https://blog.youkuaiyun.com/jpigg78451zh-cnhttps://blog.youkuaiyun.com/https://blog.youkuaiyun.com/jpigg78451/article/details/149939342https://blog.youkuaiyun.com/jpigg78451/article/details/149939342jpigg78451Tue, 05 Aug 2025 15:50:12 +0800https://blog.youkuaiyun.com/jpigg78451/article/details/149939298https://blog.youkuaiyun.com/jpigg78451/article/details/149939298jpigg78451Tue, 05 Aug 2025 15:48:32 +0800https://blog.youkuaiyun.com/jpigg78451/article/details/149939250https://blog.youkuaiyun.com/jpigg78451/article/details/149939250jpigg78451Tue, 05 Aug 2025 15:47:00 +0800https://blog.youkuaiyun.com/jpigg78451/article/details/149939190https://blog.youkuaiyun.com/jpigg78451/article/details/149939190jpigg78451Tue, 05 Aug 2025 15:44:58 +0800https://blog.youkuaiyun.com/jpigg78451/article/details/149939139https://blog.youkuaiyun.com/jpigg78451/article/details/149939139jpigg78451Tue, 05 Aug 2025 15:42:55 +0800https://blog.youkuaiyun.com/jpigg78451/article/details/149938024https://blog.youkuaiyun.com/jpigg78451/article/details/149938024jpigg78451Tue, 05 Aug 2025 15:07:31 +0800https://blog.youkuaiyun.com/jpigg78451/article/details/149937946https://blog.youkuaiyun.com/jpigg78451/article/details/149937946jpigg78451Tue, 05 Aug 2025 15:04:49 +0800https://blog.youkuaiyun.com/jpigg78451/article/details/149937890https://blog.youkuaiyun.com/jpigg78451/article/details/149937890jpigg78451Tue, 05 Aug 2025 15:02:25 +0800https://blog.youkuaiyun.com/jpigg78451/article/details/149937802https://blog.youkuaiyun.com/jpigg78451/article/details/149937802jpigg78451Tue, 05 Aug 2025 15:00:49 +0800 提取出纯文本长字符串 (`long_text`)V[文本分割] --> 选择策略（固定长度/句子/语义/结构）--> 得到文本块列表 (`chunks`)V(可选)[添加元数据] --> `chunks_with_metadata = [{"content": chunk, "source": "xx.pdf", "page": N}, ...]`V。]]>https://blog.youkuaiyun.com/jpigg78451/article/details/149937755https://blog.youkuaiyun.com/jpigg78451/article/details/149937755jpigg78451Tue, 05 Aug 2025 14:57:53 +0800