Module embeddings 

Embedding Management

Provides embedding generation from various providers (OpenAI, local models) with caching and batch processing support.

Features

• Multiple Providers: OpenAI, local models, custom implementations
• Caching: TTL-based cache to reduce redundant API calls
• Batch Processing: Efficient batch embedding generation
• Async Support: Non-blocking embedding generation

Example

use oxify_vector::embeddings::{EmbeddingProvider, MockEmbeddingProvider};

// Use mock provider for testing
let provider = MockEmbeddingProvider::new(384);

let text = "Hello, world!";
let embedding = provider.embed(text)?;

assert_eq!(embedding.len(), 384);

Structs

CachedEmbeddingProvider

Cached embedding provider

EmbeddingCache

Embedding cache with TTL

MockEmbeddingProvider

Mock embedding provider for testing

OpenAIConfig

OpenAI embedding provider configuration

OpenAIEmbeddingProvider

OpenAI embedding provider (stub for future implementation)

Traits

EmbeddingProvider

Trait for embedding providers