mirror of
https://github.com/songquanpeng/one-api.git
synced 2025-10-19 10:07:29 +00:00
fix: calculate usage if not given in non-stream mode (#352)
This commit is contained in:
@@ -92,7 +92,7 @@ func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*O
|
||||
return nil, responseText
|
||||
}
|
||||
|
||||
func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool) (*OpenAIErrorWithStatusCode, *Usage) {
|
||||
func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool, promptTokens int, model string) (*OpenAIErrorWithStatusCode, *Usage) {
|
||||
var textResponse TextResponse
|
||||
if consumeQuota {
|
||||
responseBody, err := io.ReadAll(resp.Body)
|
||||
@@ -132,5 +132,17 @@ func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool) (*Ope
|
||||
if err != nil {
|
||||
return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
|
||||
}
|
||||
|
||||
if textResponse.Usage.TotalTokens == 0 {
|
||||
completionTokens := 0
|
||||
for _, choice := range textResponse.Choices {
|
||||
completionTokens += countTokenText(choice.Message.Content, model)
|
||||
}
|
||||
textResponse.Usage = Usage{
|
||||
PromptTokens: promptTokens,
|
||||
CompletionTokens: completionTokens,
|
||||
TotalTokens: promptTokens + completionTokens,
|
||||
}
|
||||
}
|
||||
return nil, &textResponse.Usage
|
||||
}
|
||||
|
Reference in New Issue
Block a user