Module types

Module types 

Source
Expand description

Core types for vector storage.

This module provides the fundamental types for vector embedding storage:

§Entity-based embeddings

§Separated vector storage

  • VectorData - Vector data supporting dense, sparse, multi-vector, and binary formats
  • VectorRef - Reference to a vector attached to an entity

§Point collections (Qdrant-style)

Structs§

BinaryEmbedding
A binary vector embedding represented as bit-packed u64 values.
BinaryEmbeddingSpace
Metadata about a binary embedding space.
Collection
Metadata about a collection.
CollectionName
A validated collection name.
CollectionSchema
Schema for a collection defining which vectors are expected.
Embedding
A vector embedding with dimension validation.
EmbeddingName
A name for an embedding space.
EmbeddingSpace
Metadata about an embedding space.
MultiVectorEmbedding
A multi-vector embedding with validation.
MultiVectorEmbeddingSpace
Metadata about a multi-vector embedding space.
Payload
A point’s payload (JSON data).
SparseEmbedding
A sparse vector embedding with validation.
SparseEmbeddingSpace
Metadata about a sparse embedding space.
VectorConfig
Configuration for a vector in a collection schema.
VectorName
A validated vector name.
VectorRef
Reference to a vector attached to an entity.

Enums§

NamedVector
A named vector value that can be dense, sparse, or multi-vector.
VectorData
Vector data supporting different types.
VectorType
Type of vector in a collection schema.