Files
new-api/relay/rerank_handler.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

108 lines
3.3 KiB
Go

package relay
import (
"bytes"
"fmt"
"io"
"net/http"
"one-api/common"
"one-api/dto"
relaycommon "one-api/relay/common"
"one-api/relay/helper"
"one-api/service"
"one-api/setting/model_setting"
"one-api/types"
"github.com/gin-gonic/gin"
)
func getRerankPromptToken(rerankRequest dto.RerankRequest) int {
token := service.CountTokenInput(rerankRequest.Query, rerankRequest.Model)
for _, document := range rerankRequest.Documents {
tkm := service.CountTokenInput(document, rerankRequest.Model)
token += tkm
}
return token
}
func RerankHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *types.NewAPIError) {
rerankRequest, ok := info.Request.(*dto.RerankRequest)
if !ok {
common.FatalLog(fmt.Sprintf("invalid request type, expected dto.RerankRequest, got %T", info.Request))
}
err := helper.ModelMappedHelper(c, info, rerankRequest)
if err != nil {
return types.NewError(err, types.ErrorCodeChannelModelMappedError, types.ErrOptionWithSkipRetry())
}
adaptor := GetAdaptor(info.ApiType)
if adaptor == nil {
return types.NewError(fmt.Errorf("invalid api type: %d", info.ApiType), types.ErrorCodeInvalidApiType, types.ErrOptionWithSkipRetry())
}
adaptor.Init(info)
var requestBody io.Reader
if model_setting.GetGlobalSettings().PassThroughRequestEnabled || info.ChannelSetting.PassThroughBodyEnabled {
body, err := common.GetRequestBody(c)
if err != nil {
return types.NewErrorWithStatusCode(err, types.ErrorCodeReadRequestBodyFailed, http.StatusBadRequest, types.ErrOptionWithSkipRetry())
}
requestBody = bytes.NewBuffer(body)
} else {
convertedRequest, err := adaptor.ConvertRerankRequest(c, info.RelayMode, *rerankRequest)
if err != nil {
return types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
}
jsonData, err := common.Marshal(convertedRequest)
if err != nil {
return types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
}
// apply param override
if len(info.ParamOverride) > 0 {
reqMap := make(map[string]interface{})
_ = common.Unmarshal(jsonData, &reqMap)
for key, value := range info.ParamOverride {
reqMap[key] = value
}
jsonData, err = common.Marshal(reqMap)
if err != nil {
return types.NewError(err, types.ErrorCodeChannelParamOverrideInvalid, types.ErrOptionWithSkipRetry())
}
}
if common.DebugEnabled {
println(fmt.Sprintf("Rerank request body: %s", string(jsonData)))
}
requestBody = bytes.NewBuffer(jsonData)
}
resp, err := adaptor.DoRequest(c, info, requestBody)
if err != nil {
return types.NewOpenAIError(err, types.ErrorCodeDoRequestFailed, http.StatusInternalServerError)
}
statusCodeMappingStr := c.GetString("status_code_mapping")
var httpResp *http.Response
if resp != nil {
httpResp = resp.(*http.Response)
if httpResp.StatusCode != http.StatusOK {
newAPIError = service.RelayErrorHandler(httpResp, false)
// reset status code 重置状态码
service.ResetStatusCode(newAPIError, statusCodeMappingStr)
return newAPIError
}
}
usage, newAPIError := adaptor.DoResponse(c, httpResp, info)
if newAPIError != nil {
// reset status code 重置状态码
service.ResetStatusCode(newAPIError, statusCodeMappingStr)
return newAPIError
}
postConsumeQuota(c, info, usage.(*dto.Usage), "")
return nil
}