smartai-v2/smartai-qwen.git

			@@ -33,7 +33,7 @@
			for i in range(max_workers):
			model = AutoModelForVision2Seq.from_pretrained(
			model_path,
			device_map="cuda:1",
			device_map=f"cuda:{config.get('cuda')}",
			trust_remote_code=True,
			torch_dtype=torch.float16
			).eval()
			@@ -88,15 +88,30 @@
			try :
			# 1. 从集合A获取向量和元数据
			is_waning = 0
			image_des = self.image_desc(f"{res['image_desc_path']}")
			self.logger.info(image_des)
			if image_des:
			# rule_text = self.get_rule(ragurl)
			is_waning = self.image_rule_chat(image_des,res['waning_value'],ragurl,rag_mode,max_tokens)
			is_desc = 2

			# 生成图片描述
			image_des = self.image_desc(res['image_desc_path'])
			risk_description = ""
			suggestion = ""
			# 图片描述生成成功
			if image_des:
			is_desc = 2
			# 调用规则匹配方法,判断是否预警
			is_waning = self.image_rule_chat(image_des, res['waning_value'], ragurl, rag_mode, max_tokens)
			# 如果预警,则生成隐患描述和处理建议
			if is_waning == 1:
			# 获取规章制度数据
			filedata = self.get_filedata(res['waning_value'], ragurl)
			# 生成隐患描述
			risk_description = self.image_rule_chat_with_detail(filedata, res['waning_value'], ragurl, rag_mode)
			# 生成处理建议
			suggestion = self.image_rule_chat_suggestion(res['waning_value'], ragurl, rag_mode)

			else:
			is_waning = 0
			is_desc = 3

			# 数据组
			data = {
			"id": res['id'],
			"event_level_id": res['event_level_id'], # event_level_id
			@@ -117,11 +132,15 @@
			"image_path": res['image_path'], # image_path
			"image_desc_path": res['image_desc_path'], # image_desc_path
			"video_path": res['video_path'],
			"text_vector": res['text_vector']
			"text_vector": res['text_vector'],
			"risk_description": risk_description,
			"suggestion": suggestion,
			"knowledge_id": res['knowledge_id']
			}

			# 保存到milvus
			image_id = self.collection.upsert(data).primary_keys
			if is_desc == 2:
			logging.info(image_id)
			data = {
			"id": str(image_id[0]),
			"video_point_id": res['video_point_id'],
			@@ -137,7 +156,7 @@
			asyncio.run(self.insert_json_data(ragurl, data))
			return image_id
			except Exception as e:
			self.logger.info(f"线程：执行模型解析时出错:任务：{e}")
			self.logger.info(f"线程：执行模型解析时出错:任务：{res['id']} :{e}")
			return 0

			def image_desc(self, image_path):
			@@ -167,7 +186,7 @@
			padding=True,
			return_tensors="pt",
			)
			inputs = inputs.to("cuda:1")
			inputs = inputs.to(model.device)
			current_time = datetime.now()
			outputs = model.generate(**inputs,
			max_new_tokens=300,
			@@ -253,6 +272,103 @@
			self.logger.info(f"线程：执行规则匹配时出错:{image_des, rule_text, ragurl, rag_mode,e}")
			return None

			# 隐患描述
			def image_rule_chat_with_detail(self, filedata, rule_text, ollama_url, ollama_mode="qwen2.5vl:3b"):

			# API调用
			response = requests.post(
			# ollama地址
			url=f"{ollama_url}/chat",
			json={
			"prompt": "",
			# 请求内容
			"messages": [
			{
			"role": "user",
			"content": f"请根据规章制度[{filedata}]\n查找[{rule_text}]的安全隐患描述，不进行推理和think。返回信息小于800字"
			}
			],
			# 指定模型
			"llm_name": "qwen3:8b",
			"stream": False, # 关闭流式输出
			"gen_conf": {
			"temperature": 0.7, # 控制生成随机性
			"max_tokens": 800 # 最大输出长度
			}
			}
			)
			# 从json提取data字段内容
			ret = response.json()["data"]
			# result = response.json()
			# ret = result.get("data") or result.get("message", {}).get("content", "")
			# 移除<think>标签和内容
			ret = re.sub(r'<think>.*?</think>', '', ret, flags=re.DOTALL)
			# 字符串清理,移除空格,制表符,换行符,星号
			ret = ret.replace(" ", "").replace("\t", "").replace("\n", "").replace("**", "")
			print(ret)
			return ret

			# 处理建议
			def image_rule_chat_suggestion(self, rule_text, ollama_url, ollama_mode="qwen2.5vl:3b"):
			self.logger.info("----------------------------------------------------------------")
			# 请求内容
			content = (
			f"请根据违规内容[{rule_text}]\n进行返回处理违规建议，不进行推理和think。返回精准信息")
			response = requests.post(
			# ollama地址
			url=f"{ollama_url}/chat",
			json={
			# 指定模型
			"llm_name": "qwen3:8b",
			"messages": [
			{"role": "user", "content": content}
			],
			"stream": False # 关闭流式输出
			}
			)
			# 从json提取data字段内容
			ret = response.json()["data"]
			# result = response.json()
			# ret = result.get("data") or result.get("message", {}).get("content", "")
			# 移除<think>标签和内容
			ret = re.sub(r'<think>.*?</think>', '', ret, flags=re.DOTALL)
			# 字符串清理,移除空格,制表符,换行符,星号
			ret = ret.replace(" ", "").replace("\t", "").replace("\n", "").replace("**", "")
			print(ret)
			return ret

			# RAG服务发送请求,获取知识库内容
			def get_filedata(self, searchtext, ragurl):
			search_data = {
			# 知识库集合
			"collection_name": "smart_knowledge",
			# 查询文本
			"query_text": searchtext,
			# 搜索模式
			"search_mode": "hybrid",
			# 最多返回结果
			"limit": 100,
			# 调密向量搜索权重
			"weight_dense": 0.7,
			# 稀疏向量搜索权重
			"weight_sparse": 0.3,
			# 空字符串
			"filter_expr": "",
			# 只返回 text 字段
			"output_fields": ["text"]
			}
			# 向 ragurl + "/search" 端点发送POST请求
			response = requests.post(ragurl + "/search", json=search_data)
			# 从响应中获取'results'字段
			results = response.json().get('results')
			# 初始化 text
			text = ""
			# 遍历所有结果规则(rule)，将每条规则的'entity'中的'text'字段取出.
			for rule in results:
			text = text + rule['entity'].get('text') + ";\n"

			return text

			async def insert_json_data(self, ragurl, data):
			try:
			data = {'collection_name': "smartrag", "data": data, "description": ""}