Blazegraph IO Core

Core library for semantic document graph processing

🦀 High-performance Rust library for transforming PDFs into semantic graph structures optimized for RAG and hierarchical search.

Status

This crate is currently in development.

Features (Coming Soon)

• 📄 PDF Parsing - Extract text with bounding boxes and style information
• 🌳 Semantic Graphs - Build hierarchical document structures
• 🎯 Smart Boundaries - Detect sections, paragraphs, lists automatically
• ⚡ Blazingly Fast - Native Rust performance with Tika integration
• 🔧 Configurable - Fine-tune parsing behavior for any document type
• 📊 Rich Output - JSON graphs with full positional and style metadata

Use Cases

• RAG Pipelines - Semantic chunking that preserves document structure
• Document Analysis - Extract and understand document hierarchy
• GraphRAG - Build knowledge graphs from document corpora
• Custom Integrations - Embed in your Rust application

Installation

[dependencies]
blazegraph-io-core = "0.0.1"

Usage

use blazegraph_io_core::{get_info, print_info};

fn main() {
    print_info();

    let info = get_info();
    println!("Package: {}", info.name);
}

Relationship to blazegraph-io

This is the core library. For the CLI tool, see blazegraph-io.

blazegraph-io          # CLI binary (cargo install blazegraph-io)
└── blazegraph-io-core # This library (cargo add blazegraph-io-core)

Links

• Website: blazegraph.io
• Documentation: Coming Soon
• GitHub: amplifytechnology/blazegraph-io

License

Licensed under either of Apache License, Version 2.0 or MIT license at your option.

© 2025 Amplify Technology