Home assistant (#97)

* add home assistant

* update home assistant remark

* update config

* update:优化文档

---------

Co-authored-by: ck3 <kyriechen03@qq.com>
Co-authored-by: Kyrie Chen <794103684@qq.com>
Co-authored-by: hrz <1710360675@qq.com>

core/providers/llm/homeassistant/homeassistant.py

@@ -0,0 +1,62 @@
+import requests
+from requests.exceptions import RequestException
+from config.logger import setup_logging
+from core.providers.llm.base import LLMProviderBase
+
+TAG = __name__
+logger = setup_logging()
+
+
+class LLMProvider(LLMProviderBase):
+    def __init__(self, config):
+        self.agent_id = config.get("agent_id")  # 对应 agent_id
+        self.api_key = config.get("api_key")
+        self.base_url = config.get("base_url", config.get("url"))  # 默认使用 base_url
+        self.api_url = f"{self.base_url}/api/conversation/process"  # 拼接完整的 API URL
+
+    def response(self, session_id, dialogue):
+        print(dialogue)
+        try:
+            # home assistant语音助手自带意图，无需使用xiaozhi ai自带的，只需要把用户说的话传递给home assistant即可
+
+            # 提取最后一个 role 为 'user' 的 content
+            input_text = None
+            if isinstance(dialogue, list):  # 确保 dialogue 是一个列表
+                # 逆序遍历，找到最后一个 role 为 'user' 的消息
+                for message in reversed(dialogue):
+                    if message.get("role") == "user":  # 找到 role 为 'user' 的消息
+                        input_text = message.get("content", "")
+                        break  # 找到后立即退出循环
+
+            # 构造请求数据
+            payload = {
+                "text": input_text,
+                "agent_id": self.agent_id,
+                "conversation_id": session_id  # 使用 session_id 作为 conversation_id
+            }
+            # 设置请求头
+            headers = {
+                "Authorization": f"Bearer {self.api_key}",
+                "Content-Type": "application/json"
+            }
+
+            # 发起 POST 请求
+            response = requests.post(self.api_url, json=payload, headers=headers)
+
+            # 检查请求是否成功
+            response.raise_for_status()
+
+            # 解析返回数据
+            data = response.json()
+            speech = data.get("response", {}).get("speech", {}).get("plain", {}).get("speech", "")
+
+            # 返回生成的内容
+            if speech:
+                yield speech
+            else:
+                logger.bind(tag=TAG).warning("API 返回数据中没有 speech 内容")
+
+        except RequestException as e:
+            logger.bind(tag=TAG).error(f"HTTP 请求错误: {e}")
+        except Exception as e:
+            logger.bind(tag=TAG).error(f"生成响应时出错: {e}")

core/providers/tts/fishspeech.py

@@ -9,8 +9,11 @@ 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
+from config.logger import setup_logging
+
+TAG = __name__
+logger = setup_logging()
 
 
 class ServeReferenceAudio(BaseModel):
@@ -86,6 +89,9 @@ class TTSProvider(TTSProviderBase):
         self.channels = config.get("channels",1)
         self.rate = config.get("rate",44100)
         self.api_key = config.get("api_key","YOUR_API_KEY")
+        if not self.api_key or "你" in self.api_key:
+            logger.bind(tag=TAG).error("你还没配置FishSpeech TTS的密钥，请在配置文件中配置密钥，否则无法正常工作")
+            return
         self.normalize = config.get("normalize",True)
         self.max_new_tokens = config.get("max_new_tokens",1024)
         self.chunk_length = config.get("chunk_length",200)

core/providers/tts/siliconflow.py

@@ -1,7 +1,5 @@
 import os
 import uuid
-import json
-import base64
 import requests
 from datetime import datetime
 from core.providers.tts.base import TTSProviderBase