Merge branch 'main' into main

This commit is contained in:
欣南科技
2025-02-15 21:13:50 +08:00
committed by GitHub
15 changed files with 369 additions and 211 deletions
+2 -2
View File
@@ -1,8 +1,8 @@
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
from core.websocket_server import WebSocketServer
from manager.http_server import ConfigServer
async def main():
setup_logging() # 最先初始化日志
+32
View File
@@ -1,3 +1,7 @@
# 如果您是一名开发者,建议阅读以下内容。如果不是开发者,可以忽略这部分内容。
# 在开发中,建议将【config.yaml】复制一份,改成【.config.yaml】。 系统会优先读取【.config.yaml】文件的配置。
# 这样做,可以避免在提交代码的时候,错误地提交密钥信息,保护您的密钥安全。
# 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)
@@ -140,3 +144,31 @@ TTS:
output_file: tmp/
access_token: 你的硅基流动API密钥
response_format: wav
FishSpeech:
# 定义TTS API类型
#启动tts方法:
#python -m tools.api_server
#--listen 0.0.0.0:8080
#--llama-checkpoint-path "checkpoints/fish-speech-1.5"
#--decoder-checkpoint-path "checkpoints/fish-speech-1.5/firefly-gan-vq-fsq-8x1024-21hz-generator.pth"
#--decoder-config-name firefly_gan_vq
#--compile
type: fishspeech
output_file: tmp/
response_format: wav
reference_id: null
reference_audio: ["/tmp/test.wav",]
reference_text: ["你弄来这些吟词宴曲来看,还是这些混话来欺负我。",]
normalize: true
max_new_tokens: 1024
chunk_length: 200
top_p: 0.7
repetition_penalty: 1.2
temperature: 0.7
streaming: false
use_memory_cache: "on"
seed: null
channels: 1
rate: 44100
api_key: "YOUR_API_KEY"
api_url: "http://127.0.0.1:8080/v1/tts"
+18 -4
View File
@@ -1,15 +1,29 @@
import os
import argparse
from ruamel.yaml import YAML
from core.utils.util import read_config, get_project_dir
def get_config_file():
default_config_file = "config.yaml"
# 判断是否存在私有的配置文件
if os.path.exists(get_project_dir() + "." + default_config_file):
default_config_file = "." + default_config_file
return default_config_file
def load_config():
"""加载配置文件"""
parser = argparse.ArgumentParser(description="Server configuration")
default_config_file = "config.yaml"
# 判断是否存在私有的配置文件
if os.path.exists(get_project_dir() + "." + default_config_file):
default_config_file = "." + default_config_file
default_config_file = get_config_file()
parser.add_argument("--config_path", type=str, default=default_config_file)
args = parser.parse_args()
return read_config(args.config_path)
def update_config(config):
yaml = YAML()
yaml.preserve_quotes = True
"""将配置保存到YAML文件"""
with open(get_config_file(), 'w') as f:
yaml.dump(config, f)
+2 -2
View File
@@ -15,8 +15,8 @@ from core.handle.textHandle import handleTextMessage
from core.utils.util import get_string_no_punctuation_or_emoji
from concurrent.futures import ThreadPoolExecutor, TimeoutError
from core.handle.audioHandle import handleAudioMessage, sendAudioMessage
from .auth import AuthMiddleware, AuthenticationError
from config.private_config import PrivateConfig # Updated import path
from config.private_config import PrivateConfig
from core.auth import AuthMiddleware, AuthenticationError
class ConnectionHandler:
def __init__(self, config: Dict[str, Any], _vad, _asr, _llm, _tts):
+152
View File
@@ -0,0 +1,152 @@
import base64
import os
import uuid
import requests
import ormsgpack
from pathlib import Path
from pydantic import BaseModel, Field, conint, model_validator
from typing_extensions import Annotated
from datetime import datetime
from typing import Literal
# from base import TTSProviderBase
from core.providers.tts.base import TTSProviderBase
class ServeReferenceAudio(BaseModel):
audio: bytes
text: str
@model_validator(mode="before")
def decode_audio(cls, values):
audio = values.get("audio")
if (
isinstance(audio, str) and len(audio) > 255
): # Check if audio is a string (Base64)
try:
values["audio"] = base64.b64decode(audio)
except Exception as e:
# If the audio is not a valid base64 string, we will just ignore it and let the server handle it
pass
return values
def __repr__(self) -> str:
return f"ServeReferenceAudio(text={self.text!r}, audio_size={len(self.audio)})"
class ServeTTSRequest(BaseModel):
text: str
chunk_length: Annotated[int, conint(ge=100, le=300, strict=True)] = 200
# Audio format
format: Literal["wav", "pcm", "mp3"] = "wav"
# References audios for in-context learning
references: list[ServeReferenceAudio] = []
# Reference id
# For example, if you want use https://fish.audio/m/7f92f8afb8ec43bf81429cc1c9199cb1/
# Just pass 7f92f8afb8ec43bf81429cc1c9199cb1
reference_id: str | None = None
seed: int | None = None
use_memory_cache: Literal["on", "off"] = "off"
# Normalize text for en & zh, this increase stability for numbers
normalize: bool = True
# not usually used below
streaming: bool = False
max_new_tokens: int = 1024
top_p: Annotated[float, Field(ge=0.1, le=1.0, strict=True)] = 0.7
repetition_penalty: Annotated[float, Field(ge=0.9, le=2.0, strict=True)] = 1.2
temperature: Annotated[float, Field(ge=0.1, le=1.0, strict=True)] = 0.7
class Config:
# Allow arbitrary types for pytorch related types
arbitrary_types_allowed = True
def audio_to_bytes(file_path):
if not file_path or not Path(file_path).exists():
return None
with open(file_path, "rb") as wav_file:
wav = wav_file.read()
return wav
def read_ref_text(ref_text):
path = Path(ref_text)
if path.exists() and path.is_file():
with path.open("r", encoding="utf-8") as file:
return file.read()
return ref_text
class TTSProvider(TTSProviderBase):
def __init__(self, config, delete_audio_file):
super().__init__(config, delete_audio_file)
self.reference_id = config.get("reference_id")
self.reference_audio = config.get("reference_audio",[])
self.reference_text = config.get("reference_text",[])
self.format = config.get("format","wav")
self.channels = config.get("channels",1)
self.rate = config.get("rate",44100)
self.api_key = config.get("api_key","YOUR_API_KEY")
self.normalize = config.get("normalize",True)
self.max_new_tokens = config.get("max_new_tokens",1024)
self.chunk_length = config.get("chunk_length",200)
self.top_p = config.get("top_p",0.7)
self.repetition_penalty = config.get("repetition_penalty",1.2)
self.temperature = config.get("temperature",0.7)
self.streaming = config.get("streaming",False)
self.use_memory_cache = config.get("use_memory_cache","on")
self.seed = config.get("seed")
self.api_url = config.get("api_url","http://127.0.0.1:8080/v1/tts")
def generate_filename(self, extension=".wav"):
return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
async def text_to_speak(self, text, output_file):
# Prepare reference data
byte_audios = [audio_to_bytes(ref_audio) for ref_audio in self.reference_audio]
ref_texts = [read_ref_text(ref_text) for ref_text in self.reference_text]
data = {
"text": text,
"references": [
ServeReferenceAudio(
audio=audio if audio else b"", text=text
)
for text, audio in zip(ref_texts, byte_audios)
],
"reference_id": self.reference_id,
"normalize": self.normalize,
"format": self.format,
"max_new_tokens": self.max_new_tokens,
"chunk_length": self.chunk_length,
"top_p": self.top_p,
"repetition_penalty": self.repetition_penalty,
"temperature": self.temperature,
"streaming": self.streaming,
"use_memory_cache": self.use_memory_cache,
"seed": self.seed,
}
pydantic_data = ServeTTSRequest(**data)
response = requests.post(
self.api_url,
data=ormsgpack.packb(pydantic_data, option=ormsgpack.OPT_SERIALIZE_PYDANTIC),
headers={
"Authorization": f"Bearer {self.api_key}",
"Content-Type": "application/msgpack",
},
)
if response.status_code == 200:
audio_content = response.content
with open(output_file, "wb") as audio_file:
audio_file.write(audio_content)
else:
print(f"Request failed with status code {response.status_code}")
print(response.json())
+8 -3
View File
@@ -1,5 +1,7 @@
import logging
from aiohttp import web
from config.settings import update_config
from ruamel.yaml.scalarstring import PreservedScalarString
from manager.api.auth import verify_token
from manager.api.response import response_unauthorized, response_success, response_error
@@ -28,10 +30,13 @@ class PromptApi:
if 'prompt' not in data:
return response_success()
self.config['prompt'] = data['prompt']
# TODO 保存到配置文件
return response_success()
# 使用PreservedScalarString保留多行文本格式
self.config['prompt'] = PreservedScalarString(data['prompt'])
# 保存到配置文件
update_config(self.config)
return response_success()
except Exception as e:
logger.error(f"Failed to update prompt: {e}")
return response_error(str(e))
+77
View File
@@ -0,0 +1,77 @@
/* common.css */
/* 基础样式 */
body {
margin: 0;
padding: 0;
background: linear-gradient(135deg, #1a1f25 0%, #0d1117 100%);
min-height: 100vh;
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif;
}
/* 头部组件 */
.app-header {
background: rgba(13, 17, 23, 0.8);
backdrop-filter: blur(10px);
color: #fff;
padding: 1.5rem 2rem;
font-size: 1.4rem;
border-bottom: 1px solid rgba(255, 255, 255, 0.1);
display: flex;
align-items: center;
gap: 1rem;
position: relative;
z-index: 1;
}
.header-logo {
width: 32px;
height: 32px;
background: linear-gradient(45deg, #00c6fb 0%, #005bea 100%);
border-radius: 8px;
display: flex;
align-items: center;
justify-content: center;
font-weight: bold;
}
/* 页脚组件 */
.app-footer {
text-align: center;
color: rgba(255, 255, 255, 0.6);
font-size: 13px;
padding: 20px;
position: fixed;
bottom: 0;
width: 100%;
z-index: 1;
}
/* 背景动画 */
.animated-bg {
position: fixed;
top: 0;
left: 0;
width: 100%;
height: 100%;
z-index: -1;
background: linear-gradient(-45deg, #1a1f25, #0d1117, #162030, #1c1c1c);
background-size: 400% 400%;
}
.user-menu {
position: fixed;
top: 23px;
right: 32px;
z-index: 1000;
cursor: pointer;
}
.user-info {
align-items: center;
}
.user-name {
font-size: 14px;
color: #606266;
}
Binary file not shown.

After

Width:  |  Height:  |  Size: 1.1 KiB

+35 -66
View File
@@ -1,5 +1,5 @@
<!DOCTYPE html>
<html>
<!doctype html>
<html lang="zh">
<head>
<meta charset="UTF-8"/>
<meta name="viewport" content="width=device-width,initial-scale=1.0"/>
@@ -8,39 +8,11 @@
<script src="js/element-plus2.9.4.js"></script>
<script src="js/icons-vue2.3.1.js"></script>
<script src="js/common.js"></script>
<link rel="icon" href="images/favicon.ico" />
<link rel="stylesheet" href="css/common.css">
<title>小智-server</title>
<style>
body {
margin: 0;
padding: 0;
background: linear-gradient(135deg, #1a1f25 0%, #0d1117 100%);
min-height: 100vh;
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif;
}
.header {
background: rgba(13, 17, 23, 0.8);
backdrop-filter: blur(10px);
color: #fff;
padding: 1.5rem 2rem;
font-size: 1.4rem;
border-bottom: 1px solid rgba(255, 255, 255, 0.1);
display: flex;
align-items: center;
gap: 1rem;
}
.header-logo {
width: 32px;
height: 32px;
background: linear-gradient(45deg, #00c6fb 0%, #005bea 100%);
border-radius: 8px;
display: flex;
align-items: center;
justify-content: center;
font-weight: bold;
}
/* 页面特有样式 */
.content-container {
max-width: 1200px;
margin: 20px auto;
@@ -56,15 +28,6 @@
margin-bottom: 1rem;
}
.role-id {
color: #333;
margin-bottom: 1rem;
}
.role-description {
margin: 1rem 0;
}
.character-count {
text-align: right;
color: #999;
@@ -81,35 +44,33 @@
font-size: 12px;
margin-top: 1rem;
}
.footer {
text-align: center;
color: rgba(255, 255, 255, 0.6);
font-size: 13px;
padding: 20px;
position: fixed;
bottom: 0;
width: 100%;
}
</style>
</head>
<body>
<div id="app">
<div class="animated-bg"></div>
<div class="header">
<div class="header-logo">AI</div>
xiaozhi-esp32-server
<app-header>xiaozhi-esp32-server</app-header>
<div class="user-menu">
<el-dropdown @command="handleCommand">
<div class="user-info">
<el-avatar :size="32" src="https://cube.elemecdn.com/3/7c/3ea6beec64369c2642b92c6726f1epng.png"/>
<span class="user-name">管理员</span>
</div>
<template #dropdown>
<el-dropdown-menu>
<el-dropdown-item command="logout">退出</el-dropdown-item>
</el-dropdown-menu>
</template>
</el-dropdown>
</div>
<div class="content-container">
<div class="role-title">配置角色:</div>
<div class="role-id">cc:ba:97:11:a6:ac</div>
<div class="role-description">角色介绍</div>
<el-input
type="textarea"
v-model="form.prompt"
:rows="6"
:rows="10"
resize="vertical"
@input="updateCharCount"
></el-input>
@@ -117,15 +78,13 @@
<div class="button-group">
<el-button type="primary" @click="savePrompt">保存配置</el-button>
<el-button @click="resetPrompt">重置</el-button>
<el-button @click="loadPrompt">重置</el-button>
</div>
<div class="note">注意:保存配置后,需要重启设备,新的配置才会生效。</div>
</div>
<div class="footer">
© 2025 xiaozhi-esp32-server
</div>
<app-footer></app-footer>
</div>
<script>
@@ -173,14 +132,24 @@
});
}
});
}
},
// 新增退出处理方法
handleCommand(command) {
if (command === 'logout') {
this.handleLogout();
}
},
handleLogout() {
localStorage.removeItem('token');
location.href = 'login.html';
},
},
mounted() {
this.loadPrompt();
}
};
const app = Vue.createApp(App);
app.use(ElementPlus);
const app = createVueApp(App);
app.mount("#app");
</script>
</body>
+28
View File
@@ -37,4 +37,32 @@ function get(api, fn) {
}
fn(data);
});
}
// 注册全局组件
const AppHeader = {
template: `
<header class="app-header">
<div class="header-logo">AI</div>
<slot>xiaozhi-esp32-server</slot>
</header>
`
};
const AppFooter = {
template: `
<footer class="app-footer">
<slot>© 2025 xiaozhi-esp32-server</slot>
</footer>
`
};
// 初始化Vue应用的通用配置
function createVueApp(options) {
const app = Vue.createApp({
...options,
components: { AppHeader, AppFooter }
});
app.use(ElementPlus);
return app;
}
+12 -80
View File
@@ -1,46 +1,18 @@
<!DOCTYPE html>
<html>
<!doctype html>
<html lang="zh">
<head>
<meta charset="UTF-8"/>
<link rel="icon" href="images/favicon.ico" />
<meta name="viewport" content="width=device-width,initial-scale=1.0"/>
<script src="js/vue3.5.13.js"></script>
<link rel="stylesheet" href="css/element-plus2.9.4.css">
<script src="js/element-plus2.9.4.js"></script>
<script src="js/icons-vue2.3.1.js"></script>
<script src="js/common.js"></script>
<link rel="stylesheet" href="css/common.css">
<title>小智-server</title>
<style>
body {
margin: 0;
padding: 0;
background: linear-gradient(135deg, #1a1f25 0%, #0d1117 100%);
min-height: 100vh;
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif;
}
.header {
background: rgba(13, 17, 23, 0.8);
backdrop-filter: blur(10px);
color: #fff;
padding: 1.5rem 2rem;
font-size: 1.4rem;
border-bottom: 1px solid rgba(255, 255, 255, 0.1);
display: flex;
align-items: center;
gap: 1rem;
}
.header-logo {
width: 32px;
height: 32px;
background: linear-gradient(45deg, #00c6fb 0%, #005bea 100%);
border-radius: 8px;
display: flex;
align-items: center;
justify-content: center;
font-weight: bold;
}
/* 页面特有样式 */
.login-container {
max-width: 440px;
margin: 60px auto;
@@ -60,10 +32,6 @@
text-align: center;
}
.login-form {
margin-top: 20px;
}
.custom-input :deep(.el-input__wrapper) {
background: rgba(255, 255, 255, 0.05) !important;
border: 1px solid rgba(255, 255, 255, 0.1) !important;
@@ -88,49 +56,13 @@
transform: translateY(-2px);
box-shadow: 0 4px 15px rgba(0, 198, 251, 0.3) !important;
}
.footer {
text-align: center;
color: rgba(255, 255, 255, 0.6);
font-size: 13px;
padding: 20px;
position: fixed;
bottom: 0;
width: 100%;
}
@keyframes gradient {
0% {
background-position: 0% 50%
}
50% {
background-position: 100% 50%
}
100% {
background-position: 0% 50%
}
}
.animated-bg {
position: fixed;
top: 0;
left: 0;
width: 100%;
height: 100%;
z-index: -1;
background: linear-gradient(-45deg, #1a1f25, #0d1117, #162030, #1c1c1c);
background-size: 400% 400%;
animation: gradient 15s ease infinite;
}
</style>
</head>
<body>
<div id="app">
<div class="animated-bg"></div>
<div class="header">
<div class="header-logo">AI</div>
xiaozhi-esp32-server
</div>
<app-header>xiaozhi-esp32-server</app-header>
<div class="login-container">
<h2 class="login-title">安全验证</h2>
<div class="login-form">
@@ -152,10 +84,10 @@
</el-form>
</div>
</div>
<div class="footer">
© 2025 xiaozhi-esp32-server
</div>
<app-footer></app-footer>
</div>
<script>
const {ElMessage} = ElementPlus;
const App = {
@@ -198,8 +130,8 @@
}
}
};
const app = Vue.createApp(App);
app.use(ElementPlus);
const app = createVueApp(App);
app.mount("#app");
</script>
</body>
+3 -1
View File
@@ -12,4 +12,6 @@ google-generativeai==0.8.4
edge_tts==7.0.0
httpx==0.27.2
aiohttp==3.9.3
aiohttp_cors==0.7.0
aiohttp_cors==0.7.0
ormsgpack==1.7.0
ruamel.yaml==0.18.10
-53
View File
@@ -1,53 +0,0 @@
<!DOCTYPE html>
<html>
<head>
<title>小智提示词配置</title>
<meta charset="utf-8">
<style>
body { max-width: 800px; margin: 20px auto; padding: 0 20px; font-family: Arial, sans-serif; }
textarea { width: 100%; height: 300px; margin: 20px 0; padding: 10px; }
button { padding: 10px 20px; font-size: 16px; }
.success { color: green; }
.error { color: red; }
</style>
</head>
<body>
<h1>小智提示词配置</h1>
<textarea id="prompt"></textarea>
<div>
<button onclick="updatePrompt()">更新提示词</button>
<span id="status"></span>
</div>
<script>
// 加载当前prompt
fetch('/api/prompt')
.then(response => response.json())
.then(data => {
document.getElementById('prompt').value = data.prompt;
});
function updatePrompt() {
const prompt = document.getElementById('prompt').value;
fetch('/api/prompt', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
},
body: JSON.stringify({prompt: prompt})
})
.then(response => response.json())
.then(data => {
const status = document.getElementById('status');
if(data.success) {
status.textContent = '更新成功!';
status.className = 'success';
} else {
status.textContent = '更新失败: ' + data.error;
status.className = 'error';
}
setTimeout(() => status.textContent = '', 3000);
});
}
</script>
</body>
</html>