TypeDialog/examples/10-ai-backend/main.rs

//! AI Backend Example: RAG System with Batch Operations
//!
//! Demonstrates:
//! - Creating a RAG (Retrieval-Augmented Generation) system
//! - Adding documents using batch operations (efficient)
//! - Retrieving relevant documents for queries
//! - Removing documents using batch operations
//! - Performance comparison: batch vs sequential operations
//!
//! Run with: cargo run --example main --features ai_backend
//! Or via just: just build::ai && cargo run --example main --features ai_backend

#[cfg(feature = "ai_backend")]
fn main() -> Result<(), Box<dyn std::error::Error>> {
    use std::time::Instant;
    use typedialog_core::ai::rag::{RagConfig, RagSystem};

    println!("\n╔════════════════════════════════════════════════════════╗");
    println!("║  TypeDialog AI Backend - RAG System Example          ║");
    println!("║  Batch Operations Performance Demonstration          ║");
    println!("╚════════════════════════════════════════════════════════╝\n");

    // Create RAG system with default configuration
    let mut rag = RagSystem::new(RagConfig::default())?;
    println!("✓ Created RAG system with default config");
    println!("  - Semantic weight: 0.6");
    println!("  - Keyword weight: 0.4");
    println!("  - Max results: 5\n");

    // === BATCH ADD DOCUMENTS ===
    println!("╔════════════════════════════════════════════════════════╗");
    println!("║  1. BATCH ADD DOCUMENTS (Efficient)                   ║");
    println!("╚════════════════════════════════════════════════════════╝\n");

    let documents = vec![
        (
            "doc1".to_string(),
            "Rust is a systems programming language with memory safety guarantees."
                .to_string(),
        ),
        (
            "doc2".to_string(),
            "TypeDialog is an interactive forms library for multiple backends."
                .to_string(),
        ),
        (
            "doc3".to_string(),
            "RAG combines retrieval with generation for better LLM responses.".to_string(),
        ),
        (
            "doc4".to_string(),
            "Knowledge graphs model relationships between entities in data."
                .to_string(),
        ),
        (
            "doc5".to_string(),
            "Embeddings transform text into dense vector representations."
                .to_string(),
        ),
    ];

    let start = Instant::now();
    rag.add_documents_batch(documents)?;
    let batch_duration = start.elapsed();

    println!("✓ Added 5 documents using batch operation");
    println!("  Duration: {:.2}ms", batch_duration.as_secs_f64() * 1000.0);
    println!("  Document count: {}\n", rag.doc_count());

    // === RETRIEVE DOCUMENTS ===
    println!("╔════════════════════════════════════════════════════════╗");
    println!("║  2. RETRIEVE RELEVANT DOCUMENTS                       ║");
    println!("╚════════════════════════════════════════════════════════╝\n");

    let query = "programming language memory safety";
    println!("Query: \"{}\"\n", query);

    let results = rag.retrieve(query)?;
    println!("Retrieved {} document(s):\n", results.len());

    for (idx, result) in results.iter().enumerate() {
        println!(
            "{}. [{}] Score: {:.3} (Semantic: {:.3}, Keyword: {:.3})",
            idx + 1,
            result.doc_id,
            result.combined_score,
            result.semantic_score,
            result.keyword_score
        );
        println!("   Content: {}\n", result.content);
    }

    // === BATCH REMOVE DOCUMENTS ===
    println!("╔════════════════════════════════════════════════════════╗");
    println!("║  3. BATCH REMOVE DOCUMENTS (Efficient)                ║");
    println!("╚════════════════════════════════════════════════════════╝\n");

    let to_remove = vec!["doc2", "doc4"];
    println!("Removing: {:?}", to_remove);

    let removed = rag.remove_documents_batch(&to_remove);
    println!(
        "✓ Removed {} document(s)",
        removed
    );
    println!("  Remaining documents: {}\n", rag.doc_count());

    // === PERFORMANCE COMPARISON ===
    println!("╔════════════════════════════════════════════════════════╗");
    println!("║  4. PERFORMANCE: BATCH vs SEQUENTIAL (20 docs)         ║");
    println!("╚════════════════════════════════════════════════════════╝\n");

    let large_docs: Vec<_> = (0..20)
        .map(|i| {
            (
                format!("perf_doc{}", i),
                format!("Performance test document number {}", i),
            )
        })
        .collect();

    // Sequential
    let mut rag_seq = RagSystem::new(RagConfig::default())?;
    let start = Instant::now();
    rag_seq.add_documents(large_docs.clone())?;
    let seq_duration = start.elapsed();

    // Batch
    let mut rag_batch = RagSystem::new(RagConfig::default())?;
    let start = Instant::now();
    rag_batch.add_documents_batch(large_docs)?;
    let batch_duration = start.elapsed();

    let speedup = seq_duration.as_nanos() as f64 / batch_duration.as_nanos() as f64;

    println!("Sequential add (20 docs):  {:.2}ms", seq_duration.as_secs_f64() * 1000.0);
    println!("Batch add (20 docs):       {:.2}ms", batch_duration.as_secs_f64() * 1000.0);
    println!("Speedup:                   {:.2}x\n", speedup);

    println!("💡 Tip: Use batch operations for large document sets (100+)");
    println!("   Batch avoids multiple HNSW index rebuilds!\n");

    // === SUMMARY ===
    println!("╔════════════════════════════════════════════════════════╗");
    println!("║  SUMMARY                                              ║");
    println!("╚════════════════════════════════════════════════════════╝\n");

    println!("RAG System Features:");
    println!("  ✓ Semantic search (vector embeddings)");
    println!("  ✓ Keyword search (full-text indexing)");
    println!("  ✓ Hybrid retrieval (combines both)");
    println!("  ✓ Batch operations (efficient bulk processing)");
    println!("  ✓ Configurable weights and thresholds");
    println!("  ✓ Persistence (save/load to disk)\n");

    println!("Next Steps:");
    println!("  • Build with Knowledge Graph integration");
    println!("  • Use with different embedding models");
    println!("  • Integrate with LLM backends");
    println!("  • Add custom similarity metrics\n");

    Ok(())
}

#[cfg(not(feature = "ai_backend"))]
fn main() {
    eprintln!("This example requires the 'ai_backend' feature.");
    eprintln!("Run with: cargo run --example main --features ai_backend");
    std::process::exit(1);
}