oadmin/new-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Improve embedding request handling and support across channels

Browse Source 
- Update EmbeddingRequest DTO to support more flexible input types
- Add input parsing method to handle various input formats
- Implement ConvertEmbeddingRequest for multiple channel adaptors
- Remove relayMode parameter from EmbeddingHelper
- Add input validation for embedding requests
- Simplify embedding request conversion for different channels
This commit is contained in:
1808837298@qq.com
2025-02-12 14:39:36 +08:00
parent eceb6afcdd
commit f5e3063f33
14 changed files with 84 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
relay/channel/ali/adaptor.go
View File

@@ -49,9 +49,6 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
return nil, errors.New("request is nil")
}
switch info.RelayMode {
case constant.RelayModeEmbeddings:
baiduEmbeddingRequest := embeddingRequestOpenAI2Ali(*request)
return baiduEmbeddingRequest, nil
default:
aliReq := requestOpenAI2Ali(*request)
return aliReq, nil
@@ -68,8 +65,7 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
}
func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
//TODO implement me
return nil, errors.New("not implemented")
return embeddingRequestOpenAI2Ali(request), nil
}
func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {

7
relay/channel/ali/text.go
View File

@@ -25,9 +25,12 @@ func requestOpenAI2Ali(request dto.GeneralOpenAIRequest) *dto.GeneralOpenAIReque
return &request
}
func embeddingRequestOpenAI2Ali(request dto.GeneralOpenAIRequest) *AliEmbeddingRequest {
func embeddingRequestOpenAI2Ali(request dto.EmbeddingRequest) *AliEmbeddingRequest {
if request.Model == "" {
request.Model = "text-embedding-v1"
}
return &AliEmbeddingRequest{
Model: "text-embedding-v1",
Model: request.Model,
Input: struct {
Texts []string `json:"texts"`
}{

7
relay/channel/baidu/adaptor.go
View File

@@ -109,9 +109,6 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
return nil, errors.New("request is nil")
}
switch info.RelayMode {
case constant.RelayModeEmbeddings:
baiduEmbeddingRequest := embeddingRequestOpenAI2Baidu(*request)
return baiduEmbeddingRequest, nil
default:
baiduRequest := requestOpenAI2Baidu(*request)
return baiduRequest, nil
@@ -123,8 +120,8 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
}
func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
//TODO implement me
return nil, errors.New("not implemented")
baiduEmbeddingRequest := embeddingRequestOpenAI2Baidu(request)
return baiduEmbeddingRequest, nil
}
func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {

2
relay/channel/baidu/relay-baidu.go
View File

@@ -87,7 +87,7 @@ func streamResponseBaidu2OpenAI(baiduResponse *BaiduChatStreamResponse) *dto.Cha
return &response
}
func embeddingRequestOpenAI2Baidu(request dto.GeneralOpenAIRequest) *BaiduEmbeddingRequest {
func embeddingRequestOpenAI2Baidu(request dto.EmbeddingRequest) *BaiduEmbeddingRequest {
return &BaiduEmbeddingRequest{
Input: request.ParseInput(),
}

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

@@ -57,11 +57,9 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
}
func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
//TODO implement me
return nil, errors.New("not implemented")
return request, nil
}
func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
// 添加文件字段
file, _, err := c.Request.FormFile("file")

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

@@ -56,11 +56,9 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
}
func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
//TODO implement me
return nil, errors.New("not implemented")
return request, nil
}
func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
if info.RelayMode == constant.RelayModeRerank {
err, usage = jinaRerankHandler(c, resp)

11
relay/channel/ollama/adaptor.go
View File

@@ -46,12 +46,7 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
if request == nil {
return nil, errors.New("request is nil")
}
switch info.RelayMode {
case relayconstant.RelayModeEmbeddings:
return requestOpenAI2Embeddings(*request), nil
default:
return requestOpenAI2Ollama(*request), nil
}
return requestOpenAI2Ollama(*request), nil
}
func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
@@ -59,11 +54,9 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
}
func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
//TODO implement me
return nil, errors.New("not implemented")
return requestOpenAI2Embeddings(request), nil
}
func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
return channel.DoApiRequest(a, c, info, requestBody)
}

12
relay/channel/ollama/relay-ollama.go
View File

@@ -42,7 +42,7 @@ func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) *OllamaRequest {
}
}
func requestOpenAI2Embeddings(request dto.GeneralOpenAIRequest) *OllamaEmbeddingRequest {
func requestOpenAI2Embeddings(request dto.EmbeddingRequest) *OllamaEmbeddingRequest {
return &OllamaEmbeddingRequest{
Model: request.Model,
Input: request.ParseInput(),
@@ -123,9 +123,9 @@ func ollamaEmbeddingHandler(c *gin.Context, resp *http.Response, promptTokens in
}
func flattenEmbeddings(embeddings [][]float64) []float64 {
flattened := []float64{}
for _, row := range embeddings {
flattened = append(flattened, row...)
flattened := []float64{}
for _, row := range embeddings {
flattened = append(flattened, row...)
}
return flattened
}
return flattened
}

3
relay/channel/openai/adaptor.go
View File

@@ -150,8 +150,7 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
}
func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
//TODO implement me
return nil, errors.New("not implemented")
return request, nil
}
func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {

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

@@ -59,11 +59,9 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
}
func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
//TODO implement me
return nil, errors.New("not implemented")
return request, nil
}
func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
switch info.RelayMode {
case constant.RelayModeRerank:

34
relay/relay_embedding.go
View File

@@ -19,7 +19,20 @@ func getEmbeddingPromptToken(embeddingRequest dto.EmbeddingRequest) int {
return token
}
func EmbeddingHelper(c *gin.Context, relayMode int) (openaiErr *dto.OpenAIErrorWithStatusCode) {
func validateEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, embeddingRequest dto.EmbeddingRequest) error {
if embeddingRequest.Input == nil {
return fmt.Errorf("input is empty")
}
if info.RelayMode == relayconstant.RelayModeModerations && embeddingRequest.Model == "" {
embeddingRequest.Model = "omni-moderation-latest"
}
if info.RelayMode == relayconstant.RelayModeEmbeddings && embeddingRequest.Model == "" {
embeddingRequest.Model = c.Param("model")
}
return nil
}
func EmbeddingHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
relayInfo := relaycommon.GenRelayInfo(c)
var embeddingRequest *dto.EmbeddingRequest
@@ -28,15 +41,12 @@ func EmbeddingHelper(c *gin.Context, relayMode int) (openaiErr *dto.OpenAIErrorW
common.LogError(c, fmt.Sprintf("getAndValidateTextRequest failed: %s", err.Error()))
return service.OpenAIErrorWrapperLocal(err, "invalid_text_request", http.StatusBadRequest)
}
if relayMode == relayconstant.RelayModeModerations && embeddingRequest.Model == "" {
embeddingRequest.Model = "m3e-base"
}
if relayMode == relayconstant.RelayModeEmbeddings && embeddingRequest.Model == "" {
embeddingRequest.Model = c.Param("model")
}
if embeddingRequest.Input == nil || len(embeddingRequest.Input) == 0 {
return service.OpenAIErrorWrapperLocal(fmt.Errorf("input is empty"), "invalid_input", http.StatusBadRequest)
err = validateEmbeddingRequest(c, relayInfo, *embeddingRequest)
if err != nil {
return service.OpenAIErrorWrapperLocal(err, "invalid_embedding_request", http.StatusBadRequest)
}
// map model name
modelMapping := c.GetString("model_mapping")
//isModelMapped := false
@@ -89,8 +99,8 @@ func EmbeddingHelper(c *gin.Context, relayMode int) (openaiErr *dto.OpenAIErrorW
}
adaptor.Init(relayInfo)
convertedRequest, err := adaptor.ConvertEmbeddingRequest(c,relayInfo,*embeddingRequest)
convertedRequest, err := adaptor.ConvertEmbeddingRequest(c, relayInfo, *embeddingRequest)
if err != nil {
return service.OpenAIErrorWrapperLocal(err, "convert_request_failed", http.StatusInternalServerError)
}
@@ -100,7 +110,7 @@ func EmbeddingHelper(c *gin.Context, relayMode int) (openaiErr *dto.OpenAIErrorW
}
requestBody := bytes.NewBuffer(jsonData)
statusCodeMappingStr := c.GetString("status_code_mapping")
resp, err := adaptor.DoRequest(c,relayInfo, requestBody)
resp, err := adaptor.DoRequest(c, relayInfo, requestBody)
if err != nil {
return service.OpenAIErrorWrapper(err, "do_request_failed", http.StatusInternalServerError)
}