QMD - Query Markdown Documents

A high-performance local search engine for markdown files with full-text search, vector semantic search, and LLM-powered features.

Features

• Full-text search with BM25 ranking via SQLite FTS5
• Vector semantic search with local embeddings (GGUF models)
• Hybrid search with query expansion and RRF fusion
• Reranking with cross-encoder models
• Collection management for organizing document sets
• Automatic model download from HuggingFace

Quick Start

use qmd::{Store, EmbeddingEngine};
use anyhow::Result;

fn main() -> Result<()> {
    // Open the document store
    let store = Store::new()?;

    // Full-text search (BM25)
    let results = store.search_fts("rust programming", 10, None)?;

    // Vector search (requires embedding model)
    let mut engine = EmbeddingEngine::load_default()?;
    let query_emb = engine.embed_query("how to use rust")?;
    let vec_results = store.search_vec(&query_emb.embedding, 10, None)?;

    Ok(())
}

qmd

Lightweight SOTA local search engine for AI agents in Rust.

License

This project is licensed under either of the following licenses, at your option:

• Apache License, Version 2.0, (LICENSE-APACHE or https://www.apache.org/licenses/LICENSE-2.0)
• MIT license (LICENSE-MIT or https://opensource.org/licenses/MIT)

Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in this project by you, as defined in the Apache-2.0 license, shall be dually licensed as above, without any additional terms or conditions.