Evaluation logger

import weave
from openai import OpenAI
from weave import EvaluationLogger 

weave.init('my-project')

# Initialize EvaluationLogger BEFORE calling the model to ensure token tracking
eval_logger = EvaluationLogger(
    model="my_model",
    dataset="my_dataset"
)

# Example input data (this can be any data structure you want)
eval_samples = [
    {'inputs': {'a': 1, 'b': 2}, 'expected': 3},
    {'inputs': {'a': 2, 'b': 3}, 'expected': 5},
    {'inputs': {'a': 3, 'b': 4}, 'expected': 7},
]

# Example model logic using OpenAI
@weave.op
def user_model(a: int, b: int) -> int:
    oai = OpenAI()
    response = oai.chat.completions.create(
        messages=[{"role": "user", "content": f"What is {a}+{b}?"}],
        model="gpt-4o-mini"
    )
    # Use the response in some way (here we just return a + b for simplicity)
    return a + b

# Iterate through examples, predict, and log
for sample in eval_samples:
    inputs = sample["inputs"]
    model_output = user_model(**inputs) # Pass inputs as kwargs

    # Log the prediction input and output
    pred_logger = eval_logger.log_prediction(
        inputs=inputs,
        output=model_output
    )

    # Calculate and log a score for this prediction
    expected = sample["expected"]
    correctness_score = model_output == expected
    pred_logger.log_score(
        scorer="correctness", # Simple string name for the scorer
        score=correctness_score
    )

    # Finish logging for this specific prediction
    pred_logger.finish()

# Log a final summary for the entire evaluation.
# Weave auto-aggregates the 'correctness' scores logged above.
summary_stats = {"subjective_overall_score": 0.8}
eval_logger.log_summary(summary_stats)

print("Evaluation logging complete. View results in the Weave UI.")

# Initialize EvaluationLogger BEFORE calling the model to ensure token tracking
ev = EvaluationLogger(
    model="example_model", 
    dataset="example_dataset"
)

# Model outputs (e.g. OpenAI calls) must happen after logger init for token tracking
outputs = [your_output_generator(**inputs) for inputs in your_dataset]
preds = [ev.log_prediction(inputs, output) for inputs, output in zip(your_dataset, outputs)]
for pred in preds:
    pred.log_score(scorer="greater_than_5_scorer", score=output > 5)
    pred.log_score(scorer="greater_than_7_scorer", score=output > 7)
    pred.finish()

ev.log_summary()

import io
import wave
import struct
from PIL import Image
import random
from typing import Any
import weave

def generate_random_audio_wave_read(duration=2, sample_rate=44100):
    n_samples = duration * sample_rate
    amplitude = 32767  # 16-bit max amplitude

    buffer = io.BytesIO()

    # Write wave data to the buffer
    with wave.open(buffer, 'wb') as wf:
        wf.setnchannels(1)
        wf.setsampwidth(2)  # 16-bit
        wf.setframerate(sample_rate)

        for _ in range(n_samples):
            sample = random.randint(-amplitude, amplitude)
            wf.writeframes(struct.pack('<h', sample))

    # Rewind the buffer to the beginning so we can read from it
    buffer.seek(0)

    # Return a Wave_read object
    return wave.open(buffer, 'rb')

rich_media_dataset = [
    {
        'image': Image.new(
            "RGB",
            (100, 100),
            color=(
                random.randint(0, 255),
                random.randint(0, 255),
                random.randint(0, 255),
            ),
        ),
        "audio": generate_random_audio_wave_read(),
    }
    for _ in range(5)
]

@weave.op
def your_output_generator(image: Image.Image, audio) -> dict[str, Any]:
    return {
        "result": random.randint(0, 10),
        "image": image,
        "audio": audio,
    }

ev = EvaluationLogger(model="example_model", dataset="example_dataset")

for inputs in rich_media_dataset:
    output = your_output_generator(**inputs)
    pred = ev.log_prediction(inputs, output)
    pred.log_score(scorer="greater_than_5_scorer", score=output["result"] > 5)
    pred.log_score(scorer="greater_than_7_scorer", score=output["result"] > 7)

ev.log_summary()

import weave

models = [
    "model1",
    "model2",
     {"name": "model3", "metadata": {"coolness": 9001}}
]

for model in models:
    # EvalLogger must be initialized before model calls to capture tokens
    ev = EvaluationLogger(model=model, dataset="example_dataset")
    for inputs in your_dataset:
        output = your_output_generator(**inputs)
        pred = ev.log_prediction(inputs=inputs, output=output)
        pred.log_score(scorer="greater_than_3_scorer", score=output > 3)
        pred.log_score(scorer="greater_than_5_scorer", score=output > 5)
        pred.log_score(scorer="greater_than_7_scorer", score=output > 7)
        pred.finish()

    ev.log_summary()