Crate lumosai_vector_weaviate 

Lumos Vector Weaviate

Weaviate vector database implementation for the lumos-vector-core architecture.

This crate provides a high-performance Weaviate backend for vector storage, implementing the unified VectorStorage trait from lumos-vector-core.

Features

• Semantic Search: Leverages Weaviate’s semantic search capabilities
• Schema Management: Automatic schema creation and management
• Rich Filtering: Advanced metadata filtering with GraphQL
• Batch Operations: Efficient bulk insert and update operations
• Multi-tenancy: Support for Weaviate’s multi-tenant features

Example

use lumos_vector_weaviate::WeaviateVectorStorage;
use lumos_vector_core::prelude::*;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    // Create Weaviate storage
    let storage = WeaviateVectorStorage::new("http://localhost:8080").await?;
     
    // Create an index (class in Weaviate)
    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?;
     
    // Search
    let request = SearchRequest::new("Documents", vec![0.1; 384])
        .with_top_k(5);
    let results = storage.search(request).await?;
     
    Ok(())
}

Re-exports

pub use storage::WeaviateVectorStorage;

pub use config::WeaviateConfig;

pub use error::WeaviateError;

Modules

config

Weaviate configuration

error

Weaviate-specific error types

filter

Weaviate filter conversion utilities

schema

Weaviate schema management

similarity

Default similarity calculator implementations

storage

Weaviate 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_weaviate_storage

Create a new Weaviate vector storage instance

create_weaviate_storage_with_config

Create a new Weaviate 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