Comparer et classer les modèles

import weave
from weave.flow import leaderboard
from weave.trace.ref_util import get_ref
import asyncio

client = weave.init("leaderboard-demo")

dataset = [
    {
        "input": "Weave is a tool for building interactive LLM apps. It offers observability, trace inspection, and versioning.",
        "target": "Weave helps developers build and observe LLM applications."
    },
    {
        "input": "The OpenAI GPT-4o model can process text, audio, and vision inputs, making it a multimodal powerhouse.",
        "target": "GPT-4o is a multimodal model for text, audio, and images."
    },
    {
        "input": "The W&B team recently added native support for agents and evaluations in Weave.",
        "target": "W&B added agents and evals to Weave."
    }
]

@weave.op
def jaccard_similarity(target: str, output: str) -> float:
    target_tokens = set(target.lower().split())
    output_tokens = set(output.lower().split())
    intersection = len(target_tokens & output_tokens)
    union = len(target_tokens | output_tokens)
    return intersection / union if union else 0.0

evaluation = weave.Evaluation(
    name="Summarization Quality",
    dataset=dataset,
    scorers=[jaccard_similarity],
)

@weave.op
def model_vanilla(input: str) -> str:
    return input[:50]

@weave.op
def model_humanlike(input: str) -> str:
    if "Weave" in input:
        return "Weave helps developers build and observe LLM applications."
    elif "GPT-4o" in input:
        return "GPT-4o supports text, audio, and vision input."
    else:
        return "W&B added agent support to Weave."

@weave.op
def model_messy(input: str) -> str:
    return "Summarizer summarize models model input text LLMs."

async def run_all():
    await evaluation.evaluate(model_vanilla)
    await evaluation.evaluate(model_humanlike)
    await evaluation.evaluate(model_messy)

asyncio.run(run_all())

spec = leaderboard.Leaderboard(
    name="Summarization Model Comparison",
    description="Evaluate summarizer models using Jaccard similarity on three short samples.",
    columns=[
        leaderboard.LeaderboardColumn(
            evaluation_object_ref=get_ref(evaluation).uri(),
            scorer_name="jaccard_similarity",
            summary_metric_path="mean",
        )
    ]
)

weave.publish(spec)

results = leaderboard.get_leaderboard_results(spec, client)
print(results)