Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-22 07:03:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/mangger-api-voice-print' into mangger-api-voice-print

Browse Source
This commit is contained in:
JianYu Zheng
2025-07-10 11:33:28 +08:00
parent 008c446966 01158e67e0
commit f499040955
2 changed files with 81 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main/manager-api/src/main/java/xiaozhi/modules/config/service/impl/ConfigServiceImpl.java
+67
View File
@@ -9,20 +9,27 @@ import java.util.Objects;
import org.apache.commons.lang3.StringUtils;
import org.springframework.stereotype.Service;
import com.baomidou.mybatisplus.core.conditions.query.LambdaQueryWrapper;
import lombok.AllArgsConstructor;
import xiaozhi.common.constant.Constant;
import xiaozhi.common.exception.ErrorCode;
import xiaozhi.common.exception.RenException;
import xiaozhi.common.redis.RedisKeys;
import xiaozhi.common.redis.RedisUtils;
import xiaozhi.common.utils.ConvertUtils;
import xiaozhi.common.utils.JsonUtils;
import xiaozhi.modules.agent.dao.AgentVoicePrintDao;
import xiaozhi.modules.agent.entity.AgentEntity;
import xiaozhi.modules.agent.entity.AgentPluginMapping;
import xiaozhi.modules.agent.entity.AgentTemplateEntity;
import xiaozhi.modules.agent.entity.AgentVoicePrintEntity;
import xiaozhi.modules.agent.service.AgentMcpAccessPointService;
import xiaozhi.modules.agent.service.AgentPluginMappingService;
import xiaozhi.modules.agent.service.AgentService;
import xiaozhi.modules.agent.service.AgentTemplateService;
import xiaozhi.modules.agent.service.AgentVoicePrintService;
import xiaozhi.modules.agent.vo.AgentVoicePrintVO;
import xiaozhi.modules.config.service.ConfigService;
import xiaozhi.modules.device.entity.DeviceEntity;
import xiaozhi.modules.device.service.DeviceService;
@@ -45,6 +52,8 @@ public class ConfigServiceImpl implements ConfigService {
private final TimbreService timbreService;
private final AgentPluginMappingService agentPluginMappingService;
private final AgentMcpAccessPointService agentMcpAccessPointService;
private final AgentVoicePrintService agentVoicePrintService;
private final AgentVoicePrintDao agentVoicePrintDao;
@Override
public Object getConfig(Boolean isCache) {
@@ -162,6 +171,8 @@ public class ConfigServiceImpl implements ConfigService {
mcpEndpoint = mcpEndpoint.replace("/mcp/", "/call/");
result.put("mcp_endpoint", mcpEndpoint);
}
// 获取声纹信息
buildVoiceprintConfig(agent.getId(), result);
// 构建模块配置
buildModuleConfig(
@@ -255,6 +266,62 @@ public class ConfigServiceImpl implements ConfigService {
return config;
}
/**
* 构建声纹配置信息
*
* @param agentId 智能体ID
* @param result 结果Map
*/
private void buildVoiceprintConfig(String agentId, Map<String, Object> result) {
try {
// 获取声纹接口地址
String voiceprintUrl = sysParamsService.getValue("server.voice_print", true);
if (StringUtils.isBlank(voiceprintUrl) || "null".equals(voiceprintUrl)) {
return;
}
// 获取智能体关联的声纹信息（不需要用户权限验证）
List<AgentVoicePrintVO> voiceprints = getVoiceprintsByAgentId(agentId);
if (voiceprints == null || voiceprints.isEmpty()) {
return;
}
// 构建speakers列表
List<String> speakers = new ArrayList<>();
for (AgentVoicePrintVO voiceprint : voiceprints) {
String speakerStr = String.format("%s,%s,%s",
voiceprint.getId(),
voiceprint.getSourceName(),
voiceprint.getIntroduce() != null ? voiceprint.getIntroduce() : "");
speakers.add(speakerStr);
}
// 构建声纹配置
Map<String, Object> voiceprintConfig = new HashMap<>();
voiceprintConfig.put("url", voiceprintUrl);
voiceprintConfig.put("speakers", speakers);
result.put("voiceprint", voiceprintConfig);
} catch (Exception e) {
// 声纹配置获取失败时不影响其他功能
System.err.println("获取声纹配置失败: " + e.getMessage());
}
}
/**
* 获取智能体关联的声纹信息
*
* @param agentId 智能体ID
* @return 声纹信息列表
*/
private List<AgentVoicePrintVO> getVoiceprintsByAgentId(String agentId) {
LambdaQueryWrapper<AgentVoicePrintEntity> queryWrapper = new LambdaQueryWrapper<>();
queryWrapper.eq(AgentVoicePrintEntity::getAgentId, agentId);
queryWrapper.orderByAsc(AgentVoicePrintEntity::getCreateDate);
List<AgentVoicePrintEntity> entities = agentVoicePrintDao.selectList(queryWrapper);
return ConvertUtils.sourceToTarget(entities, AgentVoicePrintVO.class);
}
/**
* 构建模块配置
*
main/xiaozhi-server/core/connection.py
+14 -7
View File
@@ -496,6 +496,9 @@ class ConnectionHandler:
] = plugin_from_server.keys()
if private_config.get("prompt", None) is not None:
self.config["prompt"] = private_config["prompt"]
# 获取声纹信息
if private_config.get("voiceprint", None) is not None:
self.config["voiceprint"] = private_config["voiceprint"]
if private_config.get("summaryMemory", None) is not None:
self.config["summaryMemory"] = private_config["summaryMemory"]
if private_config.get("device_max_output_size", None) is not None:
@@ -634,25 +637,29 @@ class ConnectionHandler:
# 检查是否是JSON格式的消息（包含说话人信息）
enhanced_query = query
try:
if query.strip().startswith('{') and query.strip().endswith('}'):
if query.strip().startswith("{") and query.strip().endswith("}"):
data = json.loads(query)
if 'speaker' in data and 'content' in data:
if "speaker" in data and "content" in data:
# 直接使用JSON格式，不重新格式化
enhanced_query = query
self.logger.bind(tag=TAG).info(f"识别到说话人: {data['speaker']}")
else:
# 如果有说话人信息但不是JSON格式，按原逻辑处理
if hasattr(self, 'current_speaker') and self.current_speaker:
if hasattr(self, "current_speaker") and self.current_speaker:
enhanced_query = f"[说话人: {self.current_speaker}] {query}"
self.logger.bind(tag=TAG).info(f"识别到说话人: {self.current_speaker}")
self.logger.bind(tag=TAG).info(
f"识别到说话人: {self.current_speaker}"
)
else:
# 如果有说话人信息但不是JSON格式，按原逻辑处理
if hasattr(self, 'current_speaker') and self.current_speaker:
if hasattr(self, "current_speaker") and self.current_speaker:
enhanced_query = f"[说话人: {self.current_speaker}] {query}"
self.logger.bind(tag=TAG).info(f"识别到说话人: {self.current_speaker}")
self.logger.bind(tag=TAG).info(
f"识别到说话人: {self.current_speaker}"
)
except json.JSONDecodeError:
# JSON解析失败，按原逻辑处理
if hasattr(self, 'current_speaker') and self.current_speaker:
if hasattr(self, "current_speaker") and self.current_speaker:
enhanced_query = f"[说话人: {self.current_speaker}] {query}"
self.logger.bind(tag=TAG).info(f"识别到说话人: {self.current_speaker}")