mirror of
https://github.com/QuantumNous/new-api.git
synced 2026-03-30 15:46:44 +00:00
Compare commits
5 Commits
v0.2.7.1-a
...
v0.2.7.1-a
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
e062cf32e3 | ||
|
|
52debe7572 | ||
|
|
df6502733c | ||
|
|
9896ba0a64 | ||
|
|
e8b93ed6ec |
@@ -102,6 +102,7 @@ type ChatCompletionsStreamResponse struct {
|
||||
Model string `json:"model"`
|
||||
SystemFingerprint *string `json:"system_fingerprint"`
|
||||
Choices []ChatCompletionsStreamResponseChoice `json:"choices"`
|
||||
Usage *Usage `json:"usage"`
|
||||
}
|
||||
|
||||
type ChatCompletionsStreamResponseSimple struct {
|
||||
|
||||
@@ -68,7 +68,7 @@ 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 {
|
||||
err, usage = awsStreamHandler(c, info, a.RequestMode)
|
||||
err, usage = awsStreamHandler(c, resp, info, a.RequestMode)
|
||||
} else {
|
||||
err, usage = awsHandler(c, info, a.RequestMode)
|
||||
}
|
||||
|
||||
@@ -13,6 +13,7 @@ import (
|
||||
relaymodel "one-api/dto"
|
||||
"one-api/relay/channel/claude"
|
||||
relaycommon "one-api/relay/common"
|
||||
"one-api/service"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
@@ -112,7 +113,7 @@ func awsHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode int) (*
|
||||
return nil, &usage
|
||||
}
|
||||
|
||||
func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode int) (*relaymodel.OpenAIErrorWithStatusCode, *relaymodel.Usage) {
|
||||
func awsStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, requestMode int) (*relaymodel.OpenAIErrorWithStatusCode, *relaymodel.Usage) {
|
||||
awsCli, err := newAwsClient(c, info)
|
||||
if err != nil {
|
||||
return wrapErr(errors.Wrap(err, "newAwsClient")), nil
|
||||
@@ -162,7 +163,6 @@ func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode i
|
||||
c.Stream(func(w io.Writer) bool {
|
||||
event, ok := <-stream.Events()
|
||||
if !ok {
|
||||
c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
|
||||
return false
|
||||
}
|
||||
|
||||
@@ -214,6 +214,17 @@ func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode i
|
||||
return false
|
||||
}
|
||||
})
|
||||
|
||||
if info.ShouldIncludeUsage {
|
||||
response := service.GenerateFinalUsageResponse(id, createdTime, info.UpstreamModelName, usage)
|
||||
err := service.ObjectData(c, response)
|
||||
if err != nil {
|
||||
common.SysError("send final response failed: " + err.Error())
|
||||
}
|
||||
}
|
||||
service.Done(c)
|
||||
err = resp.Body.Close()
|
||||
if err != nil {
|
||||
return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil
|
||||
}
|
||||
return nil, &usage
|
||||
}
|
||||
|
||||
@@ -330,22 +330,15 @@ func claudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
|
||||
response.Created = createdTime
|
||||
response.Model = info.UpstreamModelName
|
||||
|
||||
jsonStr, err := json.Marshal(response)
|
||||
err = service.ObjectData(c, response)
|
||||
if err != nil {
|
||||
common.SysError("error marshalling stream response: " + err.Error())
|
||||
return true
|
||||
common.SysError(err.Error())
|
||||
}
|
||||
c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonStr)})
|
||||
return true
|
||||
case <-stopChan:
|
||||
c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
|
||||
return false
|
||||
}
|
||||
})
|
||||
err := resp.Body.Close()
|
||||
if err != nil {
|
||||
return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
|
||||
}
|
||||
if requestMode == RequestModeCompletion {
|
||||
usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
|
||||
} else {
|
||||
@@ -356,6 +349,18 @@ func claudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
|
||||
usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, usage.PromptTokens)
|
||||
}
|
||||
}
|
||||
if info.ShouldIncludeUsage {
|
||||
response := service.GenerateFinalUsageResponse(responseId, createdTime, info.UpstreamModelName, *usage)
|
||||
err := service.ObjectData(c, response)
|
||||
if err != nil {
|
||||
common.SysError("send final response failed: " + err.Error())
|
||||
}
|
||||
}
|
||||
service.Done(c)
|
||||
err := resp.Body.Close()
|
||||
if err != nil {
|
||||
return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil
|
||||
}
|
||||
return nil, usage
|
||||
}
|
||||
|
||||
|
||||
@@ -7,7 +7,6 @@ import (
|
||||
"io"
|
||||
"net/http"
|
||||
"one-api/common"
|
||||
"one-api/constant"
|
||||
"one-api/dto"
|
||||
"one-api/relay/channel"
|
||||
"one-api/relay/channel/ai360"
|
||||
@@ -20,8 +19,7 @@ import (
|
||||
)
|
||||
|
||||
type Adaptor struct {
|
||||
ChannelType int
|
||||
SupportStreamOptions bool
|
||||
ChannelType int
|
||||
}
|
||||
|
||||
func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
|
||||
@@ -33,7 +31,6 @@ func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequ
|
||||
|
||||
func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
|
||||
a.ChannelType = info.ChannelType
|
||||
a.SupportStreamOptions = info.SupportStreamOptions
|
||||
}
|
||||
|
||||
func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
|
||||
@@ -81,17 +78,6 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
|
||||
if request == nil {
|
||||
return nil, errors.New("request is nil")
|
||||
}
|
||||
// 如果不支持StreamOptions,将StreamOptions设置为nil
|
||||
if !a.SupportStreamOptions {
|
||||
request.StreamOptions = nil
|
||||
} else {
|
||||
// 如果支持StreamOptions,且请求中没有设置StreamOptions,根据配置文件设置StreamOptions
|
||||
if constant.ForceStreamOption {
|
||||
request.StreamOptions = &dto.StreamOptions{
|
||||
IncludeUsage: true,
|
||||
}
|
||||
}
|
||||
}
|
||||
return request, nil
|
||||
}
|
||||
|
||||
|
||||
@@ -28,6 +28,7 @@ type RelayInfo struct {
|
||||
Organization string
|
||||
BaseUrl string
|
||||
SupportStreamOptions bool
|
||||
ShouldIncludeUsage bool
|
||||
}
|
||||
|
||||
func GenRelayInfo(c *gin.Context) *RelayInfo {
|
||||
@@ -66,7 +67,7 @@ func GenRelayInfo(c *gin.Context) *RelayInfo {
|
||||
if info.ChannelType == common.ChannelTypeAzure {
|
||||
info.ApiVersion = GetAPIVersion(c)
|
||||
}
|
||||
if info.ChannelType == common.ChannelTypeOpenAI {
|
||||
if info.ChannelType == common.ChannelTypeOpenAI || info.ChannelType == common.ChannelTypeAnthropic || info.ChannelType == common.ChannelTypeAws {
|
||||
info.SupportStreamOptions = true
|
||||
}
|
||||
return info
|
||||
|
||||
@@ -130,6 +130,22 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
|
||||
return openaiErr
|
||||
}
|
||||
|
||||
// 如果不支持StreamOptions,将StreamOptions设置为nil
|
||||
if !relayInfo.SupportStreamOptions || !textRequest.Stream {
|
||||
textRequest.StreamOptions = nil
|
||||
} else {
|
||||
// 如果支持StreamOptions,且请求中没有设置StreamOptions,根据配置文件设置StreamOptions
|
||||
if constant.ForceStreamOption {
|
||||
textRequest.StreamOptions = &dto.StreamOptions{
|
||||
IncludeUsage: true,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if textRequest.StreamOptions != nil && textRequest.StreamOptions.IncludeUsage {
|
||||
relayInfo.ShouldIncludeUsage = textRequest.StreamOptions.IncludeUsage
|
||||
}
|
||||
|
||||
adaptor := GetAdaptor(relayInfo.ApiType)
|
||||
if adaptor == nil {
|
||||
return service.OpenAIErrorWrapperLocal(fmt.Errorf("invalid api type: %d", relayInfo.ApiType), "invalid_api_type", http.StatusBadRequest)
|
||||
|
||||
@@ -24,3 +24,15 @@ func ResponseText2Usage(responseText string, modeName string, promptTokens int)
|
||||
usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
|
||||
return usage, err
|
||||
}
|
||||
|
||||
func GenerateFinalUsageResponse(id string, createAt int64, model string, usage dto.Usage) *dto.ChatCompletionsStreamResponse {
|
||||
return &dto.ChatCompletionsStreamResponse{
|
||||
Id: id,
|
||||
Object: "chat.completion.chunk",
|
||||
Created: createAt,
|
||||
Model: model,
|
||||
SystemFingerprint: nil,
|
||||
Choices: nil,
|
||||
Usage: &usage,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -153,8 +153,8 @@ export function renderModelPrice(
|
||||
let inputRatioPrice = modelRatio * 2.0;
|
||||
let completionRatioPrice = modelRatio * 2.0 * completionRatio;
|
||||
let price =
|
||||
(inputTokens / 1000000) * inputRatioPrice +
|
||||
(completionTokens / 1000000) * completionRatioPrice;
|
||||
(inputTokens / 1000000) * inputRatioPrice * groupRatio +
|
||||
(completionTokens / 1000000) * completionRatioPrice * groupRatio;
|
||||
return (
|
||||
<>
|
||||
<article>
|
||||
|
||||
Reference in New Issue
Block a user