Merge 8726729ade into 7e51b04221

Dockerfile

@@ -5,15 +5,15 @@ COPY ./VERSION .
 COPY ./web .
 
 WORKDIR /web/default
-RUN npm install
+RUN npm config set registry https://mirrors.huaweicloud.com/repository/npm/ && npm install
 RUN DISABLE_ESLINT_PLUGIN='true' REACT_APP_VERSION=$(cat VERSION) npm run build
 
 WORKDIR /web/berry
-RUN npm install
+RUN npm config set registry https://mirrors.huaweicloud.com/repository/npm/ && npm install
 RUN DISABLE_ESLINT_PLUGIN='true' REACT_APP_VERSION=$(cat VERSION) npm run build
 
 WORKDIR /web/air
-RUN npm install
+RUN npm config set registry https://mirrors.huaweicloud.com/repository/npm/ && npm install
 RUN DISABLE_ESLINT_PLUGIN='true' REACT_APP_VERSION=$(cat VERSION) npm run build
 
 FROM golang:alpine AS builder2

README.md

@@ -90,7 +90,6 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型，开箱即用
    + [x] [together.ai](https://www.together.ai/)
    + [x] [novita.ai](https://www.novita.ai/)
    + [x] [硅基流动 SiliconCloud](https://siliconflow.cn/siliconcloud)
-   + [x] [xAI](https://x.ai/)
 2. 支持配置镜像以及众多[第三方代理服务](https://iamazing.cn/page/openai-api-third-party-services)。
 3. 支持通过**负载均衡**的方式访问多个渠道。
 4. 支持 **stream 模式**，可以通过流式传输实现打字机效果。

common/helper/helper.go

@@ -137,23 +137,3 @@ func String2Int(str string) int {
 	}
 	return num
 }
-
-func Float64PtrMax(p *float64, maxValue float64) *float64 {
-	if p == nil {
-		return nil
-	}
-	if *p > maxValue {
-		return &maxValue
-	}
-	return p
-}
-
-func Float64PtrMin(p *float64, minValue float64) *float64 {
-	if p == nil {
-		return nil
-	}
-	if *p < minValue {
-		return &minValue
-	}
-	return p
-}

relay/adaptor/ali/main.go

@@ -36,7 +36,9 @@ func ConvertRequest(request model.GeneralOpenAIRequest) *ChatRequest {
 		enableSearch = true
 		aliModel = strings.TrimSuffix(aliModel, EnableSearchModelSuffix)
 	}
-	request.TopP = helper.Float64PtrMax(request.TopP, 0.9999)
+	if request.TopP >= 1 {
+		request.TopP = 0.9999
+	}
 	return &ChatRequest{
 		Model: aliModel,
 		Input: Input{
@@ -147,7 +149,24 @@ func responseAli2OpenAI(response *ChatResponse) *openai.TextResponse {
 	return &fullTextResponse
 }
 
-func streamResponseAli2OpenAI(aliResponse *ChatResponse) *openai.ChatCompletionsStreamResponse {
+func streamResponseAli2OpenAI(aliResponse *ChatResponse) interface{} {
+	if aliResponse.Code != "" {
+		var choice openai.ChatCompletionsStreamResponseChoice
+		choice.Index = 0
+		choice.Delta = model.Message{
+			Role:    "assistant",
+			Content: "",
+		}
+		response := openai.ChatCompletionsErrorStreamResponse{
+			Id:        aliResponse.RequestId,
+			Object:    "chat.completion.chunk",
+			Created:   helper.GetTimestamp(),
+			Model:     "qwen",
+			ErrorCode: aliResponse.Code,
+			Choices:   []openai.ChatCompletionsStreamResponseChoice{choice},
+		}
+		return &response
+	}
 	if len(aliResponse.Output.Choices) == 0 {
 		return nil
 	}
@@ -199,6 +218,19 @@ func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusC
 			logger.SysError("error unmarshalling stream response: " + err.Error())
 			continue
 		}
+
+		// Check for known error codes and handle accordingly
+		if aliResponse.Code != "" {
+			response := streamResponseAli2OpenAI(&aliResponse)
+
+			err = render.ObjectData(c, response)
+			if err != nil {
+				logger.SysError(err.Error())
+			}
+			render.Done(c)
+			return nil, nil
+		}
+
 		if aliResponse.Usage.OutputTokens != 0 {
 			usage.PromptTokens = aliResponse.Usage.InputTokens
 			usage.CompletionTokens = aliResponse.Usage.OutputTokens
@@ -243,6 +275,8 @@ func Handler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *
 	if err != nil {
 		return openai.ErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
+
+	// Check for known error codes and handle accordingly
 	if aliResponse.Code != "" {
 		return &model.ErrorWithStatusCode{
 			Error: model.Error{
@@ -254,6 +288,7 @@ func Handler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *
 			StatusCode: resp.StatusCode,
 		}, nil
 	}
+
 	fullTextResponse := responseAli2OpenAI(&aliResponse)
 	fullTextResponse.Model = "qwen"
 	jsonResponse, err := json.Marshal(fullTextResponse)

relay/adaptor/ali/model.go

@@ -16,13 +16,13 @@ type Input struct {
 }
 
 type Parameters struct {
-	TopP              *float64     `json:"top_p,omitempty"`
+	TopP              float64      `json:"top_p,omitempty"`
 	TopK              int          `json:"top_k,omitempty"`
 	Seed              uint64       `json:"seed,omitempty"`
 	EnableSearch      bool         `json:"enable_search,omitempty"`
 	IncrementalOutput bool         `json:"incremental_output,omitempty"`
 	MaxTokens         int          `json:"max_tokens,omitempty"`
-	Temperature       *float64     `json:"temperature,omitempty"`
+	Temperature       float64      `json:"temperature,omitempty"`
 	ResultFormat      string       `json:"result_format,omitempty"`
 	Tools             []model.Tool `json:"tools,omitempty"`
 }

relay/adaptor/anthropic/constants.go

@@ -3,11 +3,8 @@ package anthropic
 var ModelList = []string{
 	"claude-instant-1.2", "claude-2.0", "claude-2.1",
 	"claude-3-haiku-20240307",
-	"claude-3-5-haiku-20241022",
 	"claude-3-sonnet-20240229",
 	"claude-3-opus-20240229",
 	"claude-3-5-sonnet-20240620",
 	"claude-3-5-sonnet-20241022",
-	"claude-3-5-sonnet-latest",
-	"claude-3-5-haiku-20241022",
 }

relay/adaptor/anthropic/model.go

@@ -48,8 +48,8 @@ type Request struct {
 	MaxTokens     int       `json:"max_tokens,omitempty"`
 	StopSequences []string  `json:"stop_sequences,omitempty"`
 	Stream        bool      `json:"stream,omitempty"`
-	Temperature   *float64  `json:"temperature,omitempty"`
-	TopP          *float64  `json:"top_p,omitempty"`
+	Temperature   float64   `json:"temperature,omitempty"`
+	TopP          float64   `json:"top_p,omitempty"`
 	TopK          int       `json:"top_k,omitempty"`
 	Tools         []Tool    `json:"tools,omitempty"`
 	ToolChoice    any       `json:"tool_choice,omitempty"`

relay/adaptor/aws/claude/main.go

@@ -29,13 +29,11 @@ var AwsModelIDMap = map[string]string{
 	"claude-instant-1.2":         "anthropic.claude-instant-v1",
 	"claude-2.0":                 "anthropic.claude-v2",
 	"claude-2.1":                 "anthropic.claude-v2:1",
-	"claude-3-haiku-20240307":    "anthropic.claude-3-haiku-20240307-v1:0",
 	"claude-3-sonnet-20240229":   "anthropic.claude-3-sonnet-20240229-v1:0",
-	"claude-3-opus-20240229":     "anthropic.claude-3-opus-20240229-v1:0",
 	"claude-3-5-sonnet-20240620": "anthropic.claude-3-5-sonnet-20240620-v1:0",
 	"claude-3-5-sonnet-20241022": "anthropic.claude-3-5-sonnet-20241022-v2:0",
-	"claude-3-5-sonnet-latest":   "anthropic.claude-3-5-sonnet-20241022-v2:0",
-	"claude-3-5-haiku-20241022":  "anthropic.claude-3-5-haiku-20241022-v1:0",
+	"claude-3-opus-20240229":     "anthropic.claude-3-opus-20240229-v1:0",
+	"claude-3-haiku-20240307":    "anthropic.claude-3-haiku-20240307-v1:0",
 }
 
 func awsModelID(requestModel string) (string, error) {

relay/adaptor/aws/claude/model.go

@@ -11,8 +11,8 @@ type Request struct {
 	Messages         []anthropic.Message `json:"messages"`
 	System           string              `json:"system,omitempty"`
 	MaxTokens        int                 `json:"max_tokens,omitempty"`
-	Temperature      *float64            `json:"temperature,omitempty"`
-	TopP             *float64            `json:"top_p,omitempty"`
+	Temperature      float64             `json:"temperature,omitempty"`
+	TopP             float64             `json:"top_p,omitempty"`
 	TopK             int                 `json:"top_k,omitempty"`
 	StopSequences    []string            `json:"stop_sequences,omitempty"`
 	Tools            []anthropic.Tool    `json:"tools,omitempty"`

relay/adaptor/aws/llama3/model.go

@@ -4,10 +4,10 @@ package aws
 //
 // https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html
 type Request struct {
-	Prompt      string   `json:"prompt"`
-	MaxGenLen   int      `json:"max_gen_len,omitempty"`
-	Temperature *float64 `json:"temperature,omitempty"`
-	TopP        *float64 `json:"top_p,omitempty"`
+	Prompt      string  `json:"prompt"`
+	MaxGenLen   int     `json:"max_gen_len,omitempty"`
+	Temperature float64 `json:"temperature,omitempty"`
+	TopP        float64 `json:"top_p,omitempty"`
 }
 
 // Response is the response from AWS Llama3

relay/adaptor/baidu/main.go

@@ -35,9 +35,9 @@ type Message struct {
 
 type ChatRequest struct {
 	Messages        []Message `json:"messages"`
-	Temperature     *float64  `json:"temperature,omitempty"`
-	TopP            *float64  `json:"top_p,omitempty"`
-	PenaltyScore    *float64  `json:"penalty_score,omitempty"`
+	Temperature     float64   `json:"temperature,omitempty"`
+	TopP            float64   `json:"top_p,omitempty"`
+	PenaltyScore    float64   `json:"penalty_score,omitempty"`
 	Stream          bool      `json:"stream,omitempty"`
 	System          string    `json:"system,omitempty"`
 	DisableSearch   bool      `json:"disable_search,omitempty"`

relay/adaptor/cloudflare/model.go

@@ -9,5 +9,5 @@ type Request struct {
 	Prompt      string          `json:"prompt,omitempty"`
 	Raw         bool            `json:"raw,omitempty"`
 	Stream      bool            `json:"stream,omitempty"`
-	Temperature *float64        `json:"temperature,omitempty"`
+	Temperature float64         `json:"temperature,omitempty"`
 }

relay/adaptor/cohere/main.go

@@ -43,7 +43,7 @@ func ConvertRequest(textRequest model.GeneralOpenAIRequest) *Request {
 		K:                textRequest.TopK,
 		Stream:           textRequest.Stream,
 		FrequencyPenalty: textRequest.FrequencyPenalty,
-		PresencePenalty:  textRequest.PresencePenalty,
+		PresencePenalty:  textRequest.FrequencyPenalty,
 		Seed:             int(textRequest.Seed),
 	}
 	if cohereRequest.Model == "" {

relay/adaptor/cohere/model.go

@@ -10,15 +10,15 @@ type Request struct {
 	PromptTruncation string        `json:"prompt_truncation,omitempty"` // 默认值为"AUTO"
 	Connectors       []Connector   `json:"connectors,omitempty"`
 	Documents        []Document    `json:"documents,omitempty"`
-	Temperature      *float64      `json:"temperature,omitempty"` // 默认值为0.3
+	Temperature      float64       `json:"temperature,omitempty"` // 默认值为0.3
 	MaxTokens        int           `json:"max_tokens,omitempty"`
 	MaxInputTokens   int           `json:"max_input_tokens,omitempty"`
 	K                int           `json:"k,omitempty"` // 默认值为0
-	P                *float64      `json:"p,omitempty"` // 默认值为0.75
+	P                float64       `json:"p,omitempty"` // 默认值为0.75
 	Seed             int           `json:"seed,omitempty"`
 	StopSequences    []string      `json:"stop_sequences,omitempty"`
-	FrequencyPenalty *float64      `json:"frequency_penalty,omitempty"` // 默认值为0.0
-	PresencePenalty  *float64      `json:"presence_penalty,omitempty"`  // 默认值为0.0
+	FrequencyPenalty float64       `json:"frequency_penalty,omitempty"` // 默认值为0.0
+	PresencePenalty  float64       `json:"presence_penalty,omitempty"`  // 默认值为0.0
 	Tools            []Tool        `json:"tools,omitempty"`
 	ToolResults      []ToolResult  `json:"tool_results,omitempty"`
 }

relay/adaptor/gemini/model.go

@@ -67,8 +67,8 @@ type ChatTools struct {
 type ChatGenerationConfig struct {
 	ResponseMimeType string   `json:"responseMimeType,omitempty"`
 	ResponseSchema   any      `json:"responseSchema,omitempty"`
-	Temperature      *float64 `json:"temperature,omitempty"`
-	TopP             *float64 `json:"topP,omitempty"`
+	Temperature      float64  `json:"temperature,omitempty"`
+	TopP             float64  `json:"topP,omitempty"`
 	TopK             float64  `json:"topK,omitempty"`
 	MaxOutputTokens  int      `json:"maxOutputTokens,omitempty"`
 	CandidateCount   int      `json:"candidateCount,omitempty"`

relay/adaptor/groq/constants.go

@@ -11,9 +11,7 @@ var ModelList = []string{
 	"llama-3.2-11b-vision-preview",
 	"llama-3.2-1b-preview",
 	"llama-3.2-3b-preview",
-	"llama-3.2-11b-vision-preview",
 	"llama-3.2-90b-text-preview",
-	"llama-3.2-90b-vision-preview",
 	"llama-guard-3-8b",
 	"llama3-70b-8192",
 	"llama3-8b-8192",
@@ -23,5 +21,4 @@ var ModelList = []string{
 	"mixtral-8x7b-32768",
 	"distil-whisper-large-v3-en",
 	"whisper-large-v3",
-	"whisper-large-v3-turbo",
 }

relay/adaptor/ollama/model.go

@@ -1,14 +1,14 @@
 package ollama
 
 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"`
+	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 Message struct {

relay/adaptor/openai/compatible.go

@@ -11,10 +11,9 @@ import (
 	"github.com/songquanpeng/one-api/relay/adaptor/mistral"
 	"github.com/songquanpeng/one-api/relay/adaptor/moonshot"
 	"github.com/songquanpeng/one-api/relay/adaptor/novita"
-	"github.com/songquanpeng/one-api/relay/adaptor/siliconflow"
 	"github.com/songquanpeng/one-api/relay/adaptor/stepfun"
 	"github.com/songquanpeng/one-api/relay/adaptor/togetherai"
-	"github.com/songquanpeng/one-api/relay/adaptor/xai"
+	"github.com/songquanpeng/one-api/relay/adaptor/siliconflow"
 	"github.com/songquanpeng/one-api/relay/channeltype"
 )
 
@@ -33,7 +32,6 @@ var CompatibleChannels = []int{
 	channeltype.TogetherAI,
 	channeltype.Novita,
 	channeltype.SiliconFlow,
-	channeltype.XAI,
 }
 
 func GetCompatibleChannelMeta(channelType int) (string, []string) {
@@ -66,8 +64,6 @@ func GetCompatibleChannelMeta(channelType int) (string, []string) {
 		return "novita", novita.ModelList
 	case channeltype.SiliconFlow:
 		return "siliconflow", siliconflow.ModelList
-	case channeltype.XAI:
-		return "xai", xai.ModelList
 	default:
 		return "openai", ModelList
 	}

relay/adaptor/openai/model.go

@@ -97,6 +97,16 @@ type TextResponse struct {
 	model.Usage `json:"usage"`
 }
 
+type ErrorTextResponse struct {
+	Id          string               `json:"id"`
+	Model       string               `json:"model,omitempty"`
+	Object      string               `json:"object"`
+	ErrorCode   string               `json:"error_code"`
+	Created     int64                `json:"created"`
+	Choices     []TextResponseChoice `json:"choices"`
+	model.Usage `json:"usage"`
+}
+
 type EmbeddingResponseItem struct {
 	Object    string    `json:"object"`
 	Index     int       `json:"index"`
@@ -137,6 +147,16 @@ type ChatCompletionsStreamResponse struct {
 	Usage   *model.Usage                          `json:"usage,omitempty"`
 }
 
+type ChatCompletionsErrorStreamResponse struct {
+	Id        string                                `json:"id"`
+	Object    string                                `json:"object"`
+	Created   int64                                 `json:"created"`
+	ErrorCode string                                `json:"error_code"`
+	Model     string                                `json:"model"`
+	Choices   []ChatCompletionsStreamResponseChoice `json:"choices"`
+	Usage     *model.Usage                          `json:"usage,omitempty"`
+}
+
 type CompletionsStreamResponse struct {
 	Choices []struct {
 		Text         string `json:"text"`

relay/adaptor/palm/model.go

@@ -19,11 +19,11 @@ type Prompt struct {
 }
 
 type ChatRequest struct {
-	Prompt         Prompt   `json:"prompt"`
-	Temperature    *float64 `json:"temperature,omitempty"`
-	CandidateCount int      `json:"candidateCount,omitempty"`
-	TopP           *float64 `json:"topP,omitempty"`
-	TopK           int      `json:"topK,omitempty"`
+	Prompt         Prompt  `json:"prompt"`
+	Temperature    float64 `json:"temperature,omitempty"`
+	CandidateCount int     `json:"candidateCount,omitempty"`
+	TopP           float64 `json:"topP,omitempty"`
+	TopK           int     `json:"topK,omitempty"`
 }
 
 type Error struct {

relay/adaptor/tencent/main.go

@@ -39,8 +39,8 @@ func ConvertRequest(request model.GeneralOpenAIRequest) *ChatRequest {
 		Model:       &request.Model,
 		Stream:      &request.Stream,
 		Messages:    messages,
-		TopP:        request.TopP,
-		Temperature: request.Temperature,
+		TopP:        &request.TopP,
+		Temperature: &request.Temperature,
 	}
 }
 

relay/adaptor/vertexai/claude/adapter.go

@@ -13,12 +13,7 @@ import (
 )
 
 var ModelList = []string{
-	"claude-3-haiku@20240307",
-	"claude-3-sonnet@20240229",
-	"claude-3-opus@20240229",
-	"claude-3-5-sonnet@20240620",
-	"claude-3-5-sonnet-v2@20241022",
-	"claude-3-5-haiku@20241022",
+	"claude-3-haiku@20240307", "claude-3-opus@20240229", "claude-3-5-sonnet@20240620", "claude-3-sonnet@20240229",
 }
 
 const anthropicVersion = "vertex-2023-10-16"

relay/adaptor/vertexai/claude/model.go

@@ -11,8 +11,8 @@ type Request struct {
 	MaxTokens     int                 `json:"max_tokens,omitempty"`
 	StopSequences []string            `json:"stop_sequences,omitempty"`
 	Stream        bool                `json:"stream,omitempty"`
-	Temperature   *float64            `json:"temperature,omitempty"`
-	TopP          *float64            `json:"top_p,omitempty"`
+	Temperature   float64             `json:"temperature,omitempty"`
+	TopP          float64             `json:"top_p,omitempty"`
 	TopK          int                 `json:"top_k,omitempty"`
 	Tools         []anthropic.Tool    `json:"tools,omitempty"`
 	ToolChoice    any                 `json:"tool_choice,omitempty"`

relay/adaptor/xai/constants.go

@@ -1,5 +0,0 @@
-package xai
-
-var ModelList = []string{
-	"grok-beta",
-}

relay/adaptor/xunfei/main.go

@@ -283,7 +283,7 @@ func parseAPIVersionByModelName(modelName string) string {
 func apiVersion2domain(apiVersion string) string {
 	switch apiVersion {
 	case "v1.1":
-		return "lite"
+		return "general"
 	case "v2.1":
 		return "generalv2"
 	case "v3.1":

relay/adaptor/xunfei/model.go

@@ -19,11 +19,11 @@ type ChatRequest struct {
 	} `json:"header"`
 	Parameter struct {
 		Chat struct {
-			Domain      string   `json:"domain,omitempty"`
-			Temperature *float64 `json:"temperature,omitempty"`
-			TopK        int      `json:"top_k,omitempty"`
-			MaxTokens   int      `json:"max_tokens,omitempty"`
-			Auditing    bool     `json:"auditing,omitempty"`
+			Domain      string  `json:"domain,omitempty"`
+			Temperature float64 `json:"temperature,omitempty"`
+			TopK        int     `json:"top_k,omitempty"`
+			MaxTokens   int     `json:"max_tokens,omitempty"`
+			Auditing    bool    `json:"auditing,omitempty"`
 		} `json:"chat"`
 	} `json:"parameter"`
 	Payload struct {

relay/adaptor/zhipu/adaptor.go

@@ -4,13 +4,13 @@ import (
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
-	"github.com/songquanpeng/one-api/common/helper"
 	"github.com/songquanpeng/one-api/relay/adaptor"
 	"github.com/songquanpeng/one-api/relay/adaptor/openai"
 	"github.com/songquanpeng/one-api/relay/meta"
 	"github.com/songquanpeng/one-api/relay/model"
 	"github.com/songquanpeng/one-api/relay/relaymode"
 	"io"
+	"math"
 	"net/http"
 	"strings"
 )
@@ -65,13 +65,13 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.G
 		baiduEmbeddingRequest, err := ConvertEmbeddingRequest(*request)
 		return baiduEmbeddingRequest, err
 	default:
-		// TopP [0.0, 1.0]
-		request.TopP = helper.Float64PtrMax(request.TopP, 1)
-		request.TopP = helper.Float64PtrMin(request.TopP, 0)
+		// TopP (0.0, 1.0)
+		request.TopP = math.Min(0.99, request.TopP)
+		request.TopP = math.Max(0.01, request.TopP)
 
-		// Temperature [0.0, 1.0]
-		request.Temperature = helper.Float64PtrMax(request.Temperature, 1)
-		request.Temperature = helper.Float64PtrMin(request.Temperature, 0)
+		// Temperature (0.0, 1.0)
+		request.Temperature = math.Min(0.99, request.Temperature)
+		request.Temperature = math.Max(0.01, request.Temperature)
 		a.SetVersionByModeName(request.Model)
 		if a.APIVersion == "v4" {
 			return request, nil

relay/adaptor/zhipu/model.go

@@ -12,8 +12,8 @@ type Message struct {
 
 type Request struct {
 	Prompt      []Message `json:"prompt"`
-	Temperature *float64  `json:"temperature,omitempty"`
-	TopP        *float64  `json:"top_p,omitempty"`
+	Temperature float64   `json:"temperature,omitempty"`
+	TopP        float64   `json:"top_p,omitempty"`
 	RequestId   string    `json:"request_id,omitempty"`
 	Incremental bool      `json:"incremental,omitempty"`
 }

relay/billing/ratio/model.go

@@ -79,7 +79,6 @@ var ModelRatio = map[string]float64{
 	"claude-2.0":                 8.0 / 1000 * USD,
 	"claude-2.1":                 8.0 / 1000 * USD,
 	"claude-3-haiku-20240307":    0.25 / 1000 * USD,
-	"claude-3-5-haiku-20241022":  1.0 / 1000 * USD,
 	"claude-3-sonnet-20240229":   3.0 / 1000 * USD,
 	"claude-3-5-sonnet-20240620": 3.0 / 1000 * USD,
 	"claude-3-5-sonnet-20241022": 3.0 / 1000 * USD,
@@ -209,8 +208,6 @@ var ModelRatio = map[string]float64{
 	"deepl-zh": 25.0 / 1000 * USD,
 	"deepl-en": 25.0 / 1000 * USD,
 	"deepl-ja": 25.0 / 1000 * USD,
-	// https://console.x.ai/
-	"grok-beta": 5.0 / 1000 * USD,
 }
 
 var CompletionRatio = map[string]float64{
@@ -375,8 +372,6 @@ func GetCompletionRatio(name string, channelType int) float64 {
 		return 3
 	case "command-r-plus":
 		return 5
-	case "grok-beta":
-		return 3
 	}
 	return 1
 }

relay/channeltype/define.go

@@ -46,6 +46,5 @@ const (
 	VertextAI
 	Proxy
 	SiliconFlow
-	XAI
 	Dummy
 )

relay/channeltype/url.go

@@ -45,8 +45,7 @@ var ChannelBaseURLs = []string{
 	"https://api.novita.ai/v3/openai",           // 41
 	"",                                          // 42
 	"",                                          // 43
-	"https://api.siliconflow.cn",                // 44
-	"https://api.x.ai",                          // 45
+	"https://api.siliconflow.cn",                 // 44
 }
 
 func init() {

relay/model/general.go

@@ -22,49 +22,34 @@ type StreamOptions struct {
 }
 
 type GeneralOpenAIRequest struct {
-	// https://platform.openai.com/docs/api-reference/chat/create
-	Messages            []Message       `json:"messages,omitempty"`
-	Model               string          `json:"model,omitempty"`
-	Store               *bool           `json:"store,omitempty"`
-	Metadata            any             `json:"metadata,omitempty"`
-	FrequencyPenalty    *float64        `json:"frequency_penalty,omitempty"`
-	LogitBias           any             `json:"logit_bias,omitempty"`
-	Logprobs            *bool           `json:"logprobs,omitempty"`
-	TopLogprobs         *int            `json:"top_logprobs,omitempty"`
-	MaxTokens           int             `json:"max_tokens,omitempty"`
-	MaxCompletionTokens *int            `json:"max_completion_tokens,omitempty"`
-	N                   int             `json:"n,omitempty"`
-	Modalities          []string        `json:"modalities,omitempty"`
-	Prediction          any             `json:"prediction,omitempty"`
-	Audio               *Audio          `json:"audio,omitempty"`
-	PresencePenalty     *float64        `json:"presence_penalty,omitempty"`
-	ResponseFormat      *ResponseFormat `json:"response_format,omitempty"`
-	Seed                float64         `json:"seed,omitempty"`
-	ServiceTier         *string         `json:"service_tier,omitempty"`
-	Stop                any             `json:"stop,omitempty"`
-	Stream              bool            `json:"stream,omitempty"`
-	StreamOptions       *StreamOptions  `json:"stream_options,omitempty"`
-	Temperature         *float64        `json:"temperature,omitempty"`
-	TopP                *float64        `json:"top_p,omitempty"`
-	TopK                int             `json:"top_k,omitempty"`
-	Tools               []Tool          `json:"tools,omitempty"`
-	ToolChoice          any             `json:"tool_choice,omitempty"`
-	ParallelTooCalls    *bool           `json:"parallel_tool_calls,omitempty"`
-	User                string          `json:"user,omitempty"`
-	FunctionCall        any             `json:"function_call,omitempty"`
-	Functions           any             `json:"functions,omitempty"`
-	// https://platform.openai.com/docs/api-reference/embeddings/create
-	Input          any    `json:"input,omitempty"`
-	EncodingFormat string `json:"encoding_format,omitempty"`
-	Dimensions     int    `json:"dimensions,omitempty"`
-	// https://platform.openai.com/docs/api-reference/images/create
-	Prompt  any     `json:"prompt,omitempty"`
-	Quality *string `json:"quality,omitempty"`
-	Size    string  `json:"size,omitempty"`
-	Style   *string `json:"style,omitempty"`
-	// Others
-	Instruction string `json:"instruction,omitempty"`
-	NumCtx      int    `json:"num_ctx,omitempty"`
+	Messages         []Message       `json:"messages,omitempty"`
+	Model            string          `json:"model,omitempty"`
+	Modalities       []string        `json:"modalities,omitempty"`
+	Audio            *Audio          `json:"audio,omitempty"`
+	FrequencyPenalty float64         `json:"frequency_penalty,omitempty"`
+	MaxTokens        int             `json:"max_tokens,omitempty"`
+	N                int             `json:"n,omitempty"`
+	PresencePenalty  float64         `json:"presence_penalty,omitempty"`
+	ResponseFormat   *ResponseFormat `json:"response_format,omitempty"`
+	Seed             float64         `json:"seed,omitempty"`
+	Stop             any             `json:"stop,omitempty"`
+	Stream           bool            `json:"stream,omitempty"`
+	StreamOptions    *StreamOptions  `json:"stream_options,omitempty"`
+	Temperature      float64         `json:"temperature,omitempty"`
+	TopP             float64         `json:"top_p,omitempty"`
+	TopK             int             `json:"top_k,omitempty"`
+	Tools            []Tool          `json:"tools,omitempty"`
+	ToolChoice       any             `json:"tool_choice,omitempty"`
+	FunctionCall     any             `json:"function_call,omitempty"`
+	Functions        any             `json:"functions,omitempty"`
+	User             string          `json:"user,omitempty"`
+	Prompt           any             `json:"prompt,omitempty"`
+	Input            any             `json:"input,omitempty"`
+	EncodingFormat   string          `json:"encoding_format,omitempty"`
+	Dimensions       int             `json:"dimensions,omitempty"`
+	Instruction      string          `json:"instruction,omitempty"`
+	Size             string          `json:"size,omitempty"`
+	NumCtx           int             `json:"num_ctx,omitempty"`
 }
 
 func (r GeneralOpenAIRequest) ParseInput() []string {

web/air/src/constants/channel.constants.js

@@ -30,7 +30,6 @@ export const CHANNEL_OPTIONS = [
   { key: 42, text: 'VertexAI', value: 42, color: 'blue' },
   { key: 43, text: 'Proxy', value: 43, color: 'blue' },
   { key: 44, text: 'SiliconFlow', value: 44, color: 'blue' },
-  { key: 45, text: 'xAI', value: 45, color: 'blue' },
   { key: 8, text: '自定义渠道', value: 8, color: 'pink' },
   { key: 22, text: '知识库：FastGPT', value: 22, color: 'blue' },
   { key: 21, text: '知识库：AI Proxy', value: 21, color: 'purple' },

web/air/src/pages/Channel/EditChannel.js

@@ -63,7 +63,7 @@ const EditChannel = (props) => {
             let localModels = [];
             switch (value) {
                 case 14:
-                    localModels = ["claude-instant-1.2", "claude-2", "claude-2.0", "claude-2.1", "claude-3-opus-20240229", "claude-3-sonnet-20240229", "claude-3-haiku-20240307", "claude-3-5-haiku-20241022", "claude-3-5-sonnet-20240620", "claude-3-5-sonnet-20241022"];
+                    localModels = ["claude-instant-1.2", "claude-2", "claude-2.0", "claude-2.1", "claude-3-opus-20240229", "claude-3-sonnet-20240229", "claude-3-haiku-20240307", "claude-3-5-sonnet-20240620", "claude-3-5-sonnet-20241022"];
                     break;
                 case 11:
                     localModels = ['PaLM-2'];

web/berry/src/constants/ChannelConstants.js

@@ -179,12 +179,6 @@ export const CHANNEL_OPTIONS = {
     value: 44,
     color: 'primary'
   },
-  45: {
-    key: 45,
-    text: 'xAI',
-    value: 45,
-    color: 'primary'
-  },
   41: {
     key: 41,
     text: 'Novita',

web/berry/src/views/Channel/type/Config.js

@@ -223,9 +223,6 @@ const typeConfig = {
     },
     modelGroup: 'anthropic'
   },
-  45: {
-    modelGroup: 'xai'
-  },
 };
 
 export { defaultConfig, typeConfig };

web/default/src/constants/channel.constants.js

@@ -30,7 +30,6 @@ export const CHANNEL_OPTIONS = [
     { key: 42, text: 'VertexAI', value: 42, color: 'blue' },
     { key: 43, text: 'Proxy', value: 43, color: 'blue' },
     { key: 44, text: 'SiliconFlow', value: 44, color: 'blue' },
-    { key: 45, text: 'xAI', value: 45, color: 'blue' },
     { key: 8, text: '自定义渠道', value: 8, color: 'pink' },
     { key: 22, text: '知识库：FastGPT', value: 22, color: 'blue' },
     { key: 21, text: '知识库：AI Proxy', value: 21, color: 'purple' },