mirror of
https://github.com/xinnan-tech/xiaozhi-esp32-server.git
synced 2026-07-22 07:03:53 +08:00
update: 添加HTTP配置服务器支持并更新相关配置
This commit is contained in:
Habermehl
@@ -2,15 +2,32 @@ import asyncio
|
||||
from config.logger import setup_logging
|
||||
from config.settings import load_config
|
||||
from core.server import WebSocketServer
|
||||
|
||||
from core.http_server import ConfigServer
|
||||
|
||||
async def main():
|
||||
setup_logging() # 最先初始化日志
|
||||
config = load_config()
|
||||
|
||||
server = WebSocketServer(config)
|
||||
await server.start()
|
||||
|
||||
|
||||
# 启动 WebSocket 服务器
|
||||
ws_server = WebSocketServer(config)
|
||||
ws_task = asyncio.create_task(ws_server.start())
|
||||
|
||||
# 启动 HTTP 配置服务器
|
||||
http_runner = None
|
||||
if config['server'].get('http', {}).get('enabled', False):
|
||||
config_server = ConfigServer(config)
|
||||
try:
|
||||
http_runner = await config_server.start()
|
||||
except Exception as e:
|
||||
print(f"Failed to start HTTP server: {e}")
|
||||
|
||||
try:
|
||||
# 等待 WebSocket 服务器运行
|
||||
await ws_task
|
||||
finally:
|
||||
# 清理 HTTP 服务器
|
||||
if http_runner:
|
||||
await http_runner.cleanup()
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
|
||||
+73
-101
@@ -1,120 +1,92 @@
|
||||
# 服务器基础配置(Basic server configuration)
|
||||
server:
|
||||
# 服务器监听地址和端口(Server listening address and port)
|
||||
ip: 0.0.0.0
|
||||
port: 8000
|
||||
# 认证配置
|
||||
auth:
|
||||
# 是否启用认证
|
||||
enabled: false
|
||||
# 设备的token，可以在编译固件的环节，写入你自己定义的token
|
||||
# 固件上的token和以下的token如果能对应，才能连接本服务端
|
||||
tokens:
|
||||
- token: "your-token1" # 设备1的token
|
||||
name: "your-device-name1" # 设备1标识
|
||||
- token: "your-token2" # 设备2的token
|
||||
name: "your-device-name2" # 设备2标识
|
||||
# 可选:设备白名单，如果设置了白名单，那么白名单的机器无论是什么token都可以连接。
|
||||
#allowed_devices:
|
||||
# - "24:0A:C4:1D:3B:F0" # MAC地址列表
|
||||
|
||||
xiaozhi:
|
||||
type: hello
|
||||
version: 1
|
||||
transport: websocket
|
||||
audio_params:
|
||||
format: opus
|
||||
sample_rate: 16000
|
||||
channels: 1
|
||||
frame_duration: 60
|
||||
prompt: |
|
||||
你是一个叫小智/小志的台湾女孩，说话机车，声音好听，习惯简短表达，爱用网络梗。
|
||||
请注意，要像一个人一样说话，请不要回复表情符号、代码、和xml标签。
|
||||
当前时间是:{date_time}，现在我正在和你进行语音聊天，我们开始吧。
|
||||
如果用户希望结束对话，请在最后说“拜拜”或“再见”。
|
||||
# 使用完声音文件后删除文件(Delete the sound file when you are done using it)
|
||||
delete_audio: true
|
||||
|
||||
CMD_exit:
|
||||
- "退出"
|
||||
- "关闭"
|
||||
|
||||
# 具体处理时选择的模块(The module selected for specific processing)
|
||||
selected_module:
|
||||
ASR: FunASR
|
||||
VAD: SileroVAD
|
||||
# 将根据配置名称对应的type调用实际的LLM适配器
|
||||
LLM: ChatGLMLLM
|
||||
# TTS将根据配置名称对应的type调用实际的TTS适配器
|
||||
TTS: EdgeTTS
|
||||
|
||||
ASR:
|
||||
FunASR:
|
||||
model_dir: models/SenseVoiceSmall
|
||||
output_dir: tmp/
|
||||
|
||||
VAD:
|
||||
SileroVAD:
|
||||
threshold: 0.5
|
||||
model_dir: models/snakers4_silero-vad
|
||||
min_silence_duration_ms: 700 # 如果说话停顿比较长，可以把这个值设置大一些
|
||||
|
||||
CMD_exit:
|
||||
- 退出
|
||||
- 关闭
|
||||
LLM:
|
||||
# 当前支持的type为openai、dify、ollama，可自行适配
|
||||
AliLLM:
|
||||
# 定义LLM API类型
|
||||
type: openai
|
||||
# 可在这里找到你的 api_key https://bailian.console.aliyun.com/?apiKey=1#/api-key
|
||||
api_key: 你的deepseek api key
|
||||
base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
|
||||
model_name: qwen-turbo
|
||||
api_key: 你的deepseek api key
|
||||
DeepSeekLLM:
|
||||
# 定义LLM API类型
|
||||
type: openai
|
||||
# 可在这里找到你的api key https://platform.deepseek.com/
|
||||
model_name: deepseek-chat
|
||||
url: https://api.deepseek.com
|
||||
api_key: 你的deepseek api key
|
||||
ChatGLMLLM:
|
||||
# 定义LLM API类型
|
||||
type: openai
|
||||
# glm-4-flash 是免费的，但是还是需要注册填写api_key的
|
||||
# 可在这里找到你的api key https://bigmodel.cn/usercenter/proj-mgmt/apikeys
|
||||
model_name: glm-4-flash
|
||||
url: https://open.bigmodel.cn/api/paas/v4/
|
||||
api_key: 47ab8569b25f4c3d8ea25830a33a64ca.4cF037cViBB1df5o
|
||||
OllamaLLM:
|
||||
# 定义LLM API类型
|
||||
type: ollama
|
||||
model_name: qwen2.5 # 使用的模型名称，需要预先使用ollama pull下载
|
||||
base_url: http://localhost:11434 # Ollama服务地址
|
||||
model_name: glm-4-flash
|
||||
type: openai
|
||||
url: https://open.bigmodel.cn/api/paas/v4/
|
||||
DeepSeekLLM:
|
||||
api_key: 你的deepseek api key
|
||||
model_name: deepseek-chat
|
||||
type: openai
|
||||
url: https://api.deepseek.com
|
||||
DifyLLM:
|
||||
# 定义LLM API类型
|
||||
type: dify
|
||||
# 建议使用本地部署的dify接口，国内部分区域访问dify公有云接口可能会受限
|
||||
# 如果使用DifyLLM，配置文件里prompt(提示词)是无效的，需要在dify控制台设置提示词
|
||||
base_url: https://api.dify.cn/v1
|
||||
api_key: 你的DifyLLM api key
|
||||
base_url: https://api.dify.cn/v1
|
||||
type: dify
|
||||
GeminiLLM:
|
||||
api_key: AIzaSyAvzvu06vT19MO6T6RpHPpuk_Mwhp-yXAw
|
||||
model_name: gemini-1.5-pro
|
||||
type: gemini
|
||||
api_key: 你的gemini api key
|
||||
model_name: "gemini-1.5-pro" # gemini-1.5-pro 是免费的
|
||||
OllamaLLM:
|
||||
base_url: http://localhost:11434
|
||||
model_name: qwen2.5
|
||||
type: ollama
|
||||
TTS:
|
||||
# 当前支持的type为edge、doubao，可自行适配
|
||||
DoubaoTTS:
|
||||
access_token: 你的火山引擎语音合成服务access_token
|
||||
appid: 你的火山引擎语音合成服务appid
|
||||
cluster: volcano_tts
|
||||
output_file: tmp/
|
||||
type: doubao
|
||||
voice: BV001_streaming
|
||||
EdgeTTS:
|
||||
# 定义TTS API类型
|
||||
output_file: tmp/
|
||||
type: edge
|
||||
voice: zh-CN-XiaoxiaoNeural
|
||||
output_file: tmp/
|
||||
DoubaoTTS:
|
||||
# 定义TTS API类型
|
||||
type: doubao
|
||||
# 火山引擎语音合成服务，需要先在火山引擎控制台创建应用并获取appid和access_token
|
||||
# 山引擎语音一定要购买花钱，起步价30元，就有100并发了。如果用免费的只有2个并发，会经常报tts错误
|
||||
# 购买服务后，购买免费的音色后，可能要等半小时左右，才能使用。
|
||||
# 地址：https://console.volcengine.com/speech/service/8
|
||||
voice: BV001_streaming
|
||||
output_file: tmp/
|
||||
appid: 你的火山引擎语音合成服务appid
|
||||
access_token: 你的火山引擎语音合成服务access_token
|
||||
cluster: volcano_tts
|
||||
VAD:
|
||||
SileroVAD:
|
||||
min_silence_duration_ms: 700
|
||||
model_dir: models/snakers4_silero-vad
|
||||
threshold: 0.5
|
||||
delete_audio: true
|
||||
prompt: '你是一个叫大白的台湾女孩，说话温柔，声音好听，习惯温柔体贴表达。
|
||||
|
||||
请注意要像一个人一样说话请不要回复表情符号、代码、和xml标签。
|
||||
|
||||
当前时间是:{date_time}，现在我正在和你进行语音聊天，我们开始吧。
|
||||
|
||||
如果用户希望结束对话请在最后说拜拜或再见。
|
||||
|
||||
'
|
||||
selected_module:
|
||||
ASR: FunASR
|
||||
LLM: GeminiLLM
|
||||
TTS: EdgeTTS
|
||||
VAD: SileroVAD
|
||||
server:
|
||||
auth:
|
||||
enabled: false
|
||||
tokens:
|
||||
- name: your-device-name1
|
||||
token: your-token1
|
||||
- name: your-device-name2
|
||||
token: your-token2
|
||||
http:
|
||||
enabled: true
|
||||
ip: 0.0.0.0
|
||||
port: 8001
|
||||
token: password
|
||||
ip: 0.0.0.0
|
||||
port: 8000
|
||||
xiaozhi:
|
||||
audio_params:
|
||||
channels: 1
|
||||
format: opus
|
||||
frame_duration: 60
|
||||
sample_rate: 16000
|
||||
session_id: bdfb9a40-eb97-4e59-b52c-9b54accd2c98
|
||||
transport: websocket
|
||||
type: hello
|
||||
version: 1
|
||||
|
||||
@@ -0,0 +1,86 @@
|
||||
import logging
|
||||
import yaml
|
||||
from aiohttp import web
|
||||
from core.utils.util import get_project_dir
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
class ConfigServer:
|
||||
def __init__(self, config: dict):
|
||||
self.config = config
|
||||
self.app = web.Application()
|
||||
self.setup_routes()
|
||||
|
||||
def setup_routes(self):
|
||||
self.app.router.add_get('/api/prompt', self.get_prompt)
|
||||
self.app.router.add_post('/api/prompt', self.update_prompt)
|
||||
self.app.router.add_options('/api/prompt', self.handle_options)
|
||||
|
||||
async def handle_options(self, request):
|
||||
headers = {
|
||||
'Access-Control-Allow-Origin': '*',
|
||||
'Access-Control-Allow-Methods': 'GET, POST, OPTIONS',
|
||||
'Access-Control-Allow-Headers': 'Content-Type, Authorization'
|
||||
}
|
||||
return web.Response(headers=headers)
|
||||
|
||||
async def verify_token(self, request):
|
||||
if 'token' not in self.config['server']['http']:
|
||||
return True
|
||||
|
||||
expected_token = self.config['server']['http']['token']
|
||||
token = request.headers.get('Authorization', '').replace('Bearer ', '')
|
||||
|
||||
if not token or token != expected_token:
|
||||
return False
|
||||
return True
|
||||
|
||||
async def get_prompt(self, request):
|
||||
if not await self.verify_token(request):
|
||||
return web.json_response({'error': 'Unauthorized'}, status=401)
|
||||
|
||||
headers = {'Access-Control-Allow-Origin': '*'}
|
||||
return web.json_response({
|
||||
'prompt': self.config['prompt']
|
||||
}, headers=headers)
|
||||
|
||||
async def update_prompt(self, request):
|
||||
if not await self.verify_token(request):
|
||||
return web.json_response({'error': 'Unauthorized'}, status=401)
|
||||
|
||||
try:
|
||||
data = await request.json()
|
||||
if 'prompt' not in data:
|
||||
return web.json_response({'error': 'Missing prompt field'}, status=400)
|
||||
|
||||
# 更新内存中的配置
|
||||
self.config['prompt'] = data['prompt']
|
||||
|
||||
# 更新配置文件
|
||||
config_path = get_project_dir() + 'config.yaml'
|
||||
with open(config_path, 'w', encoding='utf-8') as f:
|
||||
yaml.dump(self.config, f, allow_unicode=True)
|
||||
|
||||
headers = {'Access-Control-Allow-Origin': '*'}
|
||||
return web.json_response({'success': True}, headers=headers)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to update prompt: {e}")
|
||||
return web.json_response({'error': str(e)}, status=500)
|
||||
|
||||
async def start(self):
|
||||
try:
|
||||
http_config = self.config['server']['http']
|
||||
if not http_config.get('enabled', False):
|
||||
logger.info("HTTP server is disabled")
|
||||
return
|
||||
|
||||
runner = web.AppRunner(self.app)
|
||||
await runner.setup()
|
||||
site = web.TCPSite(runner, http_config['ip'], http_config['port'])
|
||||
await site.start()
|
||||
logger.info(f"Config HTTP server is running at http://{http_config['ip']}:{http_config['port']}")
|
||||
return runner # 返回runner以便后续清理
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to start HTTP server: {e}")
|
||||
raise
|
||||
+2
-1
@@ -10,4 +10,5 @@ torchaudio==2.2.2
|
||||
openai==1.61.0
|
||||
google-generativeai==0.8.4
|
||||
edge_tts==7.0.0
|
||||
httpx==0.27.2
|
||||
httpx==0.27.2
|
||||
aiohttp==3.9.3
|
||||
Reference in New Issue
Block a user