pip install openai weave

https://api.inference.wandb.ai/v1

import weave
import openai

# Set the Weave team and project for tracing
weave.init("<your-team>/<your-project>")

client = openai.OpenAI(
    base_url='https://api.inference.wandb.ai/v1',

    # Get your API key from https://wandb.ai/authorize
    api_key="<your-api-key>",

    # Required for W&B inference usage tracking
    project="wandb/inference-demo",
)

# Trace the model call in Weave
@weave.op()
def run_chat():
    response = client.chat.completions.create(
        model="meta-llama/Llama-3.1-8B-Instruct",
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "Tell me a joke."}
        ],
    )
    return response.choices[0].message.content

# Run and log the traced call
output = run_chat()
print(output)

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

# Set the Weave team and project for tracing
weave.init("<your-team>/<your-project>")

dataset = [
    {"input": "What is 2 + 2?", "target": "4"},
    {"input": "Name a primary color.", "target": "red"},
]

@weave.op
def exact_match(target: str, output: str) -> float:
    return float(target.strip().lower() == output.strip().lower())

class WBInferenceModel(weave.Model):
    model: str

    @weave.op
    def predict(self, prompt: str) -> str:
        client = openai.OpenAI(
            base_url="https://api.inference.wandb.ai/v1",
            # Get your API key from https://wandb.ai/authorize
            api_key="<your-api-key>",
            # Required for W&B inference usage tracking
            project="<your-team>/<your-project>",
        )
        resp = client.chat.completions.create(
            model=self.model,
            messages=[{"role": "user", "content": prompt}],
        )
        return resp.choices[0].message.content

llama = WBInferenceModel(model="meta-llama/Llama-3.1-8B-Instruct")
deepseek = WBInferenceModel(model="deepseek-ai/DeepSeek-V3-0324")

def preprocess_model_input(example):
    return {"prompt": example["input"]}

evaluation = weave.Evaluation(
    name="QA",
    dataset=dataset,
    scorers=[exact_match],
    preprocess_model_input=preprocess_model_input,
)

async def run_eval():
    await evaluation.evaluate(llama)
    await evaluation.evaluate(deepseek)

asyncio.run(run_eval())

spec = leaderboard.Leaderboard(
    name="Inference Leaderboard",
    description="Compare models on a QA dataset",
    columns=[
        leaderboard.LeaderboardColumn(
            evaluation_object_ref=get_ref(evaluation).uri(),
            scorer_name="exact_match",
            summary_metric_path="mean",
        )
    ],
)

weave.publish(spec)