LLM as judge

from agno.agent import Agent
from agno.models.google import Gemini
from pydantic import BaseModel, Field


class Score(BaseModel):
    overall: int = Field(
        ..., ge=1, le=5, description="Overall quality, 5 is excellent"
    )


agent = Agent(
    model=Gemini(id="gemini-3.5-flash"),
    instructions=(
        "Score the response on overall quality from 1 (unusable) to 5 "
        "(excellent). Use the full scale. Reserve 5 for genuinely "
        "excellent responses."
    ),
    output_schema=Score,
)


def build_input(prompt: str, response: str) -> str:
    return f"Prompt:\n{prompt}\n\nResponse:\n{response}"


prompt = "Explain why the sky is blue, in one sentence."
result = agent.run(build_input(prompt, "It just is.")).content
# Score(overall=1)

from pydantic import BaseModel, Field


class Score(BaseModel):
    overall: int = Field(..., ge=1, le=5, description="Overall quality")
    rationale: str = Field(..., description="Why this score, citing the response")

from pydantic import BaseModel, Field


class RubricScore(BaseModel):
    correctness: int = Field(..., ge=1, le=5, description="Factually correct")
    completeness: int = Field(..., ge=1, le=5, description="Covers what was asked")
    clarity: int = Field(..., ge=1, le=5, description="Easy to follow")
    concision: int = Field(..., ge=1, le=5, description="No padding")
    overall: int = Field(..., ge=1, le=5, description="Holistic quality")