Recover from invalid model outputYou let Ax validate fields and retry with specific correction feedback. Your app can still distinguish generation errors, provider failures, and cancellation.pythonacademyacademy/topics/structured-validation-errorswebsite/content-src/academy/course.mjsacademyRecover from invalid model output
You let Ax validate fields and retry with specific correction feedback. Your app can still distinguish generation errors, provider failures, and cancellation.
8 focused minutesNot started
Unit example (nearest native match)
See the idea in context
from axllm import ax
answer = ax('question:string -> answer:string')
Run the program normally
Most valid responses return through the usual typed path.
Catch the specific failure
AxGenerateError identifies a generation or validation failure you can report deliberately.
Preserve useful details
error.details gives logs and UI a concrete repair target.
Run itIn your own project
pip install axllm
import os
from axllm import ai, ax
llm = ai('openai', api_key=os.environ['OPENAI_API_KEY'])
classify = ax('review:string -> sentiment:class "positive, negative, neutral"')
result = classify.forward(llm, {
'review': 'Useful and boring in the best way.',
})
print('sentiment:', result['sentiment'])
Set OPENAI_APIKEY in your environment before running provider-backed code.
In the ax repo
From a clone of the ax repo:
npm run example -- python src/examples/python/generation/axgen-openai.py