Run evals with LangSmith

Steps

1. Set environment variables LANGCHAIN_API_KEY and LANGCHAIN_TRACING_V2=true; install the SDK: pip install langsmith
2. Create a dataset: client = langsmith.Client(); dataset = client.create_dataset('my-dataset'); client.create_examples(inputs=[{'question': '...'}], outputs=[{'answer': '...'}], dataset_id=dataset.id)
3. Define a target function that takes a dict of inputs and returns a dict of outputs — this wraps the LLM call or chain being evaluated
4. Define one or more evaluator functions that accept a dict with 'inputs', 'outputs', and 'reference_outputs' keys and return an EvaluationResult with a score or label
5. Run the evaluation: results = langsmith.evaluate(target, data='my-dataset', evaluators=[my_evaluator], experiment_prefix='run-1')
6. Inspect results in the LangSmith UI under the Datasets & Testing tab, or read results.to_pandas() programmatically