Skip to main content
Go to documentation:
⌘U
Weaviate Database

Develop AI applications using Weaviate's APIs and tools

Deploy

Deploy, configure, and maintain Weaviate Database

Weaviate Agents

Build and deploy intelligent agents with Weaviate

Weaviate Cloud

Manage and scale Weaviate in the cloud

Additional resources

Academy
Integrations
Contributor guide

Need help?

Weaviate LogoAsk AI Assistant⌘K
Community Forum

Manage collections

Use the following guides for detailed instructions and concepts related to specific Weaviate features. Learn how to perform basic collection operations, configure vectorizers, integrate models, implement multi-tenancy or multi-node setups, migrate data, and manage cross-references.



How collections work

A Weaviate collection is defined by several core components and settings that enable data storage and vector search.
Key elements include:

  • Objects:
    • The fundamental units stored within a collection. Each object contains data properties and includes vector embeddings representing its meaning. (See the 'How-to: Manage objects' guide for more details on manipulating objects).
  • AI Model Integrations:
    • Vectorizers (Embedding Models): Generate vector embeddings from object properties to enable semantic search.
    • Generative models: Used to perform RAG (Retrieval-Augmented Generation), combining retrieved data with generative AI capabilities.
    • Reranker models: Refine search relevance by re-ordering the initial results from a search query.
  • Configuration Settings:
    • Inverted index: Optimizes keyword searches by indexing textual object properties for faster lookups.
    • Multi-tenancy: Enables securely storing data for multiple distinct tenants (users or groups) within the same collection instance.
Collections in Weaviate

Questions and feedback

If you have any questions or feedback, let us know in the user forum.