Crate intent_classifier

Intent Classification Library

A flexible few-shot intent classification library for natural language processing. This library provides a simple API for classifying user intents from text using machine learning and rule-based approaches.

Features

• Few-shot learning: Train the classifier with minimal examples
• Bootstrap data: Comes with pre-trained examples for common intents
• Feedback learning: Improve accuracy through user feedback
• Async support: Fully async API for non-blocking operations
• Serializable: Export/import training data as JSON
• Configurable: Customize behavior through configuration

Quick Start

use intent_classifier::{IntentClassifier, TrainingExample, TrainingSource, IntentId};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    // Create a new classifier
    let classifier = IntentClassifier::new().await?;

    // Predict an intent
    let prediction = classifier.predict_intent("merge these JSON files together").await?;
    println!("Intent: {}, Confidence: {:.3}", 
             prediction.intent, prediction.confidence.value());

    // Add custom training data
    let example = TrainingExample {
        text: "calculate the sum of these numbers".to_string(),
        intent: IntentId::from("math_operation"),
        confidence: 1.0,
        source: TrainingSource::Programmatic,
    };
    classifier.add_training_example(example).await?;

    // Get statistics
    let stats = classifier.get_stats().await;
    println!("Training examples: {}", stats.training_examples);

    Ok(())
}

Examples

For more examples, see the examples/ directory in the repository.

Re-exports

pub use classifier::IntentClassifier;

pub use types::IntentId;

pub use types::Confidence;

pub use types::IntentPrediction;

pub use types::TrainingExample;

pub use types::TrainingSource;

pub use types::ClassificationRequest;

pub use types::ClassificationResponse;

pub use types::IntentFeedback;

pub use types::ClassifierConfig;

pub use types::ClassifierStats;

pub use types::IntentError;

pub use types::Result;

pub use types::*;

Modules

classifier

Intent Classification Library

types

Core types for intent classification