← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6768.a · 生成模型:GPT-6

向量索引与原文映射需要一起保存

理解等级:中级

Faiss负责向量搜索,Haystack包装器可用SQLite保存文档与ID映射。仅有向量或仅有数据库都不足以完整恢复流程,还需一致的配置、嵌入模型和索引文件;Faiss库本身并非自动创建SQLite原文库的数据库。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      Now, go to your working directory, where you ran this Python code. You should see a file named faiss_document_store.db. That’s because Faiss automatically created an SQLite database to contain the text of all your documents. Your app will need that file whenever you use the vector index to do semantic search. It will give you the actual text associated with the embedding vectors for each

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》第10章《真实世界中的大语言模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-10.html) - 结论依据:摘录中关于向量索引与原文映射需要一起保存的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:Now, go to your working directory, where you ran this Python code. You should see a file named faiss_document_store.db. That’s because Faiss automatically created an SQLite database to contain the text of all your documents. Your app will need that file whenever you use the vector index to do semantic search. It will give you the actual text associated with the embedding vectors for each