Files
new-api/relay/channel/palm/relay-palm.go
CaIon f5b409d74f feat: refactor token estimation logic
- 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.
2025-12-02 21:34:39 +08:00

135 lines
4.4 KiB
Go

package palm
import (
"encoding/json"
"io"
"net/http"
"github.com/QuantumNous/new-api/common"
"github.com/QuantumNous/new-api/constant"
"github.com/QuantumNous/new-api/dto"
relaycommon "github.com/QuantumNous/new-api/relay/common"
"github.com/QuantumNous/new-api/relay/helper"
"github.com/QuantumNous/new-api/service"
"github.com/QuantumNous/new-api/types"
"github.com/gin-gonic/gin"
)
// https://developers.generativeai.google/api/rest/generativelanguage/models/generateMessage#request-body
// https://developers.generativeai.google/api/rest/generativelanguage/models/generateMessage#response-body
func responsePaLM2OpenAI(response *PaLMChatResponse) *dto.OpenAITextResponse {
fullTextResponse := dto.OpenAITextResponse{
Choices: make([]dto.OpenAITextResponseChoice, 0, len(response.Candidates)),
}
for i, candidate := range response.Candidates {
choice := dto.OpenAITextResponseChoice{
Index: i,
Message: dto.Message{
Role: "assistant",
Content: candidate.Content,
},
FinishReason: "stop",
}
fullTextResponse.Choices = append(fullTextResponse.Choices, choice)
}
return &fullTextResponse
}
func streamResponsePaLM2OpenAI(palmResponse *PaLMChatResponse) *dto.ChatCompletionsStreamResponse {
var choice dto.ChatCompletionsStreamResponseChoice
if len(palmResponse.Candidates) > 0 {
choice.Delta.SetContentString(palmResponse.Candidates[0].Content)
}
choice.FinishReason = &constant.FinishReasonStop
var response dto.ChatCompletionsStreamResponse
response.Object = "chat.completion.chunk"
response.Model = "palm2"
response.Choices = []dto.ChatCompletionsStreamResponseChoice{choice}
return &response
}
func palmStreamHandler(c *gin.Context, resp *http.Response) (*types.NewAPIError, string) {
responseText := ""
responseId := helper.GetResponseID(c)
createdTime := common.GetTimestamp()
dataChan := make(chan string)
stopChan := make(chan bool)
go func() {
responseBody, err := io.ReadAll(resp.Body)
if err != nil {
common.SysLog("error reading stream response: " + err.Error())
stopChan <- true
return
}
service.CloseResponseBodyGracefully(resp)
var palmResponse PaLMChatResponse
err = json.Unmarshal(responseBody, &palmResponse)
if err != nil {
common.SysLog("error unmarshalling stream response: " + err.Error())
stopChan <- true
return
}
fullTextResponse := streamResponsePaLM2OpenAI(&palmResponse)
fullTextResponse.Id = responseId
fullTextResponse.Created = createdTime
if len(palmResponse.Candidates) > 0 {
responseText = palmResponse.Candidates[0].Content
}
jsonResponse, err := json.Marshal(fullTextResponse)
if err != nil {
common.SysLog("error marshalling stream response: " + err.Error())
stopChan <- true
return
}
dataChan <- string(jsonResponse)
stopChan <- true
}()
helper.SetEventStreamHeaders(c)
c.Stream(func(w io.Writer) bool {
select {
case data := <-dataChan:
c.Render(-1, common.CustomEvent{Data: "data: " + data})
return true
case <-stopChan:
c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
return false
}
})
service.CloseResponseBodyGracefully(resp)
return nil, responseText
}
func palmHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
responseBody, err := io.ReadAll(resp.Body)
if err != nil {
return nil, types.NewOpenAIError(err, types.ErrorCodeReadResponseBodyFailed, http.StatusInternalServerError)
}
service.CloseResponseBodyGracefully(resp)
var palmResponse PaLMChatResponse
err = json.Unmarshal(responseBody, &palmResponse)
if err != nil {
return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
}
if palmResponse.Error.Code != 0 || len(palmResponse.Candidates) == 0 {
return nil, types.WithOpenAIError(types.OpenAIError{
Message: palmResponse.Error.Message,
Type: palmResponse.Error.Status,
Param: "",
Code: palmResponse.Error.Code,
}, resp.StatusCode)
}
fullTextResponse := responsePaLM2OpenAI(&palmResponse)
usage := service.ResponseText2Usage(c, palmResponse.Candidates[0].Content, info.UpstreamModelName, info.GetEstimatePromptTokens())
fullTextResponse.Usage = *usage
jsonResponse, err := common.Marshal(fullTextResponse)
if err != nil {
return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
}
c.Writer.Header().Set("Content-Type", "application/json")
c.Writer.WriteHeader(resp.StatusCode)
service.IOCopyBytesGracefully(c, resp, jsonResponse)
return usage, nil
}