Unsupported answer
Model input
Standard plan allows 5 projects.
Synthetic instruction & Q&A generation
Generate grounded question-and-answer examples from supplied source material.
Step 01
Define and Align
Upload sample data, define your output schema, and provide feedback on the hardest cases.
Output schema
- QuestionText
A question answerable from the supplied source material.
- AnswerText
A direct answer grounded entirely in that source.
- Source evidenceText
The source passage that supports the answer.
- Answer typeChoose one
The kind of information the example teaches.
- fact
- limit
- plan_feature
- procedure
Collecting feedback · 1/3
Generate grounded question-and-answer examples from supplied source material.
Validation accuracy
—
Example 1 of 3
3 annotations saved
Sutro can now generalize the rules based on your feedback.
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 = {
"text": "Standard plan allows 5 projects."
}
result = so.run_function(
"synthetic-instruction-q-a-generation",
input_data,
)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/synthetic-instruction-q-a-generation/run" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"text": "Standard plan allows 5 projects."
}
}'Batch
import sutro as so
job_id = so.batch_run_function(
name="synthetic-instruction-q-a-generation",
data="synthetic_instruction_q_a_generation.csv",
)
results = so.await_job_completion(job_id)curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/batch-inference" \
-H "Authorization: Key $SUTRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "synthetic-instruction-q-a-generation",
"inputs": [
{
"text": "Standard plan allows 5 projects."
}
]
}'