dspy eval flow

dspy_eval.py

from dspy.evaluate import SemanticF1

# Instantiate the metric.
metric = SemanticF1(decompositional=True)

# Produce a prediction from our `cot` module, using the `example` above as input.
pred = cot(**example.inputs())

# Compute the metric score for the prediction.
score = metric(example, pred)

print(f"Question: \t {example.question}\n")
print(f"Gold Response: \t {example.response}\n")
print(f"Predicted Response: \t {pred.response}\n")
print(f"Semantic F1 Score: {score:.2f}")