AI 智能体
vector-search-refactor
更新于 2026-09-19
Vector Search · 重构规则
Refactoring rules for Vector Search: characterisation tests, behaviour-free diffs and seam-by-seam extraction.
- 技术栈
- Vector Search
- 主题
- 重构
- 条目
- 9 条
- 版本
- v0.2.0
✓ 应当这么做
- ✓ Characterise current behaviour with tests before touching structure
- ✓ Keep refactor commits free of behaviour change and vice versa
- ✓ Extract one seam at a time and delete the old path in the same change
✕ 常见反模式
- ✕ Rewriting and changing features in one unreviewable diff
- ✕ Leaving both old and new implementations alive indefinitely
- ✕ Refactoring code no requirement currently touches
◎ 交付前验证
- ◎ Row counts and key uniqueness compared against the previous run
- ◎ Backfill path tested on a partition
- ◎ Lineage graph updated for the new source
同分类条目
42 篇AI 智能体
Vector Search 工程规则
Vector search rules: chunking strategy, recall evaluation and index rebuild path
AI 智能体
Feature Store 工程规则
Feature store rules: point-in-time correctness and train/serve parity
AI 智能体
Agent Skill Design 工程规则
Skill design rules: narrow triggers, explicit boundaries and verifiable outputs
AI 智能体
Agent Tool Calls 工程规则
Tool-call rules: server-side authorisation and deny-by-default allow-lists
AI 智能体
Agent Memory 工程规则
Memory rules: scoped retrieval, expiry and user-visible deletion
AI 智能体
RAG Retrieval 工程规则
RAG rules: citation-grade retrieval and evaluated recall before shipping