feat: support OpenAI o1-preview and o1-mini

fix: tool use in claude and add gemini mapping

README.md

@@ -66,7 +66,7 @@
 - `GET_MEDIA_TOKEN_NOT_STREAM`：是否在非流（`stream=false`）情况下统计图片token，默认为 `true`。
 - `UPDATE_TASK`：是否更新异步任务（Midjourney、Suno），默认为 `true`，关闭后将不会更新任务进度。
 - `GEMINI_MODEL_MAP`：Gemini模型指定版本(v1/v1beta)，使用“模型:版本”指定，","分隔，例如：-e GEMINI_MODEL_MAP="gemini-1.5-pro-latest:v1beta,gemini-1.5-pro-001:v1beta"，为空则使用默认配置
-
+- `COHERE_SAFETY_SETTING`：Cohere模型[安全设置](https://docs.cohere.com/docs/safety-modes#overview)，可选值为 `NONE`, `CONTEXTUAL`，`STRICT`，默认为 `NONE`。
 ## 部署
 ### 部署要求
 - 本地数据库（默认）：SQLite（Docker 部署默认使用 SQLite，必须挂载 `/data` 目录到宿主机）

common/constants.go

@@ -112,6 +112,9 @@ var RelayTimeout = GetEnvOrDefault("RELAY_TIMEOUT", 0) // unit is second
 
 var GeminiSafetySetting = GetEnvOrDefaultString("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
 
+// https://docs.cohere.com/docs/safety-modes Type; NONE/CONTEXTUAL/STRICT
+var CohereSafetySetting = GetEnvOrDefaultString("COHERE_SAFETY_SETTING", "NONE")
+
 const (
 	RequestIdKey = "X-Oneapi-Request-Id"
 )

common/email.go

@@ -10,7 +10,7 @@ import (
 )
 
 func generateMessageID() string {
-	domain := strings.Split(SMTPFrom, "@")[1]
+	domain := strings.Split(SMTPAccount, "@")[1]
 	return fmt.Sprintf("<%d.%s@%s>", time.Now().UnixNano(), GetRandomString(12), domain)
 }
 
@@ -18,6 +18,9 @@ func SendEmail(subject string, receiver string, content string) error {
 	if SMTPFrom == "" { // for compatibility
 		SMTPFrom = SMTPAccount
 	}
+	if SMTPServer == "" && SMTPAccount == "" {
+		return fmt.Errorf("SMTP 服务器未配置")
+	}
 	encodedSubject := fmt.Sprintf("=?UTF-8?B?%s?=", base64.StdEncoding.EncodeToString([]byte(subject)))
 	mail := []byte(fmt.Sprintf("To: %s\r\n"+
 		"From: %s<%s>\r\n"+

common/model-ratio.go

@@ -42,6 +42,10 @@ var defaultModelRatio = map[string]float64{
 	"gpt-4o":                    2.5,  // $0.01 / 1K tokens
 	"gpt-4o-2024-05-13":         2.5,  // $0.01 / 1K tokens
 	"gpt-4o-2024-08-06":         1.25, // $0.01 / 1K tokens
+	"o1-preview":                7.5,
+	"o1-preview-2024-09-12":     7.5,
+	"o1-mini":                   1.5,
+	"o1-mini-2024-09-12":        1.5,
 	"gpt-4o-mini":               0.075,
 	"gpt-4o-mini-2024-07-18":    0.075,
 	"gpt-4-turbo":               5,    // $0.01 / 1K tokens
@@ -106,8 +110,10 @@ var defaultModelRatio = map[string]float64{
 	"gemini-pro-vision":              1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
 	"gemini-1.0-pro-vision-001":      1,
 	"gemini-1.0-pro-001":             1,
-	"gemini-1.5-pro-latest":          1,
+	"gemini-1.5-pro-latest":          1.75, // $3.5 / 1M tokens
+	"gemini-1.5-pro-exp-0827":        1.75, // $3.5 / 1M tokens
 	"gemini-1.5-flash-latest":        1,
+	"gemini-1.5-flash-exp-0827":      1,
 	"gemini-1.0-pro-latest":          1,
 	"gemini-1.0-pro-vision-latest":   1,
 	"gemini-ultra":                   1,
@@ -119,6 +125,13 @@ var defaultModelRatio = map[string]float64{
 	"glm-4v":                         0.05 * RMB, // ￥0.05 / 1k tokens
 	"glm-4-alltools":                 0.1 * RMB,  // ￥0.1 / 1k tokens
 	"glm-3-turbo":                    0.3572,
+	"glm-4-plus":                     0.05 * RMB,
+	"glm-4-0520":                     0.1 * RMB,
+	"glm-4-air":                      0.001 * RMB,
+	"glm-4-airx":                     0.01 * RMB,
+	"glm-4-long":                     0.001 * RMB,
+	"glm-4-flash":                    0,
+	"glm-4v-plus":                    0.01 * RMB,
 	"qwen-turbo":                     0.8572, // ￥0.012 / 1k tokens
 	"qwen-plus":                      10,     // ￥0.14 / 1k tokens
 	"text-embedding-v1":              0.05,   // ￥0.0007 / 1k tokens
@@ -137,26 +150,28 @@ var defaultModelRatio = map[string]float64{
 	"hunyuan":                        7.143,  // ¥0.1 / 1k tokens  // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
 	// https://platform.lingyiwanwu.com/docs#-计费单元
 	// 已经按照 7.2 来换算美元价格
-	"yi-34b-chat-0205":      0.18,
-	"yi-34b-chat-200k":      0.864,
-	"yi-vl-plus":            0.432,
-	"yi-large":              20.0 / 1000 * RMB,
-	"yi-medium":             2.5 / 1000 * RMB,
-	"yi-vision":             6.0 / 1000 * RMB,
-	"yi-medium-200k":        12.0 / 1000 * RMB,
-	"yi-spark":              1.0 / 1000 * RMB,
-	"yi-large-rag":          25.0 / 1000 * RMB,
-	"yi-large-turbo":        12.0 / 1000 * RMB,
-	"yi-large-preview":      20.0 / 1000 * RMB,
-	"yi-large-rag-preview":  25.0 / 1000 * RMB,
-	"command":               0.5,
-	"command-nightly":       0.5,
-	"command-light":         0.5,
-	"command-light-nightly": 0.5,
-	"command-r":             0.25,
-	"command-r-plus	":       1.5,
-	"deepseek-chat":         0.07,
-	"deepseek-coder":        0.07,
+	"yi-34b-chat-0205":       0.18,
+	"yi-34b-chat-200k":       0.864,
+	"yi-vl-plus":             0.432,
+	"yi-large":               20.0 / 1000 * RMB,
+	"yi-medium":              2.5 / 1000 * RMB,
+	"yi-vision":              6.0 / 1000 * RMB,
+	"yi-medium-200k":         12.0 / 1000 * RMB,
+	"yi-spark":               1.0 / 1000 * RMB,
+	"yi-large-rag":           25.0 / 1000 * RMB,
+	"yi-large-turbo":         12.0 / 1000 * RMB,
+	"yi-large-preview":       20.0 / 1000 * RMB,
+	"yi-large-rag-preview":   25.0 / 1000 * RMB,
+	"command":                0.5,
+	"command-nightly":        0.5,
+	"command-light":          0.5,
+	"command-light-nightly":  0.5,
+	"command-r":              0.25,
+	"command-r-plus":         1.5,
+	"command-r-08-2024":      0.075,
+	"command-r-plus-08-2024": 1.25,
+	"deepseek-chat":          0.07,
+	"deepseek-coder":         0.07,
 	// Perplexity online 模型对搜索额外收费，有需要应自行调整，此处不计入搜索费用
 	"llama-3-sonar-small-32k-chat":   0.2 / 1000 * USD,
 	"llama-3-sonar-small-32k-online": 0.2 / 1000 * USD,
@@ -320,17 +335,6 @@ func GetCompletionRatio(name string) float64 {
 	if strings.HasPrefix(name, "gpt-4o-gizmo") {
 		name = "gpt-4o-gizmo-*"
 	}
-	if strings.HasPrefix(name, "gpt-3.5") {
-		if name == "gpt-3.5-turbo" || strings.HasSuffix(name, "0125") {
-			// https://openai.com/blog/new-embedding-models-and-api-updates
-			// Updated GPT-3.5 Turbo model and lower pricing
-			return 3
-		}
-		if strings.HasSuffix(name, "1106") {
-			return 2
-		}
-		return 4.0 / 3.0
-	}
 	if strings.HasPrefix(name, "gpt-4") && !strings.HasSuffix(name, "-all") && !strings.HasSuffix(name, "-gizmo-*") {
 		if strings.HasPrefix(name, "gpt-4-turbo") || strings.HasSuffix(name, "preview") {
 			return 3
@@ -343,6 +347,9 @@ func GetCompletionRatio(name string) float64 {
 		}
 		return 2
 	}
+	if strings.HasPrefix(name, "o1-") {
+		return 4
+	}
 	if name == "chatgpt-4o-latest" {
 		return 3
 	}
@@ -353,6 +360,17 @@ func GetCompletionRatio(name string) float64 {
 	} else if strings.Contains(name, "claude-3") {
 		return 5
 	}
+	if strings.HasPrefix(name, "gpt-3.5") {
+		if name == "gpt-3.5-turbo" || strings.HasSuffix(name, "0125") {
+			// https://openai.com/blog/new-embedding-models-and-api-updates
+			// Updated GPT-3.5 Turbo model and lower pricing
+			return 3
+		}
+		if strings.HasSuffix(name, "1106") {
+			return 2
+		}
+		return 4.0 / 3.0
+	}
 	if strings.HasPrefix(name, "mistral-") {
 		return 3
 	}
@@ -365,6 +383,10 @@ func GetCompletionRatio(name string) float64 {
 			return 3
 		case "command-r-plus":
 			return 5
+		case "command-r-08-2024":
+			return 4
+		case "command-r-plus-08-2024":
+			return 4
 		default:
 			return 2
 		}

constant/env.go

@@ -20,14 +20,16 @@ var GetMediaTokenNotStream = common.GetEnvOrDefaultBool("GET_MEDIA_TOKEN_NOT_STR
 var UpdateTask = common.GetEnvOrDefaultBool("UPDATE_TASK", true)
 
 var GeminiModelMap = map[string]string{
-	"gemini-1.5-pro-latest":   "v1beta",
-	"gemini-1.5-pro-001":      "v1beta",
-	"gemini-1.5-pro":          "v1beta",
-	"gemini-1.5-pro-exp-0801": "v1beta",
-	"gemini-1.5-flash-latest": "v1beta",
-	"gemini-1.5-flash-001":    "v1beta",
-	"gemini-1.5-flash":        "v1beta",
-	"gemini-ultra":            "v1beta",
+	"gemini-1.5-pro-latest":     "v1beta",
+	"gemini-1.5-pro-001":        "v1beta",
+	"gemini-1.5-pro":            "v1beta",
+	"gemini-1.5-pro-exp-0801":   "v1beta",
+	"gemini-1.5-pro-exp-0827":   "v1beta",
+	"gemini-1.5-flash-latest":   "v1beta",
+	"gemini-1.5-flash-exp-0827": "v1beta",
+	"gemini-1.5-flash-001":      "v1beta",
+	"gemini-1.5-flash":          "v1beta",
+	"gemini-ultra":              "v1beta",
 }
 
 func InitEnv() {

dto/text_response.go

@@ -34,6 +34,7 @@ type OpenAITextResponseChoice struct {
 
 type OpenAITextResponse struct {
 	Id      string                     `json:"id"`
+	Model   string                     `json:"model"`
 	Object  string                     `json:"object"`
 	Created int64                      `json:"created"`
 	Choices []OpenAITextResponseChoice `json:"choices"`

relay/channel/claude/relay-claude.go

@@ -4,7 +4,6 @@ import (
 	"bufio"
 	"encoding/json"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/common"
@@ -12,6 +11,8 @@ import (
 	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )
 
 func stopReasonClaude2OpenAI(reason string) string {
@@ -108,13 +109,10 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 		}
 	}
 	formatMessages := make([]dto.Message, 0)
-	var lastMessage *dto.Message
+	lastMessage := dto.Message{
+		Role: "tool",
+	}
 	for i, message := range textRequest.Messages {
-		//if message.Role == "system" {
-		//	if i != 0 {
-		//		message.Role = "user"
-		//	}
-		//}
 		if message.Role == "" {
 			textRequest.Messages[i].Role = "user"
 		}
@@ -122,7 +120,13 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 			Role:    message.Role,
 			Content: message.Content,
 		}
-		if lastMessage != nil && lastMessage.Role == message.Role {
+		if message.Role == "tool" {
+			fmtMessage.ToolCallId = message.ToolCallId
+		}
+		if message.Role == "assistant" && message.ToolCalls != nil {
+			fmtMessage.ToolCalls = message.ToolCalls
+		}
+		if lastMessage.Role == message.Role && lastMessage.Role != "tool" {
 			if lastMessage.IsStringContent() && message.IsStringContent() {
 				content, _ := json.Marshal(strings.Trim(fmt.Sprintf("%s %s", lastMessage.StringContent(), message.StringContent()), "\""))
 				fmtMessage.Content = content
@@ -135,7 +139,7 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 			fmtMessage.Content = content
 		}
 		formatMessages = append(formatMessages, fmtMessage)
-		lastMessage = &textRequest.Messages[i]
+		lastMessage = fmtMessage
 	}
 
 	claudeMessages := make([]ClaudeMessage, 0)
@@ -174,7 +178,35 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 			claudeMessage := ClaudeMessage{
 				Role: message.Role,
 			}
-			if message.IsStringContent() {
+			if message.Role == "tool" {
+				if len(claudeMessages) > 0 && claudeMessages[len(claudeMessages)-1].Role == "user" {
+					lastMessage := claudeMessages[len(claudeMessages)-1]
+					if content, ok := lastMessage.Content.(string); ok {
+						lastMessage.Content = []ClaudeMediaMessage{
+							{
+								Type: "text",
+								Text: content,
+							},
+						}
+					}
+					lastMessage.Content = append(lastMessage.Content.([]ClaudeMediaMessage), ClaudeMediaMessage{
+						Type:      "tool_result",
+						ToolUseId: message.ToolCallId,
+						Content:   message.StringContent(),
+					})
+					claudeMessages[len(claudeMessages)-1] = lastMessage
+					continue
+				} else {
+					claudeMessage.Role = "user"
+					claudeMessage.Content = []ClaudeMediaMessage{
+						{
+							Type:      "tool_result",
+							ToolUseId: message.ToolCallId,
+							Content:   message.StringContent(),
+						},
+					}
+				}
+			} else if message.IsStringContent() && message.ToolCalls == nil {
 				claudeMessage.Content = message.StringContent()
 			} else {
 				claudeMediaMessages := make([]ClaudeMediaMessage, 0)
@@ -207,6 +239,28 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 					}
 					claudeMediaMessages = append(claudeMediaMessages, claudeMediaMessage)
 				}
+				if message.ToolCalls != nil {
+					for _, tc := range message.ToolCalls.([]interface{}) {
+						toolCallJSON, _ := json.Marshal(tc)
+						var toolCall dto.ToolCall
+						err := json.Unmarshal(toolCallJSON, &toolCall)
+						if err != nil {
+							common.SysError("tool call is not a dto.ToolCall: " + fmt.Sprintf("%v", tc))
+							continue
+						}
+						inputObj := make(map[string]any)
+						if err := json.Unmarshal([]byte(toolCall.Function.Arguments), &inputObj); err != nil {
+							common.SysError("tool call function arguments is not a map[string]any: " + fmt.Sprintf("%v", toolCall.Function.Arguments))
+							continue
+						}
+						claudeMediaMessages = append(claudeMediaMessages, ClaudeMediaMessage{
+							Type:  "tool_use",
+							Id:    toolCall.ID,
+							Name:  toolCall.Function.Name,
+							Input: inputObj,
+						})
+					}
+				}
 				claudeMessage.Content = claudeMediaMessages
 			}
 			claudeMessages = append(claudeMessages, claudeMessage)
@@ -341,6 +395,7 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
 	if len(tools) > 0 {
 		choice.Message.ToolCalls = tools
 	}
+	fullTextResponse.Model = claudeResponse.Model
 	choices = append(choices, choice)
 	fullTextResponse.Choices = choices
 	return &fullTextResponse

relay/channel/cohere/constant.go

@@ -1,7 +1,10 @@
 package cohere
 
 var ModelList = []string{
-	"command-r", "command-r-plus", "command-light", "command-light-nightly", "command", "command-nightly",
+	"command-r", "command-r-plus",
+	"command-r-08-2024", "command-r-plus-08-2024",
+	"c4ai-aya-23-35b", "c4ai-aya-23-8b",
+	"command-light", "command-light-nightly", "command", "command-nightly",
 	"rerank-english-v3.0", "rerank-multilingual-v3.0", "rerank-english-v2.0", "rerank-multilingual-v2.0",
 }
 

relay/channel/cohere/dto.go

@@ -8,6 +8,7 @@ type CohereRequest struct {
 	Message     string        `json:"message"`
 	Stream      bool          `json:"stream"`
 	MaxTokens   int           `json:"max_tokens"`
+	SafetyMode  string        `json:"safety_mode,omitempty"`
 }
 
 type ChatHistory struct {

relay/channel/cohere/relay-cohere.go

@@ -23,6 +23,9 @@ func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
 		Stream:      textRequest.Stream,
 		MaxTokens:   textRequest.GetMaxTokens(),
 	}
+	if common.CohereSafetySetting != "NONE" {
+		cohereReq.SafetyMode = common.CohereSafetySetting
+	}
 	if cohereReq.MaxTokens == 0 {
 		cohereReq.MaxTokens = 4000
 	}
@@ -44,6 +47,7 @@ func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
 			})
 		}
 	}
+
 	return &cohereReq
 }
 

relay/channel/gemini/constant.go

@@ -6,7 +6,7 @@ const (
 
 var ModelList = []string{
 	"gemini-1.0-pro-latest", "gemini-1.0-pro-001", "gemini-1.5-pro-latest", "gemini-1.5-flash-latest", "gemini-ultra",
-	"gemini-1.0-pro-vision-latest", "gemini-1.0-pro-vision-001",
+	"gemini-1.0-pro-vision-latest", "gemini-1.0-pro-vision-001", "gemini-1.5-pro-exp-0827", "gemini-1.5-flash-exp-0827",
 }
 
 var ChannelName = "google gemini"

relay/channel/jina/adaptor.go

@@ -32,7 +32,7 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	if info.RelayMode == constant.RelayModeRerank {
 		return fmt.Sprintf("%s/v1/rerank", info.BaseUrl), nil
 	} else if info.RelayMode == constant.RelayModeEmbeddings {
-		return fmt.Sprintf("%s/v1/embeddings ", info.BaseUrl), nil
+		return fmt.Sprintf("%s/v1/embeddings", info.BaseUrl), nil
 	}
 	return "", errors.New("invalid relay mode")
 }
@@ -58,6 +58,8 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.RelayMode == constant.RelayModeRerank {
 		err, usage = jinaRerankHandler(c, resp)
+	} else if info.RelayMode == constant.RelayModeEmbeddings {
+		err, usage = jinaEmbeddingHandler(c, resp)
 	}
 	return
 }

relay/channel/jina/relay-jina.go

@@ -33,3 +33,28 @@ func jinaRerankHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWit
 	_, err = c.Writer.Write(jsonResponse)
 	return nil, &jinaResp.Usage
 }
+
+func jinaEmbeddingHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	var jinaResp dto.OpenAIEmbeddingResponse
+	err = json.Unmarshal(responseBody, &jinaResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+
+	jsonResponse, err := json.Marshal(jinaResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	return nil, &jinaResp.Usage
+}

relay/channel/ollama/dto.go

@@ -17,11 +17,25 @@ type OllamaRequest struct {
 	PresencePenalty  float64        `json:"presence_penalty,omitempty"`
 }
 
+type Options struct {
+	Seed             int     `json:"seed,omitempty"`
+	Temperature      float64 `json:"temperature,omitempty"`
+	TopK             int     `json:"top_k,omitempty"`
+	TopP             float64 `json:"top_p,omitempty"`
+	FrequencyPenalty float64 `json:"frequency_penalty,omitempty"`
+	PresencePenalty  float64 `json:"presence_penalty,omitempty"`
+	NumPredict       int     `json:"num_predict,omitempty"`
+	NumCtx           int     `json:"num_ctx,omitempty"`
+}
+
 type OllamaEmbeddingRequest struct {
-	Model  string `json:"model,omitempty"`
-	Prompt any    `json:"prompt,omitempty"`
+	Model   string   `json:"model,omitempty"`
+	Input   []string `json:"input"`
+	Options *Options `json:"options,omitempty"`
 }
 
 type OllamaEmbeddingResponse struct {
+	Error     string    `json:"error,omitempty"`
+	Model     string    `json:"model"`
 	Embedding []float64 `json:"embedding,omitempty"`
 }

relay/channel/ollama/relay-ollama.go

@@ -9,7 +9,6 @@ import (
 	"net/http"
 	"one-api/dto"
 	"one-api/service"
-	"strings"
 )
 
 func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) *OllamaRequest {
@@ -45,8 +44,15 @@ func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) *OllamaRequest {
 
 func requestOpenAI2Embeddings(request dto.GeneralOpenAIRequest) *OllamaEmbeddingRequest {
 	return &OllamaEmbeddingRequest{
-		Model:  request.Model,
-		Prompt: strings.Join(request.ParseInput(), " "),
+		Model: request.Model,
+		Input: request.ParseInput(),
+		Options: &Options{
+			Seed:             int(request.Seed),
+			Temperature:      request.Temperature,
+			TopP:             request.TopP,
+			FrequencyPenalty: request.FrequencyPenalty,
+			PresencePenalty:  request.PresencePenalty,
+		},
 	}
 }
 
@@ -64,6 +70,9 @@ func ollamaEmbeddingHandler(c *gin.Context, resp *http.Response, promptTokens in
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
+	if ollamaEmbeddingResponse.Error != "" {
+		return service.OpenAIErrorWrapper(err, "ollama_error", resp.StatusCode), nil
+	}
 	data := make([]dto.OpenAIEmbeddingResponseItem, 0, 1)
 	data = append(data, dto.OpenAIEmbeddingResponseItem{
 		Embedding: ollamaEmbeddingResponse.Embedding,

relay/channel/openai/constant.go

@@ -11,6 +11,8 @@ var ModelList = []string{
 	"chatgpt-4o-latest",
 	"gpt-4o", "gpt-4o-2024-05-13", "gpt-4o-2024-08-06",
 	"gpt-4o-mini", "gpt-4o-mini-2024-07-18",
+	"o1-preview", "o1-preview-2024-09-12",
+	"o1-mini", "o1-mini-2024-09-12",
 	"text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large",
 	"text-curie-001", "text-babbage-001", "text-ada-001",
 	"text-moderation-latest", "text-moderation-stable",

relay/channel/siliconflow/adaptor.go

@@ -33,7 +33,7 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	if info.RelayMode == constant.RelayModeRerank {
 		return fmt.Sprintf("%s/v1/rerank", info.BaseUrl), nil
 	} else if info.RelayMode == constant.RelayModeEmbeddings {
-		return fmt.Sprintf("%s/v1/embeddings ", info.BaseUrl), nil
+		return fmt.Sprintf("%s/v1/embeddings", info.BaseUrl), nil
 	} else if info.RelayMode == constant.RelayModeChatCompletions {
 		return fmt.Sprintf("%s/v1/chat/completions", info.BaseUrl), nil
 	}
@@ -59,14 +59,17 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 }
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
-	if info.RelayMode == constant.RelayModeRerank {
+	switch info.RelayMode {
+	case constant.RelayModeRerank:
 		err, usage = siliconflowRerankHandler(c, resp)
-	} else if info.RelayMode == constant.RelayModeChatCompletions {
+	case constant.RelayModeChatCompletions:
 		if info.IsStream {
 			err, usage = openai.OaiStreamHandler(c, resp, info)
 		} else {
 			err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 		}
+	case constant.RelayModeEmbeddings:
+		err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 	}
 	return
 }

relay/channel/zhipu_4v/constants.go

@@ -1,7 +1,7 @@
 package zhipu_4v
 
 var ModelList = []string{
-	"glm-4", "glm-4v", "glm-3-turbo", "glm-4-alltools",
+	"glm-4", "glm-4v", "glm-3-turbo", "glm-4-alltools", "glm-4-plus", "glm-4-0520", "glm-4-air", "glm-4-airx", "glm-4-long", "glm-4-flash", "glm-4v-plus",
 }
 
 var ChannelName = "zhipu_4v"

relay/relay-text.go

@@ -52,7 +52,7 @@ func getAndValidateTextRequest(c *gin.Context, relayInfo *relaycommon.RelayInfo)
 		}
 	case relayconstant.RelayModeEmbeddings:
 	case relayconstant.RelayModeModerations:
-		if textRequest.Input == "" {
+		if textRequest.Input == "" || textRequest.Input == nil {
 			return nil, errors.New("field input is required")
 		}
 	case relayconstant.RelayModeEdits:

service/token_counter.go

@@ -52,7 +52,7 @@ func InitTokenEncoders() {
 }
 
 func getModelDefaultTokenEncoder(model string) *tiktoken.Tiktoken {
-	if strings.HasPrefix(model, "gpt-4o") {
+	if strings.HasPrefix(model, "gpt-4o") || strings.HasPrefix(model, "chatgpt-4o") {
 		return cl200kTokenEncoder
 	}
 	return defaultTokenEncoder

web/src/components/Footer.js

@@ -59,12 +59,10 @@ const Footer = () => {
     <Layout>
       <Layout.Content style={{ textAlign: 'center' }}>
         {footer ? (
-          <Tooltip content={defaultFooter}>
-            <div
-              className='custom-footer'
-              dangerouslySetInnerHTML={{ __html: footer }}
-            ></div>
-          </Tooltip>
+          <div
+            className='custom-footer'
+            dangerouslySetInnerHTML={{ __html: footer }}
+          ></div>
         ) : (
           defaultFooter
         )}

web/src/components/TokensTable.js

@@ -225,14 +225,14 @@ const TokensTable = () => {
                     onOpenLink('next-mj', record.key);
                   },
                 },
-                {
-                  node: 'item',
-                  key: 'lobe',
-                  name: 'Lobe Chat',
-                  onClick: () => {
-                    onOpenLink('lobe', record.key);
-                  },
-                },
+                // {
+                //   node: 'item',
+                //   key: 'lobe',
+                //   name: 'Lobe Chat',
+                //   onClick: () => {
+                //     onOpenLink('lobe', record.key);
+                //   },
+                // },
                 {
                   node: 'item',
                   key: 'ama',