Merge 664f7ba676 into 7e51b04221

Co-authored-by: oliang <oliang@tencent.com>

.computenest/.computenest_parameters.yaml

@@ -0,0 +1 @@
+{"ServicePort":"80","SecurityPorts":[80],"RepoName":"hanans426/one-api","Arch":"EcsSingle","RunCommand":"echo \"start run command\"\necho \"${AdminPassword}\"\n","SourceCodePath":".","CommandTimeout":3600,"ServiceType":"private","AllowedRegions":["cn-hangzhou","cn-shanghai","cn-beijing"],"ArtifactSourceType":"SourceCode","ImageId":"centos_7_9_x64_20G_alibase_20230613.vhd","RegionId":"cn-hangzhou","CustomParameters":[{"NoEcho":true,"Type":"String","AssociationProperty":"ALIYUN::ECS::Instance::Password","Label":"管理员密码","Name":"AdminPassword"}]}

.computenest/README.md

@@ -0,0 +1,21 @@
+# 代码仓库结构
+
+## 文档目录说明：
+```
+.
+├── README.md                   - README
+├── docs                        - 服务文档相关文件
+│   └── index.md
+├── resources                   - 服务资源文件
+│   ├── icons
+│   │   └── service_logo.png    - 服务logo
+│   └── artifact_resources      - 部署物相关资源文件
+├── ros_templates               - 服务ROS模板目录，支持多模板
+│   └── template.yaml           - ROS模板，ROS模板引擎根据该模板会自动创建出所有的资源
+├── config.yaml                 - 服务配置文件，服务构建过程中会使用计算巢命令行工具computenest-cli，computenest-cli会基于该配置文件构建服务
+├── preset_parameters.yaml      - （该文件只有托管版有）服务商预设参数，如VpcId，VSwitchId等，该ros模板内容会渲染为表单方便服务商填写
+```
+
+## 其他
+关于ROS模板，请参见 [资源编排](https://help.aliyun.com/zh/ros)。
+关于computenest-cli请参见 [computenest-cli](https://pypi.org/project/computenest-cli/)。

.computenest/config.yaml

@@ -0,0 +1,28 @@
+Service:
+  RegionId: cn-hangzhou
+  DeployType: ros
+  DeployMetadata:
+    SupplierDeployMetadata:
+      FileArtifactRelation:
+        '{{ computenest::file::hanans426_one-api }}':
+          ArtifactId: ${Artifact.Artifact_1.ArtifactId}
+          ArtifactVersion: ${Artifact.Artifact_1.ArtifactVersion}
+    TemplateConfigs:
+      - Name: 单机版
+        Url: 'ros_templates/template.yaml'
+        AllowedRegions:
+          - cn-hangzhou
+          - cn-shanghai
+          - cn-beijing
+  ServiceType: private
+  ServiceInfo:
+    Locale: zh-CN
+    ShortDescription: demo
+    Image: 'resources/icons/service_logo.png'
+Artifact:
+  Artifact_1:
+    ArtifactType: File
+    ArtifactName: hanans426_one-api
+    ArtifactProperty:
+      RegionId: cn-hangzhou
+      Url: 'resources/artifact_resources/file/hanans426_one-api.tar.gz'

.computenest/docs/index_ecs_single.md

@@ -0,0 +1,70 @@
+# 服务模板说明文档
+
+## 服务说明
+
+**简单描述服务的功能和用途。**  
+例如：  
+_（服务功能描述，如“WordPress 是一款免费开源的 CMS，适用于创建和管理各种类型的网站。”）_
+
+_（服务快速上手链接或文档，如果有的话）_
+
+## 服务架构
+
+此服务模板构建出的服务的部署架构为单机ecs部署。
+
+<img src="architecture_ecs_single.png" width="600" height="400" align="bottom"/>
+
+## 计费说明
+通过此服务模板构建服务不产生费用。  
+用户部署构建出的服务时，资源费用主要涉及：
+- 所选ECS实例规格
+- 磁盘容量
+- 公网带宽
+
+计费方式包括：
+- 按量付费（小时）
+- 包年包月
+
+预估费用在部署前可实时看到。
+
+## RAM账号所需权限
+
+此服务模板构建出的服务需要对ECS、VPC等资源进行访问和创建操作，若使用RAM用户创建服务实例，需要在创建服务实例前，对使用的RAM用户的账号添加相应资源的权限。添加RAM权限的详细操作，请参见[为RAM用户授权](https://help.aliyun.com/document_detail/121945.html)。所需权限如下表所示：
+
+| 权限策略名称                              | 备注                            |
+|-------------------------------------|-------------------------------|
+| AliyunECSFullAccess                 | 管理云服务器服务（ECS）的权限              |
+| AliyunVPCFullAccess                 | 管理专有网络（VPC）的权限                |
+| AliyunROSFullAccess                 | 管理资源编排服务（ROS）的权限              |
+| AliyunComputeNestUserFullAccess     | 管理计算巢服务（ComputeNest）的用户侧权限    |
+| AliyunComputeNestSupplierFullAccess | 管理计算巢服务（ComputeNest）的服务商侧权限 ｜ |
+
+## 服务实例计费说明
+
+**详细说明服务实例的计费方式。**  
+_（描述费用构成，例如所选 vCPU 和内存规格，系统盘类型和容量等）_
+
+_（列出计费方式，例如按量付费或包年包月）_
+
+## 服务实例部署流程
+
+### 部署参数说明
+
+| 参数组                             | 参数项    | 说明                                                                      |
+|---------------------------------|--------|-------------------------------------------------------------------------|
+| 服务实例                            | 服务实例名称 | 长度不超过64个字符，必须以英文字母开头，可包含数字、英文字母、短划线（-）和下划线（_）。                          |
+|                                 | 地域     | 服务实例部署的地域。                                                              |
+|                                 | 付费类型   | 资源的计费类型：按量付费和包年包月。                                                      |
+| ECS实例配置                         | 实例类型   | ECS实例规格配置。                                                              |
+|                                 | 实例密码   | 长度8-30，必须包含三项（大写字母、小写字母、数字、 ()`~!@#$%^&*-+=&#124;{}[]:;'<>,.?/ 中的特殊符号）。 |
+| 网络配置                            | 可用区    | ECS实例所在可用区。                                                             |
+
+### 部署步骤
+
+**简述如何一步步部署服务实例。**  
+
+1. _（步骤1描述和相关链接或图片，如果有的话）_
+2. _（步骤2描述和相关链接或图片，如果有的话）_
+...
+
+[部署链接](部署链接地址)

.computenest/ros_templates/template.yaml

@@ -0,0 +1,218 @@
+ROSTemplateFormatVersion: '2015-09-01'
+Description:
+  en: Source Code Service Ros Template
+  zh-cn: 源代码服务模板
+Parameters:
+  PayType:
+    Type: String
+    Label:
+      en: ECS Instance Charge Type
+      zh-cn: 付费类型
+    Default: PostPaid
+    AllowedValues:
+      - PostPaid
+      - PrePaid
+    AssociationProperty: ChargeType
+    AssociationPropertyMetadata:
+      LocaleKey: InstanceChargeType
+  PayPeriodUnit:
+    Type: String
+    Label:
+      en: Pay Period Unit
+      zh-cn: 购买资源时长周期
+    Default: Month
+    AllowedValues:
+      - Month
+      - Year
+    AssociationProperty: PayPeriodUnit
+    AssociationPropertyMetadata:
+      Visible:
+        Condition:
+          Fn::Not:
+            Fn::Equals:
+              - ${PayType}
+              - PostPaid
+  PayPeriod:
+    Type: Number
+    Label:
+      en: Period
+      zh-cn: 购买资源时长
+    Default: 1
+    AllowedValues:
+      - 1
+      - 2
+      - 3
+      - 4
+      - 5
+      - 6
+      - 7
+      - 8
+      - 9
+    AssociationProperty: PayPeriod
+    AssociationPropertyMetadata:
+      Visible:
+        Condition:
+          Fn::Not:
+            Fn::Equals:
+              - ${PayType}
+              - PostPaid
+  EcsInstanceType:
+    Type: String
+    Label:
+      en: Instance Type
+      zh-cn: 实例类型
+    AssociationProperty: ALIYUN::ECS::Instance::InstanceType
+    AssociationPropertyMetadata:
+      InstanceChargeType: ${PayType}
+      Constraints:
+        InstanceTypeFamily:
+          - ecs.u1
+          - ecs.e
+  InstancePassword:
+    NoEcho: true
+    Type: String
+    Description:
+      en: Server login password, Length 8-30, must contain three(Capital letters, lowercase letters, numbers, ()`~!@#$%^&*_-+=|{}[]:;'<>,.?/ Special symbol in)
+      zh-cn: 服务器登录密码,长度8-30，必须包含三项（大写字母、小写字母、数字、 ()`~!@#$%^&*_-+=|{}[]:;'<>,.?/ 中的特殊符号）
+    AllowedPattern: '^[a-zA-Z0-9-\(\)\`\~\!\@\#\$\%\^\&\*\_\-\+\=\|\{\}\[\]\:\;\<\>\,\.\?\/]*$'
+    Label:
+      en: Instance Password
+      zh-cn: 实例密码
+    ConstraintDescription:
+      en: Length 8-30, must contain three(Capital letters, lowercase letters, numbers, ()`~!@#$%^&*_-+=|{}[]:;'<>,.?/ Special symbol in)
+      zh-cn: 长度8-30，必须包含三项（大写字母、小写字母、数字、 ()`~!@#$%^&*_-+=|{}[]:;'<>,.?/ 中的特殊符号）
+    MinLength: 8
+    MaxLength: 30
+    AssociationProperty: ALIYUN::ECS::Instance::Password
+  ZoneId:
+    Type: String
+    Label:
+      en: Zone ID
+      zh-cn: 可用区ID
+    AssociationProperty: ALIYUN::ECS::Instance::ZoneId
+  VpcId:
+    Type: String
+    Label:
+      en: VPC ID
+      zh-cn: 专有网络VPC实例ID
+    AssociationProperty: 'ALIYUN::ECS::VPC::VPCId'
+  VSwitchId:
+    Type: String
+    Label:
+      en: VSwitch ID
+      zh-cn: 交换机实例ID
+    Default: ''
+    AssociationProperty: 'ALIYUN::ECS::VSwitch::VSwitchId'
+    AssociationPropertyMetadata:
+      VpcId: VpcId
+      ZoneId: ZoneId
+  AdminPassword:
+    Type: String
+    AssociationProperty: ALIYUN::ECS::Instance::Password
+    Label: 管理员密码
+    NoEcho: True
+Resources:
+  SecurityGroup:
+    Type: ALIYUN::ECS::SecurityGroup
+    Properties:
+      SecurityGroupName:
+        Ref: ALIYUN::StackName
+      VpcId:
+        Ref: VpcId
+      SecurityGroupIngress:
+        - PortRange: 80/80
+          Priority: 1
+          SourceCidrIp: 0.0.0.0/0
+          IpProtocol: tcp
+          NicType: internet
+  InstanceGroup:
+    Type: ALIYUN::ECS::InstanceGroup
+    Properties:
+      # 付费类型
+      InstanceChargeType:
+        Ref: PayType
+      PeriodUnit:
+        Ref: PayPeriodUnit
+      Period:
+        Ref: PayPeriod
+      VpcId:
+        Ref: VpcId
+      VSwitchId:
+        Ref: VSwitchId
+      ZoneId:
+        Ref: ZoneId
+      SecurityGroupId:
+        Ref: SecurityGroup
+      ImageId: centos_7_9_x64_20G_alibase_20230613.vhd
+      Password:
+        Ref: InstancePassword
+      InstanceType:
+        Ref: EcsInstanceType
+      SystemDiskCategory: cloud_essd
+      SystemDiskSize: 200
+      InternetMaxBandwidthOut: 5
+      IoOptimized: optimized
+      MaxAmount: 1
+  RunInstallCommand:
+    Type: ALIYUN::ECS::RunCommand
+    Properties:
+      InstanceIds:
+        Fn::GetAtt:
+        - InstanceGroup
+        - InstanceIds
+      Type: RunShellScript
+      Sync: true
+      Timeout: 3600
+      CommandContent:
+        Fn::Sub:
+          - |
+            #!/bin/bash
+            # 源代码通过computenest-cli被打包为tar.gz包，并发布为部署物
+            wget '{{ computenest::file::hanans426_one-api }}' -O hanans426_one-api.tar.gz > /var/log/download.log
+            tar -zxvf hanans426_one-api.tar.gz && cd "$(tar -tzf hanans426_one-api.tar.gz | head -1 | awk -F'/' '{print $1}')"
+            echo "start run command"
+            echo "${AdminPassword}"
+
+            ARGUS_VERSION=3.5.7 /bin/bash -c "$(curl -sS https://cms-agent-${RegionId}.oss-${RegionId}-internal.aliyuncs.com/Argus/agent_install_ecs-1.7.sh)" >> /root/install_cms_agent.log 2>&1
+          - RegionId:
+              Ref: ALIYUN::Region
+Outputs:
+  ServerAddress:
+    Description:
+      en: ServerAddress.
+      zh-cn: 访问页面。
+    Value:
+      Fn::Sub:
+        - 'http://${ServerAddress}:80'
+        - ServerAddress:
+            Fn::Select:
+            - 0
+            - Fn::GetAtt:
+              - InstanceGroup
+              - PublicIps
+Metadata:
+  ALIYUN::ROS::Interface:
+    ParameterGroups:
+      - Parameters:
+          - PayType
+          - PayPeriodUnit
+          - PayPeriod
+        Label:
+          default: 付费类型配置
+      - Parameters:
+          - EcsInstanceType
+          - InstancePassword
+        Label:
+          default: 资源配置
+      - Parameters:
+          - ZoneId
+          - VpcId
+          - VSwitchId
+        Label:
+          default: 可用区配置
+      - Parameters:
+          - AdminPassword
+        Label:
+          en: Software Configuration
+          zh-cn: 软件配置
+      

README.en.md

@@ -204,6 +204,17 @@ If you encounter a blank page after deployment, refer to [#97](https://github.co
 </div>
 </details>
 
+<details>
+<summary><strong>Deployment on Aliyun</strong></summary>
+<div>
+
+> Aliyun support one-click deployment to a dedicated VPC.。
+
+Aliyun support the fast deployment，[Deployment Link](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=One%20API%20%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+</div>
+</details>
+
 ## Configuration
 The system is ready to use out of the box.
 

README.md

@@ -302,6 +302,17 @@ Render 可以直接部署 docker 镜像，不需要 fork 仓库：https://dashbo
 </div>
 </details>
 
+<details>
+<summary><strong>部署到阿里云</strong></summary>
+<div>
+
+> 阿里云支持一键部署到专属VPC。
+
+阿里云支持快速一键部署，[部署链接](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=One%20API%20%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+</div>
+</details>
+
 ## 配置
 系统本身开箱即用。
 

controller/channel-test.go

@@ -76,9 +76,9 @@ func testChannel(channel *model.Channel, request *relaymodel.GeneralOpenAIReques
 		if len(modelNames) > 0 {
 			modelName = modelNames[0]
 		}
-		if modelMap != nil && modelMap[modelName] != "" {
-			modelName = modelMap[modelName]
-		}
+	}
+	if modelMap != nil && modelMap[modelName] != "" {
+		modelName = modelMap[modelName]
 	}
 	meta.OriginModelName, meta.ActualModelName = request.Model, modelName
 	request.Model = modelName

relay/adaptor/anthropic/constants.go

@@ -6,4 +6,5 @@ var ModelList = []string{
 	"claude-3-sonnet-20240229",
 	"claude-3-opus-20240229",
 	"claude-3-5-sonnet-20240620",
+	"claude-3-5-sonnet-20241022",
 }

relay/adaptor/aws/claude/main.go

@@ -31,6 +31,7 @@ var AwsModelIDMap = map[string]string{
 	"claude-2.1":                 "anthropic.claude-v2:1",
 	"claude-3-sonnet-20240229":   "anthropic.claude-3-sonnet-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-opus-20240229":     "anthropic.claude-3-opus-20240229-v1:0",
 	"claude-3-haiku-20240307":    "anthropic.claude-3-haiku-20240307-v1:0",
 }

relay/adaptor/gemini/main.go

@@ -4,11 +4,12 @@ import (
 	"bufio"
 	"encoding/json"
 	"fmt"
-	"github.com/songquanpeng/one-api/common/render"
 	"io"
 	"net/http"
 	"strings"
 
+	"github.com/songquanpeng/one-api/common/render"
+
 	"github.com/songquanpeng/one-api/common"
 	"github.com/songquanpeng/one-api/common/config"
 	"github.com/songquanpeng/one-api/common/helper"
@@ -28,6 +29,11 @@ const (
 	VisionMaxImageNum = 16
 )
 
+var mimeTypeMap = map[string]string{
+	"json_object": "application/json",
+	"text":        "text/plain",
+}
+
 // Setting safety to the lowest possible values since Gemini is already powerless enough
 func ConvertRequest(textRequest model.GeneralOpenAIRequest) *ChatRequest {
 	geminiRequest := ChatRequest{
@@ -56,6 +62,15 @@ func ConvertRequest(textRequest model.GeneralOpenAIRequest) *ChatRequest {
 			MaxOutputTokens: textRequest.MaxTokens,
 		},
 	}
+	if textRequest.ResponseFormat != nil {
+		if mimeType, ok := mimeTypeMap[textRequest.ResponseFormat.Type]; ok {
+			geminiRequest.GenerationConfig.ResponseMimeType = mimeType
+		}
+		if textRequest.ResponseFormat.JsonSchema != nil {
+			geminiRequest.GenerationConfig.ResponseSchema = textRequest.ResponseFormat.JsonSchema.Schema
+			geminiRequest.GenerationConfig.ResponseMimeType = mimeTypeMap["json_object"]
+		}
+	}
 	if textRequest.Tools != nil {
 		functions := make([]model.Function, 0, len(textRequest.Tools))
 		for _, tool := range textRequest.Tools {

relay/adaptor/gemini/model.go

@@ -65,10 +65,12 @@ type ChatTools struct {
 }
 
 type ChatGenerationConfig struct {
-	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"`
-	StopSequences   []string `json:"stopSequences,omitempty"`
+	ResponseMimeType string   `json:"responseMimeType,omitempty"`
+	ResponseSchema   any      `json:"responseSchema,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"`
+	StopSequences    []string `json:"stopSequences,omitempty"`
 }

relay/adaptor/groq/constants.go

@@ -4,14 +4,21 @@ package groq
 
 var ModelList = []string{
 	"gemma-7b-it",
-	"mixtral-8x7b-32768",
-	"llama3-8b-8192",
-	"llama3-70b-8192",
 	"gemma2-9b-it",
-	"llama-3.1-405b-reasoning",
 	"llama-3.1-70b-versatile",
 	"llama-3.1-8b-instant",
+	"llama-3.2-11b-text-preview",
+	"llama-3.2-11b-vision-preview",
+	"llama-3.2-1b-preview",
+	"llama-3.2-3b-preview",
+	"llama-3.2-90b-text-preview",
+	"llama-guard-3-8b",
+	"llama3-70b-8192",
+	"llama3-8b-8192",
 	"llama3-groq-70b-8192-tool-use-preview",
 	"llama3-groq-8b-8192-tool-use-preview",
+	"llava-v1.5-7b-4096-preview",
+	"mixtral-8x7b-32768",
+	"distil-whisper-large-v3-en",
 	"whisper-large-v3",
 }

relay/adaptor/openai/adaptor.go

@@ -75,6 +75,13 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *model.G
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
+	if request.Stream {
+		// always return usage in stream mode
+		if request.StreamOptions == nil {
+			request.StreamOptions = &model.StreamOptions{}
+		}
+		request.StreamOptions.IncludeUsage = true
+	}
 	return request, nil
 }
 

relay/adaptor/vertexai/gemini/adapter.go

@@ -15,7 +15,7 @@ import (
 )
 
 var ModelList = []string{
-	"gemini-1.5-pro-001", "gemini-1.5-flash-001", "gemini-pro", "gemini-pro-vision",
+	"gemini-1.5-pro-001", "gemini-1.5-flash-001", "gemini-pro", "gemini-pro-vision", "gemini-1.5-pro-002", "gemini-1.5-flash-002", 
 }
 
 type Adaptor struct {

relay/billing/ratio/model.go

@@ -81,6 +81,7 @@ var ModelRatio = map[string]float64{
 	"claude-3-haiku-20240307":    0.25 / 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,
 	"claude-3-opus-20240229":     15.0 / 1000 * USD,
 	// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7
 	"ERNIE-4.0-8K":       0.120 * RMB,
@@ -162,15 +163,21 @@ var ModelRatio = map[string]float64{
 	"mistral-embed":         0.1 / 1000 * USD,
 	// https://wow.groq.com/#:~:text=inquiries%C2%A0here.-,Model,-Current%20Speed
 	"gemma-7b-it":                           0.07 / 1000000 * USD,
-	"mixtral-8x7b-32768":                    0.24 / 1000000 * USD,
-	"llama3-8b-8192":                        0.05 / 1000000 * USD,
-	"llama3-70b-8192":                       0.59 / 1000000 * USD,
 	"gemma2-9b-it":                          0.20 / 1000000 * USD,
-	"llama-3.1-405b-reasoning":              0.89 / 1000000 * USD,
 	"llama-3.1-70b-versatile":               0.59 / 1000000 * USD,
 	"llama-3.1-8b-instant":                  0.05 / 1000000 * USD,
+	"llama-3.2-11b-text-preview":            0.05 / 1000000 * USD,
+	"llama-3.2-11b-vision-preview":          0.05 / 1000000 * USD,
+	"llama-3.2-1b-preview":                  0.05 / 1000000 * USD,
+	"llama-3.2-3b-preview":                  0.05 / 1000000 * USD,
+	"llama-3.2-90b-text-preview":            0.59 / 1000000 * USD,
+	"llama-guard-3-8b":                      0.05 / 1000000 * USD,
+	"llama3-70b-8192":                       0.59 / 1000000 * USD,
+	"llama3-8b-8192":                        0.05 / 1000000 * USD,
 	"llama3-groq-70b-8192-tool-use-preview": 0.89 / 1000000 * USD,
 	"llama3-groq-8b-8192-tool-use-preview":  0.19 / 1000000 * USD,
+	"mixtral-8x7b-32768":                    0.24 / 1000000 * USD,
+
 	// https://platform.lingyiwanwu.com/docs#-计费单元
 	"yi-34b-chat-0205": 2.5 / 1000 * RMB,
 	"yi-34b-chat-200k": 12.0 / 1000 * RMB,

relay/model/constant.go

@@ -1,6 +1,7 @@
 package model
 
 const (
-	ContentTypeText     = "text"
-	ContentTypeImageURL = "image_url"
+	ContentTypeText       = "text"
+	ContentTypeImageURL   = "image_url"
+	ContentTypeInputAudio = "input_audio"
 )

relay/model/general.go

@@ -12,9 +12,20 @@ type JSONSchema struct {
 	Strict      *bool                  `json:"strict,omitempty"`
 }
 
+type Audio struct {
+	Voice  string `json:"voice,omitempty"`
+	Format string `json:"format,omitempty"`
+}
+
+type StreamOptions struct {
+	IncludeUsage bool `json:"include_usage,omitempty"`
+}
+
 type GeneralOpenAIRequest struct {
 	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"`
@@ -23,6 +34,7 @@ type GeneralOpenAIRequest struct {
 	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"`
@@ -37,7 +49,7 @@ type GeneralOpenAIRequest struct {
 	Dimensions       int             `json:"dimensions,omitempty"`
 	Instruction      string          `json:"instruction,omitempty"`
 	Size             string          `json:"size,omitempty"`
-	NumCtx           int         	 `json:"num_ctx,omitempty"`
+	NumCtx           int             `json:"num_ctx,omitempty"`
 }
 
 func (r GeneralOpenAIRequest) ParseInput() []string {

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-sonnet-20240620"];
+                    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/default/src/components/ChannelsTable.js

@@ -59,6 +59,12 @@ function renderBalance(type, balance) {
   }
 }
 
+function isShowDetail() {
+  return localStorage.getItem("show_detail") === "true";
+}
+
+const promptID = "detail"
+
 const ChannelsTable = () => {
   const [channels, setChannels] = useState([]);
   const [loading, setLoading] = useState(true);
@@ -66,7 +72,8 @@ const ChannelsTable = () => {
   const [searchKeyword, setSearchKeyword] = useState('');
   const [searching, setSearching] = useState(false);
   const [updatingBalance, setUpdatingBalance] = useState(false);
-  const [showPrompt, setShowPrompt] = useState(shouldShowPrompt("channel-test"));
+  const [showPrompt, setShowPrompt] = useState(shouldShowPrompt(promptID));
+  const [showDetail, setShowDetail] = useState(isShowDetail());
 
   const loadChannels = async (startIdx) => {
     const res = await API.get(`/api/channel/?p=${startIdx}`);
@@ -120,6 +127,11 @@ const ChannelsTable = () => {
     await loadChannels(activePage - 1);
   };
 
+  const toggleShowDetail = () => {
+    setShowDetail(!showDetail);
+    localStorage.setItem("show_detail", (!showDetail).toString());
+  }
+
   useEffect(() => {
     loadChannels(0)
       .then()
@@ -364,11 +376,13 @@ const ChannelsTable = () => {
         showPrompt && (
           <Message onDismiss={() => {
             setShowPrompt(false);
-            setPromptShown("channel-test");
+            setPromptShown(promptID);
           }}>
             OpenAI 渠道已经不再支持通过 key 获取余额，因此余额显示为 0。对于支持的渠道类型，请点击余额进行刷新。
             <br/>
             渠道测试仅支持 chat 模型，优先使用 gpt-3.5-turbo，如果该模型不可用则使用你所配置的模型列表中的第一个模型。
+            <br/>
+            点击下方详情按钮可以显示余额以及设置额外的测试模型。
           </Message>
         )
       }
@@ -428,6 +442,7 @@ const ChannelsTable = () => {
               onClick={() => {
                 sortChannel('balance');
               }}
+              hidden={!showDetail}
             >
               余额
             </Table.HeaderCell>
@@ -439,7 +454,7 @@ const ChannelsTable = () => {
             >
               优先级
             </Table.HeaderCell>
-            <Table.HeaderCell>测试模型</Table.HeaderCell>
+            <Table.HeaderCell hidden={!showDetail}>测试模型</Table.HeaderCell>
             <Table.HeaderCell>操作</Table.HeaderCell>
           </Table.Row>
         </Table.Header>
@@ -467,7 +482,7 @@ const ChannelsTable = () => {
                       basic
                     />
                   </Table.Cell>
-                  <Table.Cell>
+                  <Table.Cell hidden={!showDetail}>
                     <Popup
                       trigger={<span onClick={() => {
                         updateChannelBalance(channel.id, channel.name, idx);
@@ -494,7 +509,7 @@ const ChannelsTable = () => {
                       basic
                     />
                   </Table.Cell>
-                  <Table.Cell>
+                  <Table.Cell hidden={!showDetail}>
                     <Dropdown
                       placeholder='请选择测试模型'
                       selection
@@ -573,7 +588,7 @@ const ChannelsTable = () => {
 
         <Table.Footer>
           <Table.Row>
-            <Table.HeaderCell colSpan='9'>
+            <Table.HeaderCell colSpan={showDetail ? "10" : "8"}>
               <Button size='small' as={Link} to='/channel/add' loading={loading}>
                 添加新的渠道
               </Button>
@@ -611,6 +626,7 @@ const ChannelsTable = () => {
                 }
               />
               <Button size='small' onClick={refresh} loading={loading}>刷新</Button>
+              <Button size='small' onClick={toggleShowDetail}>{showDetail ? "隐藏详情" : "详情"}</Button>
             </Table.HeaderCell>
           </Table.Row>
         </Table.Footer>

web/default/src/pages/Channel/index.js

@@ -2,7 +2,7 @@ import React from 'react';
 import { Header, Segment } from 'semantic-ui-react';
 import ChannelsTable from '../../components/ChannelsTable';
 
-const File = () => (
+const Channel = () => (
   <>
     <Segment>
       <Header as='h3'>管理渠道</Header>
@@ -11,4 +11,4 @@ const File = () => (
   </>
 );
 
-export default File;
+export default Channel;