7be71ebbac
Retrieval scores are each database's own rank arithmetic; the databases in a selection share an embedder, so similarity in that one space is the signal comparable across databases by construction. Measured product to product against score ordering: +8.3 to +16.6pp recall@5 across five cells on two corpora, flat in collection count and corpus shape where score ordering dips with both, closing roughly 60% of the gap to a reranker; order-sensitivity residual 0.00pp in every cell. Exact ties collapse from 51-81% of candidates to under 1%. Full-text-only searches keep retrieval-score order, having no query vector. The vector column already travels with every search result, so the similarity costs no additional transfer; per-chunk embeddings are materialized only for the federated path that reads them. |
||
|---|---|---|
| .. | ||
| index.md | ||
| processing.md | ||
| prompts.md | ||
| providers.md | ||
| qa.md | ||
| storage.md | ||