landing_page/qdrant-landing/content/documentation/concepts/hybrid-queries.md

title, weight, aliases, hideInSidebar

title	weight	aliases	hideInSidebar
Hybrid Queries	57	../hybrid-queries	false

Hybrid and Multi-Stage Queries

Available as of v1.10.0

With the introduction of many named vectors per point, there are use-cases when the best search is obtained by combining multiple queries, or by performing the search in more than one stage.

Qdrant has a flexible and universal interface to make this possible, called Query API (API reference).

The main component for making the combinations of queries possible is the prefetch parameter, which enables making sub-requests.

Specifically, whenever a query has at least one prefetch, Qdrant will:

1. Perform the prefetch query (or queries),
2. Apply the main query over the results of its prefetch(es).

Additionally, prefetches can have prefetches themselves, so you can have nested prefetches.

Using offset parameter only affects the main query. This means that the prefetches must have a limit of at least limit + offset of the main query, otherwise you can get an empty result.

Hybrid Search

One of the most common problems when you have different representations of the same data is to combine the queried points for each representation into a single result.

{{< figure src="/docs/fusion-idea.png" caption="Fusing results from multiple queries" width="80%" >}}

For example, in text search, it is often useful to combine dense and sparse vectors get the best of semantics, plus the best of matching specific words.

Qdrant currently has two ways of combining the results from different queries:

• rrf - Reciprocal Rank Fusion

  Considers the positions of results within each query, and boosts the ones that appear closer to the top in multiple of them.

• dbsf - Distribution-Based Score Fusion (available as of v1.11.0)

  Normalizes the scores of the points in each query, using the mean +/- the 3rd standard deviation as limits, and then sums the scores of the same point across different queries.

  dbsf is stateless and calculates the normalization limits only based on the results of each query, not on all the scores that it has seen.

Here is an example of Reciprocal Rank Fusion for a query containing two prefetches against different named vectors configured to respectively hold sparse and dense vectors.

{{< code-snippet path="/documentation/headless/snippets/query-points/hybrid-basic/" >}}

Multi-stage queries

In many cases, the usage of a larger vector representation gives more accurate search results, but it is also more expensive to compute.

Splitting the search into two stages is a known technique:

• First, use a smaller and cheaper representation to get a large list of candidates.
• Then, re-score the candidates using the larger and more accurate representation.

There are a few ways to build search architectures around this idea:

• The quantized vectors as a first stage, and the full-precision vectors as a second stage.
• Leverage Matryoshka Representation Learning (MRL) to generate candidate vectors with a shorter vector, and then refine them with a longer one.
• Use regular dense vectors to pre-fetch the candidates, and then re-score them with a multi-vector model like ColBERT.

To get the best of all worlds, Qdrant has a convenient interface to perform the queries in stages, such that the coarse results are fetched first, and then they are refined later with larger vectors.

Re-scoring examples

Fetch 1000 results using a shorter MRL byte vector, then re-score them using the full vector and get the top 10.

{{< code-snippet path="/documentation/headless/snippets/query-points/hybrid-rescoring/" >}}

Fetch 100 results using the default vector, then re-score them using a multi-vector to get the top 10.

{{< code-snippet path="/documentation/headless/snippets/query-points/hybrid-rescoring-multivector/" >}}

It is possible to combine all the above techniques in a single query:

{{< code-snippet path="/documentation/headless/snippets/query-points/hybrid-rescoring-multistage/" >}}

Re-ranking with payload values

The Query API can retrieve points not only by vector similarity but also by the content of the payload.

There are two ways to make use of the payload in the query:

• Apply filters to the payload fields, to only get the points that match the filter.
• Order the results by the payload field.

Let's see an example of when this might be useful:

{{< code-snippet path="/documentation/headless/snippets/query-points/hybrid-rescoring-with-payload/" >}}

In this example, we first fetch 10 points with the color "red" and then 10 points with the color "green". Then, we order the results by the price field.

This is how we can guarantee even sampling of both colors in the results and also get the cheapest ones first.