Merge branch 'songquanpeng:main' into main

controller/channel-test.go

@@ -76,10 +76,10 @@ func testChannel(channel *model.Channel, request *relaymodel.GeneralOpenAIReques
 		if len(modelNames) > 0 {
 			modelName = modelNames[0]
 		}
+	}
 	if modelMap != nil && modelMap[modelName] != "" {
 		modelName = modelMap[modelName]
 	}
-	}
 	meta.OriginModelName, meta.ActualModelName = request.Model, modelName
 	request.Model = modelName
 	convertedRequest, err := adaptor.ConvertRequest(c, relaymode.ChatCompletions, request)

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

@@ -65,6 +65,8 @@ 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"`
 	TopK             float64  `json:"topK,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/adaptor/xunfei/constants.go

@@ -7,5 +7,6 @@ var ModelList = []string{
 	"SparkDesk-v3.1",
 	"SparkDesk-v3.1-128K",
 	"SparkDesk-v3.5",
+	"SparkDesk-v3.5-32K",
 	"SparkDesk-v4.0",
 }

relay/adaptor/xunfei/main.go

@@ -292,6 +292,8 @@ func apiVersion2domain(apiVersion string) string {
 		return "pro-128k"
 	case "v3.5":
 		return "generalv3.5"
+	case "v3.5-32K":
+		return "max-32k"
 	case "v4.0":
 		return "4.0Ultra"
 	}
@@ -303,7 +305,10 @@ func getXunfeiAuthUrl(apiVersion string, apiKey string, apiSecret string) (strin
 	domain := apiVersion2domain(apiVersion)
 	switch apiVersion {
 	case "v3.1-128K":
-		authUrl = buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/%s/pro-128k", apiVersion), apiKey, apiSecret)
+		authUrl = buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/chat/pro-128k"), apiKey, apiSecret)
+		break
+	case "v3.5-32K":
+		authUrl = buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/chat/max-32k"), apiKey, apiSecret)
 		break
 	default:
 		authUrl = buildXunfeiAuthUrl(fmt.Sprintf("wss://spark-api.xf-yun.com/%s/chat", apiVersion), apiKey, apiSecret)

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,
@@ -130,6 +131,7 @@ var ModelRatio = map[string]float64{
 	"SparkDesk-v3.1":            1.2858, // ￥0.018 / 1k tokens
 	"SparkDesk-v3.1-128K":       1.2858, // ￥0.018 / 1k tokens
 	"SparkDesk-v3.5":            1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v3.5-32K":        1.2858, // ￥0.018 / 1k tokens
 	"SparkDesk-v4.0":            1.2858, // ￥0.018 / 1k tokens
 	"360GPT_S2_V9":              0.8572, // ¥0.012 / 1k tokens
 	"embedding-bert-512-v1":     0.0715, // ¥0.001 / 1k tokens
@@ -161,15 +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

@@ -3,4 +3,5 @@ package model
 const (
 	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"`

web/air/src/components/TokensTable.js

@@ -395,7 +395,7 @@ const TokensTable = () => {
         url = mjLink + `/#/?settings={"key":"sk-${key}","url":"${serverAddress}"}`;
         break;
       case 'lobechat':
-        url = chatLink + `/?settings={"keyVaults":{"openai":{"apiKey":"sk-${key}","baseURL":"${serverAddress}"/v1"}}}`;
+        url = chatLink + `/?settings={"keyVaults":{"openai":{"apiKey":"sk-${key}","baseURL":"${serverAddress}/v1"}}}`;
         break;
       default:
         if (!chatLink) {

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'];
@@ -78,7 +78,7 @@ const EditChannel = (props) => {
                     localModels = ['chatglm_pro', 'chatglm_std', 'chatglm_lite'];
                     break;
                 case 18:
-                    localModels = ['SparkDesk', 'SparkDesk-v1.1', 'SparkDesk-v2.1', 'SparkDesk-v3.1', 'SparkDesk-v3.1-128K', 'SparkDesk-v3.5', 'SparkDesk-v4.0'];
+                    localModels = ['SparkDesk', 'SparkDesk-v1.1', 'SparkDesk-v2.1', 'SparkDesk-v3.1', 'SparkDesk-v3.1-128K', 'SparkDesk-v3.5', 'SparkDesk-v3.5-32K', 'SparkDesk-v4.0'];
                     break;
                 case 19:
                     localModels = ['360GPT_S2_V9', 'embedding-bert-512-v1', 'embedding_s1_v1', 'semantic_similarity_s1_v1'];

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

@@ -91,7 +91,7 @@ const typeConfig = {
       other: '版本号'
     },
     input: {
-      models: ['SparkDesk', 'SparkDesk-v1.1', 'SparkDesk-v2.1', 'SparkDesk-v3.1', 'SparkDesk-v3.1-128K', 'SparkDesk-v3.5', 'SparkDesk-v4.0']
+      models: ['SparkDesk', 'SparkDesk-v1.1', 'SparkDesk-v2.1', 'SparkDesk-v3.1', 'SparkDesk-v3.1-128K', 'SparkDesk-v3.5', 'SparkDesk-v3.5-32K', 'SparkDesk-v4.0']
     },
     prompt: {
       key: '按照如下格式输入：APPID|APISecret|APIKey',

web/berry/src/views/Token/component/TableRow.js

@@ -33,7 +33,7 @@ const COPY_OPTIONS = [
   },
   { key: 'ama', text: 'BotGem', url: 'ama://set-api-key?server={serverAddress}&key=sk-{key}', encode: true },
   { key: 'opencat', text: 'OpenCat', url: 'opencat://team/join?domain={serverAddress}&token=sk-{key}', encode: true },
-  { key: 'lobechat', text: 'LobeChat', url: 'https://lobehub.com/?settings={"keyVaults":{"openai":{"apiKey":"user-key","baseURL":"https://your-proxy.com/v1"}}}', encode: true }
+  { key: 'lobechat', text: 'LobeChat', url: 'https://lobehub.com/?settings={"keyVaults":{"openai":{"apiKey":"sk-{key}","baseURL":"{serverAddress}"}}}', encode: true }
 ];
 
 function replacePlaceholders(text, key, serverAddress) {

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/components/TokensTable.js

@@ -117,7 +117,7 @@ const TokensTable = () => {
         url = nextUrl;
         break;
       case 'lobechat':
-        url = nextLink + `/?settings={"keyVaults":{"openai":{"apiKey":"sk-${key}","baseURL":"${serverAddress}"/v1"}}}`;
+        url = nextLink + `/?settings={"keyVaults":{"openai":{"apiKey":"sk-${key}","baseURL":"${serverAddress}/v1"}}}`;
         break;
       default:
         url = `sk-${key}`;
@@ -160,7 +160,7 @@ const TokensTable = () => {
         break;
 
       case 'lobechat':
-        url = chatLink + `/?settings={"keyVaults":{"openai":{"apiKey":"sk-${key}","baseURL":"${serverAddress}"/v1"}}}`;
+        url = chatLink + `/?settings={"keyVaults":{"openai":{"apiKey":"sk-${key}","baseURL":"${serverAddress}/v1"}}}`;
         break;
 
       default:

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;