Common Errors

@evaluation_test(
    max_concurrent_rollouts=8,      # If error during model responses
    max_concurrent_evaluations=2,   # If error during judging ("impartial judge" prompts)
    # ... other parameters
)

rm ~/.eval_protocol/logs.db

completion_params=[
    {"model": "openai/gpt-4o"},                    # OpenAI
    {"model": "anthropic/claude-3-sonnet"},        # Anthropic  
    {"model": "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct"}, # Fireworks
]

pip install 'eval-protocol[langfuse]'    # For Langfuse
pip install 'eval-protocol[braintrust]'  # For Braintrust
pip install 'eval-protocol[langsmith]'   # For LangSmith

export OPENAI_API_KEY="your_key"
export FIREWORKS_API_KEY="your_key"
export LANGFUSE_PUBLIC_KEY="your_key"
export LANGFUSE_SECRET_KEY="your_secret"

# Test with minimal filters
rows = adapter.get_evaluation_rows(limit=10, hours_back=168)
print(f"Found {len(rows)} rows")
for row in rows:
    print(f"Messages: {row.messages}")

# Stop current ep logs (Ctrl+C)
# Then restart:
ep logs