diff --git a/frontend/src/api/initialization/index.ts b/frontend/src/api/initialization/index.ts
index 7b8bdc6f..56303d17 100644
--- a/frontend/src/api/initialization/index.ts
+++ b/frontend/src/api/initialization/index.ts
@@ -313,6 +313,27 @@ export function checkRerankModel(modelConfig: {
});
}
+// 检查 ASR 模型连接(通过 /v1/audio/transcriptions 端点测试)
+export function checkASRModel(modelConfig: {
+ modelName: string;
+ baseUrl: string;
+ apiKey?: string;
+}): Promise<{
+ available: boolean;
+ message?: string;
+}> {
+ return new Promise((resolve, reject) => {
+ post('/api/v1/initialization/asr/check', modelConfig)
+ .then((response: any) => {
+ resolve(response.data || {});
+ })
+ .catch((error: any) => {
+ console.error('Failed to check ASR model:', error);
+ reject(error);
+ });
+ });
+}
+
export function testMultimodalFunction(testData: {
image: File;
vlm_model: string;
diff --git a/frontend/src/components/ModelEditorDialog.vue b/frontend/src/components/ModelEditorDialog.vue
index 8688e424..d9a041ec 100644
--- a/frontend/src/components/ModelEditorDialog.vue
+++ b/frontend/src/components/ModelEditorDialog.vue
@@ -124,10 +124,11 @@
-
import { ref, watch, computed, onUnmounted, nextTick } from 'vue'
import { MessagePlugin } from 'tdesign-vue-next'
-import { checkOllamaModels, checkRemoteModel, testEmbeddingModel, checkRerankModel, listOllamaModels, downloadOllamaModel, getDownloadProgress, checkOllamaStatus, listModelProviders, type OllamaModelInfo, type ModelProviderOption } from '@/api/initialization'
+import { checkOllamaModels, checkRemoteModel, testEmbeddingModel, checkRerankModel, checkASRModel, listOllamaModels, downloadOllamaModel, getDownloadProgress, checkOllamaStatus, listModelProviders, type OllamaModelInfo, type ModelProviderOption } from '@/api/initialization'
import { useI18n } from 'vue-i18n'
import { useUIStore } from '@/stores/ui'
@@ -323,11 +324,10 @@ const fallbackProviderOptions = computed(() => [
chat: 'https://dashscope.aliyuncs.com/compatible-mode/v1',
embedding: 'https://dashscope.aliyuncs.com/compatible-mode/v1',
rerank: 'https://dashscope.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank',
- vllm: 'https://dashscope.aliyuncs.com/compatible-mode/v1',
- asr: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
+ vllm: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
},
description: t('model.editor.providers.aliyun.description'),
- modelTypes: ['chat', 'embedding', 'rerank', 'vllm', 'asr']
+ modelTypes: ['chat', 'embedding', 'rerank', 'vllm']
},
{
value: 'zhipu',
@@ -851,9 +851,8 @@ const checkRemoteAPI = async () => {
break
case 'asr':
- // ASR 模型(语音识别)
- // ASR 使用 checkRemoteModel 进行基础连接测试
- result = await checkRemoteModel({
+ // ASR 模型(语音识别)— 使用专用的 ASR 测试接口(/v1/audio/transcriptions)
+ result = await checkASRModel({
modelName: formData.value.modelName,
baseUrl: formData.value.baseUrl,
apiKey: formData.value.apiKey || ''
@@ -1252,24 +1251,8 @@ const handleOverlayMouseUp = () => {
}
}
-// 厂商选择器样式
-.provider-option {
- display: flex;
- flex-direction: column;
- gap: 2px;
- padding: 4px 0;
-
- .provider-name {
- font-size: 14px;
- font-weight: 500;
- color: var(--td-text-color-primary);
- }
-
- .provider-desc {
- font-size: 12px;
- color: var(--td-text-color-placeholder);
- }
-}
+// 厂商选择器样式 — 移至非 scoped 块,因为 t-select popup 渲染到 body 下
+// .provider-option 样式见文件末尾
// 单选按钮组
:deep(.t-radio-group) {
@@ -1641,3 +1624,37 @@ const handleOverlayMouseUp = () => {
}
}
+
+
+
diff --git a/frontend/src/i18n/locales/en-US.ts b/frontend/src/i18n/locales/en-US.ts
index 5691ae51..b7ba29a9 100755
--- a/frontend/src/i18n/locales/en-US.ts
+++ b/frontend/src/i18n/locales/en-US.ts
@@ -1469,9 +1469,9 @@ export default {
advanced: 'Advanced Settings',
faq: 'FAQ Settings',
graph: 'Knowledge Graph',
- multimodal: 'Multimodal',
+ multimodal: 'Image Processing',
+ asr: 'Audio Processing',
datasource: 'Data Sources',
- asr: 'Speech Recognition',
share: 'Sharing'
},
basic: {
@@ -1674,11 +1674,11 @@ export default {
childChunkSizeDescription: 'Size of child chunks used for embedding matching (64-1024)'
},
multimodal: {
- title: 'Multimodal Configuration',
- description: 'Configure multimodal content understanding for parsing and retrieving non-text content like images',
+ title: 'Image Processing Configuration',
+ description: 'Configure image content understanding for parsing and retrieving non-text content like images',
},
asr: {
- title: 'Speech Recognition Configuration',
+ title: 'Audio Processing Configuration',
description: 'Configure speech recognition to upload audio files (mp3, wav, m4a, flac, ogg) and automatically transcribe to text',
label: 'Enable Speech Recognition',
desc: 'When enabled, audio files can be uploaded to the knowledge base and automatically transcribed to text',
@@ -3097,6 +3097,7 @@ export default {
fileTypeText: 'Plain Text',
fileTypeJson: 'JSON Files',
fileTypeImage: 'Images',
+ fileTypeAudio: 'Audio Files',
engines: {
builtin: {
name: 'Built-in',
diff --git a/frontend/src/i18n/locales/ko-KR.ts b/frontend/src/i18n/locales/ko-KR.ts
index 8d2751f6..03ef6d15 100755
--- a/frontend/src/i18n/locales/ko-KR.ts
+++ b/frontend/src/i18n/locales/ko-KR.ts
@@ -1957,8 +1957,8 @@ export default {
advanced: "고급 설정",
faq: "FAQ 설정",
graph: "지식 그래프",
- multimodal: "멀티모달",
- asr: "음성 인식",
+ multimodal: "이미지 처리",
+ asr: "오디오 처리",
share: "공유관리",
storage: "스토리지 엔진",
datasource: "데이터 소스",
@@ -2173,11 +2173,11 @@ export default {
childChunkSizeDescription: "임베딩 매칭에 사용되는 자식 청크의 문자 수 (64-1024)",
},
multimodal: {
- title: "멀티모달 설정",
- description: "멀티모달 콘텐츠 이해 기능을 설정하여 이미지 등 비텍스트 콘텐츠의 파싱 및 검색을 지원합니다",
+ title: "이미지 처리 설정",
+ description: "이미지 콘텐츠 이해 기능을 설정하여 이미지 등 비텍스트 콘텐츠의 파싱 및 검색을 지원합니다",
},
asr: {
- title: "음성 인식 설정",
+ title: "오디오 처리 설정",
description: "음성 인식 기능을 설정하여 오디오 파일(mp3, wav, m4a, flac, ogg)을 업로드하고 자동으로 텍스트로 전사합니다",
label: "음성 인식 활성화",
desc: "활성화하면 오디오 파일을 지식베이스에 업로드하고 자동으로 텍스트로 전사할 수 있습니다",
@@ -3151,6 +3151,7 @@ export default {
fileTypeText: '일반 텍스트',
fileTypeJson: 'JSON 파일',
fileTypeImage: '이미지',
+ fileTypeAudio: '오디오 파일',
engines: {
builtin: {
name: '내장',
diff --git a/frontend/src/i18n/locales/ru-RU.ts b/frontend/src/i18n/locales/ru-RU.ts
index ab9be06c..95dae790 100755
--- a/frontend/src/i18n/locales/ru-RU.ts
+++ b/frontend/src/i18n/locales/ru-RU.ts
@@ -1643,8 +1643,8 @@ export default {
advanced: 'Дополнительные настройки',
faq: 'FAQ настройки',
graph: 'Граф знаний',
- multimodal: 'Мультимодальность',
- asr: 'Распознавание речи',
+ multimodal: 'Обработка изображений',
+ asr: 'Обработка аудио',
storage: 'Storage Engine',
datasource: 'Источники данных',
share: 'Sharing'
@@ -1839,11 +1839,11 @@ export default {
childChunkSizeDescription: 'Размер дочерних блоков для поиска по эмбеддингам (64-1024)'
},
multimodal: {
- title: 'Мультимодальная конфигурация',
- description: 'Настройте мультимодальное понимание контента для парсинга и поиска нетекстового контента, например изображений',
+ title: 'Обработка изображений',
+ description: 'Настройте понимание изображений для парсинга и поиска нетекстового контента',
},
asr: {
- title: 'Конфигурация распознавания речи',
+ title: 'Обработка аудио',
description: 'Настройте распознавание речи для загрузки аудиофайлов (mp3, wav, m4a, flac, ogg) и автоматической транскрибации в текст',
label: 'Включить распознавание речи',
desc: 'При включении аудиофайлы могут быть загружены в базу знаний и автоматически транскрибированы в текст',
@@ -2767,6 +2767,7 @@ export default {
fileTypeText: 'Текстовые файлы',
fileTypeJson: 'Файлы JSON',
fileTypeImage: 'Изображения',
+ fileTypeAudio: 'Аудиофайлы',
engines: {
builtin: {
name: 'Встроенный',
diff --git a/frontend/src/i18n/locales/zh-CN.ts b/frontend/src/i18n/locales/zh-CN.ts
index ae983723..a68952b9 100755
--- a/frontend/src/i18n/locales/zh-CN.ts
+++ b/frontend/src/i18n/locales/zh-CN.ts
@@ -1944,9 +1944,9 @@ export default {
advanced: "高级设置",
faq: "FAQ 设置",
graph: "知识图谱",
- multimodal: "多模态",
+ multimodal: "图像处理",
+ asr: "音频处理",
datasource: "数据源",
- asr: "语音识别",
share: "共享管理",
},
basic: {
@@ -2146,11 +2146,11 @@ export default {
childChunkSizeDescription: "用于向量匹配的子块字符数(64-1024)",
},
multimodal: {
- title: "多模态配置",
- description: "配置多模态内容理解能力,启用后支持图片等非文本内容的解析和检索",
+ title: "图像处理配置",
+ description: "配置图像内容理解能力,启用后支持图片等非文本内容的解析和检索",
},
asr: {
- title: "语音识别配置",
+ title: "音频处理配置",
description: "配置语音识别功能,启用后支持上传音频文件(mp3、wav、m4a、flac、ogg)并自动转录为文本",
label: "启用语音识别",
desc: "启用后可以上传音频文件到知识库,系统将自动转录为文本进行处理",
@@ -3095,6 +3095,7 @@ export default {
fileTypeText: "纯文本",
fileTypeJson: "JSON 文件",
fileTypeImage: "图片",
+ fileTypeAudio: "音频文件",
engines: {
builtin: {
name: "内置",
diff --git a/frontend/src/views/knowledge/KnowledgeBaseEditorModal.vue b/frontend/src/views/knowledge/KnowledgeBaseEditorModal.vue
index e220c2bb..fe039368 100644
--- a/frontend/src/views/knowledge/KnowledgeBaseEditorModal.vue
+++ b/frontend/src/views/knowledge/KnowledgeBaseEditorModal.vue
@@ -202,7 +202,7 @@
-
+