1 line
1.8 KiB
JSON
1 line
1.8 KiB
JSON
{"repo": "celainica/lean-sketch", "files": {"ELAB/prompt.py": {"97accb4bdced1bdc2a3c87e1d2492a78f70a9a8f": {"t": 1785674246.8895802, "n": 1279, "h": "9b2ed7cfe793c61e", "c": "import os\r\nfrom openai import OpenAI\r\n\r\n\r\ndef get_response(messages):\r\n client = OpenAI(\r\n api_key=\"sk-49bbdcadc76e42dd8b3b47fffb45c7b6\",\r\n base_url=\"https://dashscope.aliyuncs.com/compatible-mode/v1\",\r\n )\r\n completion = client.chat.completions.create(model=\"qwen-math-plus\", messages=messages)\r\n return completion\r\n\r\nmessages = [\r\n {\r\n \"role\": \"system\",\r\n \"content\": \"\"\"您是一位精通 Lean 语言和形式化证明的专家。您的任务是基于我提供的**代码**和**关键步骤**，给出一个主次分明、富有洞察力且类似真人教学风格的解释。\r\n 尽量保持陈述的简洁精要，避免出现一切非具体的形容词和修饰，同时要做到易于读懂。\"\"\",\r\n }\r\n]\r\nassistant_output = \"The LLM is generating an answer...\"\r\n\r\n\r\ndef prompt_llm(module):\r\n file_path = \"./crucialsteps.txt\"\r\n with open(file_path, 'r', encoding='utf-8') as f:\r\n steps = f.read()\r\n lean_path = \"./\" + module + \".lean\"\r\n with open(lean_path, 'r', encoding='utf-8') as l:\r\n lean = l.read()\r\n text_input = f\"\"\"\r\n**你需要解释的代码和步骤如下：**\r\n\r\n**1. Lean 代码：**\r\n\r\n```lean\r\n{lean}\r\n```\r\n\r\n**2. 我理解的关键步骤：**\r\n\r\n```text\r\n{steps}\r\n``` \"\"\"\r\n\r\n print(text_input)\r\n messages.append({\"role\": \"user\", \"content\": text_input})\r\n assistant_output = get_response(messages).choices[0].message.content\r\n messages.append({\"role\": \"assistant\", \"content\": assistant_output})\r\n print(assistant_output)"}}}} |