DSPy: The framework for programming—not prompting—language models
Python
Update cheatsheet.md
Thomas Dybdahl Ahle7558b8f43916
diff --git a/docs/docs/cheatsheet.md b/docs/docs/cheatsheet.mdindex c5f11e0c4..af62bd248 100644--- a/docs/docs/cheatsheet.md+++ b/docs/docs/cheatsheet.md@@ -282,8 +282,13 @@ your_dspy_program_compiled = fewshot_optimizer.compile(student = your_dspy_progr#### Compiling a compiled program - bootstrapping a bootstraped program-your_dspy_program_compiledx2 = teleprompter.compile(your_dspy_program, teacher=your_dspy_program_compiled, trainset=trainset)-+```python+your_dspy_program_compiledx2 = teleprompter.compile(+ your_dspy_program,+ teacher=your_dspy_program_compiled,+ trainset=trainset,+)+```### dspy.BootstrapFewShotWithRandomSearch@@ -364,6 +369,20 @@ kwargs = dict(num_threads=NUM_THREADS, display_progress=True, display_table=0)compiled_program_optimized_bayesian_signature = teleprompter.compile(your_dspy_program, devset=devset[:DEV_NUM], optuna_trials_num=100, max_bootstrapped_demos=3, max_labeled_demos=5, eval_kwargs=kwargs)```+### Signature Optimizer with Types++```python+from dspy.teleprompt.signature_opt_typed import optimize_signature+from dspy.evaluate.metrics import answer_exact_match+from dspy.functional import TypedChainOfThought++compiled_program = optimize_signature(+ student=TypedChainOfThought("question -> answer"),+ evaluator=Evaluate(devset=devset, metric=answer_exact_match, num_threads=10, display_progress=True),+ n_iterations=50,+).program+```+### dspy.KNNFewShot```python