the model that doesn't write: an intro to decision models

Описание и применение

Модель принятия решений возвращает числовые вероятности, позволяя программно принимать решения, в отличие от чат‑ботов, которые дают текстовые ответы.

Задача

Need a way to get numeric decision outputs (probabilities) from a model for use in code branches, rather than textual chatbot responses.

Результат

The workflow demonstrates that decision models provide actionable numeric outputs, enabling automated decision logic and reducing reliance on human review for clear cases.

Рабочий процесс

• 1. Define a JSON schema with questions (type: noul, choice, score).
• 2. Send image and schema to the decision model via a single API call.
• 3. Receive structured probabilities and confidence for each question.
• 4. Apply branching logic (e.g., if dog_present < 0.5 reject, if breed confidence > 0.9 auto_tag, else send to human).
• 5. Render decisions visually with a custom Python function in a Gradio workflow.
• 6. Deploy the workflow as a single API endpoint using Gradio Client.

Доказательства

you get back a probability for every allowed answer

Источник

if answers["dog_present"]["noul"] < 0.5: reject(photo) # 0.98 — skipped

Источник