Files
new-api/relay/channel/ali/rerank.go
CaIon e2037ad756 refactor: Introduce pre-consume quota and unify relay handlers
This commit introduces a major architectural refactoring to improve quota management, centralize logging, and streamline the relay handling logic.

Key changes:
- **Pre-consume Quota:** Implements a new mechanism to check and reserve user quota *before* making the request to the upstream provider. This ensures more accurate quota deduction and prevents users from exceeding their limits due to concurrent requests.

- **Unified Relay Handlers:** Refactors the relay logic to use generic handlers (e.g., `ChatHandler`, `ImageHandler`) instead of provider-specific implementations. This significantly reduces code duplication and simplifies adding new channels.

- **Centralized Logger:** A new dedicated `logger` package is introduced, and all system logging calls are migrated to use it, moving this responsibility out of the `common` package.

- **Code Reorganization:** DTOs are generalized (e.g., `dalle.go` -> `openai_image.go`) and utility code is moved to more appropriate packages (e.g., `common/http.go` -> `service/http.go`) for better code structure.
2025-08-14 20:05:06 +08:00

75 lines
1.9 KiB
Go

package ali
import (
"encoding/json"
"io"
"net/http"
"one-api/dto"
relaycommon "one-api/relay/common"
"one-api/service"
"one-api/types"
"github.com/gin-gonic/gin"
)
func ConvertRerankRequest(request dto.RerankRequest) *AliRerankRequest {
returnDocuments := request.ReturnDocuments
if returnDocuments == nil {
t := true
returnDocuments = &t
}
return &AliRerankRequest{
Model: request.Model,
Input: AliRerankInput{
Query: request.Query,
Documents: request.Documents,
},
Parameters: AliRerankParameters{
TopN: &request.TopN,
ReturnDocuments: returnDocuments,
},
}
}
func RerankHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*types.NewAPIError, *dto.Usage) {
responseBody, err := io.ReadAll(resp.Body)
if err != nil {
return types.NewOpenAIError(err, types.ErrorCodeReadResponseBodyFailed, http.StatusInternalServerError), nil
}
service.CloseResponseBodyGracefully(resp)
var aliResponse AliRerankResponse
err = json.Unmarshal(responseBody, &aliResponse)
if err != nil {
return types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError), nil
}
if aliResponse.Code != "" {
return types.WithOpenAIError(types.OpenAIError{
Message: aliResponse.Message,
Type: aliResponse.Code,
Param: aliResponse.RequestId,
Code: aliResponse.Code,
}, resp.StatusCode), nil
}
usage := dto.Usage{
PromptTokens: aliResponse.Usage.TotalTokens,
CompletionTokens: 0,
TotalTokens: aliResponse.Usage.TotalTokens,
}
rerankResponse := dto.RerankResponse{
Results: aliResponse.Output.Results,
Usage: usage,
}
jsonResponse, err := json.Marshal(rerankResponse)
if err != nil {
return types.NewError(err, types.ErrorCodeBadResponseBody), nil
}
c.Writer.Header().Set("Content-Type", "application/json")
c.Writer.WriteHeader(resp.StatusCode)
c.Writer.Write(jsonResponse)
return nil, &usage
}