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

feat: refactor token estimation logic

Browse Source 
- Introduced new OpenAI text models in `common/model.go`.
- Added `IsOpenAITextModel` function to check for OpenAI text models.
- Refactored token estimation methods across various channels to use estimated prompt tokens instead of direct prompt token counts.
- Updated related functions and structures to accommodate the new token estimation approach, enhancing overall token management.
This commit is contained in:
CaIon
2025-12-02 21:34:39 +08:00
parent 91fcdd4f18
commit 1fededceb3
26 changed files with 389 additions and 275 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
relay/channel/volcengine/tts.go
View File

@@ -184,9 +184,9 @@ func handleTTSResponse(c *gin.Context, resp *http.Response, info *relaycommon.Re
c.Data(http.StatusOK, contentType, audioData)
usage = &dto.Usage{
PromptTokens: info.PromptTokens,
PromptTokens: info.GetEstimatePromptTokens(),
CompletionTokens: 0,
TotalTokens: info.PromptTokens,
TotalTokens: info.GetEstimatePromptTokens(),
}
return usage, nil
@@ -284,9 +284,9 @@ func handleTTSWebSocketResponse(c *gin.Context, requestURL string, volcRequest V
if msg.Sequence < 0 {
c.Status(http.StatusOK)
usage = &dto.Usage{
PromptTokens: info.PromptTokens,
PromptTokens: info.GetEstimatePromptTokens(),
CompletionTokens: 0,
TotalTokens: info.PromptTokens,
TotalTokens: info.GetEstimatePromptTokens(),
}
return usage, nil
}
@@ -297,9 +297,9 @@ func handleTTSWebSocketResponse(c *gin.Context, requestURL string, volcRequest V
c.Status(http.StatusOK)
usage = &dto.Usage{
PromptTokens: info.PromptTokens,
PromptTokens: info.GetEstimatePromptTokens(),
CompletionTokens: 0,
TotalTokens: info.PromptTokens,
TotalTokens: info.GetEstimatePromptTokens(),
}
return usage, nil
}