summarize_content
Summarize any content to a specified length ratio (default 20%) for concise understanding. Ideal for condensing information efficiently using controlled compression settings.
Instructions
将任意内容总结为指定比例的长度（默认20%）
Args:
content: 要总结的内容
target_ratio: 目标压缩比例，0.1-1.0之间
Returns:
总结后的内容Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | ||
| target_ratio | No |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Implementation Reference
- The primary MCP tool handler for 'summarize_content'. It is registered via @mcp.tool() decorator, includes input validation (schema-like), logging via ctx, and delegates to the helper summarizer.
@mcp.tool() async def summarize_content(content: str, ctx: Context, target_ratio: float = 0.2) -> str: """ 将任意内容总结为指定比例的长度（默认20%） Args: content: 要总结的内容 target_ratio: 目标压缩比例，0.1-1.0之间 Returns: 总结后的内容 """ try: # 验证参数 if not 0.1 <= target_ratio <= 1.0: return "错误: target_ratio 必须在 0.1 到 1.0 之间" ctx.info(f"开始总结内容，目标比例: {target_ratio*100}%") summary = await summarizer.summarize_content(content, target_ratio) ctx.info("内容总结完成") return summary except Exception as e: logger.error(f"内容总结失败: {e}") return f"内容总结失败: {str(e)}" - The core helper function in ContentSummarizer class that performs the actual summarization using OpenAI/MiniMax API. Called by the tool handler and other tools.
async def summarize_content(self, content: str, target_ratio: float = 0.2, custom_prompt: str = None) -> str: """ 使用大模型总结内容 Args: content: 要总结的内容 target_ratio: 目标压缩比例 (默认20%) custom_prompt: 自定义总结提示词 Returns: 总结后的内容 """ try: # 检查内容长度，避免超出限制 if len(content) > MAX_INPUT_TOKENS * 3: # 粗略估算token content = content[:MAX_INPUT_TOKENS * 3] logger.warning("内容过长，已截断") # 构建总结提示词 if custom_prompt: prompt = custom_prompt else: target_length = min(max(int(len(content) * target_ratio), 100), 1000) prompt = f"""请将以下内容总结为约{target_length}字的精炼版本，保留核心信息和关键要点： {content} 总结要求： 1. 保持原文的主要观点和逻辑结构 2. 去除冗余和次要信息 3. 使用简洁明了的语言 4. 确保信息的准确性和完整性""" response = self.client.chat.completions.create( model=OPENAI_MODEL, messages=[ {"role": "system", "content": "你是一个专业的内容总结专家，擅长将长文本压缩为精炼的摘要。"}, {"role": "user", "content": prompt} ], max_tokens=MAX_OUTPUT_TOKENS, temperature=0.1 ) return response.choices[0].message.content.strip() except Exception as e: logger.error(f"内容总结失败: {e}") return f"总结失败: {str(e)}"