Module engine 

High-level MemexEngine API for library consumers.

The MemexEngine provides a simple, ergonomic interface for storing and searching vector embeddings. It wraps the lower-level StorageManager and EmbeddingClient to provide a unified API.

Example

use rust_memex::{MemexEngine, MemexConfig};
use serde_json::json;

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    // Quick setup for an app
    let engine = MemexEngine::for_app("my-app", "documents").await?;

    // Store a document
    engine.store("doc-1", "Hello world!", json!({"source": "test"})).await?;

    // Search for similar documents
    let results = engine.search("greeting", 5).await?;

    // Get by ID
    if let Some(doc) = engine.get("doc-1").await? {
        println!("Found: {}", doc.text);
    }

    // Delete
    engine.delete("doc-1").await?;

    Ok(())
}

Re-exports

pub use crate::rag::SearchResult as Document;

Structs

BatchResult

Result of a batch operation

DiveResult

Result of a dive operation for a single layer

LayerStats

Statistics for a single layer in dive results

MemexConfig

Configuration for MemexEngine.

MemexEngine

High-level API for vector memory operations.

MetaFilter

Metadata filter for search and deletion operations.

StoreItem

Item for batch storage operations.