> ## Documentation Index
> Fetch the complete documentation index at: https://www.paradedb.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# How Hybrid Search Works

> Understand how ParadeDB combines text and vector search into a single ranking

<Note>
  Hybrid search uses [vector search](/docs/concepts/vector/overview), a beta feature
  available in versions `0.25.0` and above.
</Note>

Hybrid search combines the strengths of [text search](/docs/concepts/full-text/overview)
and [vector search](/docs/concepts/vector/overview). Text search is strongest when
the query terms and indexed text overlap. Vector search is strongest when the
right result is semantically related but uses different words.

Because those signals fail in different ways, combining them often produces a
better result set than either one alone.

## Fusing by Rank

BM25 scores and vector distances operate on different scales, so they cannot be
added together directly. ParadeDB's hybrid examples use
[Reciprocal Rank Fusion](/docs/reference/hybrid/rrf), which discards raw scores and
uses only each row's position, or rank, in each result list.

With rank fusion, a row that ranks first contributes the same amount whether
its BM25 score was `1` or `100`. That makes text and vector results comparable
without forcing them onto a shared scoring scale.