Module persistence 

Index persistence helpers for saving/loading indexes to storage

This module provides utilities for persisting trained indexes to object storage and loading them back, enabling:

• Cold start without retraining
• Index sharing across instances
• Checkpoint/restore workflows

Structs

HnswConfigSnapshot

Serializable snapshot for HNSW configuration only (lightweight) Note: For full graph persistence, use HnswFullSnapshot instead

HnswFullSnapshot

Full HNSW graph snapshot for complete persistence This allows loading the index without rebuilding the graph

IndexPersistenceManager

Index persistence manager for saving/loading indexes to object storage

IvfFullSnapshot

Full IVF index snapshot for complete persistence This allows loading the trained index without retraining

IvfTrainingSnapshot

Serializable snapshot for IVF index training data

PQSnapshot

Serializable snapshot of a ProductQuantizer (the trained codebooks)

SerializableHnswNode

Serializable representation of an HNSW node

SerializableIndexedVector

Serializable representation of an indexed vector in IVF

SpFreshFullSnapshot

Full SPFresh index snapshot for complete persistence This allows loading the trained index with all clusters and vectors

SpFreshTrainingSnapshot

Serializable snapshot for SPFresh index training data

Enums

IndexType

Index types that can be persisted

Traits

Persistable

Trait for indexes that can be persisted

Functions

deserialize_from_bytes

Helper to deserialize from bytes to any DeserializeOwned type

serialize_to_bytes

Helper to serialize any Serialize type to bytes