from fair_forge.runners import AlquimiaRunner
import os

runner = AlquimiaRunner(
    base_url=os.getenv("ALQUIMIA_URL", "https://api.alquimia.ai"),
    api_key=os.getenv("ALQUIMIA_API_KEY"),
    agent_id=os.getenv("AGENT_ID"),
    channel_id=os.getenv("CHANNEL_ID"),
    api_version="",  # Optional API version
)

batch = Batch(
    qa_id="test-001",
    query="What is the capital of France?",
    assistant="",
)

updated_batch, success, exec_time = await runner.run_batch(
    batch,
    session_id="session-001",
)

print(f"Success: {success}")
print(f"Execution time: {exec_time:.2f}ms")
print(f"Response: {updated_batch.assistant}")

dataset = Dataset(
    session_id="test-session",
    assistant_id="my-assistant",
    language="english",
    context="",
    conversation=[batch1, batch2, batch3],
)

updated_dataset, summary = await runner.run_dataset(dataset)

print(f"Successes: {summary['successes']}/{summary['total_batches']}")
print(f"Total time: {summary['total_execution_time_ms']:.2f}ms")

summary = {
    "session_id": "test-session",
    "total_batches": 10,
    "successes": 9,
    "failures": 1,
    "total_execution_time_ms": 12345.6,
    "avg_batch_time_ms": 1234.5,
}

import asyncio
import os
from fair_forge.runners import AlquimiaRunner
from fair_forge.schemas import Dataset, Batch

async def main():
    # Setup runner
    runner = AlquimiaRunner(
        base_url=os.getenv("ALQUIMIA_URL"),
        api_key=os.getenv("ALQUIMIA_API_KEY"),
        agent_id=os.getenv("AGENT_ID"),
        channel_id=os.getenv("CHANNEL_ID"),
    )

    # Create test dataset
    dataset = Dataset(
        session_id="alquimia-test-001",
        assistant_id="my-agent",
        language="english",
        context="",
        conversation=[
            Batch(
                qa_id="q1",
                query="What is machine learning?",
                assistant="",
                ground_truth_assistant="Machine learning is a type of AI...",
            ),
            Batch(
                qa_id="q2",
                query="What are neural networks?",
                assistant="",
                ground_truth_assistant="Neural networks are computing systems...",
            ),
            Batch(
                qa_id="q3",
                query="How does deep learning work?",
                assistant="",
                ground_truth_assistant="Deep learning uses multiple layers...",
            ),
        ],
    )

    # Execute tests
    print(f"Running {len(dataset.conversation)} test cases...\n")
    updated_dataset, summary = await runner.run_dataset(dataset)

    # Print summary
    print("=" * 60)
    print("EXECUTION SUMMARY")
    print("=" * 60)
    print(f"Session ID: {summary['session_id']}")
    print(f"Total batches: {summary['total_batches']}")
    print(f"Successes: {summary['successes']}")
    print(f"Failures: {summary['failures']}")
    print(f"Total time: {summary['total_execution_time_ms']:.2f}ms")
    print(f"Avg batch time: {summary['avg_batch_time_ms']:.2f}ms")
    print("=" * 60)

    # Print responses
    print("\nResponses:")
    for batch in updated_dataset.conversation:
        print(f"\nQ: {batch.query}")
        print(f"A: {batch.assistant[:200]}...")

asyncio.run(main())

ALQUIMIA_URL=https://api.alquimia.ai
ALQUIMIA_API_KEY=your-api-key
AGENT_ID=your-agent-id
CHANNEL_ID=your-channel-id

from dotenv import load_dotenv
load_dotenv()

try:
    updated_dataset, summary = await runner.run_dataset(dataset)

    if summary['failures'] > 0:
        print(f"Warning: {summary['failures']} failures occurred")

except Exception as e:
    print(f"Execution failed: {e}")

from fair_forge.runners import AlquimiaRunner
from fair_forge.storage import create_local_storage
from datetime import datetime
import uuid

# Setup
runner = AlquimiaRunner(...)
storage = create_local_storage(
    tests_dir="./test_datasets",
    results_dir="./test_results",
)

# Load test datasets
datasets = storage.load_datasets()

# Execute all
executed_datasets = []
for dataset in datasets:
    updated, summary = await runner.run_dataset(dataset)
    executed_datasets.append(updated)
    print(f"Completed {dataset.session_id}: {summary['successes']}/{summary['total_batches']}")

# Save results
result_path = storage.save_results(
    datasets=executed_datasets,
    run_id=str(uuid.uuid4()),
    timestamp=datetime.now(),
)
print(f"Results saved to: {result_path}")