feat:add funasr module

Author: ruanrongman

docker/docker-compose.yml

@@ -99,12 +99,21 @@ services:
       timeout: 10s
       retries: 3
 
+  funasr:
+    image: harryliu888/funasr-online-server:latest
+    container_name: funasr-online-server
+    ports:
+      - 10095:10095
+      - 10096:10096
+    volumes:
+      - ./models:/workspace/models
 volumes:
   mysql-volume:
   redis-volume:
   influxdb-volume:
   emqx-volume:
   chromadb-volume:  # 新增 ChromaDB 数据卷
+  funasr-volume:
 
 networks:
   emqx-bridge:

docs/get_started/quick_start.md

@@ -4,6 +4,7 @@
 物联网平台内核是一个轻量级的物联网平台，包含了物联网最核心的基础模块，
 包括物模型、监控、AI、MQTT、微信小程序、微信服务号等模块。该平台旨在帮助开发者快速搭建物联网应用，提高开发效率。
 物联网平台内核并不包括ui组件，只提供基础的api接口，开发者可以自由选择自己喜欢的ui框架来搭建应用。
+目前已经提供了一套示例UI界面，基于Vue3，可以直接使用。
 
 ## 什么是Agent智能体
 Agent智能体可以自我学习。智能体是一种通用问题解决器。从软件工程的角度看来， 
@@ -30,6 +31,7 @@ cd docker && docker-compose up -d
     - EMQX MQTT消息中间件(https://www.emqx.com/zh)
     - InfluxDB 时序数据库
     - Chroma 一个开源的向量数据库，用于存储和检索向量数据。(https://docs.trychroma.com/docs/overview/introduction)
+    - FunAsr 语音识别服务。(https://github.com/modelscope/FunASR)
 
 2. 验证容器状态（可选）：
 ```bash
@@ -194,10 +196,24 @@ ai:
   audio-temp-url: [项目运行的域名]
   glm-key: 
   deepSeek-key: 
-  dashscope-key: 
-  robot-name: [机器人名称]
+  dashscope-key:
+  uniApi-Key: 
+  robot-name: 小创
   team-name: 创万联
+  custom-key: XXX
+  custom-llm-provider-url: XXX
 ```
+>默认支持以上几种主流供应商，你可以自行添加其他供应商或者本地部署的LLM，只需要配置对应的供应商URL即可。
+
+* 对应的供应商及其名称规则如下：
+
+```yaml
+1. 硅基流动(https://siliconflow.cn/): silicon-模型名称(silicon-Qwen/Qwen3-Next-80B-A3B-Instruct)
+2. 阿里云百炼(https://www.aliyun.com/product/tongyi?utm_content=se_1021879167): dashscope-模型名称(dashscope-qwen3-max)
+3. uniapi(https://uniapi.ai/): uniapi-模型名称(uniapi-qwen3-max)
+4. 私有部署或其它供应商: custom-模型名称(custom-模型名称)
+```
+
 通过以上步骤即可完成基础环境的搭建与配置，建议通过健康检查接口验证各服务连接状态。如果你需要
 控制家里的电气，你可以选择安装homeAssistant与本平台集成，它将帮助你管理家庭的电器，并提供流畅的体验。
 

src/main/java/top/rslly/iot/services/agent/AiServiceImpl.java

@@ -35,7 +35,7 @@
 import top.rslly.iot.utility.ai.chain.Router;
 import top.rslly.iot.utility.ai.llm.LLMFactory;
 import top.rslly.iot.utility.ai.mcp.McpWebsocket;
-import top.rslly.iot.utility.ai.voice.Audio2Text;
+import top.rslly.iot.utility.ai.voice.ASR.Audio2Text;
 import top.rslly.iot.utility.ai.voice.AudioUtils;
 import top.rslly.iot.utility.ai.voice.TTS.Text2audio;
 import top.rslly.iot.utility.ai.voice.TTS.TtsService;

src/main/java/top/rslly/iot/utility/ai/voice/ASR/AsrService.java

@@ -0,0 +1,28 @@
+/**
+ * Copyright © 2023-2030 The ruanrongman Authors
+ *
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package top.rslly.iot.utility.ai.voice.ASR;
+
+import java.io.File;
+
+public interface AsrService {
+  public String getText(String url);
+
+  public String getTextRealtime(File file, int sampleRate, String format);
+}

src/main/java/top/rslly/iot/utility/ai/voice/ASR/AsrServiceFactory.java

@@ -0,0 +1,67 @@
+/**
+ * Copyright © 2023-2030 The ruanrongman Authors
+ *
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package top.rslly.iot.utility.ai.voice.ASR;
+
+import lombok.extern.slf4j.Slf4j;
+import org.springframework.beans.factory.annotation.Autowired;
+import org.springframework.beans.factory.annotation.Value;
+import org.springframework.stereotype.Component;
+
+/**
+ * ASR服务工厂类
+ */
+@Slf4j
+@Component
+public class AsrServiceFactory {
+
+  @Value("${ai.asr.provider:funasr}")
+  private String defaultProvider;
+
+  @Autowired
+  private Audio2Text audio2Text;
+
+  @Autowired
+  private FunAsrClient funAsrClient;
+
+  /**
+   * 获取默认的ASR服务
+   */
+  public AsrService getService() {
+    return getService(defaultProvider);
+  }
+
+  /**
+   * 根据提供商名称获取ASR服务
+   *
+   * @param provider 提供商名称（dashscope/funasr）
+   * @return ASR服务实例
+   */
+  public AsrService getService(String provider) {
+    if ("funasr".equalsIgnoreCase(provider)) {
+      return funAsrClient;
+    }
+    if ("dashscope".equalsIgnoreCase(provider)) {
+      return audio2Text;
+    }
+    log.warn("未知的ASR提供商: {}, 使用默认服务", provider);
+    return "funasr".equalsIgnoreCase(defaultProvider) ? funAsrClient : audio2Text;
+  }
+
+}

…lly/iot/utility/ai/voice/Audio2Text.java …iot/utility/ai/voice/ASR/Audio2Text.javasrc/main/java/top/rslly/iot/utility/ai/voice/Audio2Text.java renamed to src/main/java/top/rslly/iot/utility/ai/voice/ASR/Audio2Text.java src/main/java/top/rslly/iot/utility/ai/voice/Audio2Text.java renamed to src/main/java/top/rslly/iot/utility/ai/voice/ASR/Audio2Text.java

@@ -17,7 +17,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-package top.rslly.iot.utility.ai.voice;
+package top.rslly.iot.utility.ai.voice.ASR;
 
 import com.alibaba.dashscope.audio.asr.recognition.Recognition;
 import com.alibaba.dashscope.audio.asr.recognition.RecognitionParam;
@@ -48,7 +48,7 @@
 
 @Component
 @Slf4j
-public class Audio2Text {
+public class Audio2Text implements AsrService {
   private String apiKey;
 
   @Value("${ai.audio-tmp-path}")
@@ -126,7 +126,18 @@ public String getTextRealtime(File file, int sampleRate, String format) {
 
     try {
       // System.out.println("识别结果：" + recognizer.call(param, file));
-      return recognizer.call(param, file);
+      String text = recognizer.call(param, file);
+      StringBuilder sentences = new StringBuilder();
+      var jsonObject = JSON.parseObject(text);
+      var sentencesArray = jsonObject.getJSONArray("sentences");
+      if (sentencesArray.size() > 0) {
+        for (int i = 0; i < sentencesArray.size(); i++) {
+          sentences.append(sentencesArray.getJSONObject(i).getString("text"));
+        }
+      } else {
+        sentences.append("识别结果为空");
+      }
+      return sentences.toString();
     } catch (Exception e) {
       log.error("语音识别失败{}", e.getMessage());
       return "语音识别失败";