time"
-
-	"github.com/gin-gonic/gin"
 )
 
 func testChannel(channel *model.Channel, request ChatRequest) (err error, openaiErr *OpenAIError) {
@@ -50,6 +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,
@@ -333,6 +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-text.go

@@ -7,6 +7,7 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"math"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
@@ -32,7 +33,14 @@ var httpClient *http.Client
 var impatientHTTPClient *http.Client
 
 func init() {
+	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,
 	}
@@ -407,9 +415,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 				completionRatio := common.GetCompletionRatio(textRequest.Model)
 				promptTokens = textResponse.Usage.PromptTokens
 				completionTokens = textResponse.Usage.CompletionTokens
-
+				quota = int(math.Ceil((float64(promptTokens) + float64(completionTokens)*completionRatio) * ratio))
-				quota = promptTokens + int(float64(completionTokens)*completionRatio)
-				quota = int(float64(quota) * ratio)
 				if ratio != 0 && quota <= 0 {
 					quota = 1
 				}

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" {
+	if apiVersion != "v1.1" {
-		domain = "generalv2"
+		domain += strings.Split(apiVersion, ".")[0]
 	}
 	authUrl := buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/%s/chat", apiVersion), apiKey, apiSecret)
 	return domain, authUrl

web/src/pages/Channel/EditChannel.js

@@ -72,7 +72,7 @@ const EditChannel = () => {
           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'];