Search relevance judgments

Judge whether a result satisfies the query’s stated product constraints.

Step 01

Define and Align

Upload sample data, define your output schema, and provide feedback on the hardest cases.

Output schema
RelevantYes / No

Whether the result satisfies the query’s required constraints.

  • true
  • false
Product matchChoose one

How closely the result matches the requested product.

  • exact
  • compatible_alternative
  • wrong_product
Unmet constraintsList of values

Requested attributes or compatibility requirements the result fails.

app.sutro.sh/functions/search-relevance-judgments
Collecting feedback · 1/3
Judge whether a result satisfies the query’s stated product constraints.
Example 1 of 3

Wrong accessory

Model input
Query
laptop charger
Result
Protective laptop sleeve. No charger or power adapter included.
Model output
Relevant
Product match
Unmet constraintsMultiple values

Step 02

Model Sweep

Compare quality and cost on your examples, then choose a model or use Sutro’s default.

Compare models on expert agreement and cost. The interactive chart uses illustrative measurements.

Illustrative sweep · select Value or Best to use that model in your function.

Step 03

Deployment

Call Sutro Functions like any other software. Swap the model as soon as something more performant is released.

Selected modelWaiting for sweep results.

Real-time

import sutro as so

input_data = {
    "query": "laptop charger",
    "result": "Protective laptop sleeve. No charger or power adapter included."
}

result = so.run_function(
    "search-relevance-judgments",
    input_data,
)

Batch

import sutro as so

job_id = so.batch_run_function(
    name="search-relevance-judgments",
    data="search_relevance_judgments.csv",
)
results = so.await_job_completion(job_id)

Ready to get started?

Book time with the team

Join the self-serve waitlist

What are your bottlenecks? (Select any that apply)