Crate lumosai_vector_postgres

Expand description

§Lumos Vector PostgreSQL

PostgreSQL with pgvector implementation for the lumos-vector-core architecture.

This crate provides a PostgreSQL backend with pgvector extension for vector storage, implementing the unified VectorStorage trait from lumos-vector-core.

§Features

SQL Integration: Leverages PostgreSQL’s ACID properties
pgvector Extension: High-performance vector operations
Rich Queries: Complex SQL queries with vector similarity
Transactions: Full transaction support
Indexing: Multiple vector index types (IVFFlat, HNSW)

§Example

use lumos_vector_postgres::PostgresVectorStorage;
use lumos_vector_core::prelude::*;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    // Create PostgreSQL storage
    let storage = PostgresVectorStorage::new("postgresql://user:pass@localhost/db").await?;
     
    // Create an index
    let config = IndexConfig::new("documents", 384)
        .with_metric(SimilarityMetric::Cosine);
    storage.create_index(config).await?;
     
    // Insert documents
    let docs = vec![
        Document::new("doc1", "Hello world")
            .with_embedding(vec![0.1; 384])
            .with_metadata("type", "greeting"),
    ];
    storage.upsert_documents("documents", docs).await?;
     
    Ok(())
}

Re-exports§

pub use storage::PostgresVectorStorage;
pub use config::PostgresConfig;
pub use error::PostgresError;
pub use error::PostgresResult;

Modules§

config: PostgreSQL configuration for vector storage
error: Error types for PostgreSQL vector storage
filter: Default filter evaluator implementation
similarity: Default similarity calculator implementations
storage: PostgreSQL vector storage implementation

Structs§

BackendInfo: Backend information
CacheConfig: 缓存配置
CacheEntry: 缓存条目
CacheStats: 缓存统计信息
ConnectionPool: 连接池
ConnectionPoolConfig: 连接池配置
ConnectionPoolStats: 连接池统计信息
Document: Document representation with embedding support
IndexConfig: Index configuration
IndexCreateConfig: Index creation configuration
IndexInfo: Index statistics and information
IndexOptions: Index-specific options
LRUCache: LRU缓存
PerformanceMetrics: 性能指标
PerformanceMonitor: 性能监控器
PooledConnection: 池化连接
SearchConfig: Search configuration
SearchRequest: Search request for querying vectors
SearchResponse: Search response
SearchResult: Search result item
StorageConfigBuilder: Builder for creating storage configurations
VectorSystemConfig: Complete vector storage system configuration

Enums§

EmbeddingConfig: Embedding model configuration
FilterCondition: Filter conditions for querying vectors
MetadataValue: Metadata value that can hold various types
SearchQuery: Search query can be either a vector or text
SimilarityMetric: Similarity metrics for vector comparison
SqliteSynchronous: SQLite synchronous mode
StorageConfig: Storage backend configuration
VectorError: Comprehensive error type for vector storage operations

Traits§

Embeddable: Trait for documents that can be embedded
EmbeddingModel: Trait for embedding models
FilterEvaluator: Trait for filter evaluation
SimilarityCalculator: Trait for vector similarity calculation
VectorStorage: Core trait for vector storage backends

Functions§

create_postgres_storage: Create a new PostgreSQL vector storage instance
create_postgres_storage_with_config: Create a new PostgreSQL vector storage instance with configuration

Type Aliases§

DocumentId: Document ID type
Metadata: Metadata type for storing arbitrary key-value pairs
Result: Result type alias for vector operations
Vector: Vector type alias for f32 vectors

Crate lumosai_vector_postgresCopy item path