Skip to main content

Documentation Index

Fetch the complete documentation index at: https://dsrs.herumbshandilya.com/llms.txt

Use this file to discover all available pages before exploring further.

Constraints let you validate what the LM returns. Add them to output fields to enforce rules like “confidence must be between 0 and 1” or “answer can’t be empty”.

​
Two Flavors

#[check] - Soft constraint. The call succeeds, but you can see if the check passed or failed. #[assert] - Hard constraint. The call fails if the assertion doesn’t hold.

​
Check Example

#[derive(Signature, Clone, Debug)]
struct QA {
    #[input]
    question: String,

    #[output]
    answer: String,

    #[output]
    #[check("this >= 0.0 and this <= 1.0", label = "valid_range")]
    confidence: f32,
}
If the LM returns confidence: 1.5, the call still succeeds - you just see passed: false when you inspect the check result. The label is required for checks. It’s how you identify which constraint passed or failed.

​
Assert Example

#[derive(Signature, Clone, Debug)]
struct StrictQA {
    #[input]
    question: String,

    #[output]
    #[assert("this.len() > 0")]
    answer: String,

    #[output]
    #[assert("this >= 0.0 and this <= 1.0", label = "confidence_range")]
    confidence: f32,
}
If confidence is 1.5, the call returns a PredictError::Parse error. Label is optional for asserts.

​
Writing Expressions

Use this to refer to the field value: 
this > 0
this >= 0.0 and this <= 1.0
this == "expected"
this != "bad"
Boolean logic: 
this > 0 and this < 100
this == "a" or this == "b"
not this
String methods: 
this.len() > 0
this.startswith("https://")
this.endswith(".com")
this.contains("@")
Collections: 
this.len() < 10      # list has fewer than 10 items
this[0] == "first"   # first item equals "first"

​
Inspecting Check Results

Predicted<O> carries per-field metadata including constraint results. Access it via .metadata(): 
let predict = Predict::<QA>::new();
let result = predict.call(QAInput {
    question: "What is the capital of France?".into(),
}).await?;

// Output fields are available directly via Deref
println!("Answer: {}", result.answer);

// Inspect per-field constraint results via metadata
if let Some(field_meta) = result.metadata().field_meta.get("confidence") {
    for check in &field_meta.checks {
        if !check.passed {
            println!("Check '{}' failed", check.label);
        }
    }
}

​
Handling Assert Failures

When an assert fails, you get a PredictError: 
match predict.call(input).await {
    Ok(result) => {
        println!("{}", result.answer);
    }
    Err(PredictError::Parse { source, .. }) => {
        // The LM returned something that violated an assertion
        eprintln!("Invalid response: {source}");
    }
    Err(e) => {
        eprintln!("Other error: {e}");
    }
}

​
Common Patterns

Probability/confidence range: 
#[check("this >= 0.0 and this <= 1.0", label = "valid_probability")]
confidence: f64,
Non-empty output: 
#[assert("this.len() > 0")]
answer: String,
Length limits: 
#[check("this.len() < 500", label = "max_length")]
summary: String,
URL format: 
#[assert("this.startswith('https://')")]
url: String,
Multiple constraints on one field: 
#[output]
#[check("this.len() > 0", label = "non_empty")]
#[check("this.len() < 500", label = "not_too_long")]
response: String,

​
Compile-time Errors

If you forget the label on a check: 
#[check("this > 0")]  // oops, no label
score: i32,
You get: 
error: #[check] requires a label: #[check("expr", label = "name")]
 --> src/lib.rs:9:5
  |
9 |     #[check("this > 0")]
  |     ^^^^^^^^^^^^^^^^^^^^