Crate sz_orm_vector 

SZ-ORM pgvector Extension

Provides PostgreSQL pgvector vector similarity search capabilities, supporting three implementations:

• In-memory implementation (InMemoryVectorStore): Pure Rust vector computation, no database connection, suitable for testing and benchmarking
• Stub implementation (StubVectorStore): All methods return Unsupported, suitable for debug placeholder
• Real implementation (RealPgVectorStore, requires real-pg feature): Connects to PostgreSQL + pgvector via tokio-postgres

Quick Start

use sz_orm_vector::{InMemoryVectorStore, PgVectorStore, VectorRecord, VectorMetric};

let store = InMemoryVectorStore::new();
store.create_collection("docs", 3, None).await?;

let record = VectorRecord::new("doc1", vec![1.0, 0.0, 0.0]);
store.insert("docs", vec![record]).await?;

let results = store.search("docs", &[1.0, 0.0, 0.0], 5).await?;
println!("found {} results", results.len());

Re-exports

pub use error::VectorError;

pub use extensions::AnnIndexDef;

pub use extensions::AnnIndexRegistry;

pub use extensions::AnnIndexType;

pub use extensions::BatchOpsExt;

pub use extensions::DimensionValidator;

pub use extensions::HnswParams;

pub use extensions::IvfflatParams;

pub use extensions::MemoryBatchOps;

pub use extensions::SimilarityAlgorithms;

pub use extensions::VectorNormalizer;

pub use extensions::MAX_VECTOR_DIMENSION;

pub use extensions::MIN_VECTOR_DIMENSION;

pub use memory::InMemoryVectorStore;

pub use stub::StubVectorStore;

Modules

error

Vector 操作错误类型

extensions

pgvector 深度扩展功能

memory

内存实现：纯 Rust 向量计算（不连接数据库）

stub

Stub 实现：所有方法返回 Unsupported 错误

Structs

SearchResult

Search result

VectorRecord

Vector record

Enums

VectorMetric

Vector distance metric

Constants

MAX_TOP_K

M-16 fix: top_k maximum limit

Traits

PgVectorStore

Vector Store core trait

Functions

validate_top_k

M-16 fix: Validate whether top_k is within reasonable range