# Install OpenJudge
pip install py-openjudge

# Extra dependency for auto_arena (chart generation)
pip install matplotlib

# Run evaluation
python -m cookbooks.auto_arena --config config.yaml --save

# Use pre-generated queries
python -m cookbooks.auto_arena --config config.yaml \
  --queries_file queries.json --save

# Start fresh, ignore checkpoint
python -m cookbooks.auto_arena --config config.yaml --fresh --save

# Re-run only pairwise evaluation with new judge model
# (keeps queries, responses, and rubrics)
python -m cookbooks.auto_arena --config config.yaml --rerun-judge --save

import asyncio
from cookbooks.auto_arena.auto_arena_pipeline import AutoArenaPipeline

async def main():
    pipeline = AutoArenaPipeline.from_config("config.yaml")
    result = await pipeline.evaluate()

    print(f"Best model: {result.best_pipeline}")
    for rank, (model, win_rate) in enumerate(result.rankings, 1):
        print(f"{rank}. {model}: {win_rate:.1%}")

asyncio.run(main())

import asyncio
from cookbooks.auto_arena.auto_arena_pipeline import AutoArenaPipeline
from cookbooks.auto_arena.schema import OpenAIEndpoint

async def main():
    pipeline = AutoArenaPipeline(
        task_description="Customer service chatbot for e-commerce",
        target_endpoints={
            "gpt4": OpenAIEndpoint(
                base_url="https://api.openai.com/v1",
                api_key="sk-...",
                model="gpt-4",
            ),
            "qwen": OpenAIEndpoint(
                base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
                api_key="sk-...",
                model="qwen-max",
            ),
        },
        judge_endpoint=OpenAIEndpoint(
            base_url="https://api.openai.com/v1",
            api_key="sk-...",
            model="gpt-4",
        ),
        num_queries=20,
    )
    result = await pipeline.evaluate()
    print(f"Best: {result.best_pipeline}")

asyncio.run(main())

task:
  description: "Academic GPT assistant for research and writing tasks"

target_endpoints:
  model_v1:
    base_url: "https://api.openai.com/v1"
    api_key: "${OPENAI_API_KEY}"
    model: "gpt-4"
  model_v2:
    base_url: "https://api.openai.com/v1"
    api_key: "${OPENAI_API_KEY}"
    model: "gpt-3.5-turbo"

judge_endpoint:
  base_url: "https://api.openai.com/v1"
  api_key: "${OPENAI_API_KEY}"
  model: "gpt-4"

  1. gpt4_baseline       [################----] 80.0%
  2. qwen_candidate      [############--------] 60.0%
  3. llama_finetuned      [##########----------] 50.0%

evaluation_results/
├── evaluation_results.json     # Rankings, win rates, win matrix
├── evaluation_report.md        # Detailed Markdown report (if enabled)
├── win_rate_chart.png          # Win-rate bar chart (if enabled)
├── win_rate_matrix.png         # Matrix heatmap (if matrix_enabled)
├── queries.json                # Generated test queries
├── responses.json              # All model responses
├── rubrics.json                # Generated evaluation rubrics
├── comparison_details.json     # Pairwise comparison details
└── checkpoint.json             # Pipeline checkpoint