Struct Agent 

pub struct Agent { /* private fields */ }

System-1 decision model runtime.

Implementations

impl Agent

pub fn load(model_id_or_path: &str, opts: LoadOptions) -> Result<Agent>

Load a Laya checkpoint from a local directory or a Hugging Face repo id.

Examples found in repository

examples/predict.rs (lines 19-26)

fn main() -> Result<(), Box<dyn std::error::Error>> {
    let model =
        std::env::var("LAYA_MODEL").unwrap_or_else(|_| "convaiinnovations/laya".to_string());
    let subfolder = std::env::var("LAYA_SUBFOLDER").ok();
    let device = std::env::var("LAYA_DEVICE").ok().filter(|s| !s.is_empty());

    let t = Instant::now();
    let agent = Agent::load(
        &model,
        LoadOptions {
            subfolder,
            device: device.clone(),
            ..Default::default()
        },
    )?;
    println!(
        "loaded {model} on {} in {:?}",
        device.as_deref().unwrap_or("cpu"),
        t.elapsed()
    );

    let state: State = serde_json::json!({
        "message": "I was charged twice this month and I'm furious. Refund me now or I'm leaving."
    });
    let questions = triage_questions();

    let t = Instant::now();
    let result = agent.system_one(&state, &questions)?;
    println!("forward in {:?}\n", t.elapsed());
    println!("{}", serde_json::to_string_pretty(&result.to_json())?);

    // Sanity: every probability distribution should sum to ~1.
    for (qid, ans) in &result.answers {
        if let Some(probs) = ans.get("probabilities").and_then(|p| p.as_object()) {
            let sum: f64 = probs.values().filter_map(|v| v.as_f64()).sum();
            assert!((sum - 1.0).abs() < 1e-2, "{qid} probabilities sum to {sum}");
        }
    }
    println!("\nOK: probability distributions sum to 1.");
    Ok(())
}

examples/shortlist.rs (lines 11-17)

fn main() -> Result<(), Box<dyn std::error::Error>> {
    let model =
        std::env::var("LAYA_MODEL").unwrap_or_else(|_| "convaiinnovations/laya".to_string());
    let device = std::env::var("LAYA_DEVICE").ok().filter(|s| !s.is_empty());
    let agent = Agent::load(
        &model,
        LoadOptions {
            device,
            ..Default::default()
        },
    )?;

    // A large label set (25 intents); shortlist to the 5 most relevant before scoring.
    let criteria = json!({
        "refund": null, "cancel_subscription": null, "reset_password": null, "update_billing": null,
        "report_bug": null, "feature_request": null, "track_shipment": null, "return_item": null,
        "change_address": null, "upgrade_plan": null, "downgrade_plan": null, "dispute_charge": null,
        "account_locked": null, "two_factor_help": null, "api_error": null, "integration_help": null,
        "pricing_question": null, "demo_request": null, "gdpr_request": null, "delete_account": null,
        "invoice_copy": null, "tax_question": null, "partnership": null, "press_inquiry": null,
        "other": null
    });
    let state =
        json!({ "message": "I was double charged and want my money back for the duplicate." });

    let embed = embed_fn_from_agent(&agent, 512, 32);
    let top = shortlist_choice(&state, &criteria, &embed, 5, None)?;
    println!("top-5 shortlisted labels: {top:?}");

    let dim = agent.embed(&["hello world".to_string()], 512, 32)?[0].len();
    println!("encoder embedding dim: {dim}");
    assert!(top.len() == 5, "expected 5 labels");
    println!("OK");
    Ok(())
}

pub fn system_one( &self, state: &State, questions: &Questions, ) -> Result<SystemOneResult>

Evaluate typed questions over one state in a single forward pass.

Examples found in repository

examples/predict.rs (line 39)

fn main() -> Result<(), Box<dyn std::error::Error>> {
    let model =
        std::env::var("LAYA_MODEL").unwrap_or_else(|_| "convaiinnovations/laya".to_string());
    let subfolder = std::env::var("LAYA_SUBFOLDER").ok();
    let device = std::env::var("LAYA_DEVICE").ok().filter(|s| !s.is_empty());

    let t = Instant::now();
    let agent = Agent::load(
        &model,
        LoadOptions {
            subfolder,
            device: device.clone(),
            ..Default::default()
        },
    )?;
    println!(
        "loaded {model} on {} in {:?}",
        device.as_deref().unwrap_or("cpu"),
        t.elapsed()
    );

    let state: State = serde_json::json!({
        "message": "I was charged twice this month and I'm furious. Refund me now or I'm leaving."
    });
    let questions = triage_questions();

    let t = Instant::now();
    let result = agent.system_one(&state, &questions)?;
    println!("forward in {:?}\n", t.elapsed());
    println!("{}", serde_json::to_string_pretty(&result.to_json())?);

    // Sanity: every probability distribution should sum to ~1.
    for (qid, ans) in &result.answers {
        if let Some(probs) = ans.get("probabilities").and_then(|p| p.as_object()) {
            let sum: f64 = probs.values().filter_map(|v| v.as_f64()).sum();
            assert!((sum - 1.0).abs() < 1e-2, "{qid} probabilities sum to {sum}");
        }
    }
    println!("\nOK: probability distributions sum to 1.");
    Ok(())
}

pub fn predict( &self, state: &State, questions: &Questions, ) -> Result<SystemOneResult>

Alias for Agent::system_one.

pub fn predict_batch( &self, states: &[State], questions: &Questions, batch_size: Option<usize>, ) -> Result<Vec<SystemOneResult>>

Evaluate the same questions over many states, sharing forward passes.

pub fn embed( &self, texts: &[String], max_length: usize, batch_size: usize, ) -> Result<Vec<Vec<f32>>>

Mean-pooled encoder embeddings for a list of texts ([n, hidden_size]).

Tokenizes with special tokens, truncates to max_length, runs the checkpoint encoder in batches of batch_size, and mean-pools over non-padding tokens. Backs crate::shortlist::embed_fn_from_agent; a dedicated bi-encoder will usually shortlist better, but this needs only the loaded checkpoint.

Examples found in repository

examples/shortlist.rs (line 36)

fn main() -> Result<(), Box<dyn std::error::Error>> {
    let model =
        std::env::var("LAYA_MODEL").unwrap_or_else(|_| "convaiinnovations/laya".to_string());
    let device = std::env::var("LAYA_DEVICE").ok().filter(|s| !s.is_empty());
    let agent = Agent::load(
        &model,
        LoadOptions {
            device,
            ..Default::default()
        },
    )?;

    // A large label set (25 intents); shortlist to the 5 most relevant before scoring.
    let criteria = json!({
        "refund": null, "cancel_subscription": null, "reset_password": null, "update_billing": null,
        "report_bug": null, "feature_request": null, "track_shipment": null, "return_item": null,
        "change_address": null, "upgrade_plan": null, "downgrade_plan": null, "dispute_charge": null,
        "account_locked": null, "two_factor_help": null, "api_error": null, "integration_help": null,
        "pricing_question": null, "demo_request": null, "gdpr_request": null, "delete_account": null,
        "invoice_copy": null, "tax_question": null, "partnership": null, "press_inquiry": null,
        "other": null
    });
    let state =
        json!({ "message": "I was double charged and want my money back for the duplicate." });

    let embed = embed_fn_from_agent(&agent, 512, 32);
    let top = shortlist_choice(&state, &criteria, &embed, 5, None)?;
    println!("top-5 shortlisted labels: {top:?}");

    let dim = agent.embed(&["hello world".to_string()], 512, 32)?[0].len();
    println!("encoder embedding dim: {dim}");
    assert!(top.len() == 5, "expected 5 labels");
    println!("OK");
    Ok(())
}