Ecosystem/ai-gateway
5
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: 删除relay-text中的consumeQuota变量

Browse Source 
该变量始终为true，可以删除
This commit is contained in:
igophper 2023-11-22 22:58:04 +08:00
parent 495fc628e4
commit c499faae0a
2 changed files with 56 additions and 61 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
controller/relay-openai.go
View File

@ -88,30 +88,29 @@ func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*O
return nil, responseText
}
func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool, promptTokens int, model string) (*OpenAIErrorWithStatusCode, *Usage) {
func openaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*OpenAIErrorWithStatusCode, *Usage) {
var textResponse TextResponse
if consumeQuota {
responseBody, err := io.ReadAll(resp.Body)
if err != nil {
return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
}
err = resp.Body.Close()
if err != nil {
return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
}
err = json.Unmarshal(responseBody, &textResponse)
if err != nil {
return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
}
if textResponse.Error.Type != "" {
return &OpenAIErrorWithStatusCode{
OpenAIError: textResponse.Error,
StatusCode: resp.StatusCode,
}, nil
}
// Reset response body
resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
responseBody, err := io.ReadAll(resp.Body)
if err != nil {
return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
}
err = resp.Body.Close()
if err != nil {
return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
}
err = json.Unmarshal(responseBody, &textResponse)
if err != nil {
return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
}
if textResponse.Error.Type != "" {
return &OpenAIErrorWithStatusCode{
OpenAIError: textResponse.Error,
StatusCode: resp.StatusCode,
}, nil
}
// Reset response body
resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
// We shouldn't set the header before we parse the response body, because the parse part may fail.
// And then we will have to send an error response, but in this case, the header has already been set.
// So the httpClient will be confused by the response.
@ -120,7 +119,7 @@ func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool, promp
c.Writer.Header().Set(k, v[0])
}
c.Writer.WriteHeader(resp.StatusCode)
_, err := io.Copy(c.Writer, resp.Body)
_, err = io.Copy(c.Writer, resp.Body)
if err != nil {
return errorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError), nil
}

72
controller/relay-text.go
View File

@ -51,14 +51,11 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
channelId := c.GetInt("channel_id")
tokenId := c.GetInt("token_id")
userId := c.GetInt("id")
consumeQuota := c.GetBool("consume_quota")
group := c.GetString("group")
var textRequest GeneralOpenAIRequest
if consumeQuota || channelType == common.ChannelTypeAzure || channelType == common.ChannelTypePaLM {
err := common.UnmarshalBodyReusable(c, &textRequest)
if err != nil {
return errorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
}
err := common.UnmarshalBodyReusable(c, &textRequest)
if err != nil {
return errorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
}
if relayMode == RelayModeModerations && textRequest.Model == "" {
textRequest.Model = "text-moderation-latest"
@ -235,7 +232,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
preConsumedQuota = 0
common.LogInfo(c.Request.Context(), fmt.Sprintf("user %d has enough quota %d, trusted and no need to pre-consume", userId, userQuota))
}
if consumeQuota && preConsumedQuota > 0 {
if preConsumedQuota > 0 {
err := model.PreConsumeTokenQuota(tokenId, preConsumedQuota)
if err != nil {
return errorWrapper(err, "pre_consume_token_quota_failed", http.StatusForbidden)
@ -414,37 +411,36 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
defer func(ctx context.Context) {
// c.Writer.Flush()
go func() {
if consumeQuota {
quota := 0
completionRatio := common.GetCompletionRatio(textRequest.Model)
promptTokens = textResponse.Usage.PromptTokens
completionTokens = textResponse.Usage.CompletionTokens
quota = int(math.Ceil((float64(promptTokens) + float64(completionTokens)*completionRatio) * ratio))
if ratio != 0 && quota <= 0 {
quota = 1
}
totalTokens := promptTokens + completionTokens
if totalTokens == 0 {
// in this case, must be some error happened
// we cannot just return, because we may have to return the pre-consumed quota
quota = 0
}
quotaDelta := quota - preConsumedQuota
err := model.PostConsumeTokenQuota(tokenId, quotaDelta)
if err != nil {
common.LogError(ctx, "error consuming token remain quota: "+err.Error())
}
err = model.CacheUpdateUserQuota(userId)
if err != nil {
common.LogError(ctx, "error update user quota cache: "+err.Error())
}
if quota != 0 {
logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
model.RecordConsumeLog(ctx, userId, channelId, promptTokens, completionTokens, textRequest.Model, tokenName, quota, logContent)
model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
model.UpdateChannelUsedQuota(channelId, quota)
}
quota := 0
completionRatio := common.GetCompletionRatio(textRequest.Model)
promptTokens = textResponse.Usage.PromptTokens
completionTokens = textResponse.Usage.CompletionTokens
quota = int(math.Ceil((float64(promptTokens) + float64(completionTokens)*completionRatio) * ratio))
if ratio != 0 && quota <= 0 {
quota = 1
}
totalTokens := promptTokens + completionTokens
if totalTokens == 0 {
// in this case, must be some error happened
// we cannot just return, because we may have to return the pre-consumed quota
quota = 0
}
quotaDelta := quota - preConsumedQuota
err := model.PostConsumeTokenQuota(tokenId, quotaDelta)
if err != nil {
common.LogError(ctx, "error consuming token remain quota: "+err.Error())
}
err = model.CacheUpdateUserQuota(userId)
if err != nil {
common.LogError(ctx, "error update user quota cache: "+err.Error())
}
if quota != 0 {
logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
model.RecordConsumeLog(ctx, userId, channelId, promptTokens, completionTokens, textRequest.Model, tokenName, quota, logContent)
model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
model.UpdateChannelUsedQuota(channelId, quota)
}
}()
}(c.Request.Context())
switch apiType {
@ -458,7 +454,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
textResponse.Usage.CompletionTokens = countTokenText(responseText, textRequest.Model)
return nil
} else {
err, usage := openaiHandler(c, resp, consumeQuota, promptTokens, textRequest.Model)
err, usage := openaiHandler(c, resp, promptTokens, textRequest.Model)
if err != nil {
return err
}