xinyin025/one-api
1
0
Fork 0
mirror of https://github.com/songquanpeng/one-api.git synced 2025-09-20 02:26:38 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix: Improve quota consumption and logging in relay controller

Browse Source 
- Modify `PostConsumeQuota` function in `common.go` to check if `totalQuota` is less than 0 and add error logging
- Update log content in `RecordConsumeLog` function of `common.go` to include model ratio and group ratio
- Change the method of calculating user used quota and request count in `UpdateUserUsedQuotaAndRequestCount` function of `common.go`
- Implement calculation of `completionRatio` and update `quota` calculation based on `completionRatio` in `postConsumeQuota` function of `helper.go`
- Implement error handling for `model.PostConsumeTokenQuota` and `model.CacheUpdateUserQuota` in `helper.go`
- Update `UserUsedQuota` and `ChannelUsedQuota` with new `quota` value in `helper.go`
This commit is contained in:
Laisky.Cai 2024-03-08 03:22:29 +00:00
parent 849920b91f
commit cad6f9d3ba
2 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
relay/controller/helper.go
View File

@ -172,6 +172,7 @@ func postConsumeQuota(ctx context.Context, usage *relaymodel.Usage, meta *util.R
if err != nil { if err != nil {
logger.Error(ctx, "error update user quota cache: "+err.Error()) logger.Error(ctx, "error update user quota cache: "+err.Error())
} }
logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f，补全倍率 %.2f", modelRatio, groupRatio, completionRatio) logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f，补全倍率 %.2f", modelRatio, groupRatio, completionRatio)
model.RecordConsumeLog(ctx, meta.UserId, meta.ChannelId, promptTokens, completionTokens, textRequest.Model, meta.TokenName, quota, logContent) model.RecordConsumeLog(ctx, meta.UserId, meta.ChannelId, promptTokens, completionTokens, textRequest.Model, meta.TokenName, quota, logContent)
model.UpdateUserUsedQuotaAndRequestCount(meta.UserId, quota) model.UpdateUserUsedQuotaAndRequestCount(meta.UserId, quota)

5
relay/util/common.go
View File

@ -147,13 +147,14 @@ func PostConsumeQuota(ctx context.Context, tokenId int, quotaDelta int, totalQuo
logger.SysError("error update user quota cache: " + err.Error()) logger.SysError("error update user quota cache: " + err.Error())
} }
// totalQuota is total quota consumed // totalQuota is total quota consumed
if totalQuota != 0 { if totalQuota >= 0 {
logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio) logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
model.RecordConsumeLog(ctx, userId, channelId, totalQuota, 0, modelName, tokenName, totalQuota, logContent) model.RecordConsumeLog(ctx, userId, channelId, totalQuota, 0, modelName, tokenName, totalQuota, logContent)
model.UpdateUserUsedQuotaAndRequestCount(userId, totalQuota) model.UpdateUserUsedQuotaAndRequestCount(userId, totalQuota)
model.UpdateChannelUsedQuota(channelId, totalQuota) model.UpdateChannelUsedQuota(channelId, totalQuota)
} }
if totalQuota <= 0 {
if totalQuota < 0 {
logger.Error(ctx, fmt.Sprintf("totalQuota consumed is %d, something is wrong", totalQuota)) logger.Error(ctx, fmt.Sprintf("totalQuota consumed is %d, something is wrong", totalQuota))
} }
} }