merge upstream

Signed-off-by: wozulong <>

common/model-ratio.go

@@ -35,6 +35,7 @@ var defaultModelRatio = map[string]float64{
 	"gpt-4o-mini-2024-07-18":         0.075,
 	"gpt-4o":                         2.5,  // $0.005 / 1K tokens
 	"gpt-4o-2024-05-13":              2.5,  // $0.005 / 1K tokens
+	"gpt-4o-2024-08-06":              1.25, // $0.01 / 1K tokens
 	"gpt-4-turbo":                    5,    // $0.01 / 1K tokens
 	"gpt-4-turbo-2024-04-09":         5,    // $0.01 / 1K tokens
 	"gpt-4-1106-preview":             5,    // $0.01 / 1K tokens
@@ -333,7 +334,7 @@ func GetCompletionRatio(name string) float64 {
 		return 4.0 / 3.0
 	}
 	if strings.HasPrefix(name, "gpt-4") && name != "gpt-4-all" && name != "gpt-4-gizmo-*" {
-		if strings.HasPrefix(name, "gpt-4o-mini") {
+		if strings.HasPrefix(name, "gpt-4o-mini") || "gpt-4o-2024-08-06" == name {
 			return 4
 		}
 

dto/text_request.go

@@ -2,10 +2,6 @@ package dto
 
 import "encoding/json"
 
-type ResponseFormat struct {
-	Type string `json:"type,omitempty"`
-}
-
 type GeneralOpenAIRequest struct {
 	Model             string         `json:"model,omitempty"`
 	Messages          []Message      `json:"messages,omitempty"`
@@ -27,7 +23,7 @@ type GeneralOpenAIRequest struct {
 	Functions         any            `json:"functions,omitempty"`
 	FrequencyPenalty  float64        `json:"frequency_penalty,omitempty"`
 	PresencePenalty   float64        `json:"presence_penalty,omitempty"`
-	ResponseFormat   *ResponseFormat `json:"response_format,omitempty"`
+	ResponseFormat    any            `json:"response_format,omitempty"`
 	Seed              float64        `json:"seed,omitempty"`
 	Tools             []ToolCall     `json:"tools,omitempty"`
 	ToolChoice        any            `json:"tool_choice,omitempty"`
@@ -36,6 +32,7 @@ type GeneralOpenAIRequest struct {
 	LogProbs          any            `json:"logprobs,omitempty"`
 	TopLogProbs       int            `json:"top_logprobs,omitempty"`
 	Dimensions        int            `json:"dimensions,omitempty"`
+	ParallelToolCalls bool           `json:"parallel_Tool_Calls,omitempty"`
 }
 
 type OpenAITools struct {

middleware/auth.go

@@ -156,7 +156,7 @@ func TokenAuth() func(c *gin.Context) {
 		if token != nil {
 			id := c.GetInt("id")
 			if id == 0 {
-				c.Set("id", token.Id)
+				c.Set("id", token.UserId)
 			}
 		}
 		if err != nil {

relay/channel/ollama/dto.go

@@ -12,7 +12,7 @@ type OllamaRequest struct {
 	TopK             int            `json:"top_k,omitempty"`
 	Stop             any            `json:"stop,omitempty"`
 	Tools            []dto.ToolCall `json:"tools,omitempty"`
-	ResponseFormat   *dto.ResponseFormat `json:"response_format,omitempty"`
+	ResponseFormat   any            `json:"response_format,omitempty"`
 	FrequencyPenalty float64        `json:"frequency_penalty,omitempty"`
 	PresencePenalty  float64        `json:"presence_penalty,omitempty"`
 }

relay/channel/openai/constant.go

@@ -8,7 +8,7 @@ var ModelList = []string{
 	"gpt-4-32k", "gpt-4-32k-0314", "gpt-4-32k-0613",
 	"gpt-4-turbo-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
 	"gpt-4-vision-preview",
-	"gpt-4o", "gpt-4o-2024-05-13",
+	"gpt-4o", "gpt-4o-2024-05-13", "gpt-4o-2024-08-06",
 	"gpt-4o-mini", "gpt-4o-mini-2024-07-18",
 	"text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large",
 	"text-curie-001", "text-babbage-001", "text-ada-001", "text-davinci-002", "text-davinci-003",