update:合并最新代码

main/xiaozhi-server/core/providers/llm/AliBL/AliBL.py

@@ -0,0 +1,52 @@
+from config.logger import setup_logging
+from http import HTTPStatus
+from dashscope import Application
+from core.providers.llm.base import LLMProviderBase
+
+TAG = __name__
+logger = setup_logging()
+
+class LLMProvider(LLMProviderBase):
+    def __init__(self, config):
+        self.api_key = config["api_key"]
+        self.app_id = config["app_id"]
+        self.base_url = config.get("base_url")
+        self.is_No_prompt = config.get("is_no_prompt")
+        self.memory_id = config.get("ali_memory_id")
+
+    def response(self, session_id, dialogue):
+        try:
+            # 处理dialogue
+            if self.is_No_prompt:
+                dialogue.pop(0)
+                logger.bind(tag=TAG).debug(f"【阿里百练API服务】处理后的dialogue: {dialogue}")
+
+            # 构造调用参数
+            call_params = {
+                "api_key": self.api_key,
+                "app_id": self.app_id,
+                "session_id": session_id,
+                "messages": dialogue
+            }
+            if self.memory_id != False:
+                # 百练memory需要prompt参数
+                prompt = dialogue[-1].get("content")
+                call_params["memory_id"] = self.memory_id
+                call_params["prompt"] = prompt
+                logger.bind(tag=TAG).debug(f"【阿里百练API服务】处理后的prompt: {prompt}")
+
+            responses = Application.call(**call_params)
+            if responses.status_code != HTTPStatus.OK:
+                logger.bind(tag=TAG).error(
+                    f"code={responses.status_code}, "
+                    f"message={responses.message}, "
+                    f"请参考文档：https://help.aliyun.com/zh/model-studio/developer-reference/error-code"
+                )
+                yield "【阿里百练API服务响应异常】"
+            else:
+                logger.bind(tag=TAG).debug(f"【阿里百练API服务】构造参数: {call_params}")
+                yield responses.output.text
+
+        except Exception as e:
+            logger.bind(tag=TAG).error(f"【阿里百练API服务】响应异常: {e}")
+            yield "【LLM服务响应异常】"

main/xiaozhi-server/core/providers/llm/dify/dify.py

@@ -6,11 +6,12 @@ from core.providers.llm.base import LLMProviderBase
 TAG = __name__
 logger = setup_logging()
 
+
 class LLMProvider(LLMProviderBase):
     def __init__(self, config):
         self.api_key = config["api_key"]
         self.mode = config.get("mode", "chat-messages")
-        self.base_url = config.get("base_url", "https://api.dify.ai/v1").rstrip('/')
+        self.base_url = config.get("base_url", "https://api.dify.ai/v1").rstrip("/")
         self.session_conversation_map = {}  # 存储session_id和conversation_id的映射
 
     def response(self, session_id, dialogue):
@@ -22,57 +23,58 @@ class LLMProvider(LLMProviderBase):
             # 发起流式请求
             if self.mode == "chat-messages":
                 request_json = {
-                        "query": last_msg["content"],
-                        "response_mode": "streaming",
-                        "user": session_id,
-                        "inputs": {},
-                        "conversation_id": conversation_id
-                    }
+                    "query": last_msg["content"],
+                    "response_mode": "streaming",
+                    "user": session_id,
+                    "inputs": {},
+                    "conversation_id": conversation_id,
+                }
             elif self.mode == "workflows/run":
                 request_json = {
                     "inputs": {"query": last_msg["content"]},
                     "response_mode": "streaming",
-                    "user": session_id
+                    "user": session_id,
                 }
             elif self.mode == "completion-messages":
                 request_json = {
                     "inputs": {"query": last_msg["content"]},
                     "response_mode": "streaming",
-                    "user": session_id
+                    "user": session_id,
                 }
 
             with requests.post(
-                    f"{self.base_url}/{self.mode}",
-                    headers={"Authorization": f"Bearer {self.api_key}"},
-                    json=request_json,
-                    stream=True
+                f"{self.base_url}/{self.mode}",
+                headers={"Authorization": f"Bearer {self.api_key}"},
+                json=request_json,
+                stream=True,
             ) as r:
                 if self.mode == "chat-messages":
                     for line in r.iter_lines():
-                        if line.startswith(b'data: '):
+                        if line.startswith(b"data: "):
                             event = json.loads(line[6:])
                             # 如果没有找到conversation_id，则获取此次conversation_id
                             if not conversation_id:
-                                conversation_id = event.get('conversation_id')
-                                self.session_conversation_map[session_id] = conversation_id  # 更新映射
-                            if event.get('answer'):
-                                yield event['answer']
+                                conversation_id = event.get("conversation_id")
+                                self.session_conversation_map[session_id] = (
+                                    conversation_id  # 更新映射
+                                )
+                            if event.get("answer"):
+                                yield event["answer"]
                 elif self.mode == "workflows/run":
                     for line in r.iter_lines():
-                        # logger.bind(tag=TAG).info(f"chat message response: {line}")
-                        if line.startswith(b'data: '):
+                        if line.startswith(b"data: "):
                             event = json.loads(line[6:])
-                            if event.get('event') == "workflow_finished":
-                                if event['data']['status'] == "succeeded":
-                                    yield event['data']['outputs']['answer']
+                            if event.get("event") == "workflow_finished":
+                                if event["data"]["status"] == "succeeded":
+                                    yield event["data"]["outputs"]["answer"]
                                 else:
                                     yield "【服务响应异常】"
                 elif self.mode == "completion-messages":
                     for line in r.iter_lines():
-                        if line.startswith(b'data: '):
+                        if line.startswith(b"data: "):
                             event = json.loads(line[6:])
-                            if event.get('answer'):
-                                yield event['answer'] 
+                            if event.get("answer"):
+                                yield event["answer"]
 
         except Exception as e:
             logger.bind(tag=TAG).error(f"Error in response generation: {e}")

main/xiaozhi-server/core/providers/llm/homeassistant/homeassistant.py

@@ -1,62 +0,0 @@
-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}")

main/xiaozhi-server/core/providers/llm/openai/openai.py

@@ -64,5 +64,5 @@ class LLMProvider(LLMProviderBase):
                 yield chunk.choices[0].delta.content, chunk.choices[0].delta.tool_calls
 
         except Exception as e:
-            self.logger.bind(tag=TAG).error(f"Error in function call streaming: {e}")
+            logger.bind(tag=TAG).error(f"Error in function call streaming: {e}")
             yield {"type": "content", "content": f"【OpenAI服务响应异常: {e}】"}

main/xiaozhi-server/core/providers/llm/xinference/xinference.py

@@ -0,0 +1,85 @@
+from config.logger import setup_logging
+from openai import OpenAI
+import json
+from core.providers.llm.base import LLMProviderBase
+
+TAG = __name__
+logger = setup_logging()
+
+
+class LLMProvider(LLMProviderBase):
+    def __init__(self, config):
+        self.model_name = config.get("model_name")
+        self.base_url = config.get("base_url", "http://localhost:9997")
+        # Initialize OpenAI client with Xinference base URL
+        # 如果没有v1，增加v1
+        if not self.base_url.endswith("/v1"):
+            self.base_url = f"{self.base_url}/v1"
+            
+        logger.bind(tag=TAG).info(f"Initializing Xinference LLM provider with model: {self.model_name}, base_url: {self.base_url}")
+
+        try:
+            self.client = OpenAI(
+                base_url=self.base_url,
+                api_key="xinference"  # Xinference has a similar setup to Ollama where it doesn't need an actual key
+            )
+            logger.bind(tag=TAG).info("Xinference client initialized successfully")
+        except Exception as e:
+            logger.bind(tag=TAG).error(f"Error initializing Xinference client: {e}")
+            raise
+
+    def response(self, session_id, dialogue):
+        try:
+            logger.bind(tag=TAG).debug(f"Sending request to Xinference with model: {self.model_name}, dialogue length: {len(dialogue)}")
+            responses = self.client.chat.completions.create(
+                model=self.model_name,
+                messages=dialogue,
+                stream=True
+            )
+            is_active=True
+            for chunk in responses:
+                try:
+                    delta = chunk.choices[0].delta if getattr(chunk, 'choices', None) else None
+                    content = delta.content if hasattr(delta, 'content') else ''
+                    if content:
+                        if '<think>' in content:
+                            is_active = False
+                            content = content.split('<think>')[0]
+                        if '</think>' in content:
+                            is_active = True
+                            content = content.split('</think>')[-1]
+                        if is_active:
+                            yield content
+                except Exception as e:
+                    logger.bind(tag=TAG).error(f"Error processing chunk: {e}")
+
+        except Exception as e:
+            logger.bind(tag=TAG).error(f"Error in Xinference response generation: {e}")
+            yield "【Xinference服务响应异常】"
+
+    def response_with_functions(self, session_id, dialogue, functions=None):
+        try:
+            logger.bind(tag=TAG).debug(f"Sending function call request to Xinference with model: {self.model_name}, dialogue length: {len(dialogue)}")
+            if functions:
+                logger.bind(tag=TAG).debug(f"Function calls enabled with: {[f.get('function', {}).get('name') for f in functions]}")
+                
+            stream = self.client.chat.completions.create(
+                model=self.model_name,
+                messages=dialogue,
+                stream=True,
+                tools=functions,
+            )
+
+            for chunk in stream:
+                delta = chunk.choices[0].delta
+                content = delta.content
+                tool_calls = delta.tool_calls
+                
+                if content:
+                    yield content, tool_calls
+                elif tool_calls:
+                    yield None, tool_calls
+
+        except Exception as e:
+            logger.bind(tag=TAG).error(f"Error in Xinference function call: {e}")
+            yield {"type": "content", "content": f"【Xinference服务响应异常: {str(e)}】"}