Short answer: combine lexical and embedding candidates, fuse ranks rather than raw scores, rerank only a small merged set, and refuse to produce a code-review finding unless the final evidence still points to an accessible, current policy passage. This costs more latency than a single search, bu...
Source: [Dev.to](https://dev.to/fairchildblake8483/code-review-retrieval-explained-simple-semantic-and-keyword-search-with-portable-reranking-p0)