Responses

from uiform import UiForm
from pydantic import BaseModel

client = UiForm()

class Step(BaseModel):
    explanation: str
    output: str

class MathReasoning(BaseModel):
    steps: list[Step]
    final_answer: str

response = client.consensus.responses.parse(
    model="gpt-4o-2024-08-06",
    input=[
        {
            "role": "system",
            "content": "You are a helpful math tutor. Guide the user through the solution step by step.",
        },
        {"role": "user", "content": "how can I solve 8x + 7 = -23"},
    ],
    text_format=MathReasoning,
    n_consensus=4
)

math_reasoning = response.output_parsed

{
  "id": "resp_67ccd2bed1ec8190b14f964abc0542670bb6a6b452d3795b",
  "object": "response",
  "created_at": 1741476542,
  "status": "completed",
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "model": "gpt-4.1-2025-04-14",
  "output": [
    {
      "type": "message",
      "id": "msg_67ccd2bf17f0819081ff3bb2cf6508e60bb6a6b452d3795b",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "'{"steps": [{"explanation": "Start with the equation 8x + 7 = -23.", "output": "8x + 7 = -23"}, {"explanation": "Subtract 7 from both sides to isolate the term with the variable.", "output": "8x = -23 - 7"}, {"explanation": "Simplify the right side of the equation.", "output": "8x = -30"}, {"explanation": "Divide both sides by 8 to solve for x.", "output": "x = -30 / 8"}, {"explanation": "Simplify the fraction.", "output": "x = -15 / 4"}], "final_answer": "x = -15 / 4"}'",
          "annotations": []
        }
      ]
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": null,
  "reasoning": {
    "effort": null,
    "summary": null
  },
  "store": true,
  "temperature": 1.0,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tool_choice": "auto",
  "tools": [],
  "top_p": 1.0,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 36,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 87,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 123
  },
  "user": null,
  "metadata": {}
}