See failures, cost, and latency in production
You add traces, usage and cost accounting, cache policy, cancellation, bounded retries, and safe logs. Debug output becomes evidence for tests and operations.
Unit example (nearest native match)
See the idea in context
set_rate_limiter(Some(global_limiter));
set_tracer(Some(tracer.clone()));
set_meter(Some(meter.clone()));
workflow.forward_with_hooks(&mut client, input, Value::Null, AxRuntimeHooks { rate_limiter: Some(call_limiter), tracer: Some(tracer), meter: Some(meter) })?;
set_rate_limiter(None); set_tracer(None); set_meter(None);- Trace the run
tracer connects model and tool activity to the surrounding request.
- Make cancellation possible
abortSignal lets callers stop work that is no longer useful.
- Control repeated work
contextCache makes reuse an explicit operational policy.
Run itIn your own project
cargo add axllm
use axllm::{ai, ax, AxResult};
use serde_json::json;
fn main() -> AxResult<()> {
let mut llm = ai("openai", json!({"apiKey": std::env::var("OPENAI_API_KEY")?}))?;
let mut classify = ax("review:string -> sentiment:class \"positive, negative, neutral\"")?;
let result = classify.forward(&mut llm, json!({
"review": "Useful and boring in the best way."
}))?;
println!("sentiment: {}", result["sentiment"].as_str().unwrap_or_default());
Ok(())
}Set OPENAI_APIKEY in your environment before running provider-backed code.
From a clone of the ax repo:
npm run example -- rust src/examples/rust/long-agents/smart_defaults_agent.rsActive practice
Answer 2 in a row to learn this · attempt 1