oadmin/new-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Add self-use mode for model ratio and price configuration

Browse Source 
- Introduce `SelfUseModeEnabled` setting to allow flexible model ratio configuration
- Update error handling to provide more informative messages when model ratios are not set
- Modify pricing and relay logic to support self-use mode
- Add UI toggle for enabling self-use mode in operation settings
- Implement fallback mechanism for model ratios when self-use mode is enabled
This commit is contained in:
1808837298@qq.com
2025-03-01 21:13:48 +08:00
parent ce1854847b
commit 7dbb6b017c
15 changed files with 76 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
service/quota.go
View File

@@ -38,9 +38,9 @@ func calculateAudioQuota(info QuotaInfo) int {
return int(info.ModelPrice * common.QuotaPerUnit * info.GroupRatio)
}
completionRatio := common.GetCompletionRatio(info.ModelName)
audioRatio := common.GetAudioRatio(info.ModelName)
audioCompletionRatio := common.GetAudioCompletionRatio(info.ModelName)
completionRatio := setting.GetCompletionRatio(info.ModelName)
audioRatio := setting.GetAudioRatio(info.ModelName)
audioCompletionRatio := setting.GetAudioCompletionRatio(info.ModelName)
ratio := info.GroupRatio * info.ModelRatio
quota := info.InputDetails.TextTokens + int(math.Round(float64(info.OutputDetails.TextTokens)*completionRatio))
@@ -75,7 +75,7 @@ func PreWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usag
audioInputTokens := usage.InputTokenDetails.AudioTokens
audioOutTokens := usage.OutputTokenDetails.AudioTokens
groupRatio := setting.GetGroupRatio(relayInfo.Group)
modelRatio, _ := common.GetModelRatio(modelName)
modelRatio, _ := setting.GetModelRatio(modelName)
quotaInfo := QuotaInfo{
InputDetails: TokenDetails{
@@ -122,9 +122,9 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
audioOutTokens := usage.OutputTokenDetails.AudioTokens
tokenName := ctx.GetString("token_name")
completionRatio := common.GetCompletionRatio(modelName)
audioRatio := common.GetAudioRatio(relayInfo.OriginModelName)
audioCompletionRatio := common.GetAudioCompletionRatio(modelName)
completionRatio := setting.GetCompletionRatio(modelName)
audioRatio := setting.GetAudioRatio(relayInfo.OriginModelName)
audioCompletionRatio := setting.GetAudioCompletionRatio(modelName)
quotaInfo := QuotaInfo{
InputDetails: TokenDetails{
@@ -184,9 +184,9 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
audioOutTokens := usage.CompletionTokenDetails.AudioTokens
tokenName := ctx.GetString("token_name")
completionRatio := common.GetCompletionRatio(relayInfo.OriginModelName)
audioRatio := common.GetAudioRatio(relayInfo.OriginModelName)
audioCompletionRatio := common.GetAudioCompletionRatio(relayInfo.OriginModelName)
completionRatio := setting.GetCompletionRatio(relayInfo.OriginModelName)
audioRatio := setting.GetAudioRatio(relayInfo.OriginModelName)
audioCompletionRatio := setting.GetAudioCompletionRatio(relayInfo.OriginModelName)
modelRatio := priceData.ModelRatio
groupRatio := priceData.GroupRatio

3
service/token_counter.go
View File

@@ -10,6 +10,7 @@ import (
"one-api/constant"
"one-api/dto"
relaycommon "one-api/relay/common"
"one-api/setting"
"strings"
"unicode/utf8"
@@ -32,7 +33,7 @@ func InitTokenEncoders() {
if err != nil {
common.FatalLog(fmt.Sprintf("failed to get gpt-4o token encoder: %s", err.Error()))
}
for model, _ := range common.GetDefaultModelRatioMap() {
for model, _ := range setting.GetDefaultModelRatioMap() {
if strings.HasPrefix(model, "gpt-3.5") {
tokenEncoderMap[model] = cl100TokenEncoder
} else if strings.HasPrefix(model, "gpt-4") {