Files

42 lines
1.3 KiB
Markdown
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
id: backend.elasticsearch.index
title: Elasticsearch
type: index
domain: backend
stack: [elasticsearch]
tags: [Elasticsearch, 全文检索, 混合检索, 向量检索]
week: [6, 14]
---
# Elasticsearch
倒排索引、中文分词、BM25 与 kNN 向量检索、混合检索和数据同步。BOSS直聘 2026-10-23 的调研中多个 RAG 岗位提到“ES 混合检索”,是 RAG 全链路的重要一环。
## 学习路线
| 顺序 | 课程 | 级别 | 预计 |
| --- | --- | --- | --- |
| 1 | [Elasticsearch:倒排索引、映射与中文分词、BM25、kNN 向量检索、混合检索和别名重建](01-search-basics-hybrid.md) | 进阶 | 3 小时 |
## 企业场景
- [知识库混合检索:数据库到 ES 的同步、权限过滤、分词词典和检索效果评估](scenarios/kb-search-sync.md)
## 面试题
- [Elasticsearch 面试题](interview.md)
## 示例代码
- [examples/hybrid-search](examples/hybrid-search/):`cjk` 分词、租户过滤、BM25、kNN、应用层 RRF、别名切换(ES 9.5.1 单节点实际运行通过)
## 在 16 周计划中
- [第 6 周:RAG(二)](../../../plan/week06-rag-2.md)
- [第 14 周:后端扩展与部署](../../../plan/week14-backend-extend-deploy.md)
## 官方资料
- https://www.elastic.co/docs
- IK 分词插件:https://github.com/infinilabs/analysis-ik