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

feat: convert gemini format to openai chat completions

Browse Source
This commit is contained in:
creamlike1024
2025-08-01 22:23:35 +08:00
parent 9758a9e60d
commit d2183af23f
36 changed files with 648 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
relay/channel/gemini/adaptor.go
View File

@@ -20,6 +20,10 @@ import (
type Adaptor struct {
}
func (a *Adaptor) ConvertGeminiRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeminiChatRequest) (any, error) {
return request, nil
}
func (a *Adaptor) ConvertClaudeRequest(c *gin.Context, info *relaycommon.RelayInfo, req *dto.ClaudeRequest) (any, error) {
adaptor := openai.Adaptor{}
oaiReq, err := adaptor.ConvertClaudeRequest(c, info, req)
@@ -51,13 +55,13 @@ func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInf
}
// build gemini imagen request
geminiRequest := GeminiImageRequest{
Instances: []GeminiImageInstance{
geminiRequest := dto.GeminiImageRequest{
Instances: []dto.GeminiImageInstance{
{
Prompt: request.Prompt,
},
},
Parameters: GeminiImageParameters{
Parameters: dto.GeminiImageParameters{
SampleCount: request.N,
AspectRatio: aspectRatio,
PersonGeneration: "allow_adult", // default allow adult
@@ -138,9 +142,9 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
}
// only process the first input
geminiRequest := GeminiEmbeddingRequest{
Content: GeminiChatContent{
Parts: []GeminiPart{
geminiRequest := dto.GeminiEmbeddingRequest{
Content: dto.GeminiChatContent{
Parts: []dto.GeminiPart{
{
Text: inputs[0],
},

225
relay/channel/gemini/dto.go
View File

@@ -1,225 +0,0 @@
package gemini
import (
"encoding/json"
"one-api/common"
)
type GeminiChatRequest struct {
Contents []GeminiChatContent `json:"contents"`
SafetySettings []GeminiChatSafetySettings `json:"safetySettings,omitempty"`
GenerationConfig GeminiChatGenerationConfig `json:"generationConfig,omitempty"`
Tools []GeminiChatTool `json:"tools,omitempty"`
SystemInstructions *GeminiChatContent `json:"systemInstruction,omitempty"`
}
type GeminiThinkingConfig struct {
IncludeThoughts bool `json:"includeThoughts,omitempty"`
ThinkingBudget *int `json:"thinkingBudget,omitempty"`
}
func (c *GeminiThinkingConfig) SetThinkingBudget(budget int) {
c.ThinkingBudget = &budget
}
type GeminiInlineData struct {
MimeType string `json:"mimeType"`
Data string `json:"data"`
}
// UnmarshalJSON custom unmarshaler for GeminiInlineData to support snake_case and camelCase for MimeType
func (g *GeminiInlineData) UnmarshalJSON(data []byte) error {
type Alias GeminiInlineData // Use type alias to avoid recursion
var aux struct {
Alias
MimeTypeSnake string `json:"mime_type"`
}
if err := common.Unmarshal(data, &aux); err != nil {
return err
}
*g = GeminiInlineData(aux.Alias) // Copy other fields if any in future
// Prioritize snake_case if present
if aux.MimeTypeSnake != "" {
g.MimeType = aux.MimeTypeSnake
} else if aux.MimeType != "" { // Fallback to camelCase from Alias
g.MimeType = aux.MimeType
}
// g.Data would be populated by aux.Alias.Data
return nil
}
type FunctionCall struct {
FunctionName string `json:"name"`
Arguments any `json:"args"`
}
type FunctionResponse struct {
Name string `json:"name"`
Response map[string]interface{} `json:"response"`
}
type GeminiPartExecutableCode struct {
Language string `json:"language,omitempty"`
Code string `json:"code,omitempty"`
}
type GeminiPartCodeExecutionResult struct {
Outcome string `json:"outcome,omitempty"`
Output string `json:"output,omitempty"`
}
type GeminiFileData struct {
MimeType string `json:"mimeType,omitempty"`
FileUri string `json:"fileUri,omitempty"`
}
type GeminiPart struct {
Text string `json:"text,omitempty"`
Thought bool `json:"thought,omitempty"`
InlineData *GeminiInlineData `json:"inlineData,omitempty"`
FunctionCall *FunctionCall `json:"functionCall,omitempty"`
FunctionResponse *FunctionResponse `json:"functionResponse,omitempty"`
FileData *GeminiFileData `json:"fileData,omitempty"`
ExecutableCode *GeminiPartExecutableCode `json:"executableCode,omitempty"`
CodeExecutionResult *GeminiPartCodeExecutionResult `json:"codeExecutionResult,omitempty"`
}
// UnmarshalJSON custom unmarshaler for GeminiPart to support snake_case and camelCase for InlineData
func (p *GeminiPart) UnmarshalJSON(data []byte) error {
// Alias to avoid recursion during unmarshalling
type Alias GeminiPart
var aux struct {
Alias
InlineDataSnake *GeminiInlineData `json:"inline_data,omitempty"` // snake_case variant
}
if err := common.Unmarshal(data, &aux); err != nil {
return err
}
// Assign fields from alias
*p = GeminiPart(aux.Alias)
// Prioritize snake_case for InlineData if present
if aux.InlineDataSnake != nil {
p.InlineData = aux.InlineDataSnake
} else if aux.InlineData != nil { // Fallback to camelCase from Alias
p.InlineData = aux.InlineData
}
// Other fields like Text, FunctionCall etc. are already populated via aux.Alias
return nil
}
type GeminiChatContent struct {
Role string `json:"role,omitempty"`
Parts []GeminiPart `json:"parts"`
}
type GeminiChatSafetySettings struct {
Category string `json:"category"`
Threshold string `json:"threshold"`
}
type GeminiChatTool struct {
GoogleSearch any `json:"googleSearch,omitempty"`
GoogleSearchRetrieval any `json:"googleSearchRetrieval,omitempty"`
CodeExecution any `json:"codeExecution,omitempty"`
FunctionDeclarations any `json:"functionDeclarations,omitempty"`
}
type GeminiChatGenerationConfig struct {
Temperature *float64 `json:"temperature,omitempty"`
TopP float64 `json:"topP,omitempty"`
TopK float64 `json:"topK,omitempty"`
MaxOutputTokens uint `json:"maxOutputTokens,omitempty"`
CandidateCount int `json:"candidateCount,omitempty"`
StopSequences []string `json:"stopSequences,omitempty"`
ResponseMimeType string `json:"responseMimeType,omitempty"`
ResponseSchema any `json:"responseSchema,omitempty"`
Seed int64 `json:"seed,omitempty"`
ResponseModalities []string `json:"responseModalities,omitempty"`
ThinkingConfig *GeminiThinkingConfig `json:"thinkingConfig,omitempty"`
SpeechConfig json.RawMessage `json:"speechConfig,omitempty"` // RawMessage to allow flexible speech config
}
type GeminiChatCandidate struct {
Content GeminiChatContent `json:"content"`
FinishReason *string `json:"finishReason"`
Index int64 `json:"index"`
SafetyRatings []GeminiChatSafetyRating `json:"safetyRatings"`
}
type GeminiChatSafetyRating struct {
Category string `json:"category"`
Probability string `json:"probability"`
}
type GeminiChatPromptFeedback struct {
SafetyRatings []GeminiChatSafetyRating `json:"safetyRatings"`
}
type GeminiChatResponse struct {
Candidates []GeminiChatCandidate `json:"candidates"`
PromptFeedback GeminiChatPromptFeedback `json:"promptFeedback"`
UsageMetadata GeminiUsageMetadata `json:"usageMetadata"`
}
type GeminiUsageMetadata struct {
PromptTokenCount int `json:"promptTokenCount"`
CandidatesTokenCount int `json:"candidatesTokenCount"`
TotalTokenCount int `json:"totalTokenCount"`
ThoughtsTokenCount int `json:"thoughtsTokenCount"`
PromptTokensDetails []GeminiPromptTokensDetails `json:"promptTokensDetails"`
}
type GeminiPromptTokensDetails struct {
Modality string `json:"modality"`
TokenCount int `json:"tokenCount"`
}
// Imagen related structs
type GeminiImageRequest struct {
Instances []GeminiImageInstance `json:"instances"`
Parameters GeminiImageParameters `json:"parameters"`
}
type GeminiImageInstance struct {
Prompt string `json:"prompt"`
}
type GeminiImageParameters struct {
SampleCount int `json:"sampleCount,omitempty"`
AspectRatio string `json:"aspectRatio,omitempty"`
PersonGeneration string `json:"personGeneration,omitempty"`
}
type GeminiImageResponse struct {
Predictions []GeminiImagePrediction `json:"predictions"`
}
type GeminiImagePrediction struct {
MimeType string `json:"mimeType"`
BytesBase64Encoded string `json:"bytesBase64Encoded"`
RaiFilteredReason string `json:"raiFilteredReason,omitempty"`
SafetyAttributes any `json:"safetyAttributes,omitempty"`
}
// Embedding related structs
type GeminiEmbeddingRequest struct {
Content GeminiChatContent `json:"content"`
TaskType string `json:"taskType,omitempty"`
Title string `json:"title,omitempty"`
OutputDimensionality int `json:"outputDimensionality,omitempty"`
}
type GeminiEmbeddingResponse struct {
Embedding ContentEmbedding `json:"embedding"`
}
type ContentEmbedding struct {
Values []float64 `json:"values"`
}

4
relay/channel/gemini/relay-gemini-native.go
View File

@@ -28,7 +28,7 @@ func GeminiTextGenerationHandler(c *gin.Context, info *relaycommon.RelayInfo, re
}
// 解析为 Gemini 原生响应格式
var geminiResponse GeminiChatResponse
var geminiResponse dto.GeminiChatResponse
err = common.Unmarshal(responseBody, &geminiResponse)
if err != nil {
return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
@@ -71,7 +71,7 @@ func GeminiTextGenerationStreamHandler(c *gin.Context, info *relaycommon.RelayIn
responseText := strings.Builder{}
helper.StreamScannerHandler(c, resp, info, func(data string) bool {
var geminiResponse GeminiChatResponse
var geminiResponse dto.GeminiChatResponse
err := common.UnmarshalJsonStr(data, &geminiResponse)
if err != nil {
common.LogError(c, "error unmarshalling stream response: "+err.Error())

78
relay/channel/gemini/relay-gemini.go
View File

@@ -81,7 +81,7 @@ func clampThinkingBudget(modelName string, budget int) int {
return budget
}
func ThinkingAdaptor(geminiRequest *GeminiChatRequest, info *relaycommon.RelayInfo) {
func ThinkingAdaptor(geminiRequest *dto.GeminiChatRequest, info *relaycommon.RelayInfo) {
if model_setting.GetGeminiSettings().ThinkingAdapterEnabled {
modelName := info.UpstreamModelName
isNew25Pro := strings.HasPrefix(modelName, "gemini-2.5-pro") &&
@@ -93,7 +93,7 @@ func ThinkingAdaptor(geminiRequest *GeminiChatRequest, info *relaycommon.RelayIn
if len(parts) == 2 && parts[1] != "" {
if budgetTokens, err := strconv.Atoi(parts[1]); err == nil {
clampedBudget := clampThinkingBudget(modelName, budgetTokens)
geminiRequest.GenerationConfig.ThinkingConfig = &GeminiThinkingConfig{
geminiRequest.GenerationConfig.ThinkingConfig = &dto.GeminiThinkingConfig{
ThinkingBudget: common.GetPointer(clampedBudget),
IncludeThoughts: true,
}
@@ -113,11 +113,11 @@ func ThinkingAdaptor(geminiRequest *GeminiChatRequest, info *relaycommon.RelayIn
}
if isUnsupported {
geminiRequest.GenerationConfig.ThinkingConfig = &GeminiThinkingConfig{
geminiRequest.GenerationConfig.ThinkingConfig = &dto.GeminiThinkingConfig{
IncludeThoughts: true,
}
} else {
geminiRequest.GenerationConfig.ThinkingConfig = &GeminiThinkingConfig{
geminiRequest.GenerationConfig.ThinkingConfig = &dto.GeminiThinkingConfig{
IncludeThoughts: true,
}
if geminiRequest.GenerationConfig.MaxOutputTokens > 0 {
@@ -128,7 +128,7 @@ func ThinkingAdaptor(geminiRequest *GeminiChatRequest, info *relaycommon.RelayIn
}
} else if strings.HasSuffix(modelName, "-nothinking") {
if !isNew25Pro {
geminiRequest.GenerationConfig.ThinkingConfig = &GeminiThinkingConfig{
geminiRequest.GenerationConfig.ThinkingConfig = &dto.GeminiThinkingConfig{
ThinkingBudget: common.GetPointer(0),
}
}
@@ -137,11 +137,11 @@ func ThinkingAdaptor(geminiRequest *GeminiChatRequest, info *relaycommon.RelayIn
}
// Setting safety to the lowest possible values since Gemini is already powerless enough
func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest, info *relaycommon.RelayInfo) (*GeminiChatRequest, error) {
func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest, info *relaycommon.RelayInfo) (*dto.GeminiChatRequest, error) {
geminiRequest := GeminiChatRequest{
Contents: make([]GeminiChatContent, 0, len(textRequest.Messages)),
GenerationConfig: GeminiChatGenerationConfig{
geminiRequest := dto.GeminiChatRequest{
Contents: make([]dto.GeminiChatContent, 0, len(textRequest.Messages)),
GenerationConfig: dto.GeminiChatGenerationConfig{
Temperature: textRequest.Temperature,
TopP: textRequest.TopP,
MaxOutputTokens: textRequest.MaxTokens,
@@ -158,9 +158,9 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest, info *relaycommon
ThinkingAdaptor(&geminiRequest, info)
safetySettings := make([]GeminiChatSafetySettings, 0, len(SafetySettingList))
safetySettings := make([]dto.GeminiChatSafetySettings, 0, len(SafetySettingList))
for _, category := range SafetySettingList {
safetySettings = append(safetySettings, GeminiChatSafetySettings{
safetySettings = append(safetySettings, dto.GeminiChatSafetySettings{
Category: category,
Threshold: model_setting.GetGeminiSafetySetting(category),
})
@@ -198,17 +198,17 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest, info *relaycommon
functions = append(functions, tool.Function)
}
if codeExecution {
geminiRequest.Tools = append(geminiRequest.Tools, GeminiChatTool{
geminiRequest.Tools = append(geminiRequest.Tools, dto.GeminiChatTool{
CodeExecution: make(map[string]string),
})
}
if googleSearch {
geminiRequest.Tools = append(geminiRequest.Tools, GeminiChatTool{
geminiRequest.Tools = append(geminiRequest.Tools, dto.GeminiChatTool{
GoogleSearch: make(map[string]string),
})
}
if len(functions) > 0 {
geminiRequest.Tools = append(geminiRequest.Tools, GeminiChatTool{
geminiRequest.Tools = append(geminiRequest.Tools, dto.GeminiChatTool{
FunctionDeclarations: functions,
})
}
@@ -238,7 +238,7 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest, info *relaycommon
continue
} else if message.Role == "tool" || message.Role == "function" {
if len(geminiRequest.Contents) == 0 || geminiRequest.Contents[len(geminiRequest.Contents)-1].Role == "model" {
geminiRequest.Contents = append(geminiRequest.Contents, GeminiChatContent{
geminiRequest.Contents = append(geminiRequest.Contents, dto.GeminiChatContent{
Role: "user",
})
}
@@ -265,18 +265,18 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest, info *relaycommon
}
}
functionResp := &FunctionResponse{
functionResp := &dto.GeminiFunctionResponse{
Name: name,
Response: contentMap,
}
*parts = append(*parts, GeminiPart{
*parts = append(*parts, dto.GeminiPart{
FunctionResponse: functionResp,
})
continue
}
var parts []GeminiPart
content := GeminiChatContent{
var parts []dto.GeminiPart
content := dto.GeminiChatContent{
Role: message.Role,
}
// isToolCall := false
@@ -290,8 +290,8 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest, info *relaycommon
return nil, fmt.Errorf("invalid arguments for function %s, args: %s", call.Function.Name, call.Function.Arguments)
}
}
toolCall := GeminiPart{
FunctionCall: &FunctionCall{
toolCall := dto.GeminiPart{
FunctionCall: &dto.FunctionCall{
FunctionName: call.Function.Name,
Arguments: args,
},
@@ -308,7 +308,7 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest, info *relaycommon
if part.Text == "" {
continue
}
parts = append(parts, GeminiPart{
parts = append(parts, dto.GeminiPart{
Text: part.Text,
})
} else if part.Type == dto.ContentTypeImageURL {
@@ -331,8 +331,8 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest, info *relaycommon
return nil, fmt.Errorf("mime type is not supported by Gemini: '%s', url: '%s', supported types are: %v", fileData.MimeType, url, getSupportedMimeTypesList())
}
parts = append(parts, GeminiPart{
InlineData: &GeminiInlineData{
parts = append(parts, dto.GeminiPart{
InlineData: &dto.GeminiInlineData{
MimeType: fileData.MimeType, // 使用原始的 MimeType，因为大小写可能对API有意义
Data: fileData.Base64Data,
},
@@ -342,8 +342,8 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest, info *relaycommon
if err != nil {
return nil, fmt.Errorf("decode base64 image data failed: %s", err.Error())
}
parts = append(parts, GeminiPart{
InlineData: &GeminiInlineData{
parts = append(parts, dto.GeminiPart{
InlineData: &dto.GeminiInlineData{
MimeType: format,
Data: base64String,
},
@@ -357,8 +357,8 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest, info *relaycommon
if err != nil {
return nil, fmt.Errorf("decode base64 file data failed: %s", err.Error())
}
parts = append(parts, GeminiPart{
InlineData: &GeminiInlineData{
parts = append(parts, dto.GeminiPart{
InlineData: &dto.GeminiInlineData{
MimeType: format,
Data: base64String,
},
@@ -371,8 +371,8 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest, info *relaycommon
if err != nil {
return nil, fmt.Errorf("decode base64 audio data failed: %s", err.Error())
}
parts = append(parts, GeminiPart{
InlineData: &GeminiInlineData{
parts = append(parts, dto.GeminiPart{
InlineData: &dto.GeminiInlineData{
MimeType: "audio/" + part.GetInputAudio().Format,
Data: base64String,
},
@@ -392,8 +392,8 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest, info *relaycommon
}
if len(system_content) > 0 {
geminiRequest.SystemInstructions = &GeminiChatContent{
Parts: []GeminiPart{
geminiRequest.SystemInstructions = &dto.GeminiChatContent{
Parts: []dto.GeminiPart{
{
Text: strings.Join(system_content, "\n"),
},
@@ -636,7 +636,7 @@ func unescapeMapOrSlice(data interface{}) interface{} {
return data
}
func getResponseToolCall(item *GeminiPart) *dto.ToolCallResponse {
func getResponseToolCall(item *dto.GeminiPart) *dto.ToolCallResponse {
var argsBytes []byte
var err error
if result, ok := item.FunctionCall.Arguments.(map[string]interface{}); ok {
@@ -658,7 +658,7 @@ func getResponseToolCall(item *GeminiPart) *dto.ToolCallResponse {
}
}
func responseGeminiChat2OpenAI(c *gin.Context, response *GeminiChatResponse) *dto.OpenAITextResponse {
func responseGeminiChat2OpenAI(c *gin.Context, response *dto.GeminiChatResponse) *dto.OpenAITextResponse {
fullTextResponse := dto.OpenAITextResponse{
Id: helper.GetResponseID(c),
Object: "chat.completion",
@@ -725,7 +725,7 @@ func responseGeminiChat2OpenAI(c *gin.Context, response *GeminiChatResponse) *dt
return &fullTextResponse
}
func streamResponseGeminiChat2OpenAI(geminiResponse *GeminiChatResponse) (*dto.ChatCompletionsStreamResponse, bool, bool) {
func streamResponseGeminiChat2OpenAI(geminiResponse *dto.GeminiChatResponse) (*dto.ChatCompletionsStreamResponse, bool, bool) {
choices := make([]dto.ChatCompletionsStreamResponseChoice, 0, len(geminiResponse.Candidates))
isStop := false
hasImage := false
@@ -830,7 +830,7 @@ func GeminiChatStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *
respCount := 0
helper.StreamScannerHandler(c, resp, info, func(data string) bool {
var geminiResponse GeminiChatResponse
var geminiResponse dto.GeminiChatResponse
err := common.UnmarshalJsonStr(data, &geminiResponse)
if err != nil {
common.LogError(c, "error unmarshalling stream response: "+err.Error())
@@ -913,7 +913,7 @@ func GeminiChatHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.R
if common.DebugEnabled {
println(string(responseBody))
}
var geminiResponse GeminiChatResponse
var geminiResponse dto.GeminiChatResponse
err = common.Unmarshal(responseBody, &geminiResponse)
if err != nil {
return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
@@ -959,7 +959,7 @@ func GeminiEmbeddingHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *h
return nil, types.NewOpenAIError(readErr, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
}
var geminiResponse GeminiEmbeddingResponse
var geminiResponse dto.GeminiEmbeddingResponse
if jsonErr := common.Unmarshal(responseBody, &geminiResponse); jsonErr != nil {
return nil, types.NewOpenAIError(jsonErr, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
}
@@ -1005,7 +1005,7 @@ func GeminiImageHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.
}
_ = resp.Body.Close()
var geminiResponse GeminiImageResponse
var geminiResponse dto.GeminiImageResponse
if jsonErr := common.Unmarshal(responseBody, &geminiResponse); jsonErr != nil {
return nil, types.NewOpenAIError(jsonErr, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
}