Collection

Everything you need to know about operations on collections, partitions, indexes, and similarity searches.

Manage Collections [READ MORE]

Learn about how to manipulate collections on the Zilliz Cloud console or via SDKs.

Manage Indexes [READ MORE]

Learn how to manipulate indexes on vector and scalar fields via SDKs.

Manage Partitions [READ MORE]

This guide walks you through how to create and manage partitions in a collection.

Insert, Upsert & Delete [READ MORE]

This guide walks you through the data manipulation operations within a collection, including insertion, upsertion, and deletion.

Search, Query & Get [READ MORE]

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

Enable Dynamic Field [READ MORE]

This page explains how to use the dynamic field in a collection for flexible data insertion and retrieval.

Use Partition Key [READ MORE]

This guide walks you through using the partition key to accelerate data retrieval from your collection.

Use JSON Fields [READ MORE]

This guide explains how to use the JSON fields, such as inserting JSON values as well as searching and querying in JSON fields with basic and advanced operators.

Use Array Fields [READ MORE]

This guide explains how to use the array fields, such as inserting array values as well as searching and querying in array fields with basic and advanced operators.

Use Sparse Vector [READ MORE]

Sparse vectors represent words or phrases using vector embeddings where most elements are zero, with only one non-zero element indicating the presence of a specific word. Sparse vector models, such as SPLADEv2, outperform dense models in out-of-domain knowledge search, keyword-awareness, and interpretability. They are particularly useful in information retrieval, natural language processing, and recommendation systems, where combining sparse vectors for recall with a large model for ranking can significantly improve retrieval results.

Use Binary Vector [READ MORE]

Binary vectors are a type of data representation where each element is either 0 or 1. These are particularly useful in contexts such as similarity search in large datasets, where the binary nature allows for efficient computation of similarities using metrics like Hamming or Jaccard distance. This guide will demonstrate how to use binary vectors in Zilliz Cloud.