diff --git a/.github/workflows/linux-release.yml b/.github/workflows/linux-release.yml index a3db3e79..3ddabc6d 100644 --- a/.github/workflows/linux-release.yml +++ b/.github/workflows/linux-release.yml @@ -17,7 +17,7 @@ jobs: fetch-depth: 0 - uses: actions/setup-node@v3 with: - node-version: 16 + node-version: 18 - name: Build Frontend env: CI: "" diff --git a/.github/workflows/macos-release.yml b/.github/workflows/macos-release.yml index cdb577ba..dbdeac56 100644 --- a/.github/workflows/macos-release.yml +++ b/.github/workflows/macos-release.yml @@ -17,7 +17,7 @@ jobs: fetch-depth: 0 - uses: actions/setup-node@v3 with: - node-version: 16 + node-version: 18 - name: Build Frontend env: CI: "" diff --git a/.github/workflows/windows-release.yml b/.github/workflows/windows-release.yml index b90eb592..6b63ad0b 100644 --- a/.github/workflows/windows-release.yml +++ b/.github/workflows/windows-release.yml @@ -20,7 +20,7 @@ jobs: fetch-depth: 0 - uses: actions/setup-node@v3 with: - node-version: 16 + node-version: 18 - name: Build Frontend env: CI: "" diff --git a/Dockerfile b/Dockerfile index 4e0d0511..a32fd615 100644 --- a/Dockerfile +++ b/Dockerfile @@ -24,8 +24,8 @@ FROM alpine RUN apk update \ && apk upgrade \ - && apk add --no-cache ca-certificates tzdata ffmpeg\ - && update-ca-certificates 2>/dev/null || true + && apk add --no-cache ca-certificates tzdata ffmpeg \ + && update-ca-certificates COPY --from=builder2 /build/one-api / EXPOSE 3000 diff --git a/README.en.md b/README.en.md index 1ebea4e5..dc6696a0 100644 --- a/README.en.md +++ b/README.en.md @@ -59,6 +59,10 @@ 13. 🎵 Added [Suno API](https://github.com/Suno-API/Suno-API) interface support, [Integration Guide](Suno.md) 14. 🔄 Support for Rerank models, compatible with Cohere and Jina, can integrate with Dify, [Integration Guide](Rerank.md) 15. ⚡ **[OpenAI Realtime API](https://platform.openai.com/docs/guides/realtime/integration)** - Support for OpenAI's Realtime API, including Azure channels +16. 🧠 Support for setting reasoning effort through model name suffix: + - Add suffix `-high` to set high reasoning effort (e.g., `o3-mini-high`) + - Add suffix `-medium` to set medium reasoning effort + - Add suffix `-low` to set low reasoning effort ## Model Support This version additionally supports: @@ -84,6 +88,7 @@ You can add custom models gpt-4-gizmo-* in channels. These are third-party model - `GEMINI_VISION_MAX_IMAGE_NUM`: Gemini model maximum image number, default `16`, set to `-1` to disable - `MAX_FILE_DOWNLOAD_MB`: Maximum file download size in MB, default `20` - `CRYPTO_SECRET`: Encryption key for encrypting database content +- `AZURE_DEFAULT_API_VERSION`: Azure channel default API version, if not specified in channel settings, use this version, default `2024-12-01-preview` ## Deployment > [!TIP] diff --git a/README.md b/README.md index 8e868061..8ee539ec 100644 --- a/README.md +++ b/README.md @@ -65,6 +65,10 @@ 14. 🔄 支持Rerank模型，目前兼容Cohere和Jina，可接入Dify，[对接文档](Rerank.md) 15. ⚡ **[OpenAI Realtime API](https://platform.openai.com/docs/guides/realtime/integration)** - 支持OpenAI的Realtime API，支持Azure渠道 16. 支持使用路由/chat2link 进入聊天界面 +17. 🧠 支持通过模型名称后缀设置 reasoning effort： + - 添加后缀 `-high` 设置为 high reasoning effort (例如: `o3-mini-high`) + - 添加后缀 `-medium` 设置为 medium reasoning effort (例如: `o3-mini-medium`) + - 添加后缀 `-low` 设置为 low reasoning effort (例如: `o3-mini-low`) ## 模型支持 此版本额外支持以下模型： @@ -85,11 +89,12 @@ - `GET_MEDIA_TOKEN`：是否统计图片token，默认为 `true`，关闭后将不再在本地计算图片token，可能会导致和上游计费不同，此项覆盖 `GET_MEDIA_TOKEN_NOT_STREAM` 选项作用。 - `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(v1beta) -- `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`。 +- `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(v1beta) +- `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`。 - `GEMINI_VISION_MAX_IMAGE_NUM`：Gemini模型最大图片数量，默认为 `16`，设置为 `-1` 则不限制。 - `MAX_FILE_DOWNLOAD_MB`: 最大文件下载大小，单位 MB，默认为 `20`。 - `CRYPTO_SECRET`：加密密钥，用于加密数据库内容。 +- `AZURE_DEFAULT_API_VERSION`：Azure渠道默认API版本，如果渠道设置中未指定API版本，则使用此版本，默认为 `2024-12-01-preview` ## 部署 > [!TIP] > 最新版Docker镜像：`calciumion/new-api:latest` diff --git a/common/logger.go b/common/logger.go index 02ddb71c..93d557d8 100644 --- a/common/logger.go +++ b/common/logger.go @@ -36,7 +36,7 @@ func SetupLogger() { setupLogLock.Unlock() setupLogWorking = false }() - logPath := filepath.Join(*LogDir, fmt.Sprintf("oneapi-%s.log", time.Now().Format("20060102"))) + logPath := filepath.Join(*LogDir, fmt.Sprintf("oneapi-%s.log", time.Now().Format("20060102150405"))) fd, err := os.OpenFile(logPath, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0644) if err != nil { log.Fatal("failed to open log file") diff --git a/common/model-ratio.go b/common/model-ratio.go index 8fd996d6..e3482ba1 100644 --- a/common/model-ratio.go +++ b/common/model-ratio.go @@ -50,16 +50,24 @@ var defaultModelRatio = map[string]float64{ "gpt-4o-realtime-preview-2024-12-17": 2.5, "gpt-4o-mini-realtime-preview": 0.3, "gpt-4o-mini-realtime-preview-2024-12-17": 0.3, - "o1": 7.5, - "o1-2024-12-17": 7.5, - "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 - "gpt-4-turbo-2024-04-09": 5, // $0.01 / 1K tokens + "o1": 7.5, + "o1-2024-12-17": 7.5, + "o1-preview": 7.5, + "o1-preview-2024-09-12": 7.5, + "o1-mini": 0.55, + "o1-mini-2024-09-12": 0.55, + "o3-mini": 0.55, + "o3-mini-2025-01-31": 0.55, + "o3-mini-high": 0.55, + "o3-mini-2025-01-31-high": 0.55, + "o3-mini-low": 0.55, + "o3-mini-2025-01-31-low": 0.55, + "o3-mini-medium": 0.55, + "o3-mini-2025-01-31-medium": 0.55, + "gpt-4o-mini": 0.075, + "gpt-4o-mini-2024-07-18": 0.075, + "gpt-4-turbo": 5, // $0.01 / 1K tokens + "gpt-4-turbo-2024-04-09": 5, // $0.01 / 1K tokens //"gpt-3.5-turbo-0301": 0.75, //deprecated "gpt-3.5-turbo": 0.25, "gpt-3.5-turbo-0613": 0.75, @@ -342,6 +350,12 @@ func UpdateCompletionRatioByJSONString(jsonStr string) error { } func GetCompletionRatio(name string) float64 { + if strings.Contains(name, "/") { + if ratio, ok := CompletionRatio[name]; ok { + return ratio + } + } + lowercaseName := strings.ToLower(name) if strings.HasPrefix(name, "gpt-4-gizmo") { name = "gpt-4-gizmo-*" } @@ -360,7 +374,7 @@ func GetCompletionRatio(name string) float64 { } return 2 } - if strings.HasPrefix(name, "o1") { + if strings.HasPrefix(name, "o1") || strings.HasPrefix(name, "o3") { return 4 } if name == "chatgpt-4o-latest" { @@ -404,8 +418,8 @@ func GetCompletionRatio(name string) float64 { return 4 } } - if strings.HasPrefix(name, "deepseek") { - if name == "deepseek-reasoner" { + if strings.HasPrefix(lowercaseName, "deepseek") { + if strings.HasSuffix(lowercaseName, "reasoner") || strings.HasSuffix(lowercaseName, "r1") { return 4 } return 2 diff --git a/constant/channel_setting.go b/constant/channel_setting.go index 71b9f58b..6eccfb84 100644 --- a/constant/channel_setting.go +++ b/constant/channel_setting.go @@ -1,5 +1,6 @@ package constant var ( - ForceFormat = "force_format" // ForceFormat 强制格式化为OpenAI格式 + ForceFormat = "force_format" // ForceFormat 强制格式化为OpenAI格式 + ChanelSettingProxy = "proxy" // Proxy 代理 ) diff --git a/constant/env.go b/constant/env.go index cd2d71b2..4135e8c7 100644 --- a/constant/env.go +++ b/constant/env.go @@ -21,6 +21,8 @@ var GetMediaTokenNotStream = common.GetEnvOrDefaultBool("GET_MEDIA_TOKEN_NOT_STR var UpdateTask = common.GetEnvOrDefaultBool("UPDATE_TASK", true) +var AzureDefaultAPIVersion = common.GetEnvOrDefaultString("AZURE_DEFAULT_API_VERSION", "2024-12-01-preview") + var GeminiModelMap = map[string]string{ "gemini-1.0-pro": "v1", } diff --git a/controller/channel-billing.go b/controller/channel-billing.go index 96f82ee3..41f8d8f7 100644 --- a/controller/channel-billing.go +++ b/controller/channel-billing.go @@ -78,6 +78,36 @@ type APGC2DGPTUsageResponse struct { TotalUsed float64 `json:"total_used"` } +type SiliconFlowUsageResponse struct { + Code int `json:"code"` + Message string `json:"message"` + Status bool `json:"status"` + Data struct { + ID string `json:"id"` + Name string `json:"name"` + Image string `json:"image"` + Email string `json:"email"` + IsAdmin bool `json:"isAdmin"` + Balance string `json:"balance"` + Status string `json:"status"` + Introduction string `json:"introduction"` + Role string `json:"role"` + ChargeBalance string `json:"chargeBalance"` + TotalBalance string `json:"totalBalance"` + Category string `json:"category"` + } `json:"data"` +} + +type DeepSeekUsageResponse struct { + IsAvailable bool `json:"is_available"` + BalanceInfos []struct { + Currency string `json:"currency"` + TotalBalance string `json:"total_balance"` + GrantedBalance string `json:"granted_balance"` + ToppedUpBalance string `json:"topped_up_balance"` + } `json:"balance_infos"` +} + // GetAuthHeader get auth header func GetAuthHeader(token string) http.Header { h := http.Header{} @@ -185,6 +215,57 @@ func updateChannelAPI2GPTBalance(channel *model.Channel) (float64, error) { return response.TotalRemaining, nil } +func updateChannelSiliconFlowBalance(channel *model.Channel) (float64, error) { + url := "https://api.siliconflow.cn/v1/user/info" + body, err := GetResponseBody("GET", url, channel, GetAuthHeader(channel.Key)) + if err != nil { + return 0, err + } + response := SiliconFlowUsageResponse{} + err = json.Unmarshal(body, &response) + if err != nil { + return 0, err + } + if response.Code != 20000 { + return 0, fmt.Errorf("code: %d, message: %s", response.Code, response.Message) + } + balance, err := strconv.ParseFloat(response.Data.TotalBalance, 64) + if err != nil { + return 0, err + } + channel.UpdateBalance(balance) + return balance, nil +} + +func updateChannelDeepSeekBalance(channel *model.Channel) (float64, error) { + url := "https://api.deepseek.com/user/balance" + body, err := GetResponseBody("GET", url, channel, GetAuthHeader(channel.Key)) + if err != nil { + return 0, err + } + response := DeepSeekUsageResponse{} + err = json.Unmarshal(body, &response) + if err != nil { + return 0, err + } + index := -1 + for i, balanceInfo := range response.BalanceInfos { + if balanceInfo.Currency == "CNY" { + index = i + break + } + } + if index == -1 { + return 0, errors.New("currency CNY not found") + } + balance, err := strconv.ParseFloat(response.BalanceInfos[index].TotalBalance, 64) + if err != nil { + return 0, err + } + channel.UpdateBalance(balance) + return balance, nil +} + func updateChannelAIGC2DBalance(channel *model.Channel) (float64, error) { url := "https://api.aigc2d.com/dashboard/billing/credit_grants" body, err := GetResponseBody("GET", url, channel, GetAuthHeader(channel.Key)) @@ -222,6 +303,10 @@ func updateChannelBalance(channel *model.Channel) (float64, error) { return updateChannelAPI2GPTBalance(channel) case common.ChannelTypeAIGC2D: return updateChannelAIGC2DBalance(channel) + case common.ChannelTypeSiliconFlow: + return updateChannelSiliconFlowBalance(channel) + case common.ChannelTypeDeepSeek: + return updateChannelDeepSeekBalance(channel) default: return 0, errors.New("尚未实现") } @@ -300,9 +385,9 @@ func updateAllChannelsBalance() error { continue } // TODO: support Azure - if channel.Type != common.ChannelTypeOpenAI && channel.Type != common.ChannelTypeCustom { - continue - } + //if channel.Type != common.ChannelTypeOpenAI && channel.Type != common.ChannelTypeCustom { + // continue + //} balance, err := updateChannelBalance(channel) if err != nil { continue diff --git a/controller/channel-test.go b/controller/channel-test.go index ea325b47..de530988 100644 --- a/controller/channel-test.go +++ b/controller/channel-test.go @@ -170,6 +170,7 @@ func buildTestRequest(model string) *dto.GeneralOpenAIRequest { Model: "", // this will be set later Stream: false, } + // 先判断是否为 Embedding 模型 if strings.Contains(strings.ToLower(model), "embedding") || strings.HasPrefix(model, "m3e") || // m3e 系列模型 @@ -180,10 +181,10 @@ func buildTestRequest(model string) *dto.GeneralOpenAIRequest { return testRequest } // 并非Embedding 模型 - if strings.HasPrefix(model, "o1") { + if strings.HasPrefix(model, "o1") || strings.HasPrefix(model, "o3") { testRequest.MaxCompletionTokens = 10 } else if strings.HasPrefix(model, "gemini-2.0-flash-thinking") { - testRequest.MaxTokens = 2 + testRequest.MaxTokens = 10 } else { testRequest.MaxTokens = 1 } diff --git a/controller/channel.go b/controller/channel.go index b1fdd0c3..f3ec6b3a 100644 --- a/controller/channel.go +++ b/controller/channel.go @@ -510,6 +510,7 @@ func UpdateChannel(c *gin.Context) { func FetchModels(c *gin.Context) { var req struct { BaseURL string `json:"base_url"` + Type int `json:"type"` Key string `json:"key"` } @@ -523,7 +524,7 @@ func FetchModels(c *gin.Context) { baseURL := req.BaseURL if baseURL == "" { - baseURL = "https://api.openai.com" + baseURL = common.ChannelBaseURLs[req.Type] } client := &http.Client{} @@ -538,7 +539,11 @@ func FetchModels(c *gin.Context) { return } - request.Header.Set("Authorization", "Bearer "+req.Key) + // remove line breaks and extra spaces. + key := strings.TrimSpace(req.Key) + // If the key contains a line break, only take the first part. + key = strings.Split(key, "\n")[0] + request.Header.Set("Authorization", "Bearer "+key) response, err := client.Do(request) if err != nil { diff --git a/controller/misc.go b/controller/misc.go index db94840d..1ea0c133 100644 --- a/controller/misc.go +++ b/controller/misc.go @@ -66,6 +66,7 @@ func GetStatus(c *gin.Context) { "enable_online_topup": setting.PayAddress != "" && setting.EpayId != "" && setting.EpayKey != "", "mj_notify_enabled": setting.MjNotifyEnabled, "chats": setting.Chats, + "demo_site_enabled": setting.DemoSiteEnabled, }, }) return diff --git a/docs/channel/other_setting.md b/docs/channel/other_setting.md new file mode 100644 index 00000000..775da557 --- /dev/null +++ b/docs/channel/other_setting.md @@ -0,0 +1,28 @@ +# 渠道而外设置说明 + +该配置用于设置一些额外的渠道参数，可以通过 JSON 对象进行配置。主要包含以下两个设置项： + +1. force_format + - 用于标识是否对数据进行强制格式化为 OpenAI 格式 + - 类型为布尔值，设置为 true 时启用强制格式化 + +2. proxy + - 用于配置网络代理 + - 类型为字符串，填写代理地址（例如 socks5 协议的代理地址） + +-------------------------------------------------------------- + +## JSON 格式示例 + +以下是一个示例配置，启用强制格式化并设置了代理地址： + +```json +{ + "force_format": true, + "proxy": "socks5://xxxxxxx" +} +``` + +-------------------------------------------------------------- + +通过调整上述 JSON 配置中的值，可以灵活控制渠道的额外行为，比如是否进行格式化以及使用特定的网络代理。 \ No newline at end of file diff --git a/dto/openai_request.go b/dto/openai_request.go index 4590e7b2..628b3dd2 100644 --- a/dto/openai_request.go +++ b/dto/openai_request.go @@ -23,7 +23,7 @@ type GeneralOpenAIRequest struct { MaxTokens uint `json:"max_tokens,omitempty"` MaxCompletionTokens uint `json:"max_completion_tokens,omitempty"` ReasoningEffort string `json:"reasoning_effort,omitempty"` - Temperature float64 `json:"temperature,omitempty"` + Temperature *float64 `json:"temperature,omitempty"` TopP float64 `json:"top_p,omitempty"` TopK int `json:"top_k,omitempty"` Stop any `json:"stop,omitempty"` diff --git a/model/log.go b/model/log.go index dd5a3162..d050fb6a 100644 --- a/model/log.go +++ b/model/log.go @@ -43,6 +43,7 @@ const ( func formatUserLogs(logs []*Log) { for i := range logs { + logs[i].ChannelName = "" var otherMap map[string]interface{} otherMap = common.StrToMap(logs[i].Other) if otherMap != nil { @@ -129,38 +130,38 @@ func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName if logType == LogTypeUnknown { tx = LOG_DB } else { - tx = LOG_DB.Where("type = ?", logType) + tx = LOG_DB.Where("logs.type = ?", logType) } tx = tx.Joins("LEFT JOIN channels ON logs.channel_id = channels.id") tx = tx.Select("logs.*, channels.name as channel_name") if modelName != "" { - tx = tx.Where("model_name like ?", modelName) + tx = tx.Where("logs.model_name like ?", modelName) } if username != "" { - tx = tx.Where("username = ?", username) + tx = tx.Where("logs.username = ?", username) } if tokenName != "" { - tx = tx.Where("token_name = ?", tokenName) + tx = tx.Where("logs.token_name = ?", tokenName) } if startTimestamp != 0 { - tx = tx.Where("created_at >= ?", startTimestamp) + tx = tx.Where("logs.created_at >= ?", startTimestamp) } if endTimestamp != 0 { - tx = tx.Where("created_at <= ?", endTimestamp) + tx = tx.Where("logs.created_at <= ?", endTimestamp) } if channel != 0 { - tx = tx.Where("channel_id = ?", channel) + tx = tx.Where("logs.channel_id = ?", channel) } if group != "" { - tx = tx.Where(groupCol+" = ?", group) + tx = tx.Where("logs."+groupCol+" = ?", group) } err = tx.Model(&Log{}).Count(&total).Error if err != nil { return nil, 0, err } - err = tx.Order("id desc").Limit(num).Offset(startIdx).Find(&logs).Error + err = tx.Order("logs.id desc").Limit(num).Offset(startIdx).Find(&logs).Error if err != nil { return nil, 0, err } @@ -170,34 +171,34 @@ func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int64, modelName string, tokenName string, startIdx int, num int, group string) (logs []*Log, total int64, err error) { var tx *gorm.DB if logType == LogTypeUnknown { - tx = LOG_DB.Where("user_id = ?", userId) + tx = LOG_DB.Where("logs.user_id = ?", userId) } else { - tx = LOG_DB.Where("user_id = ? and type = ?", userId, logType) + tx = LOG_DB.Where("logs.user_id = ? and logs.type = ?", userId, logType) } tx = tx.Joins("LEFT JOIN channels ON logs.channel_id = channels.id") tx = tx.Select("logs.*, channels.name as channel_name") if modelName != "" { - tx = tx.Where("model_name like ?", modelName) + tx = tx.Where("logs.model_name like ?", modelName) } if tokenName != "" { - tx = tx.Where("token_name = ?", tokenName) + tx = tx.Where("logs.token_name = ?", tokenName) } if startTimestamp != 0 { - tx = tx.Where("created_at >= ?", startTimestamp) + tx = tx.Where("logs.created_at >= ?", startTimestamp) } if endTimestamp != 0 { - tx = tx.Where("created_at <= ?", endTimestamp) + tx = tx.Where("logs.created_at <= ?", endTimestamp) } if group != "" { - tx = tx.Where(groupCol+" = ?", group) + tx = tx.Where("logs."+groupCol+" = ?", group) } err = tx.Model(&Log{}).Count(&total).Error if err != nil { return nil, 0, err } - err = tx.Order("id desc").Limit(num).Offset(startIdx).Find(&logs).Error + err = tx.Order("logs.id desc").Limit(num).Offset(startIdx).Find(&logs).Error formatUserLogs(logs) return logs, total, err } diff --git a/model/option.go b/model/option.go index 1daf40fb..f1f2809d 100644 --- a/model/option.go +++ b/model/option.go @@ -104,6 +104,7 @@ func InitOptionMap() { common.OptionMap["MjForwardUrlEnabled"] = strconv.FormatBool(setting.MjForwardUrlEnabled) common.OptionMap["MjActionCheckSuccessEnabled"] = strconv.FormatBool(setting.MjActionCheckSuccessEnabled) common.OptionMap["CheckSensitiveEnabled"] = strconv.FormatBool(setting.CheckSensitiveEnabled) + common.OptionMap["DemoSiteEnabled"] = strconv.FormatBool(setting.DemoSiteEnabled) common.OptionMap["CheckSensitiveOnPromptEnabled"] = strconv.FormatBool(setting.CheckSensitiveOnPromptEnabled) //common.OptionMap["CheckSensitiveOnCompletionEnabled"] = strconv.FormatBool(constant.CheckSensitiveOnCompletionEnabled) common.OptionMap["StopOnSensitiveEnabled"] = strconv.FormatBool(setting.StopOnSensitiveEnabled) @@ -220,6 +221,8 @@ func updateOptionMap(key string, value string) (err error) { setting.MjActionCheckSuccessEnabled = boolValue case "CheckSensitiveEnabled": setting.CheckSensitiveEnabled = boolValue + case "DemoSiteEnabled": + setting.DemoSiteEnabled = boolValue case "CheckSensitiveOnPromptEnabled": setting.CheckSensitiveOnPromptEnabled = boolValue //case "CheckSensitiveOnCompletionEnabled": diff --git a/relay/channel/api_request.go b/relay/channel/api_request.go index 8b51c535..cd1b5153 100644 --- a/relay/channel/api_request.go +++ b/relay/channel/api_request.go @@ -39,7 +39,7 @@ func DoApiRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody if err != nil { return nil, fmt.Errorf("setup request header failed: %w", err) } - resp, err := doRequest(c, req) + resp, err := doRequest(c, req, info) if err != nil { return nil, fmt.Errorf("do request failed: %w", err) } @@ -62,7 +62,7 @@ func DoFormRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBod if err != nil { return nil, fmt.Errorf("setup request header failed: %w", err) } - resp, err := doRequest(c, req) + resp, err := doRequest(c, req, info) if err != nil { return nil, fmt.Errorf("do request failed: %w", err) } @@ -90,8 +90,18 @@ func DoWssRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody return targetConn, nil } -func doRequest(c *gin.Context, req *http.Request) (*http.Response, error) { - resp, err := service.GetHttpClient().Do(req) +func doRequest(c *gin.Context, req *http.Request, info *common.RelayInfo) (*http.Response, error) { + var client *http.Client + var err error + if proxyURL, ok := info.ChannelSetting["proxy"]; ok { + client, err = service.NewProxyHttpClient(proxyURL.(string)) + if err != nil { + return nil, fmt.Errorf("new proxy http client failed: %w", err) + } + } else { + client = service.GetHttpClient() + } + resp, err := client.Do(req) if err != nil { return nil, err } @@ -120,7 +130,7 @@ func DoTaskApiRequest(a TaskAdaptor, c *gin.Context, info *common.TaskRelayInfo, if err != nil { return nil, fmt.Errorf("setup request header failed: %w", err) } - resp, err := doRequest(c, req) + resp, err := doRequest(c, req, info.ToRelayInfo()) if err != nil { return nil, fmt.Errorf("do request failed: %w", err) } diff --git a/relay/channel/aws/dto.go b/relay/channel/aws/dto.go index 9f4221a1..505967ad 100644 --- a/relay/channel/aws/dto.go +++ b/relay/channel/aws/dto.go @@ -10,7 +10,7 @@ type AwsClaudeRequest struct { System string `json:"system,omitempty"` Messages []claude.ClaudeMessage `json:"messages"` MaxTokens uint `json:"max_tokens,omitempty"` - Temperature float64 `json:"temperature,omitempty"` + Temperature *float64 `json:"temperature,omitempty"` TopP float64 `json:"top_p,omitempty"` TopK int `json:"top_k,omitempty"` StopSequences []string `json:"stop_sequences,omitempty"` diff --git a/relay/channel/baidu/dto.go b/relay/channel/baidu/dto.go index f0c6f048..a486de5a 100644 --- a/relay/channel/baidu/dto.go +++ b/relay/channel/baidu/dto.go @@ -12,7 +12,7 @@ type BaiduMessage struct { type BaiduChatRequest struct { Messages []BaiduMessage `json:"messages"` - Temperature float64 `json:"temperature,omitempty"` + Temperature *float64 `json:"temperature,omitempty"` TopP float64 `json:"top_p,omitempty"` PenaltyScore float64 `json:"penalty_score,omitempty"` Stream bool `json:"stream,omitempty"` diff --git a/relay/channel/claude/dto.go b/relay/channel/claude/dto.go index 8f289e3a..13a1430c 100644 --- a/relay/channel/claude/dto.go +++ b/relay/channel/claude/dto.go @@ -50,7 +50,7 @@ type ClaudeRequest struct { MaxTokens uint `json:"max_tokens,omitempty"` MaxTokensToSample uint `json:"max_tokens_to_sample,omitempty"` StopSequences []string `json:"stop_sequences,omitempty"` - Temperature float64 `json:"temperature,omitempty"` + Temperature *float64 `json:"temperature,omitempty"` TopP float64 `json:"top_p,omitempty"` TopK int `json:"top_k,omitempty"` //ClaudeMetadata `json:"metadata,omitempty"` diff --git a/relay/channel/cloudflare/dto.go b/relay/channel/cloudflare/dto.go index 2f6531c0..62a45c40 100644 --- a/relay/channel/cloudflare/dto.go +++ b/relay/channel/cloudflare/dto.go @@ -9,7 +9,7 @@ type CfRequest 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"` } type CfAudioResponse struct { diff --git a/relay/channel/gemini/dto.go b/relay/channel/gemini/dto.go index 6ab002ef..08a5db84 100644 --- a/relay/channel/gemini/dto.go +++ b/relay/channel/gemini/dto.go @@ -71,7 +71,7 @@ type GeminiChatTool struct { } type GeminiChatGenerationConfig struct { - Temperature float64 `json:"temperature,omitempty"` + Temperature *float64 `json:"temperature,omitempty"` TopP float64 `json:"topP,omitempty"` TopK float64 `json:"topK,omitempty"` MaxOutputTokens uint `json:"maxOutputTokens,omitempty"` diff --git a/relay/channel/ollama/dto.go b/relay/channel/ollama/dto.go index 980992a0..08019115 100644 --- a/relay/channel/ollama/dto.go +++ b/relay/channel/ollama/dto.go @@ -6,7 +6,7 @@ type OllamaRequest struct { Model string `json:"model,omitempty"` Messages []dto.Message `json:"messages,omitempty"` Stream bool `json:"stream,omitempty"` - Temperature float64 `json:"temperature,omitempty"` + Temperature *float64 `json:"temperature,omitempty"` Seed float64 `json:"seed,omitempty"` Topp float64 `json:"top_p,omitempty"` TopK int `json:"top_k,omitempty"` @@ -18,14 +18,14 @@ type OllamaRequest struct { } 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 OllamaEmbeddingRequest struct { diff --git a/relay/channel/openai/adaptor.go b/relay/channel/openai/adaptor.go index 718b26a1..d86b33e0 100644 --- a/relay/channel/openai/adaptor.go +++ b/relay/channel/openai/adaptor.go @@ -10,6 +10,7 @@ import ( "mime/multipart" "net/http" "one-api/common" + constant2 "one-api/constant" "one-api/dto" "one-api/relay/channel" "one-api/relay/channel/ai360" @@ -44,16 +45,20 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) { } switch info.ChannelType { case common.ChannelTypeAzure: + apiVersion := info.ApiVersion + if apiVersion == "" { + apiVersion = constant2.AzureDefaultAPIVersion + } // https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=rest-api&tabs=command-line#rest-api requestURL := strings.Split(info.RequestURLPath, "?")[0] - requestURL = fmt.Sprintf("%s?api-version=%s", requestURL, info.ApiVersion) + requestURL = fmt.Sprintf("%s?api-version=%s", requestURL, apiVersion) task := strings.TrimPrefix(requestURL, "/v1/") model_ := info.UpstreamModelName model_ = strings.Replace(model_, ".", "", -1) // https://github.com/songquanpeng/one-api/issues/67 requestURL = fmt.Sprintf("/openai/deployments/%s/%s", model_, task) if info.RelayMode == constant.RelayModeRealtime { - requestURL = fmt.Sprintf("/openai/realtime?deployment=%s&api-version=%s", model_, info.ApiVersion) + requestURL = fmt.Sprintf("/openai/realtime?deployment=%s&api-version=%s", model_, apiVersion) } return relaycommon.GetFullRequestURL(info.BaseUrl, requestURL, info.ChannelType), nil case common.ChannelTypeMiniMax: @@ -109,13 +114,28 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re if info.ChannelType != common.ChannelTypeOpenAI && info.ChannelType != common.ChannelTypeAzure { request.StreamOptions = nil } - if strings.HasPrefix(request.Model, "o1") { + if strings.HasPrefix(request.Model, "o1") || strings.HasPrefix(request.Model, "o3") { if request.MaxCompletionTokens == 0 && request.MaxTokens != 0 { request.MaxCompletionTokens = request.MaxTokens request.MaxTokens = 0 } + if strings.HasPrefix(request.Model, "o3") { + request.Temperature = nil + } + if strings.HasSuffix(request.Model, "-high") { + request.ReasoningEffort = "high" + request.Model = strings.TrimSuffix(request.Model, "-high") + } else if strings.HasSuffix(request.Model, "-low") { + request.ReasoningEffort = "low" + request.Model = strings.TrimSuffix(request.Model, "-low") + } else if strings.HasSuffix(request.Model, "-medium") { + request.ReasoningEffort = "medium" + request.Model = strings.TrimSuffix(request.Model, "-medium") + } + info.ReasoningEffort = request.ReasoningEffort + info.UpstreamModelName = request.Model } - if request.Model == "o1" || request.Model == "o1-2024-12-17" { + if request.Model == "o1" || request.Model == "o1-2024-12-17" || strings.HasPrefix(request.Model, "o3") { //修改第一个Message的内容，将system改为developer if len(request.Messages) > 0 && request.Messages[0].Role == "system" { request.Messages[0].Role = "developer" diff --git a/relay/channel/openai/constant.go b/relay/channel/openai/constant.go index 342957ee..d55242ed 100644 --- a/relay/channel/openai/constant.go +++ b/relay/channel/openai/constant.go @@ -13,6 +13,10 @@ var ModelList = []string{ "gpt-4o-mini", "gpt-4o-mini-2024-07-18", "o1-preview", "o1-preview-2024-09-12", "o1-mini", "o1-mini-2024-09-12", + "o3-mini", "o3-mini-2025-01-31", + "o3-mini-high", "o3-mini-2025-01-31-high", + "o3-mini-low", "o3-mini-2025-01-31-low", + "o3-mini-medium", "o3-mini-2025-01-31-medium", "o1", "o1-2024-12-17", "gpt-4o-audio-preview", "gpt-4o-audio-preview-2024-10-01", "gpt-4o-realtime-preview", "gpt-4o-realtime-preview-2024-10-01", "gpt-4o-realtime-preview-2024-12-17", diff --git a/relay/channel/palm/dto.go b/relay/channel/palm/dto.go index 46cf59da..b8a48e73 100644 --- a/relay/channel/palm/dto.go +++ b/relay/channel/palm/dto.go @@ -18,7 +18,7 @@ type PaLMPrompt struct { type PaLMChatRequest struct { Prompt PaLMPrompt `json:"prompt"` - Temperature float64 `json:"temperature,omitempty"` + Temperature *float64 `json:"temperature,omitempty"` CandidateCount int `json:"candidateCount,omitempty"` TopP float64 `json:"topP,omitempty"` TopK uint `json:"topK,omitempty"` diff --git a/relay/channel/tencent/relay-tencent.go b/relay/channel/tencent/relay-tencent.go index 6d0f3471..dd3ac93f 100644 --- a/relay/channel/tencent/relay-tencent.go +++ b/relay/channel/tencent/relay-tencent.go @@ -39,9 +39,7 @@ func requestOpenAI2Tencent(a *Adaptor, request dto.GeneralOpenAIRequest) *Tencen if request.TopP != 0 { req.TopP = &request.TopP } - if request.Temperature != 0 { - req.Temperature = &request.Temperature - } + req.Temperature = request.Temperature return &req } diff --git a/relay/channel/vertex/dto.go b/relay/channel/vertex/dto.go index b54a4aa8..3889c343 100644 --- a/relay/channel/vertex/dto.go +++ b/relay/channel/vertex/dto.go @@ -9,7 +9,7 @@ type VertexAIClaudeRequest struct { MaxTokens int `json:"max_tokens,omitempty"` StopSequences []string `json:"stop_sequences,omitempty"` Stream bool `json:"stream,omitempty"` - Temperature float64 `json:"temperature,omitempty"` + Temperature *float64 `json:"temperature,omitempty"` TopP float64 `json:"top_p,omitempty"` TopK int `json:"top_k,omitempty"` Tools []claude.Tool `json:"tools,omitempty"` diff --git a/relay/channel/xunfei/dto.go b/relay/channel/xunfei/dto.go index 55566176..c169e5f7 100644 --- a/relay/channel/xunfei/dto.go +++ b/relay/channel/xunfei/dto.go @@ -13,11 +13,11 @@ type XunfeiChatRequest struct { } `json:"header"` Parameter struct { Chat struct { - Domain string `json:"domain,omitempty"` - Temperature float64 `json:"temperature,omitempty"` - TopK int `json:"top_k,omitempty"` - MaxTokens uint `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 uint `json:"max_tokens,omitempty"` + Auditing bool `json:"auditing,omitempty"` } `json:"chat"` } `json:"parameter"` Payload struct { diff --git a/relay/channel/zhipu/dto.go b/relay/channel/zhipu/dto.go index 1040124c..2682dd3a 100644 --- a/relay/channel/zhipu/dto.go +++ b/relay/channel/zhipu/dto.go @@ -12,7 +12,7 @@ type ZhipuMessage struct { type ZhipuRequest struct { Prompt []ZhipuMessage `json:"prompt"` - Temperature float64 `json:"temperature,omitempty"` + Temperature *float64 `json:"temperature,omitempty"` TopP float64 `json:"top_p,omitempty"` RequestId string `json:"request_id,omitempty"` Incremental bool `json:"incremental,omitempty"` diff --git a/relay/common/relay_info.go b/relay/common/relay_info.go index 7a117968..4978f84f 100644 --- a/relay/common/relay_info.go +++ b/relay/common/relay_info.go @@ -30,6 +30,7 @@ type RelayInfo struct { RelayMode int UpstreamModelName string OriginModelName string + RecodeModelName string RequestURLPath string ApiVersion string PromptTokens int @@ -45,6 +46,7 @@ type RelayInfo struct { RealtimeTools []dto.RealTimeTool IsFirstRequest bool AudioUsage bool + ReasoningEffort string ChannelSetting map[string]interface{} } @@ -87,6 +89,7 @@ func GenRelayInfo(c *gin.Context) *RelayInfo { FirstResponseTime: startTime.Add(-time.Second), OriginModelName: c.GetString("original_model"), UpstreamModelName: c.GetString("original_model"), + RecodeModelName: c.GetString("recode_model"), ApiType: apiType, ApiVersion: c.GetString("api_version"), ApiKey: strings.TrimPrefix(c.Request.Header.Get("Authorization"), "Bearer "), diff --git a/relay/relay-text.go b/relay/relay-text.go index 1e2dfbaa..f303ff6a 100644 --- a/relay/relay-text.go +++ b/relay/relay-text.go @@ -93,6 +93,7 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) { } } relayInfo.UpstreamModelName = textRequest.Model + relayInfo.RecodeModelName = textRequest.Model modelPrice, getModelPriceSuccess := common.GetModelPrice(textRequest.Model, false) groupRatio := setting.GetGroupRatio(relayInfo.Group) @@ -218,10 +219,10 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) { return openaiErr } - if strings.HasPrefix(relayInfo.UpstreamModelName, "gpt-4o-audio") { + if strings.HasPrefix(relayInfo.RecodeModelName, "gpt-4o-audio") { service.PostAudioConsumeQuota(c, relayInfo, usage.(*dto.Usage), preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "") } else { - postConsumeQuota(c, relayInfo, textRequest.Model, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "") + postConsumeQuota(c, relayInfo, relayInfo.RecodeModelName, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "") } return nil } diff --git a/service/http_client.go b/service/http_client.go index df920bd6..992c73a0 100644 --- a/service/http_client.go +++ b/service/http_client.go @@ -1,7 +1,12 @@ package service import ( + "context" + "fmt" + "golang.org/x/net/proxy" + "net" "net/http" + "net/url" "one-api/common" "time" ) @@ -30,3 +35,43 @@ func GetHttpClient() *http.Client { func GetImpatientHttpClient() *http.Client { return impatientHTTPClient } + +// NewProxyHttpClient 创建支持代理的 HTTP 客户端 +func NewProxyHttpClient(proxyURL string) (*http.Client, error) { + if proxyURL == "" { + return http.DefaultClient, nil + } + + // 解析代理URL + parsedURL, err := url.Parse(proxyURL) + if err != nil { + return nil, err + } + + switch parsedURL.Scheme { + case "http", "https": + return &http.Client{ + Transport: &http.Transport{ + Proxy: http.ProxyURL(parsedURL), + }, + }, nil + + case "socks5": + // 创建 SOCKS5 代理拨号器 + dialer, err := proxy.SOCKS5("tcp", parsedURL.Host, nil, proxy.Direct) + if err != nil { + return nil, err + } + + return &http.Client{ + Transport: &http.Transport{ + DialContext: func(ctx context.Context, network, addr string) (net.Conn, error) { + return dialer.Dial(network, addr) + }, + }, + }, nil + + default: + return nil, fmt.Errorf("unsupported proxy scheme: %s", parsedURL.Scheme) + } +} diff --git a/service/log_info_generate.go b/service/log_info_generate.go index 4372130c..1ce09d92 100644 --- a/service/log_info_generate.go +++ b/service/log_info_generate.go @@ -13,6 +13,9 @@ func GenerateTextOtherInfo(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, m other["completion_ratio"] = completionRatio other["model_price"] = modelPrice other["frt"] = float64(relayInfo.FirstResponseTime.UnixMilli() - relayInfo.StartTime.UnixMilli()) + if relayInfo.ReasoningEffort != "" { + other["reasoning_effort"] = relayInfo.ReasoningEffort + } adminInfo := make(map[string]interface{}) adminInfo["use_channel"] = ctx.GetStringSlice("use_channel") other["admin_info"] = adminInfo diff --git a/service/quota.go b/service/quota.go index 234ddc5b..ab048008 100644 --- a/service/quota.go +++ b/service/quota.go @@ -182,9 +182,9 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, audioOutTokens := usage.CompletionTokenDetails.AudioTokens tokenName := ctx.GetString("token_name") - completionRatio := common.GetCompletionRatio(relayInfo.UpstreamModelName) - audioRatio := common.GetAudioRatio(relayInfo.UpstreamModelName) - audioCompletionRatio := common.GetAudioCompletionRatio(relayInfo.UpstreamModelName) + completionRatio := common.GetCompletionRatio(relayInfo.RecodeModelName) + audioRatio := common.GetAudioRatio(relayInfo.RecodeModelName) + audioCompletionRatio := common.GetAudioCompletionRatio(relayInfo.RecodeModelName) quotaInfo := QuotaInfo{ InputDetails: TokenDetails{ @@ -195,7 +195,7 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, TextTokens: textOutTokens, AudioTokens: audioOutTokens, }, - ModelName: relayInfo.UpstreamModelName, + ModelName: relayInfo.RecodeModelName, UsePrice: usePrice, ModelRatio: modelRatio, GroupRatio: groupRatio, @@ -218,7 +218,7 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, quota = 0 logContent += fmt.Sprintf("（可能是上游超时）") common.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, "+ - "tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, relayInfo.UpstreamModelName, preConsumedQuota)) + "tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, relayInfo.RecodeModelName, preConsumedQuota)) } else { quotaDelta := quota - preConsumedQuota if quotaDelta != 0 { @@ -231,7 +231,7 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota) } - logModel := relayInfo.UpstreamModelName + logModel := relayInfo.RecodeModelName if extraContent != "" { logContent += ", " + extraContent } diff --git a/setting/operation_setting.go b/setting/operation_setting.go new file mode 100644 index 00000000..0f2b4ffd --- /dev/null +++ b/setting/operation_setting.go @@ -0,0 +1,3 @@ +package setting + +var DemoSiteEnabled = false diff --git a/web/src/components/LogsTable.js b/web/src/components/LogsTable.js index 7acc2cc4..576efbc2 100644 --- a/web/src/components/LogsTable.js +++ b/web/src/components/LogsTable.js @@ -608,7 +608,12 @@ const LogsTable = () => { key: t('计费过程'), value: content, }); - + if (other?.reasoning_effort) { + expandDataLocal.push({ + key: t('Reasoning Effort'), + value: other.reasoning_effort, + }); + } } expandDatesLocal[logs[i].key] = expandDataLocal; } diff --git a/web/src/components/OperationSetting.js b/web/src/components/OperationSetting.js index eebff04f..98b67c67 100644 --- a/web/src/components/OperationSetting.js +++ b/web/src/components/OperationSetting.js @@ -58,6 +58,7 @@ const OperationSetting = () => { DefaultCollapseSidebar: false, // 默认折叠侧边栏 RetryTimes: 0, Chats: "[]", + DemoSiteEnabled: false, }); let [loading, setLoading] = useState(false); diff --git a/web/src/pages/Channel/EditChannel.js b/web/src/pages/Channel/EditChannel.js index 457dff42..3e99b7da 100644 --- a/web/src/pages/Channel/EditChannel.js +++ b/web/src/pages/Channel/EditChannel.js @@ -218,6 +218,7 @@ const EditChannel = (props) => { try { const res = await API.post('/api/channel/fetch_models', { base_url: inputs['base_url'], + type: inputs['type'], key: inputs['key'] }); @@ -885,7 +886,7 @@ const EditChannel = (props) => {