Search, Query & Get

This series of guides demonstrate similarity searches and scalar queries in a Zilliz Cloud collection.

Single-Vector Search [READ MORE]

After your data is inserted, the next step is to send a `search` request to search for vectors that are similar to your query vector. A single-vector search compares your query vector against the existing vectors in your collection to find the most similar entities, returning their IDs and the distances between them. This process can optionally return the vector values and metadata of the results.

Hybrid Search [READ MORE]

Zilliz Cloud introduced multi-vector support and a hybrid search framework, which means users can bring in several vector fields into a single collection. These vectors in different columns represent diverse facets of data, originating from different embedding models or undergoing distinct processing methods. The results of hybrid searches are integrated using reranking strategies, such as Reciprocal Rank Fusion (RRF) and Weighted Scoring. To learn more about reranking strategies, refer to Reranking.

Get & Scalar Query [READ MORE]

This guide demonstrates how to get entities by ID and conduct scalar filtering. A scalar filtering retrieves entities that match the specified filtering conditions.

With Iterators [READ MORE]

Zilliz Cloud provides search and query iterators for iterating results with a large volume of entities.