update:单模块部署xiaozhi-server，支持mcp调用摄像头识图

2026-07-25 08:33:53 +08:00 · 2025-06-01 02:26:19 +08:00
parent 3c3be950e9
commit c4f2411fee
15 changed files with 426 additions and 70 deletions
@@ -0,0 +1,121 @@
+import json
+from aiohttp import web
+from config.logger import setup_logging
+from core.utils.util import get_vision_url, is_valid_image_file
+from core.utils.vllm import create_instance
+import base64
+
+TAG = __name__
+
+# 设置最大文件大小为5MB
+MAX_FILE_SIZE = 5 * 1024 * 1024
+
+
+class VisionHandler:
+    def __init__(self, config: dict):
+        self.config = config
+        self.logger = setup_logging()
+
+    def _create_error_response(self, message: str) -> dict:
+        """创建统一的错误响应格式"""
+        return {"success": False, "message": message}
+
+    async def handle_post(self, request):
+        """处理 MCP Vision POST 请求"""
+        try:
+            # 获取请求头信息
+            device_id = request.headers.get("Device-Id", "")
+            client_id = request.headers.get("Client-Id", "")
+            self.logger.bind(tag=TAG).debug(f"Device-Id: {device_id}")
+            self.logger.bind(tag=TAG).debug(f"Client-Id: {client_id}")
+
+            # 解析multipart/form-data请求
+            reader = await request.multipart()
+
+            # 读取question字段
+            question_field = await reader.next()
+            if question_field is None:
+                raise ValueError("缺少问题字段")
+            question = await question_field.text()
+            self.logger.bind(tag=TAG).debug(f"Question: {question}")
+
+            # 读取图片文件
+            image_field = await reader.next()
+            if image_field is None:
+                raise ValueError("缺少图片文件")
+
+            # 读取图片数据
+            image_data = await image_field.read()
+            if not image_data:
+                raise ValueError("图片数据为空")
+
+            # 检查文件大小
+            if len(image_data) > MAX_FILE_SIZE:
+                raise ValueError(
+                    f"图片大小超过限制，最大允许{MAX_FILE_SIZE/1024/1024}MB"
+                )
+
+            # 检查文件格式
+            if not is_valid_image_file(image_data):
+                raise ValueError(
+                    "不支持的文件格式，请上传有效的图片文件（支持JPEG、PNG、GIF、BMP、TIFF、WEBP格式）"
+                )
+
+            # 将图片转换为base64编码
+            image_base64 = base64.b64encode(image_data).decode("utf-8")
+
+            vllm_config = self.config["VLLM"]["ChatGLMVLLM"]
+            provider = create_instance("openai", vllm_config)
+            response = provider.response(question, image_base64)
+
+            return_json = {
+                "success": True,
+                "result": response,
+            }
+
+            response = web.Response(
+                text=json.dumps(return_json, separators=(",", ":")),
+                content_type="application/json",
+            )
+        except ValueError as e:
+            self.logger.bind(tag=TAG).error(f"MCP Vision POST请求异常: {e}")
+            return_json = self._create_error_response(str(e))
+            response = web.Response(
+                text=json.dumps(return_json, separators=(",", ":")),
+                content_type="application/json",
+            )
+        except Exception as e:
+            self.logger.bind(tag=TAG).error(f"MCP Vision POST请求异常: {e}")
+            return_json = self._create_error_response("处理请求时发生错误")
+            response = web.Response(
+                text=json.dumps(return_json, separators=(",", ":")),
+                content_type="application/json",
+            )
+        finally:
+            self._add_cors_headers(response)
+            return response
+
+    async def handle_get(self, request):
+        """处理 MCP Vision GET 请求"""
+        try:
+            vision_explain = get_vision_url(self.config)
+            message = f"MCP Vision 接口运行正常，视觉解释接口地址是：{vision_explain}"
+            response = web.Response(text=message, content_type="text/plain")
+        except Exception as e:
+            self.logger.bind(tag=TAG).error(f"MCP Vision GET请求异常: {e}")
+            return_json = self._create_error_response("服务器内部错误")
+            response = web.Response(
+                text=json.dumps(return_json, separators=(",", ":")),
+                content_type="application/json",
+            )
+        finally:
+            self._add_cors_headers(response)
+            return response
+
+    def _add_cors_headers(self, response):
+        """添加CORS头信息"""
+        response.headers["Access-Control-Allow-Headers"] = (
+            "client-id, content-type, device-id"
+        )
+        response.headers["Access-Control-Allow-Credentials"] = "true"
+        response.headers["Access-Control-Allow-Origin"] = "*"