xinyin025/new-api
1
0
Fork 0
mirror of https://github.com/linux-do/new-api.git synced 2025-11-08 15:13:42 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

feat: 完善函数计费

Browse Source
This commit is contained in:
CaIon
2024-04-23 23:01:06 +08:00
parent 89ebd85503
commit 2841669246
8 changed files with 65 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
relay/channel/ollama/adaptor.go
View File

@@ -52,7 +52,7 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
if info.IsStream {
var responseText string
err, responseText = openai.OpenaiStreamHandler(c, resp, info.RelayMode)
err, responseText, _ = openai.OpenaiStreamHandler(c, resp, info.RelayMode)
usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
} else {
if info.RelayMode == relayconstant.RelayModeEmbeddings {

4
relay/channel/openai/adaptor.go
View File

@@ -72,8 +72,10 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
if info.IsStream {
var responseText string
err, responseText = OpenaiStreamHandler(c, resp, info.RelayMode)
var toolCount int
err, responseText, toolCount = OpenaiStreamHandler(c, resp, info.RelayMode)
usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
usage.CompletionTokens += toolCount * 7
} else {
err, usage = OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
}

13
relay/channel/openai/relay-openai.go
View File

@@ -16,9 +16,10 @@ import (
"time"
)
func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*dto.OpenAIErrorWithStatusCode, string) {
func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*dto.OpenAIErrorWithStatusCode, string, int) {
//checkSensitive := constant.ShouldCheckCompletionSensitive()
var responseTextBuilder strings.Builder
toolCount := 0
scanner := bufio.NewScanner(resp.Body)
scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
if atEOF && len(data) == 0 {
@@ -69,6 +70,9 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*d
for _, choice := range streamResponse.Choices {
responseTextBuilder.WriteString(choice.Delta.Content)
if choice.Delta.ToolCalls != nil {
if len(choice.Delta.ToolCalls) > toolCount {
toolCount = len(choice.Delta.ToolCalls)
}
for _, tool := range choice.Delta.ToolCalls {
responseTextBuilder.WriteString(tool.Function.Name)
responseTextBuilder.WriteString(tool.Function.Arguments)
@@ -82,6 +86,9 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*d
for _, choice := range streamResponse.Choices {
responseTextBuilder.WriteString(choice.Delta.Content)
if choice.Delta.ToolCalls != nil {
if len(choice.Delta.ToolCalls) > toolCount {
toolCount = len(choice.Delta.ToolCalls)
}
for _, tool := range choice.Delta.ToolCalls {
responseTextBuilder.WriteString(tool.Function.Name)
responseTextBuilder.WriteString(tool.Function.Arguments)
@@ -135,10 +142,10 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*d
})
err := resp.Body.Close()
if err != nil {
return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), "", toolCount
}
wg.Wait()
return nil, responseTextBuilder.String()
return nil, responseTextBuilder.String(), toolCount
}
func OpenaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {

2
relay/channel/perplexity/adaptor.go
View File

@@ -46,7 +46,7 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
if info.IsStream {
var responseText string
err, responseText = openai.OpenaiStreamHandler(c, resp, info.RelayMode)
err, responseText, _ = openai.OpenaiStreamHandler(c, resp, info.RelayMode)
usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
} else {
err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)

4
relay/channel/zhipu_4v/adaptor.go
View File

@@ -47,8 +47,10 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
if info.IsStream {
var responseText string
err, responseText = openai.OpenaiStreamHandler(c, resp, info.RelayMode)
var toolCount int
err, responseText, toolCount = openai.OpenaiStreamHandler(c, resp, info.RelayMode)
usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
usage.CompletionTokens += toolCount * 7
} else {
err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
}

2
relay/relay-text.go
View File

@@ -189,7 +189,7 @@ func getPromptTokens(textRequest *dto.GeneralOpenAIRequest, info *relaycommon.Re
checkSensitive := constant.ShouldCheckPromptSensitive()
switch info.RelayMode {
case relayconstant.RelayModeChatCompletions:
promptTokens, err, sensitiveTrigger = service.CountTokenMessages(textRequest.Messages, textRequest.Model, checkSensitive)
promptTokens, err, sensitiveTrigger = service.CountTokenChatRequest(*textRequest, textRequest.Model, checkSensitive)
case relayconstant.RelayModeCompletions:
promptTokens, err, sensitiveTrigger = service.CountTokenInput(textRequest.Prompt, textRequest.Model, checkSensitive)
case relayconstant.RelayModeModerations: