### Task: Respond to the user query using the provided context, incorporating inline citations in the format [id] only when the tag includes an explicit id attribute (e.g., ). ### Guidelines: - If you don't know the answer, clearly state that. - If uncertain, ask the user for clarification. - Respond in the same language as the user's query. - If the context is unreadable or of poor quality, inform the user and provide the best possible answer. - If the answer isn't present in the context but you possess the knowledge, explain this to the user and provide the answer using your own understanding. - Only include inline citations using [id] (e.g., [1], [2]) when the tag includes an id attribute. - Do not cite if the tag does not contain an id attribute. - Do not use XML tags in your response. - Ensure citations are concise and directly related to the information provided. ### Example of Citation: If the user asks about a specific topic and the information is found in a source with a provided id attribute, the response should include the citation like in the following example: "According to the study, the proposed method increases efficiency by 20% [1]." ### Output: Provide a clear and direct response to the user's query, including inline citations in the format [id] only when the tag with id attribute is present in the context. or {}).get(\n \"chat_id\", body.get(\"chat_id\", \"web-user\")\n ),\n \"user_email\": (__user__ or {}).get(\"email\", \"anonymous\"),\n }\n\n # -------- 2) Streaming generator --------\n def _gen():\n # Первая строка — статус\n yield \"⏳\"\n\n result_holder = {\"ok\": False, \"text\": \"\", \"err\": \"\"}\n\n def _do_request():\n try:\n if files and files.get(\"data\"):\n r = requests.post(url, data=payload, files=files, timeout=300)\n else:\n # ИСПРАВЛЕНО: Прямая отправка payload без обертки \"body\"\n r = requests.post(url, json=payload, timeout=300)\n\n r.raise_for_status()\n\n try:\n data = r.json()\n\n out_obj = data.get(\"output\")\n result_text = last_shown_sec:\n yield f\" -{elapsed}s-\"\n last_shown_sec = elapsed\n\n time.sleep(0.2)\n\n # -------- Ответ с нового абзаца --------\n if result_holder[\"ok\"]:\n yield \"\\n\\n\" + (result_holder[\"text\"] or \"…\")\n else:\n yield \"\\n\\n\" + (result_holder[\"err\"] or \"…\")\n\n return _gen()\n","meta":{"description":"raumai4pro","manifest":{}},"is_active":true,"is_global":false,"updated_at":1775806109,"created_at":1775573732}] [{"id":"raumai4pro","user_id":"58aa593f-3b9f-4895-b3f1-aeaf7097b14f","name":"RaumAI4Pro","type":"pipe","content":"import requests\nimport base64\nimport io\nimport json\nimport threading\nimport time\nfrom typing import Union, Generator, Iterator\n\n\nclass Pipe:\n def __init__(self):\n self.type = \"manifold\"\n self.id = \"raumai_v4_pro\" # ИСПРАВЛЕНО: Уникальный ID\n self.name = \"RaumAI 4 Pro\" # ИСПРАВЛЕНО: Понятное имя в интерфейсе\n\n def pipe(\n self, body: dict, __user__: dict = None, __metadata__: dict = None\n ) -> Union[str, Generator, Iterator]:\n\n # ИСПРАВЛЕНО: Ваш локальный IP и точный путь вебхука\n url = \"http://10.0.0.20:5678/webhook/raumai04pro\"\n\n messages = body.get(\"messages\", [])\n user_message = \"\"\n files = {}\n\n # -------- 1) Сбор текста и изображений --------\n if messages:\n last_content = messages[-1].get(\"content\", [])\n text_part = скажите пожалуйста а этот код позволяет обработать только одно вложение или несколько?