DistX

A fast, in-memory vector database written in Rust. Designed with Redis-style simplicity and full Qdrant API compatibility.

Performance

DistX delivers comparable performance to Qdrant with the following characteristics:

Benchmarks: 5,000 vectors, 128 dimensions, Cosine distance, Docker deployment

See Performance Benchmarks for detailed results.

Quick Start with Docker

The fastest way to get started - no compilation required:

# Pull and run
docker pull distx/distx:latest
docker run -p 6333:6333 -p 6334:6334 \
    -v "$(pwd)/distx_storage:/qdrant/storage" \
    distx/distx:latest

Or with Docker Compose:

docker-compose up -d

DistX is now accessible at:

• REST API: http://localhost:6333 (Qdrant-compatible)
• Web UI: http://localhost:6333/dashboard
• gRPC API: localhost:6334

See Docker Guide for more options.

Installation

From crates.io

cargo install distx

As a Library

Add to your Cargo.toml:

[dependencies]
distx = "0.1.0"

# Or individual components:
distx-core = "0.1.0"      # Core data structures (Vector, HNSW, BM25)
distx-storage = "0.1.0"   # Persistence layer (WAL, snapshots)
distx-api = "0.1.0"       # REST and gRPC APIs

From Source

git clone https://github.com/antonellof/DistX.git
cd DistX
cargo build --release

Prerequisites

• Rust 1.75+: Install from rustup.rs
• LMDB (for persistence):
  • Linux: sudo apt-get install liblmdb-dev
  • macOS: brew install lmdb

Quick Start

Run the Server

# Using cargo install
distx

# Or from source
./target/release/distx

# With custom options
distx --data-dir ./data --http-port 6333 --grpc-port 6334

The server will start and listen on:

• REST API: http://localhost:6333 (Qdrant-compatible)
• Web UI: http://localhost:6333/dashboard
• gRPC API: localhost:6334

Create a Collection

curl -X PUT http://localhost:6333/collections/my_collection \
  -H "Content-Type: application/json" \
  -d '{
    "vectors": {
      "size": 128,
      "distance": "Cosine"
    }
  }'

Insert Vectors

curl -X PUT http://localhost:6333/collections/my_collection/points \
  -H "Content-Type: application/json" \
  -d '{
    "points": [
      {
        "id": "point1",
        "vector": [0.1, 0.2, 0.3, ...],
        "payload": {"text": "example document"}
      }
    ]
  }'

Search Vectors

curl -X POST http://localhost:6333/collections/my_collection/points/search \
  -H "Content-Type: application/json" \
  -d '{
    "vector": [0.1, 0.2, 0.3, ...],
    "limit": 10
  }'

Features

• Fast Vector Search: HNSW index with SIMD optimizations (AVX2, SSE, NEON)
• Text Search: BM25 full-text search with ranking
• Payload Filtering: Filter results by JSON metadata
• Dual API: REST (Qdrant-compatible) and gRPC
• Web Dashboard: Uses Qdrant's fully compatible dashboard UI
• Docker Ready: Single command deployment
• Persistence: Redis-style snapshots, WAL, and LMDB storage
• Lightweight: Single ~6MB binary

Configuration

distx [OPTIONS]

Options:
  --data-dir <PATH>      Data directory (default: ./data)
  --http-port <PORT>     HTTP API port (default: 6333)
  --grpc-port <PORT>     gRPC API port (default: 6334)
  --log-level <LEVEL>    Log level: trace, debug, info, warn, error (default: info)

Architecture

distx/
├── lib/
│   ├── core/          # Core data structures (Vector, Point, Collection, HNSW)
│   ├── storage/       # Persistence layer (WAL, snapshots, LMDB)
│   └── api/           # REST and gRPC APIs
└── src/
    └── main.rs        # Main entry point

Web Dashboard

DistX uses Qdrant's Web UI, which is fully compatible thanks to our Qdrant API implementation:

Access it at http://localhost:6333/dashboard

Features:

• View all collections and their statistics
• Create and delete collections
• Browse points with pagination
• Interactive API console for testing
• Full compatibility with Qdrant's dashboard features

Documentation

• Quick Start Guide - Get started quickly
• Docker Deployment - Docker and docker-compose guide
• Architecture - System design
• API Reference - REST and gRPC API docs
• Performance - Benchmarks and optimizations

Links

• Crates.io: https://crates.io/crates/distx
• Documentation: https://docs.rs/distx
• GitHub: https://github.com/antonellof/DistX

License

Licensed under either of:

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

at your option.