Search on Qdrant - Vector Search Engine

Search

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Similarity search

Searching for the nearest vectors is at the core of many representational learning applications. Modern neural networks are trained to transform objects into vectors so that objects close in the real world appear close in vector space. It could be, for example, texts with similar meanings, visually similar pictures, or songs of the same genre.

This is how vector similarity works

Query API

Available as of v1.10.0

Filtering

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Filtering

With Qdrant, you can set conditions when searching or retrieving points. For example, you can impose conditions on both the payload and the id of the point.

Setting additional conditions is important when it is impossible to express all the features of the object in the embedding. Examples include a variety of business requirements: stock availability, user location, or desired price range.

A Complete Guide to Filtering in Vector Search	Developer advice on proper usage and advanced practices.

Filtering clauses

Qdrant allows you to combine conditions in clauses. Clauses are different logical operations, such as OR, AND, and NOT. Clauses can be recursively nested into each other so that you can reproduce an arbitrary boolean expression.

Hybrid Queries

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Hybrid and Multi-Stage Queries

Available as of v1.10.0

With the introduction of multiple 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.

Explore

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Explore the data

After mastering the concepts in search, you can start exploring your data in other ways. Qdrant provides a stack of APIs that allow you to find similar vectors in a different fashion, as well as to find the most dissimilar ones. These are useful tools for recommendation systems, data exploration, and data cleaning.

Recommendation API

In addition to the regular search, Qdrant also allows you to search based on multiple positive and negative examples. The API is called recommend, and the examples can be point IDs, so that you can leverage the already encoded objects; and, as of v1.6, you can also use raw vectors as input, so that you can create your vectors on the fly without uploading them as points.

Text Search

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Text Search

Qdrant is a vector search engine, making it a great tool for semantic search. However, Qdrant’s capabilities go beyond just vector search. It also supports a range of lexical search features, including filtering on text fields and full-text search using popular algorithms like BM25.

Semantic Search

Semantic search is a search technique that focuses on the meaning of the text rather than just matching on keywords. This is achieved by converting text into vectors (embeddings) using machine learning models. These vectors capture the semantic meaning of the text, enabling you to find similar text even if it doesn’t share exact keywords.

Search Relevance

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Search Relevance

By default, Qdrant ranks search results based on vector similarity scores. However, you may wish to consider additional factors when ranking results. Qdrant offers several tools to help you accomplish this.

Score Boosting

Available as of v1.14.0

When introducing vector search to specific applications, sometimes business logic needs to be considered for ranking the final list of results.

A quick example is our own documentation search bar. It has vectors for every part of the documentation site. If one were to perform a search by “just” using the vectors, all kinds of elements would be equally considered good results. However, when searching for documentation, we can establish a hierarchy of importance:

Low-Latency Search

info@qdrant.tech (Andrey Vasnetsov) — Mon, 01 Jan 0001 00:00:00 +0000

Tips for Low-Latency Search with Qdrant

Scale Horizontally with Replicas

Qdrant can be deployed in a distributed configuration. In distributed mode, multiple instances of Qdrant, called peers, operate as a single entity, called a cluster. Data is stored in collections, which are divided into shards that are distributed across the peers. Each shard can have multiple replicas for redundancy and load balancing. Because every replica of the same shard contains the same data, read requests can be distributed across replicas, reducing latency and increasing throughput.

Search on Qdrant - Vector Search Engine

Search

Similarity search

Query API

Filtering

Filtering

Related Content

Filtering clauses

Hybrid Queries

Hybrid and Multi-Stage Queries

Explore

Explore the data

Recommendation API

Text Search

Text Search

Semantic Search

Search Relevance

Search Relevance

Score Boosting

Low-Latency Search

Tips for Low-Latency Search with Qdrant

Scale Horizontally with Replicas