Merge 5f6b515bb3 into 8df4a2670b

closes #49

README.md

@@ -72,7 +72,7 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型，开箱即用
    + [x] [Anthropic Claude 系列模型](https://anthropic.com) (支持 AWS Claude)
    + [x] [Google PaLM2/Gemini 系列模型](https://developers.generativeai.google)
    + [x] [Mistral 系列模型](https://mistral.ai/)
-   + [x] [字节跳动豆包大模型](https://console.volcengine.com/ark/region:ark+cn-beijing/model)
+   + [x] [字节跳动豆包大模型（火山引擎）](https://www.volcengine.com/experience/ark?utm_term=202502dsinvite&ac=DSASUQY5&rc=2QXCA1VI)
    + [x] [百度文心一言系列模型](https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html)
    + [x] [阿里通义千问系列模型](https://help.aliyun.com/document_detail/2400395.html)
    + [x] [讯飞星火认知大模型](https://www.xfyun.cn/doc/spark/Web.html)

relay/adaptor/gemini/adaptor.go

@@ -25,7 +25,7 @@ func (a *Adaptor) Init(meta *meta.Meta) {
 
 func (a *Adaptor) GetRequestURL(meta *meta.Meta) (string, error) {
 	defaultVersion := config.GeminiVersion
-	if strings.Contains(meta.ActualModelName, "gemini-2.0") ||
+	if strings.Contains(meta.ActualModelName, "gemini-2") ||
 		strings.Contains(meta.ActualModelName, "gemini-1.5") {
 		defaultVersion = "v1beta"
 	}

relay/adaptor/geminiv2/constants.go

@@ -6,15 +6,17 @@ import "strings"
 
 var ModelList = []string{
 	"gemini-pro", "gemini-1.0-pro",
-	// "gemma-2-2b-it", "gemma-2-9b-it", "gemma-2-27b-it",
+	"gemma-2-2b-it", "gemma-2-9b-it", "gemma-2-27b-it",
+	"gemma-3-27b-it",
 	"gemini-1.5-flash", "gemini-1.5-flash-8b",
 	"gemini-1.5-pro", "gemini-1.5-pro-experimental",
 	"text-embedding-004", "aqa",
 	"gemini-2.0-flash", "gemini-2.0-flash-exp",
 	"gemini-2.0-flash-lite-preview-02-05",
 	"gemini-2.0-flash-thinking-exp-01-21",
-	"gemini-2.0-pro-exp-02-05",
 	"gemini-2.0-flash-exp-image-generation",
+	"gemini-2.0-pro-exp-02-05",
+	"gemini-2.5-pro-exp-03-25",
 }
 
 const (
@@ -28,5 +30,10 @@ func GetModelModalities(model string) []string {
 		return []string{ModalityText, ModalityImage}
 	}
 
+	// Until 2025-03-26, the following models do not accept the responseModalities field
+	if model == "gemini-2.5-pro-exp-03-25" {
+		return nil
+	}
+
 	return []string{ModalityText}
 }

relay/billing/ratio/model.go

@@ -144,9 +144,10 @@ var ModelRatio = map[string]float64{
 	"tao-8k":             0.002 * KiloRmb,
 	// https://ai.google.dev/pricing
 	// https://cloud.google.com/vertex-ai/generative-ai/pricing
-	// "gemma-2-2b-it":                       0,
-	// "gemma-2-9b-it":                       0,
-	// "gemma-2-27b-it":                      0,
+	"gemma-2-2b-it":                         0,
+	"gemma-2-9b-it":                         0,
+	"gemma-2-27b-it":                        0,
+	"gemma-3-27b-it":                        0,
 	"gemini-pro":                            0.25 * MilliTokensUsd, // $0.00025 / 1k characters -> $0.001 / 1k tokens
 	"gemini-1.0-pro":                        0.125 * MilliTokensUsd,
 	"gemini-1.0-pro-vision":                 0.125 * MilliTokensUsd,
@@ -165,8 +166,9 @@ var ModelRatio = map[string]float64{
 	"gemini-2.0-flash-lite-001":             0.075 * MilliTokensUsd,
 	"gemini-2.0-flash-lite-preview-02-05":   0.075 * MilliTokensUsd,
 	"gemini-2.0-flash-thinking-exp-01-21":   0.075 * MilliTokensUsd,
-	"gemini-2.0-pro-exp-02-05":              1.25 * MilliTokensUsd,
 	"gemini-2.0-flash-exp-image-generation": 0.075 * MilliTokensUsd,
+	"gemini-2.0-pro-exp-02-05":              1.25 * MilliTokensUsd,
+	"gemini-2.5-pro-exp-03-25":              1.25 * MilliTokensUsd,
 	"aqa":                                   1,
 	// https://open.bigmodel.cn/pricing
 	"glm-zero-preview": 0.01 * KiloRmb,
@@ -914,7 +916,7 @@ func GetModelRatio(name string, channelType int) float64 {
 	}
 
 	logger.SysError("model ratio not found: " + name)
-	return 0.1 * QuotaPerUsd
+	return 2.5 * MilliTokensUsd
 }
 
 // CompletionRatio2JSONString returns the CompletionRatio map as a JSON string.

web/air/src/components/LogsTable.js

@@ -245,7 +245,7 @@ const LogsTable = () => {
     if (isAdminUser) {
       url = `/api/log/?p=${startIdx}&page_size=${pageSize}&type=${logType}&username=${username}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}&channel=${channel}`;
     } else {
-      url = `/api/log/self/?p=${startIdx}&page_size=${pageSize}&type=${logType}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`;
+      url = `/api/log/self?p=${startIdx}&page_size=${pageSize}&type=${logType}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`;
     }
     const res = await API.get(url);
     const { success, message, data } = res.data;

web/default/src/components/LogsTable.js

@@ -225,7 +225,7 @@ const LogsTable = () => {
     if (isAdminUser) {
       url = `/api/log/?p=${startIdx}&type=${logType}&username=${username}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}&channel=${channel}`;
     } else {
-      url = `/api/log/self/?p=${startIdx}&type=${logType}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`;
+      url = `/api/log/self?p=${startIdx}&type=${logType}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`;
     }
     const res = await API.get(url);
     const { success, message, data } = res.data;