Accessory versus device
Model input
Listing sells a protective case for a phone, not the phone itself.
Place products in the category matching their primary function.
Step 01
Upload sample data, define your output schema, and provide feedback on the hardest cases.
Primary category based on what the listing actually sells.
Distinguish a product from an accessory or miniature replica.
Secondary functions that should not override the primary category.
Place products in the category matching their primary function.
Listing sells a protective case for a phone, not the phone itself.
Sutro can now generalize the rules based on your feedback.
Step 02
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
Call Sutro Functions like any other software. Swap the model as soon as something more performant is released.
import sutro as so
input_data = {
"text": "Listing sells a protective case for a phone, not the phone itself."
}
result = so.run_function(
"product-taxonomy-classification",
input_data,
)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/product-taxonomy-classification/run" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"text": "Listing sells a protective case for a phone, not the phone itself."
}
}'import sutro as so
job_id = so.batch_run_function(
name="product-taxonomy-classification",
data="product_taxonomy_classification.csv",
)
results = so.await_job_completion(job_id)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/batch-inference" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "product-taxonomy-classification",
"inputs": [
{
"text": "Listing sells a protective case for a phone, not the phone itself."
}
]
}'